{"object":"list","data":[{"id":"openai/gpt-3.5-turbo","info":{"releasedAt":"2025-08-07","name":"GPT-3.5 Turbo","developer":"Open AI","description":"Fast and cost-efficient OpenAI model for a wide range of text generation and conversation tasks.","contextLength":16000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/openai/gpt-3.5-turbo","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fgpt-3.5-turbo&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["gpt-3.5-turbo"],"tags":["playground:chat","tier:tier_2"]},{"id":"openai/gpt-3.5-turbo","info":{"releasedAt":"2025-08-07","name":"GPT-3.5 Turbo","developer":"Open AI","description":"Fast and cost-efficient OpenAI model for a wide range of text generation and conversation tasks.","contextLength":16000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/openai/gpt-3.5-turbo","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fgpt-3.5-turbo&endpoint=openai%2Fresponses%2Fsubmit"},"type":"openai/responses/submit","aliases":["gpt-3.5-turbo"],"tags":["playground:chat","tier:tier_2"]},{"id":"openai/gpt-3.5-turbo-0125","info":{"releasedAt":"2025-08-07","name":"GPT-3.5 Turbo","developer":"Open AI","description":"Fast and cost-efficient OpenAI model for a wide range of text generation and conversation tasks.","contextLength":16000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/openai/gpt-3.5-turbo","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fgpt-3.5-turbo-0125&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["gpt-3.5-turbo-0125"],"tags":["playground:chat","tier:tier_2"]},{"id":"openai/gpt-3.5-turbo-0125","info":{"releasedAt":"2025-08-07","name":"GPT-3.5 Turbo","developer":"Open AI","description":"Fast and cost-efficient OpenAI model for a wide range of text generation and conversation tasks.","contextLength":16000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/openai/gpt-3.5-turbo","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fgpt-3.5-turbo-0125&endpoint=openai%2Fresponses%2Fsubmit"},"type":"openai/responses/submit","aliases":["gpt-3.5-turbo-0125"],"tags":["playground:chat","tier:tier_2"]},{"id":"openai/gpt-3.5-turbo-1106","info":{"releasedAt":"2025-08-07","name":"GPT-3.5 Turbo","developer":"Open AI","description":"Fast and cost-efficient OpenAI model for a wide range of text generation and conversation tasks.","contextLength":16000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/openai/gpt-3.5-turbo","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fgpt-3.5-turbo-1106&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["gpt-3.5-turbo-1106"],"tags":["playground:chat","tier:tier_2"]},{"id":"openai/gpt-3.5-turbo-1106","info":{"releasedAt":"2025-08-07","name":"GPT-3.5 Turbo","developer":"Open AI","description":"Fast and cost-efficient OpenAI model for a wide range of text generation and conversation tasks.","contextLength":16000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/openai/gpt-3.5-turbo","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fgpt-3.5-turbo-1106&endpoint=openai%2Fresponses%2Fsubmit"},"type":"openai/responses/submit","aliases":["gpt-3.5-turbo-1106"],"tags":["playground:chat","tier:tier_2"]},{"id":"openai/gpt-4","info":{"releasedAt":"2025-08-07","name":"GPT-4","developer":"Open AI","description":"Revolutionary AI model for unparalleled natural language interaction. API for ChatGPT 4.","contextLength":8000,"url":"https://aimlapi.com/models/chat-gpt-4","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/openai/gpt-4","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fgpt-4&endpoint=openai%2Fresponses%2Fsubmit"},"type":"openai/responses/submit","aliases":["gpt-4"],"tags":["playground:chat","tier:tier_2"]},{"id":"openai/gpt-4","info":{"releasedAt":"2025-08-07","name":"GPT-4","developer":"Open AI","description":"Revolutionary AI model for unparalleled natural language interaction. API for ChatGPT 4.","contextLength":8000,"url":"https://aimlapi.com/models/chat-gpt-4","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/openai/gpt-4","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fgpt-4&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["gpt-4"],"tags":["playground:chat","tier:tier_2"]},{"id":"openai/gpt-4.1-mini","info":{"releasedAt":"2025-08-07","name":"GPT-4.1 Mini","developer":"Open AI","description":"GPT-4.1 mini is a cost-effective variant of GPT-4.1 with 1M token context, optimized for speed and efficiency.","contextLength":1000000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/openai/gpt-4.1-mini","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fgpt-4.1-mini&endpoint=openai%2Fresponses%2Fsubmit"},"type":"openai/responses/submit","aliases":["gpt-4.1-mini"],"tags":["playground:chat","tier:tier_2"]},{"id":"openai/gpt-4.1-mini","info":{"releasedAt":"2025-08-07","name":"GPT-4.1 Mini","developer":"Open AI","description":"GPT-4.1 mini is a cost-effective variant of GPT-4.1 with 1M token context, optimized for speed and efficiency.","contextLength":1000000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/openai/gpt-4.1-mini","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fgpt-4.1-mini&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["gpt-4.1-mini"],"tags":["playground:chat","tier:tier_2"]},{"id":"openai/gpt-4.1-mini-2025-04-14","info":{"releasedAt":"2025-08-07","name":"GPT-4.1 Mini","developer":"Open AI","description":"GPT-4.1 mini is a cost-effective variant of GPT-4.1 with 1M token context, optimized for speed and efficiency.","contextLength":1000000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/openai/gpt-4.1-mini","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fgpt-4.1-mini-2025-04-14&endpoint=openai%2Fresponses%2Fsubmit"},"type":"openai/responses/submit","aliases":["gpt-4.1-mini-2025-04-14"],"tags":["playground:chat","tier:tier_2"]},{"id":"openai/gpt-4.1-mini-2025-04-14","info":{"releasedAt":"2025-08-07","name":"GPT-4.1 Mini","developer":"Open AI","description":"GPT-4.1 mini is a cost-effective variant of GPT-4.1 with 1M token context, optimized for speed and efficiency.","contextLength":1000000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/openai/gpt-4.1-mini","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fgpt-4.1-mini-2025-04-14&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["gpt-4.1-mini-2025-04-14"],"tags":["playground:chat","tier:tier_2"]},{"id":"openai/gpt-4.1-nano","info":{"releasedAt":"2025-08-07","name":"GPT-4.1 Nano","developer":"Open AI","description":"GPT-4.1 nano is the most lightweight GPT-4.1 variant, designed for minimal latency and resource usage.","contextLength":1000000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/openai/gpt-4.1-nano","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fgpt-4.1-nano&endpoint=openai%2Fresponses%2Fsubmit"},"type":"openai/responses/submit","aliases":["gpt-4.1-nano"],"tags":["playground:chat","tier:tier_2"]},{"id":"openai/gpt-4.1-nano","info":{"releasedAt":"2025-08-07","name":"GPT-4.1 Nano","developer":"Open AI","description":"GPT-4.1 nano is the most lightweight GPT-4.1 variant, designed for minimal latency and resource usage.","contextLength":1000000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/openai/gpt-4.1-nano","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fgpt-4.1-nano&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["gpt-4.1-nano"],"tags":["playground:chat","tier:tier_2"]},{"id":"openai/gpt-4.1-nano-2025-04-14","info":{"releasedAt":"2025-08-07","name":"GPT-4.1 Nano","developer":"Open AI","description":"GPT-4.1 nano is the most lightweight GPT-4.1 variant, designed for minimal latency and resource usage.","contextLength":1000000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/openai/gpt-4.1-nano","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fgpt-4.1-nano-2025-04-14&endpoint=openai%2Fresponses%2Fsubmit"},"type":"openai/responses/submit","aliases":["gpt-4.1-nano-2025-04-14"],"tags":["playground:chat","tier:tier_2"]},{"id":"openai/gpt-4.1-nano-2025-04-14","info":{"releasedAt":"2025-08-07","name":"GPT-4.1 Nano","developer":"Open AI","description":"GPT-4.1 nano is the most lightweight GPT-4.1 variant, designed for minimal latency and resource usage.","contextLength":1000000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/openai/gpt-4.1-nano","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fgpt-4.1-nano-2025-04-14&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["gpt-4.1-nano-2025-04-14"],"tags":["playground:chat","tier:tier_2"]},{"id":"openai/gpt-4.1","info":{"releasedAt":"2025-08-07","name":"GPT-4.1","developer":"Open AI","description":"GPT-4.1 is OpenAI's large-context language model with up to 1M token input and improved instruction following.","contextLength":1047576,"outputMax":32768,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/openai/gpt-4.1","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fgpt-4.1&endpoint=openai%2Fresponses%2Fsubmit"},"type":"openai/responses/submit","aliases":["gpt-4.1"],"tags":["playground:chat","tier:tier_2"]},{"id":"openai/gpt-4.1","info":{"releasedAt":"2025-08-07","name":"GPT-4.1","developer":"Open AI","description":"GPT-4.1 is OpenAI's large-context language model with up to 1M token input and improved instruction following.","contextLength":1047576,"outputMax":32768,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/openai/gpt-4.1","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fgpt-4.1&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["gpt-4.1"],"tags":["playground:chat","tier:tier_2"]},{"id":"openai/gpt-4.1-2025-04-14","info":{"releasedAt":"2025-08-07","name":"GPT-4.1","developer":"Open AI","description":"GPT-4.1 is OpenAI's large-context language model with up to 1M token input and improved instruction following.","contextLength":1047576,"outputMax":32768,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/openai/gpt-4.1","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fgpt-4.1-2025-04-14&endpoint=openai%2Fresponses%2Fsubmit"},"type":"openai/responses/submit","aliases":["gpt-4.1-2025-04-14"],"tags":["playground:chat","tier:tier_2"]},{"id":"openai/gpt-4.1-2025-04-14","info":{"releasedAt":"2025-08-07","name":"GPT-4.1","developer":"Open AI","description":"GPT-4.1 is OpenAI's large-context language model with up to 1M token input and improved instruction following.","contextLength":1047576,"outputMax":32768,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/openai/gpt-4.1","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fgpt-4.1-2025-04-14&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["gpt-4.1-2025-04-14"],"tags":["playground:chat","tier:tier_2"]},{"id":"openai/gpt-4-turbo","info":{"releasedAt":"2025-08-07","name":"GPT-4 Turbo","developer":"Open AI","description":"High-speed AI model for instant language processing. API for ChatGPT 4 Turbo.","contextLength":128000,"url":"https://aimlapi.com/models/chat-gpt-4-turbo","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/openai/gpt-4-turbo","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fgpt-4-turbo&endpoint=openai%2Fresponses%2Fsubmit"},"type":"openai/responses/submit","aliases":["gpt-4-turbo"],"tags":["playground:chat","tier:tier_2"]},{"id":"openai/gpt-4-turbo","info":{"releasedAt":"2025-08-07","name":"GPT-4 Turbo","developer":"Open AI","description":"High-speed AI model for instant language processing. API for ChatGPT 4 Turbo.","contextLength":128000,"url":"https://aimlapi.com/models/chat-gpt-4-turbo","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/openai/gpt-4-turbo","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fgpt-4-turbo&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["gpt-4-turbo"],"tags":["playground:chat","tier:tier_2"]},{"id":"openai/gpt-4-turbo-2024-04-09","info":{"releasedAt":"2025-08-07","name":"GPT-4 Turbo","developer":"Open AI","description":"High-speed AI model for instant language processing. API for ChatGPT 4 Turbo.","contextLength":128000,"url":"https://aimlapi.com/models/chat-gpt-4-turbo","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/openai/gpt-4-turbo","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fgpt-4-turbo-2024-04-09&endpoint=openai%2Fresponses%2Fsubmit"},"type":"openai/responses/submit","aliases":["gpt-4-turbo-2024-04-09"],"tags":["playground:chat","tier:tier_2"]},{"id":"openai/gpt-4-turbo-2024-04-09","info":{"releasedAt":"2025-08-07","name":"GPT-4 Turbo","developer":"Open AI","description":"High-speed AI model for instant language processing. API for ChatGPT 4 Turbo.","contextLength":128000,"url":"https://aimlapi.com/models/chat-gpt-4-turbo","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/openai/gpt-4-turbo","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fgpt-4-turbo-2024-04-09&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["gpt-4-turbo-2024-04-09"],"tags":["playground:chat","tier:tier_2"]},{"id":"openai/gpt-4o-mini","info":{"releasedAt":"2025-08-07","name":"GPT-4o Mini","developer":"Open AI","description":"GPT-4o Mini: Cost-efficient, advanced model for diverse AI applications.","contextLength":128000,"url":"https://aimlapi.com/models/chat-gpt-4o-mini","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/openai/gpt-4o-mini","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fgpt-4o-mini&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["gpt-4o-mini"],"tags":["playground:chat","tier:tier_2"]},{"id":"openai/gpt-4o-mini","info":{"releasedAt":"2025-08-07","name":"GPT-4o Mini","developer":"Open AI","description":"GPT-4o Mini: Cost-efficient, advanced model for diverse AI applications.","contextLength":128000,"url":"https://aimlapi.com/models/chat-gpt-4o-mini","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/openai/gpt-4o-mini","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fgpt-4o-mini&endpoint=openai%2Fresponses%2Fsubmit"},"type":"openai/responses/submit","aliases":["gpt-4o-mini"],"tags":["playground:chat","tier:tier_2"]},{"id":"openai/gpt-4o-mini-2024-07-18","info":{"releasedAt":"2025-08-07","name":"GPT-4o Mini","developer":"Open AI","description":"GPT-4o Mini: Cost-efficient, advanced model for diverse AI applications.","contextLength":128000,"url":"https://aimlapi.com/models/chat-gpt-4o-mini","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/openai/gpt-4o-mini","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fgpt-4o-mini-2024-07-18&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["gpt-4o-mini-2024-07-18"],"tags":["playground:chat","tier:tier_2"]},{"id":"openai/gpt-4o-mini-2024-07-18","info":{"releasedAt":"2025-08-07","name":"GPT-4o Mini","developer":"Open AI","description":"GPT-4o Mini: Cost-efficient, advanced model for diverse AI applications.","contextLength":128000,"url":"https://aimlapi.com/models/chat-gpt-4o-mini","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/openai/gpt-4o-mini","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fgpt-4o-mini-2024-07-18&endpoint=openai%2Fresponses%2Fsubmit"},"type":"openai/responses/submit","aliases":["gpt-4o-mini-2024-07-18"],"tags":["playground:chat","tier:tier_2"]},{"id":"openai/gpt-4o","info":{"releasedAt":"2025-08-07","name":"GPT-4o","developer":"Open AI","description":"Multimodal AI model by OpenAI enhancing human-computer interaction.","contextLength":128000,"outputMax":16384,"cutoffAt":"2023-10-01","url":"https://aimlapi.com/models/gpt-4o-2024-08-06-api","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/openai/gpt-4o","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fgpt-4o&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["gpt-4o"],"tags":["playground:chat","tier:tier_2"]},{"id":"openai/gpt-4o","info":{"releasedAt":"2025-08-07","name":"GPT-4o","developer":"Open AI","description":"Multimodal AI model by OpenAI enhancing human-computer interaction.","contextLength":128000,"outputMax":16384,"cutoffAt":"2023-10-01","url":"https://aimlapi.com/models/gpt-4o-2024-08-06-api","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/openai/gpt-4o","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fgpt-4o&endpoint=openai%2Fresponses%2Fsubmit"},"type":"openai/responses/submit","aliases":["gpt-4o"],"tags":["playground:chat","tier:tier_2"]},{"id":"openai/gpt-4o-2024-08-06","info":{"releasedAt":"2025-08-07","name":"GPT-4o","developer":"Open AI","description":"Multimodal AI model by OpenAI enhancing human-computer interaction.","contextLength":128000,"outputMax":16384,"cutoffAt":"2023-10-01","url":"https://aimlapi.com/models/gpt-4o-2024-08-06-api","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/openai/gpt-4o","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fgpt-4o-2024-08-06&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["gpt-4o-2024-08-06"],"tags":["playground:chat","tier:tier_2"]},{"id":"openai/gpt-4o-2024-08-06","info":{"releasedAt":"2025-08-07","name":"GPT-4o","developer":"Open AI","description":"Multimodal AI model by OpenAI enhancing human-computer interaction.","contextLength":128000,"outputMax":16384,"cutoffAt":"2023-10-01","url":"https://aimlapi.com/models/gpt-4o-2024-08-06-api","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/openai/gpt-4o","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fgpt-4o-2024-08-06&endpoint=openai%2Fresponses%2Fsubmit"},"type":"openai/responses/submit","aliases":["gpt-4o-2024-08-06"],"tags":["playground:chat","tier:tier_2"]},{"id":"openai/gpt-4o-2024-11-20","info":{"releasedAt":"2025-08-07","name":"GPT-4o","developer":"Open AI","description":"Multimodal AI model by OpenAI enhancing human-computer interaction.","contextLength":128000,"outputMax":16384,"cutoffAt":"2023-10-01","url":"https://aimlapi.com/models/gpt-4o-2024-08-06-api","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/openai/gpt-4o","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fgpt-4o-2024-11-20&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["gpt-4o-2024-11-20"],"tags":["playground:chat","tier:tier_2"]},{"id":"openai/gpt-4o-2024-11-20","info":{"releasedAt":"2025-08-07","name":"GPT-4o","developer":"Open AI","description":"Multimodal AI model by OpenAI enhancing human-computer interaction.","contextLength":128000,"outputMax":16384,"cutoffAt":"2023-10-01","url":"https://aimlapi.com/models/gpt-4o-2024-08-06-api","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/openai/gpt-4o","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fgpt-4o-2024-11-20&endpoint=openai%2Fresponses%2Fsubmit"},"type":"openai/responses/submit","aliases":["gpt-4o-2024-11-20"],"tags":["playground:chat","tier:tier_2"]},{"id":"openai/gpt-4o-2024-05-13","info":{"releasedAt":"2025-08-07","name":"GPT-4o","developer":"Open AI","description":"Multimodal AI model by OpenAI enhancing human-computer interaction.","contextLength":128000,"outputMax":16384,"cutoffAt":"2023-10-01","url":"https://aimlapi.com/models/gpt-4o-2024-08-06-api","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/openai/gpt-4o","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fgpt-4o-2024-05-13&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["gpt-4o-2024-05-13"],"tags":["playground:chat","tier:tier_2"]},{"id":"openai/gpt-4o-2024-05-13","info":{"releasedAt":"2025-08-07","name":"GPT-4o","developer":"Open AI","description":"Multimodal AI model by OpenAI enhancing human-computer interaction.","contextLength":128000,"outputMax":16384,"cutoffAt":"2023-10-01","url":"https://aimlapi.com/models/gpt-4o-2024-08-06-api","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/openai/gpt-4o","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fgpt-4o-2024-05-13&endpoint=openai%2Fresponses%2Fsubmit"},"type":"openai/responses/submit","aliases":["gpt-4o-2024-05-13"],"tags":["playground:chat","tier:tier_2"]},{"id":"openai/o1","info":{"releasedAt":"2025-08-07","name":"o1 Preview","developer":"Open AI","description":"New AI model from OpenAI for complex reasoning in science, coding, and mathematics.","contextLength":128000,"url":"https://aimlapi.com/models/openai-o1-preview-api","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/openai/o1","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fo1&endpoint=openai%2Fresponses%2Fsubmit"},"type":"openai/responses/submit","aliases":["o1"],"tags":["playground:chat","tier:tier_2"]},{"id":"openai/o1","info":{"releasedAt":"2025-08-07","name":"o1 Preview","developer":"Open AI","description":"New AI model from OpenAI for complex reasoning in science, coding, and mathematics.","contextLength":128000,"url":"https://aimlapi.com/models/openai-o1-preview-api","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/openai/o1","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fo1&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["o1"],"tags":["playground:chat","tier:tier_2"]},{"id":"openai/o1-2024-12-17","info":{"releasedAt":"2025-08-07","name":"o1 Preview","developer":"Open AI","description":"New AI model from OpenAI for complex reasoning in science, coding, and mathematics.","contextLength":128000,"url":"https://aimlapi.com/models/openai-o1-preview-api","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/openai/o1","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fo1-2024-12-17&endpoint=openai%2Fresponses%2Fsubmit"},"type":"openai/responses/submit","aliases":["o1-2024-12-17"],"tags":["playground:chat","tier:tier_2"]},{"id":"openai/o1-2024-12-17","info":{"releasedAt":"2025-08-07","name":"o1 Preview","developer":"Open AI","description":"New AI model from OpenAI for complex reasoning in science, coding, and mathematics.","contextLength":128000,"url":"https://aimlapi.com/models/openai-o1-preview-api","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/openai/o1","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fo1-2024-12-17&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["o1-2024-12-17"],"tags":["playground:chat","tier:tier_2"]},{"id":"openai/o3-mini","info":{"releasedAt":"2025-08-07","name":"o3 Mini","developer":"Open AI","description":"OpenAI o3-mini excels in reasoning tasks with advanced features like deliberative alignment and extensive context support.","contextLength":200000,"url":"https://aimlapi.com/models/openai-o3-mini-api","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/openai/o3-mini","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fo3-mini&endpoint=openai%2Fresponses%2Fsubmit"},"type":"openai/responses/submit","aliases":["o3-mini"],"tags":["playground:chat","tier:tier_2"]},{"id":"openai/o3-mini","info":{"releasedAt":"2025-08-07","name":"o3 Mini","developer":"Open AI","description":"OpenAI o3-mini excels in reasoning tasks with advanced features like deliberative alignment and extensive context support.","contextLength":200000,"url":"https://aimlapi.com/models/openai-o3-mini-api","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/openai/o3-mini","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fo3-mini&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["o3-mini"],"tags":["playground:chat","tier:tier_2"]},{"id":"openai/o3-mini-2025-01-31","info":{"releasedAt":"2025-08-07","name":"o3 Mini","developer":"Open AI","description":"OpenAI o3-mini excels in reasoning tasks with advanced features like deliberative alignment and extensive context support.","contextLength":200000,"url":"https://aimlapi.com/models/openai-o3-mini-api","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/openai/o3-mini","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fo3-mini-2025-01-31&endpoint=openai%2Fresponses%2Fsubmit"},"type":"openai/responses/submit","aliases":["o3-mini-2025-01-31"],"tags":["playground:chat","tier:tier_2"]},{"id":"openai/o3-mini-2025-01-31","info":{"releasedAt":"2025-08-07","name":"o3 Mini","developer":"Open AI","description":"OpenAI o3-mini excels in reasoning tasks with advanced features like deliberative alignment and extensive context support.","contextLength":200000,"url":"https://aimlapi.com/models/openai-o3-mini-api","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/openai/o3-mini","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fo3-mini-2025-01-31&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["o3-mini-2025-01-31"],"tags":["playground:chat","tier:tier_2"]},{"id":"openai/o4-mini-2025-04-16","info":{"releasedAt":"2025-08-07","name":"o4 Mini","developer":"Open AI","description":"OpenAI o4-mini is a compact reasoning model that delivers strong performance with lower latency and cost.","contextLength":200000,"outputMax":100000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/openai/o4-mini","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fo4-mini-2025-04-16&endpoint=openai%2Fresponses%2Fsubmit"},"type":"openai/responses/submit","aliases":["o4-mini-2025-04-16"],"tags":["playground:chat","tier:tier_2"]},{"id":"openai/o4-mini-2025-04-16","info":{"releasedAt":"2025-08-07","name":"o4 Mini","developer":"Open AI","description":"OpenAI o4-mini is a compact reasoning model that delivers strong performance with lower latency and cost.","contextLength":200000,"outputMax":100000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/openai/o4-mini","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fo4-mini-2025-04-16&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["o4-mini-2025-04-16"],"tags":["playground:chat","tier:tier_2"]},{"id":"openai/gpt-5-nano-2025-08-07","info":{"releasedAt":"2025-09-30","name":"GPT-5 Nano","developer":"Open AI","description":"GPT-5 nano is the most lightweight GPT-5 variant, built for ultra-low latency use cases.","contextLength":400000,"outputMax":128000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/openai/gpt-5-nano","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fgpt-5-nano-2025-08-07&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["gpt-5-nano-2025-08-07"],"tags":["playground:chat","tier:tier_2"]},{"id":"openai/gpt-5-nano-2025-08-07","info":{"releasedAt":"2025-09-30","name":"GPT-5 Nano","developer":"Open AI","description":"GPT-5 nano is the most lightweight GPT-5 variant, built for ultra-low latency use cases.","contextLength":400000,"outputMax":128000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/openai/gpt-5-nano","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fgpt-5-nano-2025-08-07&endpoint=openai%2Fresponses%2Fsubmit"},"type":"openai/responses/submit","aliases":["gpt-5-nano-2025-08-07"],"tags":["playground:chat","tier:tier_2"]},{"id":"openai/gpt-5-chat-latest","info":{"releasedAt":"2025-09-30","name":"GPT-5 Chat","developer":"Open AI","description":"GPT-5 Chat is a conversational variant of GPT-5 optimized for dialogue and instruction-following interactions.","contextLength":400000,"outputMax":16384,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/openai/gpt-5-chat","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fgpt-5-chat-latest&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["gpt-5-chat-latest"],"tags":["playground:chat","tier:tier_2"]},{"id":"openai/gpt-5-chat-latest","info":{"releasedAt":"2025-09-30","name":"GPT-5 Chat","developer":"Open AI","description":"GPT-5 Chat is a conversational variant of GPT-5 optimized for dialogue and instruction-following interactions.","contextLength":400000,"outputMax":16384,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/openai/gpt-5-chat","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fgpt-5-chat-latest&endpoint=openai%2Fresponses%2Fsubmit"},"type":"openai/responses/submit","aliases":["gpt-5-chat-latest"],"tags":["playground:chat","tier:tier_2"]},{"id":"openai/gpt-5-pro","info":{"releasedAt":"2025-11-21","name":"GPT-5 Pro","developer":"Open AI","description":"GPT-5 Pro is the most powerful GPT-5 variant, offering extended output and superior performance for complex tasks.","contextLength":400000,"outputMax":272000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/openai/gpt-5-pro","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fgpt-5-pro&endpoint=openai%2Fresponses%2Fsubmit"},"type":"openai/responses/submit","aliases":["gpt-5-pro"],"tags":["playground:chat","tier:tier_2"]},{"id":"openai/gpt-5.1-2025-11-13","info":{"releasedAt":"2025-11-14","name":"GPT-5.1","developer":"Open AI","description":"GPT-5.1 is an incremental update to GPT-5 with improved accuracy and instruction adherence.","contextLength":400000,"outputMax":128000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/openai/gpt-5-1","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fgpt-5.1-2025-11-13&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["gpt-5.1-2025-11-13"],"tags":["playground:chat","tier:tier_2"]},{"id":"openai/gpt-5.1-2025-11-13","info":{"releasedAt":"2025-11-14","name":"GPT-5.1","developer":"Open AI","description":"GPT-5.1 is an incremental update to GPT-5 with improved accuracy and instruction adherence.","contextLength":400000,"outputMax":128000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/openai/gpt-5-1","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fgpt-5.1-2025-11-13&endpoint=openai%2Fresponses%2Fsubmit"},"type":"openai/responses/submit","aliases":["gpt-5.1-2025-11-13"],"tags":["playground:chat","tier:tier_2"]},{"id":"openai/gpt-5.1-chat-latest","info":{"releasedAt":"2025-11-14","name":"GPT-5.1 Chat Latest","developer":"Open AI","description":"The latest conversational release in the GPT-5.1 series, updated for improved dialogue and reasoning.","contextLength":400000,"outputMax":128000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/openai/gpt-5-1-chat-latest","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fgpt-5.1-chat-latest&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["gpt-5.1-chat-latest"],"tags":["playground:chat","tier:tier_2"]},{"id":"openai/gpt-5.1-chat-latest","info":{"releasedAt":"2025-11-14","name":"GPT-5.1 Chat Latest","developer":"Open AI","description":"The latest conversational release in the GPT-5.1 series, updated for improved dialogue and reasoning.","contextLength":400000,"outputMax":128000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/openai/gpt-5-1-chat-latest","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fgpt-5.1-chat-latest&endpoint=openai%2Fresponses%2Fsubmit"},"type":"openai/responses/submit","aliases":["gpt-5.1-chat-latest"],"tags":["playground:chat","tier:tier_2"]},{"id":"openai/gpt-5.1-codex","info":{"releasedAt":"2025-11-14","name":"GPT-5.1 Codex","developer":"Open AI","description":"GPT-5.1 Codex is a coding-specialized model from the GPT-5.1 series for code generation and understanding.","contextLength":400000,"outputMax":128000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/openai/gpt-5-1-codex","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fgpt-5.1-codex&endpoint=openai%2Fresponses%2Fsubmit"},"type":"openai/responses/submit","aliases":["gpt-5.1-codex"],"tags":["playground:chat","tier:tier_2","playground:code"]},{"id":"openai/gpt-5.1-codex-mini","info":{"releasedAt":"2025-11-14","name":"GPT-5.1 Codex Mini","developer":"Open AI","description":"GPT-5.1 Codex Mini is a lighter coding model optimized for fast code completions and suggestions.","contextLength":400000,"outputMax":128000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/openai/gpt-5-1-codex-mini","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fgpt-5.1-codex-mini&endpoint=openai%2Fresponses%2Fsubmit"},"type":"openai/responses/submit","aliases":["gpt-5.1-codex-mini"],"tags":["playground:chat","tier:tier_2","playground:code"]},{"id":"openai/gpt-5.2-2025-12-11","info":{"releasedAt":"2025-12-11","name":"GPT-5.2","developer":"Open AI","description":"GPT-5.2 is OpenAI's next-generation language model with extended context and enhanced performance.","contextLength":400000,"outputMax":128000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/openai/gpt-5.2","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fgpt-5.2-2025-12-11&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["gpt-5.2-2025-12-11"],"tags":["playground:chat","tier:tier_2"]},{"id":"openai/gpt-5.2-2025-12-11","info":{"releasedAt":"2025-12-11","name":"GPT-5.2","developer":"Open AI","description":"GPT-5.2 is OpenAI's next-generation language model with extended context and enhanced performance.","contextLength":400000,"outputMax":128000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/openai/gpt-5.2","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fgpt-5.2-2025-12-11&endpoint=openai%2Fresponses%2Fsubmit"},"type":"openai/responses/submit","aliases":["gpt-5.2-2025-12-11"],"tags":["playground:chat","tier:tier_2"]},{"id":"openai/gpt-5.2-chat-latest","info":{"releasedAt":"2025-12-11","name":"GPT-5.2 Chat Latest","developer":"Open AI","description":"The latest conversational release in the GPT-5.2 series with improved dialogue quality.","contextLength":128000,"outputMax":16000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/openai/gpt-5.2-chat-latest","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fgpt-5.2-chat-latest&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["gpt-5.2-chat-latest"],"tags":["playground:chat","tier:tier_2"]},{"id":"openai/gpt-5.2-chat-latest","info":{"releasedAt":"2025-12-11","name":"GPT-5.2 Chat Latest","developer":"Open AI","description":"The latest conversational release in the GPT-5.2 series with improved dialogue quality.","contextLength":128000,"outputMax":16000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/openai/gpt-5.2-chat-latest","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fgpt-5.2-chat-latest&endpoint=openai%2Fresponses%2Fsubmit"},"type":"openai/responses/submit","aliases":["gpt-5.2-chat-latest"],"tags":["playground:chat","tier:tier_2"]},{"id":"openai/gpt-5.2-pro-2025-12-11","info":{"releasedAt":"2025-12-11","name":"GPT-5.2 Pro","developer":"Open AI","description":"GPT-5.2 Pro is the flagship GPT-5.2 variant offering maximum output size and reasoning depth.","contextLength":400000,"outputMax":128000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/openai/gpt-5.2-pro","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fgpt-5.2-pro-2025-12-11&endpoint=openai%2Fresponses%2Fsubmit"},"type":"openai/responses/submit","aliases":["gpt-5.2-pro-2025-12-11"],"tags":["playground:chat","tier:tier_2"]},{"id":"openai/gpt-5.2-codex","info":{"releasedAt":"2026-01-21","name":"GPT-5.2 Codex","developer":"Open AI","description":"GPT-5.2 Codex is a coding-specialized model from the GPT-5.2 series for advanced code generation.","contextLength":400000,"outputMax":128000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/openai/gpt-5.2-codex","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fgpt-5.2-codex&endpoint=openai%2Fresponses%2Fsubmit"},"type":"openai/responses/submit","aliases":["gpt-5.2-codex"],"tags":["playground:chat","tier:tier_2","playground:code"]},{"id":"openai/gpt-5.3-codex","info":{"releasedAt":"2026-03-02","name":"GPT-5.3 Codex","developer":"Open AI","description":"GPT-5.3 Codex is a coding-specialized model from the GPT-5.3 series for advanced code generation.","contextLength":400000,"outputMax":128000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/openai/gpt-5.3-codex","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fgpt-5.3-codex&endpoint=openai%2Fresponses%2Fsubmit"},"type":"openai/responses/submit","aliases":["gpt-5.3-codex"],"tags":["playground:chat","tier:tier_2","playground:code"]},{"id":"openai/gpt-5.4-2026-03-05","info":{"releasedAt":"2026-03-16","name":"GPT-5.4","developer":"Open AI","description":"","contextLength":1050000,"outputMax":128000,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fgpt-5.4-2026-03-05&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["gpt-5.4-2026-03-05"],"tags":["playground:chat","tier:tier_2"]},{"id":"openai/gpt-5.4-2026-03-05","info":{"releasedAt":"2026-03-16","name":"GPT-5.4","developer":"Open AI","description":"","contextLength":1050000,"outputMax":128000,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fgpt-5.4-2026-03-05&endpoint=openai%2Fresponses%2Fsubmit"},"type":"openai/responses/submit","aliases":["gpt-5.4-2026-03-05"],"tags":["playground:chat","tier:tier_2"]},{"id":"openai/gpt-5.4-pro-2026-03-05","info":{"releasedAt":"2026-03-16","name":"GPT-5.4 Pro","developer":"Open AI","description":"","contextLength":1050000,"outputMax":128000,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fgpt-5.4-pro-2026-03-05&endpoint=openai%2Fresponses%2Fsubmit"},"type":"openai/responses/submit","aliases":["gpt-5.4-pro-2026-03-05"],"tags":["playground:chat","tier:tier_2"]},{"id":"openai/gpt-5.5-2026-04-23","info":{"releasedAt":"2026-04-24","name":"GPT-5.5","developer":"Open AI","description":"","contextLength":1050000,"outputMax":128000,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fgpt-5.5-2026-04-23&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["gpt-5.5-2026-04-23"],"tags":["playground:chat","tier:tier_2"]},{"id":"openai/gpt-5.5-2026-04-23","info":{"releasedAt":"2026-04-24","name":"GPT-5.5","developer":"Open AI","description":"","contextLength":1050000,"outputMax":128000,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fgpt-5.5-2026-04-23&endpoint=openai%2Fresponses%2Fsubmit"},"type":"openai/responses/submit","aliases":["gpt-5.5-2026-04-23"],"tags":["playground:chat","tier:tier_2"]},{"id":"openai/gpt-5.5-pro-2026-04-23","info":{"releasedAt":"2026-04-24","name":"GPT-5.5 Pro","developer":"Open AI","description":"","contextLength":1050000,"outputMax":128000,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fgpt-5.5-pro-2026-04-23&endpoint=openai%2Fresponses%2Fsubmit"},"type":"openai/responses/submit","aliases":["gpt-5.5-pro-2026-04-23"],"tags":["playground:chat","tier:tier_2"]},{"id":"openai/gpt-5.6-sol","info":{"releasedAt":"2026-07-09","name":"GPT-5.6 Sol","developer":"Open AI","description":"","contextLength":1050000,"outputMax":128000,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fgpt-5.6-sol&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["gpt-5.6-sol"],"tags":["playground:chat","tier:tier_2"]},{"id":"openai/gpt-5.6-sol","info":{"releasedAt":"2026-07-09","name":"GPT-5.6 Sol","developer":"Open AI","description":"","contextLength":1050000,"outputMax":128000,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fgpt-5.6-sol&endpoint=openai%2Fresponses%2Fsubmit"},"type":"openai/responses/submit","aliases":["gpt-5.6-sol"],"tags":["playground:chat","tier:tier_2"]},{"id":"openai/gpt-5.6-terra","info":{"releasedAt":"2026-07-09","name":"GPT-5.6 Terra","developer":"Open AI","contextLength":1050000,"outputMax":128000,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fgpt-5.6-terra&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["gpt-5.6-terra"],"tags":["playground:chat","tier:tier_2"]},{"id":"openai/gpt-5.6-terra","info":{"releasedAt":"2026-07-09","name":"GPT-5.6 Terra","developer":"Open AI","contextLength":1050000,"outputMax":128000,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fgpt-5.6-terra&endpoint=openai%2Fresponses%2Fsubmit"},"type":"openai/responses/submit","aliases":["gpt-5.6-terra"],"tags":["playground:chat","tier:tier_2"]},{"id":"openai/gpt-5.6-luna","info":{"releasedAt":"2026-07-09","name":"GPT-5.6 Luna","developer":"Open AI","description":"","contextLength":1050000,"outputMax":128000,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fgpt-5.6-luna&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["gpt-5.6-luna"],"tags":["playground:chat","tier:tier_2"]},{"id":"openai/gpt-5.6-luna","info":{"releasedAt":"2026-07-09","name":"GPT-5.6 Luna","developer":"Open AI","description":"","contextLength":1050000,"outputMax":128000,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fgpt-5.6-luna&endpoint=openai%2Fresponses%2Fsubmit"},"type":"openai/responses/submit","aliases":["gpt-5.6-luna"],"tags":["playground:chat","tier:tier_2"]},{"id":"openai/gpt-audio","info":{"releasedAt":"2025-11-11","name":"Chat GPT audio","developer":"Open AI","description":"GPT Audio is OpenAI's latest flagship model capable of understanding and generating text and audio in real-time, designed for natural conversation and auditory tasks.","contextLength":128000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/openai/gpt-4o-audio-preview","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fgpt-audio&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["gpt-audio"],"tags":["tier:tier_2","playground:chat_audio"]},{"id":"openai/gpt-audio-2025-08-28","info":{"releasedAt":"2025-11-11","name":"Chat GPT audio","developer":"Open AI","description":"GPT Audio is OpenAI's latest flagship model capable of understanding and generating text and audio in real-time, designed for natural conversation and auditory tasks.","contextLength":128000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/openai/gpt-4o-audio-preview","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fgpt-audio-2025-08-28&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["gpt-audio-2025-08-28"],"tags":["tier:tier_2","playground:chat_audio"]},{"id":"openai/gpt-audio-mini","info":{"releasedAt":"2025-11-11","name":"Chat GPT mini audio","developer":"Open AI","description":"GPT Mini Audio adds speech-to-text and text-to-speech abilities to the efficient GPT Mini model, optimized for voice interfaces in smaller applications.","contextLength":128000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/openai/gpt-4o-mini-audio-preview","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fgpt-audio-mini&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["gpt-audio-mini"],"tags":["tier:tier_2","playground:chat_audio"]},{"id":"openai/gpt-audio-mini-2025-10-06","info":{"releasedAt":"2025-11-11","name":"Chat GPT mini audio","developer":"Open AI","description":"GPT Mini Audio adds speech-to-text and text-to-speech abilities to the efficient GPT Mini model, optimized for voice interfaces in smaller applications.","contextLength":128000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/openai/gpt-4o-mini-audio-preview","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fgpt-audio-mini-2025-10-06&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["gpt-audio-mini-2025-10-06"],"tags":["tier:tier_2","playground:chat_audio"]},{"id":"openai/text-embedding-3-small","info":{"releasedAt":"2025-12-12","name":"Text Embedding 3 Small","developer":"Open AI","description":"OpenAI's efficient text embedding model for semantic search and similarity tasks at lower cost.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/embedding-models/openai/text-embedding-3-small","contextLength":8000,"docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Ftext-embedding-3-small&endpoint=openai%2Fembeddings"},"type":"openai/embeddings","aliases":["text-embedding-3-small"],"tags":["playground:embeddings","tier:tier_2"]},{"id":"openai/text-embedding-3-large","info":{"releasedAt":"2025-12-12","name":"Text Embedding 3 Large","developer":"Open AI","description":"High-performance embedding model with flexible dimensions and superior accuracy.","url":"https://aimlapi.com/models/text-embedding-3-large","docsUrl":"https://docs.aimlapi.com/api-references/embedding-models/openai/text-embedding-3-large","contextLength":8000,"docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Ftext-embedding-3-large&endpoint=openai%2Fembeddings"},"type":"openai/embeddings","aliases":["text-embedding-3-large"],"tags":["playground:embeddings","tier:tier_2"]},{"id":"openai/text-embedding-ada-002","info":{"releasedAt":"2025-12-12","name":"Text Embedding Ada 002","developer":"Open AI","description":"Reliable embedding model offering solid performance for various tasks.","url":"https://aimlapi.com/models/text-embedding-ada-002","docsUrl":"https://docs.aimlapi.com/api-references/embedding-models/openai/text-embedding-ada-002","contextLength":8000,"docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Ftext-embedding-ada-002&endpoint=openai%2Fembeddings"},"type":"openai/embeddings","aliases":["text-embedding-ada-002"],"tags":["playground:embeddings","tier:tier_2"]},{"id":"openai/sora-2-t2v","info":{"releasedAt":"2025-12-02","name":"Sora 2 Text to Video","developer":"Open AI","description":"Sora 2 generates high-quality videos from text descriptions using OpenAI's advanced video generation architecture.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/video-models/openai/sora-2-t2v","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fsora-2-t2v&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":["sora-2-t2v"],"tags":["playground:video","tier:tier_2"]},{"id":"openai/sora-2","info":{"releasedAt":"2025-12-02","name":"Sora 2 Text to Video","developer":"Open AI","description":"Sora 2 generates high-quality videos from text descriptions using OpenAI's advanced video generation architecture.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/video-models/openai/sora-2-t2v","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fsora-2&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":["sora-2"],"tags":["playground:video","tier:tier_2"]},{"id":"openai/sora-2-i2v","info":{"releasedAt":"2025-12-02","name":"Sora 2 Image to Video","developer":"Open AI","description":"Sora 2 animates still images into coherent videos using OpenAI's advanced video generation architecture.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/video-models/openai/sora-2-i2v","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fsora-2-i2v&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":["sora-2-i2v"],"tags":["playground:video","tier:tier_2"]},{"id":"openai/sora-2-pro-t2v","info":{"releasedAt":"2025-12-02","name":"Sora 2 Pro Text to Video","developer":"Open AI","description":"Sora 2 Pro generates high-fidelity, longer-duration videos from text prompts with enhanced cinematic quality.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/video-models/openai/sora-2-pro-t2v","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fsora-2-pro-t2v&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":["sora-2-pro-t2v"],"tags":["playground:video","tier:tier_2"]},{"id":"openai/sora-2-pro","info":{"releasedAt":"2025-12-02","name":"Sora 2 Pro Text to Video","developer":"Open AI","description":"Sora 2 Pro generates high-fidelity, longer-duration videos from text prompts with enhanced cinematic quality.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/video-models/openai/sora-2-pro-t2v","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fsora-2-pro&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":["sora-2-pro"],"tags":["playground:video","tier:tier_2"]},{"id":"openai/sora-2-pro-i2v","info":{"releasedAt":"2025-12-02","name":"Sora 2 Pro Image to Video","developer":"Open AI","description":"Sora 2 Pro animates still images into high-fidelity, longer-duration videos with enhanced cinematic quality.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/video-models/openai/sora-2-pro-i2v","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fsora-2-pro-i2v&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":["sora-2-pro-i2v"],"tags":["playground:video","tier:tier_2"]},{"id":"openai/gpt-4o-transcribe","info":{"releasedAt":"2025-12-30","name":"GPT-4o Transcribe","developer":"Open AI","description":"Advanced speech-to-text model using GPT-4o for improved accuracy and language recognition. 16,000 context window, 2,000 max output tokens.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/speech-models/speech-to-text/openai/gpt-4o-transcribe","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fgpt-4o-transcribe&endpoint=internal%2Fspeech-to-text%2Fsubmit"},"type":"internal/speech-to-text/submit","aliases":["gpt-4o-transcribe"],"tags":["playground:stt","tier:tier_2"]},{"id":"openai/gpt-4o-mini-transcribe","info":{"releasedAt":"2025-12-30","name":"GPT-4o Mini Transcribe","developer":"Open AI","description":"Efficient speech-to-text model using GPT-4o mini with improved accuracy compared to Whisper. 16,000 context window, 2,000 max output tokens.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/speech-models/speech-to-text/openai/gpt-4o-mini-transcribe","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fgpt-4o-mini-transcribe&endpoint=internal%2Fspeech-to-text%2Fsubmit"},"type":"internal/speech-to-text/submit","aliases":["gpt-4o-mini-transcribe"],"tags":["playground:stt","tier:tier_2"]},{"id":"openai/gpt-4o-mini-tts","info":{"releasedAt":"2026-01-05","name":"GPT-4o Mini TTS","developer":"Open AI","description":"GPT-4o mini TTS is a text-to-speech model built on GPT-4o mini, a fast and powerful language model. Use it to convert text to natural sounding spoken text with customizable voice characteristics through instructions. The maximum number of input tokens is 2000.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/speech-models/text-to-speech/openai/gpt-4o-mini-tts","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fgpt-4o-mini-tts&endpoint=internal%2Ftext-to-speech"},"type":"internal/text-to-speech","aliases":["gpt-4o-mini-tts"],"tags":["playground:tts","tier:tier_2"]},{"id":"openai/tts-1","info":{"releasedAt":"2026-01-05","name":"TTS-1","developer":"Open AI","description":"TTS-1 is a real-time text-to-speech model optimized for speed. Provides lower latency but at a lower quality than TTS-1 HD.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/speech-models/text-to-speech/openai/tts-1","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Ftts-1&endpoint=internal%2Ftext-to-speech"},"type":"internal/text-to-speech","aliases":["tts-1"],"tags":["playground:tts","tier:tier_2"]},{"id":"openai/tts-1-hd","info":{"releasedAt":"2026-01-05","name":"TTS-1 HD","developer":"Open AI","description":"TTS-1 HD is a high-quality text-to-speech model that provides superior audio quality compared to TTS-1.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/speech-models/text-to-speech/openai/tts-1-hd","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Ftts-1-hd&endpoint=internal%2Ftext-to-speech"},"type":"internal/text-to-speech","aliases":["tts-1-hd"],"tags":["playground:tts","tier:tier_2"]},{"id":"openai/o3-pro","info":{"releasedAt":"2025-08-07","name":"o3 Pro","developer":"Open AI","description":"OpenAI o3-pro is an enhanced reasoning model designed for the most demanding tasks requiring deep deliberation.","contextLength":200000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/openai/o3-pro","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fo3-pro&endpoint=openai%2Fresponses%2Fsubmit"},"type":"openai/responses/submit","aliases":["o3-pro"],"tags":["playground:chat","tier:tier_2"]},{"id":"openai/o3-2025-04-16","info":{"releasedAt":"2025-09-30","name":"o3","developer":"Open AI","description":"OpenAI o3 is a frontier reasoning model with exceptional performance on complex scientific, math, and coding tasks.","contextLength":200000,"outputMax":100000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/openai/o3","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fo3-2025-04-16&endpoint=openai%2Fresponses%2Fsubmit"},"type":"openai/responses/submit","aliases":["o3-2025-04-16"],"tags":["playground:chat","tier:tier_2"]},{"id":"openai/o3-2025-04-16","info":{"releasedAt":"2025-09-30","name":"o3","developer":"Open AI","description":"OpenAI o3 is a frontier reasoning model with exceptional performance on complex scientific, math, and coding tasks.","contextLength":200000,"outputMax":100000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/openai/o3","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fo3-2025-04-16&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["o3-2025-04-16"],"tags":["playground:chat","tier:tier_2"]},{"id":"openai/gpt-5-2025-08-07","info":{"releasedAt":"2025-09-30","name":"GPT-5","developer":"Open AI","description":"GPT-5 is OpenAI's most advanced language model with a 400K token context window and superior reasoning capabilities.","contextLength":400000,"outputMax":128000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/openai/gpt-5","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fgpt-5-2025-08-07&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["gpt-5-2025-08-07"],"tags":["playground:chat","tier:tier_2","playground:code"]},{"id":"openai/gpt-5-2025-08-07","info":{"releasedAt":"2025-09-30","name":"GPT-5","developer":"Open AI","description":"GPT-5 is OpenAI's most advanced language model with a 400K token context window and superior reasoning capabilities.","contextLength":400000,"outputMax":128000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/openai/gpt-5","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fgpt-5-2025-08-07&endpoint=openai%2Fresponses%2Fsubmit"},"type":"openai/responses/submit","aliases":["gpt-5-2025-08-07"],"tags":["playground:chat","tier:tier_2","playground:code"]},{"id":"openai/gpt-5-mini-2025-08-07","info":{"releasedAt":"2025-09-30","name":"GPT-5 Mini","developer":"Open AI","description":"GPT-5 mini delivers GPT-5 capabilities in a smaller, faster package optimized for cost-sensitive applications.","contextLength":400000,"outputMax":128000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/openai/gpt-5-mini","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fgpt-5-mini-2025-08-07&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["gpt-5-mini-2025-08-07"],"tags":["playground:chat","tier:tier_2"]},{"id":"openai/gpt-5-mini-2025-08-07","info":{"releasedAt":"2025-09-30","name":"GPT-5 Mini","developer":"Open AI","description":"GPT-5 mini delivers GPT-5 capabilities in a smaller, faster package optimized for cost-sensitive applications.","contextLength":400000,"outputMax":128000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/openai/gpt-5-mini","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fgpt-5-mini-2025-08-07&endpoint=openai%2Fresponses%2Fsubmit"},"type":"openai/responses/submit","aliases":["gpt-5-mini-2025-08-07"],"tags":["playground:chat","tier:tier_2","playground:code"]},{"id":"openai/gpt-image-1","info":{"releasedAt":"2025-10-13","developer":"Open AI","description":"GPT Image 1 is OpenAI's first-generation image generation model combining language understanding with visual synthesis.","name":"GPT Image 1","url":"","docsUrl":"https://docs.aimlapi.com/api-references/image-models/openai/gpt-image-1","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fgpt-image-1&endpoint=openai%2Fimage-generations"},"type":"openai/image-generations","aliases":["gpt-image-1"],"tags":["playground:image","tier:tier_2"]},{"id":"openai/gpt-image-1","info":{"releasedAt":"2025-10-13","developer":"Open AI","description":"GPT Image 1 is OpenAI's first-generation image generation model combining language understanding with visual synthesis.","name":"GPT Image 1","url":"","docsUrl":"https://docs.aimlapi.com/api-references/image-models/openai/gpt-image-1","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fgpt-image-1&endpoint=openai%2Fimage-editing"},"type":"openai/image-editing","aliases":["gpt-image-1"],"tags":["playground:image","tier:tier_2"]},{"id":"openai/gpt-image-1-mini","info":{"releasedAt":"2025-11-07","developer":"Open AI","description":"GPT Image 1 Mini is a compact image generation model offering faster and more affordable image creation.","name":"GPT Image 1 Mini","url":"","docsUrl":"https://docs.aimlapi.com/api-references/image-models/openai/gpt-image-1-mini","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fgpt-image-1-mini&endpoint=openai%2Fimage-generations"},"type":"openai/image-generations","aliases":["gpt-image-1-mini"],"tags":["playground:image","tier:tier_2"]},{"id":"openai/gpt-image-1-mini","info":{"releasedAt":"2025-11-07","developer":"Open AI","description":"GPT Image 1 Mini is a compact image generation model offering faster and more affordable image creation.","name":"GPT Image 1 Mini","url":"","docsUrl":"https://docs.aimlapi.com/api-references/image-models/openai/gpt-image-1-mini","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fgpt-image-1-mini&endpoint=openai%2Fimage-editing"},"type":"openai/image-editing","aliases":["gpt-image-1-mini"],"tags":["playground:image","tier:tier_2"]},{"id":"openai/gpt-image-1.5","info":{"releasedAt":"2025-12-17","developer":"Open AI","description":"GPT-Image-1.5 is an updated image generation model with improved visual quality and prompt adherence.","name":"GPT Image 1.5","url":"","docsUrl":"https://docs.aimlapi.com/api-references/image-models/openai/gpt-image-1-mini-1","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fgpt-image-1.5&endpoint=openai%2Fimage-generations"},"type":"openai/image-generations","aliases":["gpt-image-1.5"],"tags":["playground:image","tier:tier_2"]},{"id":"openai/gpt-image-1.5","info":{"releasedAt":"2025-12-17","developer":"Open AI","description":"GPT-Image-1.5 is an updated image generation model with improved visual quality and prompt adherence.","name":"GPT Image 1.5","url":"","docsUrl":"https://docs.aimlapi.com/api-references/image-models/openai/gpt-image-1-mini-1","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fgpt-image-1.5&endpoint=openai%2Fimage-editing"},"type":"openai/image-editing","aliases":["gpt-image-1.5"],"tags":["playground:image","tier:tier_2"]},{"id":"openai/gpt-image-2","info":{"releasedAt":"2026-04-22","developer":"Open AI","description":"","name":"GPT Image 2","url":"","docsUrl":"","isHottest":true,"docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fgpt-image-2&endpoint=openai%2Fimage-generations"},"type":"openai/image-generations","aliases":["gpt-image-2"],"tags":["playground:image","tier:tier_2"]},{"id":"openai/gpt-image-2","info":{"releasedAt":"2026-04-22","developer":"Open AI","description":"","name":"GPT Image 2","url":"","docsUrl":"","isHottest":true,"docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fgpt-image-2&endpoint=openai%2Fimage-editing"},"type":"openai/image-editing","aliases":["gpt-image-2"],"tags":["playground:image","tier:tier_2"]},{"id":"openai/gpt-4o-mini-search-preview","info":{"releasedAt":"2025-08-07","name":"GPT-4o Mini Search Preview","developer":"Open AI","description":"GPT-4o Mini Search Preview is a more efficient variant of GPT-4o that includes search capabilities while being optimized for speed and affordability.","contextLength":128000,"url":"https://aimlapi.com/models/gpt-4o-mini-search-preview-api","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/openai/gpt-4o-mini-search-preview","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fgpt-4o-mini-search-preview&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["gpt-4o-mini-search-preview"],"tags":["playground:chat","tier:tier_2"]},{"id":"openai/gpt-4o-search-preview","info":{"releasedAt":"2025-08-07","name":"GPT-4o Search Preview","developer":"Open AI","description":"GPT-4o Search Preview blends OpenAI's GPT-4o capabilities with live web search results, allowing users to get up-to-date answers grounded in real-time data.","contextLength":128000,"url":"https://aimlapi.com/models/gpt-4o-search-preview-api","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/openai/gpt-4o-search-preview","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fgpt-4o-search-preview&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["gpt-4o-search-preview"],"tags":["playground:chat","tier:tier_2"]},{"id":"openai/gpt-oss-120b","info":{"releasedAt":"2025-09-09","name":"GPT OSS 120B","developer":"Open AI","description":"GPT OSS 120B is the most powerful Open AI open weight model.","contextLength":131000,"outputMax":131072,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/openai/gpt-oss-120b","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fgpt-oss-120b&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["gpt-oss-120b"],"tags":["playground:chat","tier:tier_2"]},{"id":"openai/gpt-oss-20b","info":{"releasedAt":"2025-09-09","name":"GPT OSS 20B","developer":"Open AI","description":"GPT OSS 20B is a powerful Open AI open weight model.","contextLength":131000,"outputMax":131072,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/openai/gpt-oss-20b","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fgpt-oss-20b&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["gpt-oss-20b"],"tags":["playground:chat","tier:tier_2"]},{"id":"openai/gpt-5","info":{"releasedAt":"2025-09-30","name":"GPT-5","developer":"Open AI","description":"GPT-5 is OpenAI's most advanced language model with a 400K token context window and superior reasoning capabilities.","contextLength":400000,"outputMax":128000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/openai/gpt-5","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fgpt-5&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["gpt-5","gpt-5-2025-08-07","openai/gpt-5-2025-08-07"],"tags":["playground:chat","tier:tier_2","playground:code"]},{"id":"openai/gpt-5-mini","info":{"releasedAt":"2025-09-30","name":"GPT-5 Mini","developer":"Open AI","description":"GPT-5 mini delivers GPT-5 capabilities in a smaller, faster package optimized for cost-sensitive applications.","contextLength":400000,"outputMax":128000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/openai/gpt-5-mini","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fgpt-5-mini&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["gpt-5-mini","gpt-5-mini-2025-08-07","openai/gpt-5-mini-2025-08-07"],"tags":["playground:chat","tier:tier_2","playground:code"]},{"id":"openai/gpt-5-nano","info":{"releasedAt":"2025-09-30","name":"GPT-5 Nano","developer":"Open AI","description":"GPT-5 nano is the most lightweight GPT-5 variant, built for ultra-low latency use cases.","contextLength":400000,"outputMax":128000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/openai/gpt-5-nano","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fgpt-5-nano&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["gpt-5-nano","gpt-5-nano-2025-08-07","openai/gpt-5-nano-2025-08-07"],"tags":["playground:chat","tier:tier_2"]},{"id":"openai/gpt-5.6-luna-pro","info":{"releasedAt":"2026-07-09","name":"GPT-5.6 Luna Pro","developer":"Open AI","description":"","contextLength":1050000,"outputMax":128000,"url":"","docsUrl":"","isHottest":true,"docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fgpt-5.6-luna-pro&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["gpt-5.6-luna-pro"],"tags":["playground:chat","tier:tier_2"]},{"id":"openai/gpt-5.6-terra-pro","info":{"releasedAt":"2026-07-09","name":"GPT-5.6 Terra Pro","developer":"Open AI","description":"","contextLength":1050000,"outputMax":128000,"url":"","docsUrl":"","isHottest":true,"docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fgpt-5.6-terra-pro&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["gpt-5.6-terra-pro"],"tags":["playground:chat","tier:tier_2"]},{"id":"openai/gpt-5.6-sol-pro","info":{"releasedAt":"2026-07-09","name":"GPT-5.6 Sol Pro","developer":"Open AI","description":"","contextLength":1050000,"outputMax":128000,"url":"","docsUrl":"","isHottest":true,"docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fgpt-5.6-sol-pro&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["gpt-5.6-sol-pro"],"tags":["playground:chat","tier:tier_2"]},{"id":"openai/gpt-chat-latest","info":{"releasedAt":"2026-05-05","name":"GPT Chat Latest","developer":"Open AI","contextLength":400000,"outputMax":128000,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fgpt-chat-latest&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["gpt-chat-latest"],"tags":["playground:chat","tier:tier_2"]},{"id":"openai/gpt-5.5-pro","info":{"releasedAt":"2026-04-24","name":"GPT-5.5 Pro","developer":"Open AI","description":"","contextLength":1050000,"outputMax":128000,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fgpt-5.5-pro&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["gpt-5.5-pro"],"tags":["playground:chat","tier:tier_2"]},{"id":"openai/gpt-5.4-image-2","info":{"releasedAt":"2026-04-21","name":"GPT-5.4 Image 2","developer":"Open AI","contextLength":272000,"outputMax":128000,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fgpt-5.4-image-2&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["gpt-5.4-image-2"],"tags":["playground:chat","tier:tier_2"]},{"id":"openai/gpt-5.4-nano","info":{"releasedAt":"2026-03-17","name":"GPT-5.4 Nano","developer":"Open AI","contextLength":400000,"outputMax":128000,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fgpt-5.4-nano&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["gpt-5.4-nano"],"tags":["playground:chat","tier:tier_2"]},{"id":"openai/gpt-5.4-mini","info":{"releasedAt":"2026-03-17","name":"GPT-5.4 Mini","developer":"Open AI","contextLength":400000,"outputMax":128000,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fgpt-5.4-mini&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["gpt-5.4-mini"],"tags":["playground:chat","tier:tier_2"]},{"id":"openai/gpt-5.4-pro","info":{"releasedAt":"2026-03-16","name":"GPT-5.4 Pro","developer":"Open AI","description":"","contextLength":1050000,"outputMax":128000,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fgpt-5.4-pro&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["gpt-5.4-pro"],"tags":["playground:chat","tier:tier_2"]},{"id":"openai/gpt-5.3-chat","info":{"releasedAt":"2026-03-03","name":"GPT-5.3 Chat","developer":"Open AI","contextLength":128000,"outputMax":16384,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fgpt-5.3-chat&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["gpt-5.3-chat"],"tags":["playground:chat","tier:tier_2"]},{"id":"openai/gpt-5.3-codex","info":{"releasedAt":"2026-03-02","name":"GPT-5.3 Codex","developer":"Open AI","description":"GPT-5.3 Codex is a coding-specialized model from the GPT-5.3 series for advanced code generation.","contextLength":400000,"outputMax":128000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/openai/gpt-5.3-codex","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fgpt-5.3-codex&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["gpt-5.3-codex"],"tags":["playground:chat","tier:tier_2"]},{"id":"openai/gpt-5.2-codex","info":{"releasedAt":"2026-01-21","name":"GPT-5.2 Codex","developer":"Open AI","description":"GPT-5.2 Codex is a coding-specialized model from the GPT-5.2 series for advanced code generation.","contextLength":400000,"outputMax":128000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/openai/gpt-5.2-codex","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fgpt-5.2-codex&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["gpt-5.2-codex"],"tags":["playground:chat","tier:tier_2"]},{"id":"openai/gpt-5.2-chat","info":{"releasedAt":"2025-12-10","name":"GPT-5.2 Chat","developer":"Open AI","contextLength":128000,"outputMax":16384,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fgpt-5.2-chat&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["gpt-5.2-chat"],"tags":["playground:chat","tier:tier_2"]},{"id":"openai/gpt-5.2-pro","info":{"releasedAt":"2025-12-11","name":"GPT-5.2 Pro","developer":"Open AI","description":"GPT-5.2 Pro is the flagship GPT-5.2 variant offering maximum output size and reasoning depth.","contextLength":400000,"outputMax":128000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/openai/gpt-5.2-pro","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fgpt-5.2-pro&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["gpt-5.2-pro"],"tags":["playground:chat","tier:tier_2"]},{"id":"openai/gpt-5.1-codex-max","info":{"releasedAt":"2025-12-04","name":"GPT-5.1-Codex-Max","developer":"Open AI","contextLength":400000,"outputMax":128000,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fgpt-5.1-codex-max&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["gpt-5.1-codex-max"],"tags":["playground:chat","tier:tier_2"]},{"id":"openai/gpt-5.1-chat","info":{"releasedAt":"2025-11-13","name":"GPT-5.1 Chat","developer":"Open AI","contextLength":128000,"outputMax":32000,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fgpt-5.1-chat&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["gpt-5.1-chat"],"tags":["playground:chat","tier:tier_2"]},{"id":"openai/gpt-5.1-codex","info":{"releasedAt":"2025-11-14","name":"GPT-5.1 Codex","developer":"Open AI","description":"GPT-5.1 Codex is a coding-specialized model from the GPT-5.1 series for code generation and understanding.","contextLength":400000,"outputMax":128000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/openai/gpt-5-1-codex","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fgpt-5.1-codex&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["gpt-5.1-codex"],"tags":["playground:chat","tier:tier_2"]},{"id":"openai/gpt-5.1-codex-mini","info":{"releasedAt":"2025-11-14","name":"GPT-5.1 Codex Mini","developer":"Open AI","description":"GPT-5.1 Codex Mini is a lighter coding model optimized for fast code completions and suggestions.","contextLength":400000,"outputMax":128000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/openai/gpt-5-1-codex-mini","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fgpt-5.1-codex-mini&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["gpt-5.1-codex-mini"],"tags":["playground:chat","tier:tier_2"]},{"id":"openai/gpt-oss-safeguard-20b","info":{"releasedAt":"2025-10-29","name":"gpt-oss-safeguard-20b","developer":"Open AI","contextLength":131072,"outputMax":65536,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fgpt-oss-safeguard-20b&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["gpt-oss-safeguard-20b"],"tags":["playground:chat","tier:tier_2"]},{"id":"openai/gpt-5-image-mini","info":{"releasedAt":"2025-10-16","name":"GPT-5 Image Mini","developer":"Open AI","contextLength":400000,"outputMax":128000,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fgpt-5-image-mini&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["gpt-5-image-mini"],"tags":["playground:chat","tier:tier_2"]},{"id":"openai/gpt-5-image","info":{"releasedAt":"2025-10-14","name":"GPT-5 Image","developer":"Open AI","contextLength":400000,"outputMax":128000,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fgpt-5-image&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["gpt-5-image"],"tags":["playground:chat","tier:tier_2"]},{"id":"openai/o3-deep-research","info":{"releasedAt":"2025-10-10","name":"o3 Deep Research","developer":"Open AI","contextLength":200000,"outputMax":100000,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fo3-deep-research&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["o3-deep-research"],"tags":["playground:chat","tier:tier_2"]},{"id":"openai/o4-mini-deep-research","info":{"releasedAt":"2025-10-10","name":"o4 Mini Deep Research","developer":"Open AI","contextLength":200000,"outputMax":100000,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fo4-mini-deep-research&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["o4-mini-deep-research"],"tags":["playground:chat","tier:tier_2"]},{"id":"openai/gpt-5-pro","info":{"releasedAt":"2025-11-21","name":"GPT-5 Pro","developer":"Open AI","description":"GPT-5 Pro is the most powerful GPT-5 variant, offering extended output and superior performance for complex tasks.","contextLength":400000,"outputMax":272000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/openai/gpt-5-pro","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fgpt-5-pro&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["gpt-5-pro"],"tags":["playground:chat","tier:tier_2"]},{"id":"openai/gpt-5-codex","info":{"releasedAt":"2025-09-23","name":"GPT-5 Codex","developer":"Open AI","contextLength":400000,"outputMax":128000,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fgpt-5-codex&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["gpt-5-codex"],"tags":["playground:chat","tier:tier_2"]},{"id":"openai/o3-pro","info":{"releasedAt":"2025-08-07","name":"o3 Pro","developer":"Open AI","description":"OpenAI o3-pro is an enhanced reasoning model designed for the most demanding tasks requiring deep deliberation.","contextLength":200000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/openai/o3-pro","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fo3-pro&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["o3-pro"],"tags":["playground:chat","tier:tier_2"]},{"id":"openai/o1-pro","info":{"releasedAt":"2025-03-19","name":"o1-pro","developer":"Open AI","contextLength":200000,"outputMax":100000,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fo1-pro&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["o1-pro"],"tags":["playground:chat","tier:tier_2"]},{"id":"openai/gpt-4-turbo-preview","info":{"releasedAt":"2024-01-25","name":"GPT-4 Turbo Preview","developer":"Open AI","contextLength":128000,"outputMax":4096,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fgpt-4-turbo-preview&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["gpt-4-turbo-preview"],"tags":["playground:chat","tier:tier_2"]},{"id":"openai/gpt-5","info":{"releasedAt":"2025-09-30","name":"GPT-5","developer":"Open AI","description":"GPT-5 is OpenAI's most advanced language model with a 400K token context window and superior reasoning capabilities.","contextLength":400000,"outputMax":128000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/openai/gpt-5","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fgpt-5&endpoint=openai%2Fresponses%2Fsubmit"},"type":"openai/responses/submit","aliases":["gpt-5","gpt-5-2025-08-07","openai/gpt-5-2025-08-07"],"tags":["playground:chat","tier:tier_2","playground:code"]},{"id":"openai/gpt-5-mini","info":{"releasedAt":"2025-09-30","name":"GPT-5 Mini","developer":"Open AI","description":"GPT-5 mini delivers GPT-5 capabilities in a smaller, faster package optimized for cost-sensitive applications.","contextLength":400000,"outputMax":128000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/openai/gpt-5-mini","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fgpt-5-mini&endpoint=openai%2Fresponses%2Fsubmit"},"type":"openai/responses/submit","aliases":["gpt-5-mini","gpt-5-mini-2025-08-07","openai/gpt-5-mini-2025-08-07"],"tags":["playground:chat","tier:tier_2","playground:code"]},{"id":"openai/gpt-5-nano","info":{"releasedAt":"2025-09-30","name":"GPT-5 Nano","developer":"Open AI","description":"GPT-5 nano is the most lightweight GPT-5 variant, built for ultra-low latency use cases.","contextLength":400000,"outputMax":128000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/openai/gpt-5-nano","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fgpt-5-nano&endpoint=openai%2Fresponses%2Fsubmit"},"type":"openai/responses/submit","aliases":["gpt-5-nano","gpt-5-nano-2025-08-07","openai/gpt-5-nano-2025-08-07"],"tags":["playground:chat","tier:tier_2"]},{"id":"openai/gpt-latest","info":{"releasedAt":"2026-04-27","name":"GPT Latest","developer":"Open AI","contextLength":1050000,"outputMax":128000,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fgpt-latest&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["gpt-latest"],"tags":["playground:chat","tier:tier_2"]},{"id":"openai/gpt-mini-latest","info":{"releasedAt":"2026-04-27","name":"GPT Mini Latest","developer":"Open AI","contextLength":400000,"outputMax":128000,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fgpt-mini-latest&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["gpt-mini-latest"],"tags":["playground:chat","tier:tier_2"]},{"id":"openai/gpt-5-1","info":{"releasedAt":"2025-11-14","name":"GPT-5.1","developer":"Open AI","description":"GPT-5.1 is an incremental update to GPT-5 with improved accuracy and instruction adherence.","contextLength":400000,"outputMax":128000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/openai/gpt-5-1","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fgpt-5-1&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":[],"tags":["playground:chat","tier:tier_2"]},{"id":"openai/gpt-5-1","info":{"releasedAt":"2025-11-14","name":"GPT-5.1","developer":"Open AI","description":"GPT-5.1 is an incremental update to GPT-5 with improved accuracy and instruction adherence.","contextLength":400000,"outputMax":128000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/openai/gpt-5-1","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fgpt-5-1&endpoint=openai%2Fresponses%2Fsubmit"},"type":"openai/responses/submit","aliases":[],"tags":["playground:chat","tier:tier_2"]},{"id":"openai/gpt-5-1-chat-latest","info":{"releasedAt":"2025-11-14","name":"GPT-5.1 Chat Latest","developer":"Open AI","description":"The latest conversational release in the GPT-5.1 series, updated for improved dialogue and reasoning.","contextLength":400000,"outputMax":128000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/openai/gpt-5-1-chat-latest","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fgpt-5-1-chat-latest&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":[],"tags":["playground:chat","tier:tier_2"]},{"id":"openai/gpt-5-1-chat-latest","info":{"releasedAt":"2025-11-14","name":"GPT-5.1 Chat Latest","developer":"Open AI","description":"The latest conversational release in the GPT-5.1 series, updated for improved dialogue and reasoning.","contextLength":400000,"outputMax":128000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/openai/gpt-5-1-chat-latest","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fgpt-5-1-chat-latest&endpoint=openai%2Fresponses%2Fsubmit"},"type":"openai/responses/submit","aliases":[],"tags":["playground:chat","tier:tier_2"]},{"id":"openai/gpt-5-1-codex","info":{"releasedAt":"2025-11-14","name":"GPT-5.1 Codex","developer":"Open AI","description":"GPT-5.1 Codex is a coding-specialized model from the GPT-5.1 series for code generation and understanding.","contextLength":400000,"outputMax":128000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/openai/gpt-5-1-codex","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fgpt-5-1-codex&endpoint=openai%2Fresponses%2Fsubmit"},"type":"openai/responses/submit","aliases":[],"tags":["playground:chat","tier:tier_2","playground:code"]},{"id":"openai/gpt-5-1-codex-mini","info":{"releasedAt":"2025-11-14","name":"GPT-5.1 Codex Mini","developer":"Open AI","description":"GPT-5.1 Codex Mini is a lighter coding model optimized for fast code completions and suggestions.","contextLength":400000,"outputMax":128000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/openai/gpt-5-1-codex-mini","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fgpt-5-1-codex-mini&endpoint=openai%2Fresponses%2Fsubmit"},"type":"openai/responses/submit","aliases":[],"tags":["playground:chat","tier:tier_2","playground:code"]},{"id":"openai/gpt-5-2","info":{"releasedAt":"2025-12-11","name":"GPT-5.2","developer":"Open AI","description":"GPT-5.2 is OpenAI's next-generation language model with extended context and enhanced performance.","contextLength":400000,"outputMax":128000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/openai/gpt-5.2","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fgpt-5-2&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":[],"tags":["playground:chat","tier:tier_2"]},{"id":"openai/gpt-5-2","info":{"releasedAt":"2025-12-11","name":"GPT-5.2","developer":"Open AI","description":"GPT-5.2 is OpenAI's next-generation language model with extended context and enhanced performance.","contextLength":400000,"outputMax":128000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/openai/gpt-5.2","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fgpt-5-2&endpoint=openai%2Fresponses%2Fsubmit"},"type":"openai/responses/submit","aliases":[],"tags":["playground:chat","tier:tier_2"]},{"id":"openai/gpt-5-2-chat-latest","info":{"releasedAt":"2025-12-11","name":"GPT-5.2 Chat Latest","developer":"Open AI","description":"The latest conversational release in the GPT-5.2 series with improved dialogue quality.","contextLength":128000,"outputMax":16000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/openai/gpt-5.2-chat-latest","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fgpt-5-2-chat-latest&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":[],"tags":["playground:chat","tier:tier_2"]},{"id":"openai/gpt-5-2-chat-latest","info":{"releasedAt":"2025-12-11","name":"GPT-5.2 Chat Latest","developer":"Open AI","description":"The latest conversational release in the GPT-5.2 series with improved dialogue quality.","contextLength":128000,"outputMax":16000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/openai/gpt-5.2-chat-latest","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fgpt-5-2-chat-latest&endpoint=openai%2Fresponses%2Fsubmit"},"type":"openai/responses/submit","aliases":[],"tags":["playground:chat","tier:tier_2"]},{"id":"openai/gpt-5-2-pro","info":{"releasedAt":"2025-12-11","name":"GPT-5.2 Pro","developer":"Open AI","description":"GPT-5.2 Pro is the flagship GPT-5.2 variant offering maximum output size and reasoning depth.","contextLength":400000,"outputMax":128000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/openai/gpt-5.2-pro","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fgpt-5-2-pro&endpoint=openai%2Fresponses%2Fsubmit"},"type":"openai/responses/submit","aliases":[],"tags":["playground:chat","tier:tier_2"]},{"id":"openai/gpt-5-2-codex","info":{"releasedAt":"2026-01-21","name":"GPT-5.2 Codex","developer":"Open AI","description":"GPT-5.2 Codex is a coding-specialized model from the GPT-5.2 series for advanced code generation.","contextLength":400000,"outputMax":128000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/openai/gpt-5.2-codex","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fgpt-5-2-codex&endpoint=openai%2Fresponses%2Fsubmit"},"type":"openai/responses/submit","aliases":[],"tags":["playground:chat","tier:tier_2","playground:code"]},{"id":"openai/gpt-5-3-codex","info":{"releasedAt":"2026-03-02","name":"GPT-5.3 Codex","developer":"Open AI","description":"GPT-5.3 Codex is a coding-specialized model from the GPT-5.3 series for advanced code generation.","contextLength":400000,"outputMax":128000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/openai/gpt-5.3-codex","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fgpt-5-3-codex&endpoint=openai%2Fresponses%2Fsubmit"},"type":"openai/responses/submit","aliases":[],"tags":["playground:chat","tier:tier_2","playground:code"]},{"id":"openai/gpt-5-4","info":{"releasedAt":"2026-03-16","name":"GPT-5.4","developer":"Open AI","description":"","contextLength":1050000,"outputMax":128000,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fgpt-5-4&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":[],"tags":["playground:chat","tier:tier_2"]},{"id":"openai/gpt-5-4","info":{"releasedAt":"2026-03-16","name":"GPT-5.4","developer":"Open AI","description":"","contextLength":1050000,"outputMax":128000,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fgpt-5-4&endpoint=openai%2Fresponses%2Fsubmit"},"type":"openai/responses/submit","aliases":[],"tags":["playground:chat","tier:tier_2"]},{"id":"openai/gpt-5-4-pro","info":{"releasedAt":"2026-03-16","name":"GPT-5.4 Pro","developer":"Open AI","description":"","contextLength":1050000,"outputMax":128000,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fgpt-5-4-pro&endpoint=openai%2Fresponses%2Fsubmit"},"type":"openai/responses/submit","aliases":[],"tags":["playground:chat","tier:tier_2"]},{"id":"openai/gpt-5-5","info":{"releasedAt":"2026-04-24","name":"GPT-5.5","developer":"Open AI","description":"","contextLength":1050000,"outputMax":128000,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fgpt-5-5&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":[],"tags":["playground:chat","tier:tier_2"]},{"id":"openai/gpt-5-5","info":{"releasedAt":"2026-04-24","name":"GPT-5.5","developer":"Open AI","description":"","contextLength":1050000,"outputMax":128000,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fgpt-5-5&endpoint=openai%2Fresponses%2Fsubmit"},"type":"openai/responses/submit","aliases":[],"tags":["playground:chat","tier:tier_2"]},{"id":"openai/gpt-5-5-pro","info":{"releasedAt":"2026-04-24","name":"GPT-5.5 Pro","developer":"Open AI","description":"","contextLength":1050000,"outputMax":128000,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fgpt-5-5-pro&endpoint=openai%2Fresponses%2Fsubmit"},"type":"openai/responses/submit","aliases":[],"tags":["playground:chat","tier:tier_2"]},{"id":"openai/gpt-image-1-5","info":{"releasedAt":"2025-12-17","developer":"Open AI","description":"GPT-Image-1.5 is an updated image generation model with improved visual quality and prompt adherence.","name":"GPT Image 1.5","url":"","docsUrl":"https://docs.aimlapi.com/api-references/image-models/openai/gpt-image-1-mini-1","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fgpt-image-1-5&endpoint=openai%2Fimage-generations"},"type":"openai/image-generations","aliases":[],"tags":["playground:image","tier:tier_2"]},{"id":"openai/gpt-image-1-5","info":{"releasedAt":"2025-12-17","developer":"Open AI","description":"GPT-Image-1.5 is an updated image generation model with improved visual quality and prompt adherence.","name":"GPT Image 1.5","url":"","docsUrl":"https://docs.aimlapi.com/api-references/image-models/openai/gpt-image-1-mini-1","docsJson":"https://api.aimlapi.com/docs-json?model=openai%2Fgpt-image-1-5&endpoint=openai%2Fimage-editing"},"type":"openai/image-editing","aliases":[],"tags":["playground:image","tier:tier_2"]},{"id":"anthropic/claude-opus-4-1-20250805","info":{"releasedAt":"2025-09-30","name":"Claude 4.1 Opus","developer":"Anthropic","description":"Claude 4.1 Opus is an enhanced version of Claude 4 Opus with improved reasoning and instruction-following capabilities.","contextLength":200000,"outputMax":32000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/anthropic/claude-opus-4.1","docsJson":"https://api.aimlapi.com/docs-json?model=anthropic%2Fclaude-opus-4-1-20250805&endpoint=anthropic%2Fmessages"},"type":"anthropic/messages","aliases":["claude-opus-4-1-20250805"],"tags":["playground:chat","tier:tier_2","playground:code"]},{"id":"anthropic/claude-opus-4-1-20250805","info":{"releasedAt":"2025-09-30","name":"Claude 4.1 Opus","developer":"Anthropic","description":"Claude 4.1 Opus is an enhanced version of Claude 4 Opus with improved reasoning and instruction-following capabilities.","contextLength":200000,"outputMax":32000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/anthropic/claude-opus-4.1","docsJson":"https://api.aimlapi.com/docs-json?model=anthropic%2Fclaude-opus-4-1-20250805&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["claude-opus-4-1-20250805"],"tags":["playground:chat","tier:tier_2","playground:code"]},{"id":"anthropic/claude-opus-4-1-20250805","info":{"releasedAt":"2025-09-30","name":"Claude 4.1 Opus","developer":"Anthropic","description":"Claude 4.1 Opus is an enhanced version of Claude 4 Opus with improved reasoning and instruction-following capabilities.","contextLength":200000,"outputMax":32000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/anthropic/claude-opus-4.1","docsJson":"https://api.aimlapi.com/docs-json?model=anthropic%2Fclaude-opus-4-1-20250805&endpoint=anthropic%2Fbatches"},"type":"anthropic/batches","aliases":["claude-opus-4-1-20250805"],"tags":["playground:chat","tier:tier_2"]},{"id":"anthropic/claude-opus-4-1-20250805","info":{"releasedAt":"2025-09-30","name":"Claude 4.1 Opus","developer":"Anthropic","description":"Claude 4.1 Opus is an enhanced version of Claude 4 Opus with improved reasoning and instruction-following capabilities.","contextLength":200000,"outputMax":32000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/anthropic/claude-opus-4.1","docsJson":"https://api.aimlapi.com/docs-json?model=anthropic%2Fclaude-opus-4-1-20250805&endpoint=anthropic%2Fbatches-status"},"type":"anthropic/batches-status","aliases":["claude-opus-4-1-20250805"],"tags":["playground:chat","tier:tier_2"]},{"id":"anthropic/claude-opus-4-1-20250805","info":{"releasedAt":"2025-09-30","name":"Claude 4.1 Opus","developer":"Anthropic","description":"Claude 4.1 Opus is an enhanced version of Claude 4 Opus with improved reasoning and instruction-following capabilities.","contextLength":200000,"outputMax":32000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/anthropic/claude-opus-4.1","docsJson":"https://api.aimlapi.com/docs-json?model=anthropic%2Fclaude-opus-4-1-20250805&endpoint=anthropic%2Fbatches-cancel"},"type":"anthropic/batches-cancel","aliases":["claude-opus-4-1-20250805"],"tags":["playground:chat","tier:tier_2"]},{"id":"anthropic/claude-sonnet-4-5-20250929","info":{"releasedAt":"2025-10-01","name":"Claude 4.5 Sonnet","developer":"Anthropic","description":"Claude 4.5 Sonnet offers a balance of intelligence and speed for diverse enterprise and coding tasks.","contextLength":200000,"outputMax":64000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/anthropic/claude-4-5-sonnet","docsJson":"https://api.aimlapi.com/docs-json?model=anthropic%2Fclaude-sonnet-4-5-20250929&endpoint=anthropic%2Fmessages"},"type":"anthropic/messages","aliases":["claude-sonnet-4-5-20250929"],"tags":["playground:chat","tier:tier_2","playground:code"]},{"id":"anthropic/claude-sonnet-4-5-20250929","info":{"releasedAt":"2025-10-01","name":"Claude 4.5 Sonnet","developer":"Anthropic","description":"Claude 4.5 Sonnet offers a balance of intelligence and speed for diverse enterprise and coding tasks.","contextLength":200000,"outputMax":64000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/anthropic/claude-4-5-sonnet","docsJson":"https://api.aimlapi.com/docs-json?model=anthropic%2Fclaude-sonnet-4-5-20250929&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["claude-sonnet-4-5-20250929"],"tags":["playground:chat","tier:tier_2","playground:code"]},{"id":"anthropic/claude-sonnet-4-5-20250929","info":{"releasedAt":"2025-10-01","name":"Claude 4.5 Sonnet","developer":"Anthropic","description":"Claude 4.5 Sonnet offers a balance of intelligence and speed for diverse enterprise and coding tasks.","contextLength":200000,"outputMax":64000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/anthropic/claude-4-5-sonnet","docsJson":"https://api.aimlapi.com/docs-json?model=anthropic%2Fclaude-sonnet-4-5-20250929&endpoint=anthropic%2Fbatches"},"type":"anthropic/batches","aliases":["claude-sonnet-4-5-20250929"],"tags":["playground:chat","tier:tier_2"]},{"id":"anthropic/claude-sonnet-4-5-20250929","info":{"releasedAt":"2025-10-01","name":"Claude 4.5 Sonnet","developer":"Anthropic","description":"Claude 4.5 Sonnet offers a balance of intelligence and speed for diverse enterprise and coding tasks.","contextLength":200000,"outputMax":64000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/anthropic/claude-4-5-sonnet","docsJson":"https://api.aimlapi.com/docs-json?model=anthropic%2Fclaude-sonnet-4-5-20250929&endpoint=anthropic%2Fbatches-status"},"type":"anthropic/batches-status","aliases":["claude-sonnet-4-5-20250929"],"tags":["playground:chat","tier:tier_2"]},{"id":"anthropic/claude-sonnet-4-5-20250929","info":{"releasedAt":"2025-10-01","name":"Claude 4.5 Sonnet","developer":"Anthropic","description":"Claude 4.5 Sonnet offers a balance of intelligence and speed for diverse enterprise and coding tasks.","contextLength":200000,"outputMax":64000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/anthropic/claude-4-5-sonnet","docsJson":"https://api.aimlapi.com/docs-json?model=anthropic%2Fclaude-sonnet-4-5-20250929&endpoint=anthropic%2Fbatches-cancel"},"type":"anthropic/batches-cancel","aliases":["claude-sonnet-4-5-20250929"],"tags":["playground:chat","tier:tier_2"]},{"id":"anthropic/claude-haiku-4-5-20251001","info":{"releasedAt":"2025-10-16","name":"Claude 4.5 Haiku","developer":"Anthropic","description":"Claude 4.5 Haiku is a fast, lightweight model optimized for quick responses and high-throughput applications.","contextLength":200000,"outputMax":64000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/anthropic/claude-4.5-haiku","docsJson":"https://api.aimlapi.com/docs-json?model=anthropic%2Fclaude-haiku-4-5-20251001&endpoint=anthropic%2Fmessages"},"type":"anthropic/messages","aliases":["claude-haiku-4-5-20251001"],"tags":["playground:chat","tier:tier_2","playground:code"]},{"id":"anthropic/claude-haiku-4-5-20251001","info":{"releasedAt":"2025-10-16","name":"Claude 4.5 Haiku","developer":"Anthropic","description":"Claude 4.5 Haiku is a fast, lightweight model optimized for quick responses and high-throughput applications.","contextLength":200000,"outputMax":64000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/anthropic/claude-4.5-haiku","docsJson":"https://api.aimlapi.com/docs-json?model=anthropic%2Fclaude-haiku-4-5-20251001&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["claude-haiku-4-5-20251001"],"tags":["playground:chat","tier:tier_2","playground:code"]},{"id":"anthropic/claude-haiku-4-5-20251001","info":{"releasedAt":"2025-10-16","name":"Claude 4.5 Haiku","developer":"Anthropic","description":"Claude 4.5 Haiku is a fast, lightweight model optimized for quick responses and high-throughput applications.","contextLength":200000,"outputMax":64000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/anthropic/claude-4.5-haiku","docsJson":"https://api.aimlapi.com/docs-json?model=anthropic%2Fclaude-haiku-4-5-20251001&endpoint=anthropic%2Fbatches"},"type":"anthropic/batches","aliases":["claude-haiku-4-5-20251001"],"tags":["playground:chat","tier:tier_2"]},{"id":"anthropic/claude-haiku-4-5-20251001","info":{"releasedAt":"2025-10-16","name":"Claude 4.5 Haiku","developer":"Anthropic","description":"Claude 4.5 Haiku is a fast, lightweight model optimized for quick responses and high-throughput applications.","contextLength":200000,"outputMax":64000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/anthropic/claude-4.5-haiku","docsJson":"https://api.aimlapi.com/docs-json?model=anthropic%2Fclaude-haiku-4-5-20251001&endpoint=anthropic%2Fbatches-status"},"type":"anthropic/batches-status","aliases":["claude-haiku-4-5-20251001"],"tags":["playground:chat","tier:tier_2"]},{"id":"anthropic/claude-haiku-4-5-20251001","info":{"releasedAt":"2025-10-16","name":"Claude 4.5 Haiku","developer":"Anthropic","description":"Claude 4.5 Haiku is a fast, lightweight model optimized for quick responses and high-throughput applications.","contextLength":200000,"outputMax":64000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/anthropic/claude-4.5-haiku","docsJson":"https://api.aimlapi.com/docs-json?model=anthropic%2Fclaude-haiku-4-5-20251001&endpoint=anthropic%2Fbatches-cancel"},"type":"anthropic/batches-cancel","aliases":["claude-haiku-4-5-20251001"],"tags":["playground:chat","tier:tier_2"]},{"id":"anthropic/claude-opus-4-5-20251101","info":{"releasedAt":"2025-11-25","name":"Claude 4.5 Opus","developer":"Anthropic","description":"Claude 4.5 Opus is Anthropic's flagship model for the most demanding reasoning and analysis tasks.","contextLength":200000,"outputMax":64000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/anthropic/claude-4.5-opus","docsJson":"https://api.aimlapi.com/docs-json?model=anthropic%2Fclaude-opus-4-5-20251101&endpoint=anthropic%2Fmessages"},"type":"anthropic/messages","aliases":["claude-opus-4-5-20251101"],"tags":["playground:chat","tier:tier_2","playground:code"]},{"id":"anthropic/claude-opus-4-5-20251101","info":{"releasedAt":"2025-11-25","name":"Claude 4.5 Opus","developer":"Anthropic","description":"Claude 4.5 Opus is Anthropic's flagship model for the most demanding reasoning and analysis tasks.","contextLength":200000,"outputMax":64000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/anthropic/claude-4.5-opus","docsJson":"https://api.aimlapi.com/docs-json?model=anthropic%2Fclaude-opus-4-5-20251101&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["claude-opus-4-5-20251101"],"tags":["playground:chat","tier:tier_2","playground:code"]},{"id":"anthropic/claude-opus-4-5-20251101","info":{"releasedAt":"2025-11-25","name":"Claude 4.5 Opus","developer":"Anthropic","description":"Claude 4.5 Opus is Anthropic's flagship model for the most demanding reasoning and analysis tasks.","contextLength":200000,"outputMax":64000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/anthropic/claude-4.5-opus","docsJson":"https://api.aimlapi.com/docs-json?model=anthropic%2Fclaude-opus-4-5-20251101&endpoint=anthropic%2Fbatches"},"type":"anthropic/batches","aliases":["claude-opus-4-5-20251101"],"tags":["playground:chat","tier:tier_2"]},{"id":"anthropic/claude-opus-4-5-20251101","info":{"releasedAt":"2025-11-25","name":"Claude 4.5 Opus","developer":"Anthropic","description":"Claude 4.5 Opus is Anthropic's flagship model for the most demanding reasoning and analysis tasks.","contextLength":200000,"outputMax":64000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/anthropic/claude-4.5-opus","docsJson":"https://api.aimlapi.com/docs-json?model=anthropic%2Fclaude-opus-4-5-20251101&endpoint=anthropic%2Fbatches-status"},"type":"anthropic/batches-status","aliases":["claude-opus-4-5-20251101"],"tags":["playground:chat","tier:tier_2"]},{"id":"anthropic/claude-opus-4-5-20251101","info":{"releasedAt":"2025-11-25","name":"Claude 4.5 Opus","developer":"Anthropic","description":"Claude 4.5 Opus is Anthropic's flagship model for the most demanding reasoning and analysis tasks.","contextLength":200000,"outputMax":64000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/anthropic/claude-4.5-opus","docsJson":"https://api.aimlapi.com/docs-json?model=anthropic%2Fclaude-opus-4-5-20251101&endpoint=anthropic%2Fbatches-cancel"},"type":"anthropic/batches-cancel","aliases":["claude-opus-4-5-20251101"],"tags":["playground:chat","tier:tier_2"]},{"id":"anthropic/claude-opus-4-6","info":{"releasedAt":"2026-02-06","name":"Claude 4.6 Opus","developer":"Anthropic","description":"Claude 4.6 Opus delivers Anthropic's highest intelligence with extended output for complex, long-horizon tasks.","contextLength":200000,"outputMax":128000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/anthropic/claude-4.6-opus","docsJson":"https://api.aimlapi.com/docs-json?model=anthropic%2Fclaude-opus-4-6&endpoint=anthropic%2Fmessages"},"type":"anthropic/messages","aliases":["claude-opus-4-6"],"tags":["playground:chat","tier:tier_2","playground:code"]},{"id":"anthropic/claude-opus-4-6","info":{"releasedAt":"2026-02-06","name":"Claude 4.6 Opus","developer":"Anthropic","description":"Claude 4.6 Opus delivers Anthropic's highest intelligence with extended output for complex, long-horizon tasks.","contextLength":200000,"outputMax":128000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/anthropic/claude-4.6-opus","docsJson":"https://api.aimlapi.com/docs-json?model=anthropic%2Fclaude-opus-4-6&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["claude-opus-4-6"],"tags":["playground:chat","tier:tier_2","playground:code"]},{"id":"anthropic/claude-opus-4-6","info":{"releasedAt":"2026-02-06","name":"Claude 4.6 Opus","developer":"Anthropic","description":"Claude 4.6 Opus delivers Anthropic's highest intelligence with extended output for complex, long-horizon tasks.","contextLength":200000,"outputMax":128000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/anthropic/claude-4.6-opus","docsJson":"https://api.aimlapi.com/docs-json?model=anthropic%2Fclaude-opus-4-6&endpoint=anthropic%2Fbatches"},"type":"anthropic/batches","aliases":["claude-opus-4-6"],"tags":["playground:chat","tier:tier_2"]},{"id":"anthropic/claude-opus-4-6","info":{"releasedAt":"2026-02-06","name":"Claude 4.6 Opus","developer":"Anthropic","description":"Claude 4.6 Opus delivers Anthropic's highest intelligence with extended output for complex, long-horizon tasks.","contextLength":200000,"outputMax":128000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/anthropic/claude-4.6-opus","docsJson":"https://api.aimlapi.com/docs-json?model=anthropic%2Fclaude-opus-4-6&endpoint=anthropic%2Fbatches-status"},"type":"anthropic/batches-status","aliases":["claude-opus-4-6"],"tags":["playground:chat","tier:tier_2"]},{"id":"anthropic/claude-opus-4-6","info":{"releasedAt":"2026-02-06","name":"Claude 4.6 Opus","developer":"Anthropic","description":"Claude 4.6 Opus delivers Anthropic's highest intelligence with extended output for complex, long-horizon tasks.","contextLength":200000,"outputMax":128000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/anthropic/claude-4.6-opus","docsJson":"https://api.aimlapi.com/docs-json?model=anthropic%2Fclaude-opus-4-6&endpoint=anthropic%2Fbatches-cancel"},"type":"anthropic/batches-cancel","aliases":["claude-opus-4-6"],"tags":["playground:chat","tier:tier_2"]},{"id":"anthropic/claude-sonnet-4-6","info":{"releasedAt":"2026-02-18","name":"Claude 4.6 Sonnet","developer":"Anthropic","description":"Claude 4.6 Sonnet is a highly capable model balancing performance and efficiency for everyday AI tasks.","contextLength":200000,"outputMax":64000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/anthropic/claude-4.6-sonnet","docsJson":"https://api.aimlapi.com/docs-json?model=anthropic%2Fclaude-sonnet-4-6&endpoint=anthropic%2Fmessages"},"type":"anthropic/messages","aliases":["claude-sonnet-4-6"],"tags":["playground:chat","tier:tier_2","playground:code"]},{"id":"anthropic/claude-sonnet-4-6","info":{"releasedAt":"2026-02-18","name":"Claude 4.6 Sonnet","developer":"Anthropic","description":"Claude 4.6 Sonnet is a highly capable model balancing performance and efficiency for everyday AI tasks.","contextLength":200000,"outputMax":64000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/anthropic/claude-4.6-sonnet","docsJson":"https://api.aimlapi.com/docs-json?model=anthropic%2Fclaude-sonnet-4-6&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["claude-sonnet-4-6"],"tags":["playground:chat","tier:tier_2","playground:code"]},{"id":"anthropic/claude-sonnet-4-6","info":{"releasedAt":"2026-02-18","name":"Claude 4.6 Sonnet","developer":"Anthropic","description":"Claude 4.6 Sonnet is a highly capable model balancing performance and efficiency for everyday AI tasks.","contextLength":200000,"outputMax":64000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/anthropic/claude-4.6-sonnet","docsJson":"https://api.aimlapi.com/docs-json?model=anthropic%2Fclaude-sonnet-4-6&endpoint=anthropic%2Fbatches"},"type":"anthropic/batches","aliases":["claude-sonnet-4-6"],"tags":["playground:chat","tier:tier_2"]},{"id":"anthropic/claude-sonnet-4-6","info":{"releasedAt":"2026-02-18","name":"Claude 4.6 Sonnet","developer":"Anthropic","description":"Claude 4.6 Sonnet is a highly capable model balancing performance and efficiency for everyday AI tasks.","contextLength":200000,"outputMax":64000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/anthropic/claude-4.6-sonnet","docsJson":"https://api.aimlapi.com/docs-json?model=anthropic%2Fclaude-sonnet-4-6&endpoint=anthropic%2Fbatches-status"},"type":"anthropic/batches-status","aliases":["claude-sonnet-4-6"],"tags":["playground:chat","tier:tier_2"]},{"id":"anthropic/claude-sonnet-4-6","info":{"releasedAt":"2026-02-18","name":"Claude 4.6 Sonnet","developer":"Anthropic","description":"Claude 4.6 Sonnet is a highly capable model balancing performance and efficiency for everyday AI tasks.","contextLength":200000,"outputMax":64000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/anthropic/claude-4.6-sonnet","docsJson":"https://api.aimlapi.com/docs-json?model=anthropic%2Fclaude-sonnet-4-6&endpoint=anthropic%2Fbatches-cancel"},"type":"anthropic/batches-cancel","aliases":["claude-sonnet-4-6"],"tags":["playground:chat","tier:tier_2"]},{"id":"anthropic/claude-opus-4-7","info":{"releasedAt":"2026-04-16","name":"Claude 4.7 Opus","developer":"Anthropic","description":"","contextLength":1000000,"outputMax":128000,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=anthropic%2Fclaude-opus-4-7&endpoint=anthropic%2Fmessages"},"type":"anthropic/messages","aliases":["claude-opus-4-7"],"tags":["playground:chat","tier:tier_2","playground:code"]},{"id":"anthropic/claude-opus-4-7","info":{"releasedAt":"2026-04-16","name":"Claude 4.7 Opus","developer":"Anthropic","description":"","contextLength":1000000,"outputMax":128000,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=anthropic%2Fclaude-opus-4-7&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["claude-opus-4-7"],"tags":["playground:chat","tier:tier_2","playground:code"]},{"id":"anthropic/claude-opus-4-7","info":{"releasedAt":"2026-04-16","name":"Claude 4.7 Opus","developer":"Anthropic","description":"","contextLength":1000000,"outputMax":128000,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=anthropic%2Fclaude-opus-4-7&endpoint=anthropic%2Fbatches"},"type":"anthropic/batches","aliases":["claude-opus-4-7"],"tags":["playground:chat","tier:tier_2","playground:code"]},{"id":"anthropic/claude-opus-4-7","info":{"releasedAt":"2026-04-16","name":"Claude 4.7 Opus","developer":"Anthropic","description":"","contextLength":1000000,"outputMax":128000,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=anthropic%2Fclaude-opus-4-7&endpoint=anthropic%2Fbatches-status"},"type":"anthropic/batches-status","aliases":["claude-opus-4-7"],"tags":["playground:chat","tier:tier_2"]},{"id":"anthropic/claude-opus-4-7","info":{"releasedAt":"2026-04-16","name":"Claude 4.7 Opus","developer":"Anthropic","description":"","contextLength":1000000,"outputMax":128000,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=anthropic%2Fclaude-opus-4-7&endpoint=anthropic%2Fbatches-cancel"},"type":"anthropic/batches-cancel","aliases":["claude-opus-4-7"],"tags":["playground:chat","tier:tier_2"]},{"id":"anthropic/claude-opus-4-8","info":{"releasedAt":"2026-05-28","name":"Claude 4.8 Opus","developer":"Anthropic","description":"Claude 4.8 Opus is Anthropic's most capable model designed for complex reasoning and agentic coding workflows. Features a 1M token context window, adaptive thinking, and top-tier performance across multilingual tasks, long-context handling, and vision.","contextLength":1000000,"outputMax":128000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/anthropic/claude-4.8-opus","isHottest":true,"docsJson":"https://api.aimlapi.com/docs-json?model=anthropic%2Fclaude-opus-4-8&endpoint=anthropic%2Fmessages"},"type":"anthropic/messages","aliases":["claude-opus-4-8"],"tags":["playground:chat","tier:tier_2","playground:code"]},{"id":"anthropic/claude-opus-4-8","info":{"releasedAt":"2026-05-28","name":"Claude 4.8 Opus","developer":"Anthropic","description":"Claude 4.8 Opus is Anthropic's most capable model designed for complex reasoning and agentic coding workflows. Features a 1M token context window, adaptive thinking, and top-tier performance across multilingual tasks, long-context handling, and vision.","contextLength":1000000,"outputMax":128000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/anthropic/claude-4.8-opus","isHottest":true,"docsJson":"https://api.aimlapi.com/docs-json?model=anthropic%2Fclaude-opus-4-8&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["claude-opus-4-8"],"tags":["playground:chat","tier:tier_2","playground:code"]},{"id":"anthropic/claude-opus-4-8","info":{"releasedAt":"2026-05-28","name":"Claude 4.8 Opus","developer":"Anthropic","description":"Claude 4.8 Opus is Anthropic's most capable model designed for complex reasoning and agentic coding workflows. Features a 1M token context window, adaptive thinking, and top-tier performance across multilingual tasks, long-context handling, and vision.","contextLength":1000000,"outputMax":128000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/anthropic/claude-4.8-opus","isHottest":true,"docsJson":"https://api.aimlapi.com/docs-json?model=anthropic%2Fclaude-opus-4-8&endpoint=anthropic%2Fbatches"},"type":"anthropic/batches","aliases":["claude-opus-4-8"],"tags":["playground:chat","tier:tier_2","playground:code"]},{"id":"anthropic/claude-opus-4-8","info":{"releasedAt":"2026-05-28","name":"Claude 4.8 Opus","developer":"Anthropic","description":"Claude 4.8 Opus is Anthropic's most capable model designed for complex reasoning and agentic coding workflows. Features a 1M token context window, adaptive thinking, and top-tier performance across multilingual tasks, long-context handling, and vision.","contextLength":1000000,"outputMax":128000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/anthropic/claude-4.8-opus","isHottest":true,"docsJson":"https://api.aimlapi.com/docs-json?model=anthropic%2Fclaude-opus-4-8&endpoint=anthropic%2Fbatches-status"},"type":"anthropic/batches-status","aliases":["claude-opus-4-8"],"tags":["playground:chat","tier:tier_2"]},{"id":"anthropic/claude-opus-4-8","info":{"releasedAt":"2026-05-28","name":"Claude 4.8 Opus","developer":"Anthropic","description":"Claude 4.8 Opus is Anthropic's most capable model designed for complex reasoning and agentic coding workflows. Features a 1M token context window, adaptive thinking, and top-tier performance across multilingual tasks, long-context handling, and vision.","contextLength":1000000,"outputMax":128000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/anthropic/claude-4.8-opus","isHottest":true,"docsJson":"https://api.aimlapi.com/docs-json?model=anthropic%2Fclaude-opus-4-8&endpoint=anthropic%2Fbatches-cancel"},"type":"anthropic/batches-cancel","aliases":["claude-opus-4-8"],"tags":["playground:chat","tier:tier_2"]},{"id":"anthropic/claude-fable-5","info":{"releasedAt":"2026-06-09","name":"Claude Fable 5","developer":"Anthropic","description":"Claude Fable 5 is Anthropic's model designed for complex reasoning and agentic coding workflows. Features a 1M token context window, adaptive thinking, and strong performance across multilingual tasks, long-context handling, and vision.","contextLength":1000000,"outputMax":128000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/anthropic/claude-fable-5","isHottest":true,"docsJson":"https://api.aimlapi.com/docs-json?model=anthropic%2Fclaude-fable-5&endpoint=anthropic%2Fmessages"},"type":"anthropic/messages","aliases":["claude-fable-5"],"tags":["playground:chat","tier:tier_2","playground:code"]},{"id":"anthropic/claude-fable-5","info":{"releasedAt":"2026-06-09","name":"Claude Fable 5","developer":"Anthropic","description":"Claude Fable 5 is Anthropic's model designed for complex reasoning and agentic coding workflows. Features a 1M token context window, adaptive thinking, and strong performance across multilingual tasks, long-context handling, and vision.","contextLength":1000000,"outputMax":128000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/anthropic/claude-fable-5","isHottest":true,"docsJson":"https://api.aimlapi.com/docs-json?model=anthropic%2Fclaude-fable-5&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["claude-fable-5"],"tags":["playground:chat","tier:tier_2","playground:code"]},{"id":"anthropic/claude-fable-5","info":{"releasedAt":"2026-06-09","name":"Claude Fable 5","developer":"Anthropic","description":"Claude Fable 5 is Anthropic's model designed for complex reasoning and agentic coding workflows. Features a 1M token context window, adaptive thinking, and strong performance across multilingual tasks, long-context handling, and vision.","contextLength":1000000,"outputMax":128000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/anthropic/claude-fable-5","isHottest":true,"docsJson":"https://api.aimlapi.com/docs-json?model=anthropic%2Fclaude-fable-5&endpoint=anthropic%2Fbatches"},"type":"anthropic/batches","aliases":["claude-fable-5"],"tags":["playground:chat","tier:tier_2","playground:code"]},{"id":"anthropic/claude-fable-5","info":{"releasedAt":"2026-06-09","name":"Claude Fable 5","developer":"Anthropic","description":"Claude Fable 5 is Anthropic's model designed for complex reasoning and agentic coding workflows. Features a 1M token context window, adaptive thinking, and strong performance across multilingual tasks, long-context handling, and vision.","contextLength":1000000,"outputMax":128000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/anthropic/claude-fable-5","isHottest":true,"docsJson":"https://api.aimlapi.com/docs-json?model=anthropic%2Fclaude-fable-5&endpoint=anthropic%2Fbatches-status"},"type":"anthropic/batches-status","aliases":["claude-fable-5"],"tags":["playground:chat","tier:tier_2"]},{"id":"anthropic/claude-fable-5","info":{"releasedAt":"2026-06-09","name":"Claude Fable 5","developer":"Anthropic","description":"Claude Fable 5 is Anthropic's model designed for complex reasoning and agentic coding workflows. Features a 1M token context window, adaptive thinking, and strong performance across multilingual tasks, long-context handling, and vision.","contextLength":1000000,"outputMax":128000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/anthropic/claude-fable-5","isHottest":true,"docsJson":"https://api.aimlapi.com/docs-json?model=anthropic%2Fclaude-fable-5&endpoint=anthropic%2Fbatches-cancel"},"type":"anthropic/batches-cancel","aliases":["claude-fable-5"],"tags":["playground:chat","tier:tier_2"]},{"id":"anthropic/claude-sonnet-5","info":{"releasedAt":"2026-06-30","name":"Claude Sonnet 5","developer":"Anthropic","description":"Claude Sonnet 5 is a high-performance model for coding and agentic workflows, delivering near-Opus quality at Sonnet cost. Features a 1M token context window, adaptive thinking, and high-resolution vision.","contextLength":1000000,"outputMax":128000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/anthropic/claude-sonnet-5","isHottest":true,"docsJson":"https://api.aimlapi.com/docs-json?model=anthropic%2Fclaude-sonnet-5&endpoint=anthropic%2Fmessages"},"type":"anthropic/messages","aliases":["claude-sonnet-5"],"tags":["playground:chat","tier:tier_2","playground:code"]},{"id":"anthropic/claude-sonnet-5","info":{"releasedAt":"2026-06-30","name":"Claude Sonnet 5","developer":"Anthropic","description":"Claude Sonnet 5 is a high-performance model for coding and agentic workflows, delivering near-Opus quality at Sonnet cost. Features a 1M token context window, adaptive thinking, and high-resolution vision.","contextLength":1000000,"outputMax":128000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/anthropic/claude-sonnet-5","isHottest":true,"docsJson":"https://api.aimlapi.com/docs-json?model=anthropic%2Fclaude-sonnet-5&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["claude-sonnet-5"],"tags":["playground:chat","tier:tier_2","playground:code"]},{"id":"anthropic/claude-sonnet-5","info":{"releasedAt":"2026-06-30","name":"Claude Sonnet 5","developer":"Anthropic","description":"Claude Sonnet 5 is a high-performance model for coding and agentic workflows, delivering near-Opus quality at Sonnet cost. Features a 1M token context window, adaptive thinking, and high-resolution vision.","contextLength":1000000,"outputMax":128000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/anthropic/claude-sonnet-5","isHottest":true,"docsJson":"https://api.aimlapi.com/docs-json?model=anthropic%2Fclaude-sonnet-5&endpoint=anthropic%2Fbatches"},"type":"anthropic/batches","aliases":["claude-sonnet-5"],"tags":["playground:chat","tier:tier_2","playground:code"]},{"id":"anthropic/claude-sonnet-5","info":{"releasedAt":"2026-06-30","name":"Claude Sonnet 5","developer":"Anthropic","description":"Claude Sonnet 5 is a high-performance model for coding and agentic workflows, delivering near-Opus quality at Sonnet cost. Features a 1M token context window, adaptive thinking, and high-resolution vision.","contextLength":1000000,"outputMax":128000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/anthropic/claude-sonnet-5","isHottest":true,"docsJson":"https://api.aimlapi.com/docs-json?model=anthropic%2Fclaude-sonnet-5&endpoint=anthropic%2Fbatches-status"},"type":"anthropic/batches-status","aliases":["claude-sonnet-5"],"tags":["playground:chat","tier:tier_2"]},{"id":"anthropic/claude-sonnet-5","info":{"releasedAt":"2026-06-30","name":"Claude Sonnet 5","developer":"Anthropic","description":"Claude Sonnet 5 is a high-performance model for coding and agentic workflows, delivering near-Opus quality at Sonnet cost. Features a 1M token context window, adaptive thinking, and high-resolution vision.","contextLength":1000000,"outputMax":128000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/anthropic/claude-sonnet-5","isHottest":true,"docsJson":"https://api.aimlapi.com/docs-json?model=anthropic%2Fclaude-sonnet-5&endpoint=anthropic%2Fbatches-cancel"},"type":"anthropic/batches-cancel","aliases":["claude-sonnet-5"],"tags":["playground:chat","tier:tier_2"]},{"id":"anthropic/voyage-large-2-instruct","info":{"releasedAt":"2025-12-13","name":"Voyage Large 2 Instruct","developer":"Anthropic","description":"Voyage Large 2 Instruct excels in text embedding tasks.","url":"https://aimlapi.com/models/voyage-large-2-instruct-api","docsUrl":"https://docs.aimlapi.com/api-references/embedding-models/anthropic/voyage-large-2-instruct","contextLength":16000,"docsJson":"https://api.aimlapi.com/docs-json?model=anthropic%2Fvoyage-large-2-instruct&endpoint=openai%2Fembeddings"},"type":"openai/embeddings","aliases":["voyage-large-2-instruct"],"tags":["playground:embeddings","tier:tier_2"]},{"id":"anthropic/voyage-finance-2","info":{"releasedAt":"2025-12-13","name":"Voyage finance 2","developer":"Anthropic","description":"Voyage Finance 2 is a domain-specific embedding model optimized for financial text retrieval and semantic search.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/embedding-models/anthropic/voyage-finance-2","contextLength":32000,"docsJson":"https://api.aimlapi.com/docs-json?model=anthropic%2Fvoyage-finance-2&endpoint=openai%2Fembeddings"},"type":"openai/embeddings","aliases":["voyage-finance-2"],"tags":["playground:embeddings","tier:tier_2"]},{"id":"anthropic/voyage-multilingual-2","info":{"releasedAt":"2025-12-13","name":"Voyage Multilingual 2","developer":"Anthropic","description":"Voyage Multilingual 2 is an embedding model supporting 30+ languages for cross-lingual semantic search and retrieval.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/embedding-models/anthropic/voyage-multilingual-2","contextLength":32000,"docsJson":"https://api.aimlapi.com/docs-json?model=anthropic%2Fvoyage-multilingual-2&endpoint=openai%2Fembeddings"},"type":"openai/embeddings","aliases":["voyage-multilingual-2"],"tags":["playground:embeddings","tier:tier_2"]},{"id":"anthropic/voyage-law-2","info":{"releasedAt":"2025-12-13","name":"Voyage law 2","developer":"Anthropic","description":"Voyage Law 2 is a domain-specific embedding model fine-tuned for legal document retrieval and similarity tasks.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/embedding-models/anthropic/voyage-law-2","contextLength":16000,"docsJson":"https://api.aimlapi.com/docs-json?model=anthropic%2Fvoyage-law-2&endpoint=openai%2Fembeddings"},"type":"openai/embeddings","aliases":["voyage-law-2"],"tags":["playground:embeddings","tier:tier_2"]},{"id":"anthropic/voyage-code-2","info":{"releasedAt":"2025-12-13","name":"Voyage code 2","developer":"Anthropic","description":"Voyage Code 2 is an embedding model optimized for code retrieval, similarity search, and programming tasks.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/embedding-models/anthropic/voyage-code-2","contextLength":16000,"docsJson":"https://api.aimlapi.com/docs-json?model=anthropic%2Fvoyage-code-2&endpoint=openai%2Fembeddings"},"type":"openai/embeddings","aliases":["voyage-code-2"],"tags":["playground:embeddings","tier:tier_2"]},{"id":"anthropic/voyage-large-2","info":{"releasedAt":"2025-12-13","name":"Voyage Large 2","developer":"Anthropic","description":"Voyage Large 2 is a high-capacity embedding model offering strong performance across general-purpose retrieval tasks.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/embedding-models/anthropic/voyage-large-2","contextLength":16000,"docsJson":"https://api.aimlapi.com/docs-json?model=anthropic%2Fvoyage-large-2&endpoint=openai%2Fembeddings"},"type":"openai/embeddings","aliases":["voyage-large-2"],"tags":["playground:embeddings","tier:tier_2"]},{"id":"anthropic/voyage-2","info":{"releasedAt":"2025-12-13","name":"Voyage 2","developer":"Anthropic","description":"Voyage 2 is a general-purpose text embedding model for semantic search and similarity tasks.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/embedding-models/anthropic/voyage-2","contextLength":4000,"docsJson":"https://api.aimlapi.com/docs-json?model=anthropic%2Fvoyage-2&endpoint=openai%2Fembeddings"},"type":"openai/embeddings","aliases":["voyage-2"],"tags":["playground:embeddings","tier:tier_2"]},{"id":"anthropic/claude-opus-4.8-fast","info":{"releasedAt":"2026-05-27","name":"Claude Opus 4.8 (Fast)","developer":"Anthropic","contextLength":1000000,"outputMax":128000,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=anthropic%2Fclaude-opus-4.8-fast&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["claude-opus-4.8-fast"],"tags":["playground:chat","tier:tier_2"]},{"id":"anthropic/claude-opus-4.8-fast","info":{"releasedAt":"2026-05-27","name":"Claude Opus 4.8 (Fast)","developer":"Anthropic","contextLength":1000000,"outputMax":128000,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=anthropic%2Fclaude-opus-4.8-fast&endpoint=anthropic%2Fmessages"},"type":"anthropic/messages","aliases":["claude-opus-4.8-fast"],"tags":["playground:chat","tier:tier_2"]},{"id":"anthropic/claude-opus-4.8","info":{"releasedAt":"2026-05-28","name":"Claude 4.8 Opus","developer":"Anthropic","description":"Claude 4.8 Opus is Anthropic's most capable model designed for complex reasoning and agentic coding workflows. Features a 1M token context window, adaptive thinking, and top-tier performance across multilingual tasks, long-context handling, and vision.","contextLength":1000000,"outputMax":128000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/anthropic/claude-4.8-opus","isHottest":true,"docsJson":"https://api.aimlapi.com/docs-json?model=anthropic%2Fclaude-opus-4.8&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["claude-opus-4.8","claude-opus-4-8","anthropic/claude-opus-4-8"],"tags":["playground:chat","tier:tier_2"]},{"id":"anthropic/claude-opus-4.8","info":{"releasedAt":"2026-05-28","name":"Claude 4.8 Opus","developer":"Anthropic","description":"Claude 4.8 Opus is Anthropic's most capable model designed for complex reasoning and agentic coding workflows. Features a 1M token context window, adaptive thinking, and top-tier performance across multilingual tasks, long-context handling, and vision.","contextLength":1000000,"outputMax":128000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/anthropic/claude-4.8-opus","isHottest":true,"docsJson":"https://api.aimlapi.com/docs-json?model=anthropic%2Fclaude-opus-4.8&endpoint=anthropic%2Fmessages"},"type":"anthropic/messages","aliases":["claude-opus-4.8","claude-opus-4-8","anthropic/claude-opus-4-8"],"tags":["playground:chat","tier:tier_2"]},{"id":"anthropic/claude-opus-4.7-fast","info":{"releasedAt":"2026-05-12","name":"Claude Opus 4.7 (Fast)","developer":"Anthropic","contextLength":1000000,"outputMax":128000,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=anthropic%2Fclaude-opus-4.7-fast&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["claude-opus-4.7-fast"],"tags":["playground:chat","tier:tier_2"]},{"id":"anthropic/claude-opus-4.7-fast","info":{"releasedAt":"2026-05-12","name":"Claude Opus 4.7 (Fast)","developer":"Anthropic","contextLength":1000000,"outputMax":128000,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=anthropic%2Fclaude-opus-4.7-fast&endpoint=anthropic%2Fmessages"},"type":"anthropic/messages","aliases":["claude-opus-4.7-fast"],"tags":["playground:chat","tier:tier_2"]},{"id":"anthropic/claude-opus-4.7","info":{"releasedAt":"2026-04-16","name":"Claude 4.7 Opus","developer":"Anthropic","description":"","contextLength":1000000,"outputMax":128000,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=anthropic%2Fclaude-opus-4.7&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["claude-opus-4.7","claude-opus-4-7","anthropic/claude-opus-4-7"],"tags":["playground:chat","tier:tier_2"]},{"id":"anthropic/claude-opus-4.7","info":{"releasedAt":"2026-04-16","name":"Claude 4.7 Opus","developer":"Anthropic","description":"","contextLength":1000000,"outputMax":128000,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=anthropic%2Fclaude-opus-4.7&endpoint=anthropic%2Fmessages"},"type":"anthropic/messages","aliases":["claude-opus-4.7","claude-opus-4-7","anthropic/claude-opus-4-7"],"tags":["playground:chat","tier:tier_2"]},{"id":"anthropic/claude-sonnet-4.6","info":{"releasedAt":"2026-02-18","name":"Claude 4.6 Sonnet","developer":"Anthropic","description":"Claude 4.6 Sonnet is a highly capable model balancing performance and efficiency for everyday AI tasks.","contextLength":200000,"outputMax":64000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/anthropic/claude-4.6-sonnet","docsJson":"https://api.aimlapi.com/docs-json?model=anthropic%2Fclaude-sonnet-4.6&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["claude-sonnet-4.6","claude-sonnet-4-6","anthropic/claude-sonnet-4-6-20260218"],"tags":["playground:chat","tier:tier_2"]},{"id":"anthropic/claude-sonnet-4.6","info":{"releasedAt":"2026-02-18","name":"Claude 4.6 Sonnet","developer":"Anthropic","description":"Claude 4.6 Sonnet is a highly capable model balancing performance and efficiency for everyday AI tasks.","contextLength":200000,"outputMax":64000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/anthropic/claude-4.6-sonnet","docsJson":"https://api.aimlapi.com/docs-json?model=anthropic%2Fclaude-sonnet-4.6&endpoint=anthropic%2Fmessages"},"type":"anthropic/messages","aliases":["claude-sonnet-4.6","claude-sonnet-4-6","anthropic/claude-sonnet-4-6-20260218"],"tags":["playground:chat","tier:tier_2"]},{"id":"anthropic/claude-opus-4.5","info":{"releasedAt":"2025-11-25","name":"Claude 4.5 Opus","developer":"Anthropic","description":"Claude 4.5 Opus is Anthropic's flagship model for the most demanding reasoning and analysis tasks.","contextLength":200000,"outputMax":64000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/anthropic/claude-4.5-opus","docsJson":"https://api.aimlapi.com/docs-json?model=anthropic%2Fclaude-opus-4.5&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["claude-opus-4.5","anthropic/claude-opus-4-5","claude-opus-4-5"],"tags":["playground:chat","tier:tier_2"]},{"id":"anthropic/claude-opus-4.5","info":{"releasedAt":"2025-11-25","name":"Claude 4.5 Opus","developer":"Anthropic","description":"Claude 4.5 Opus is Anthropic's flagship model for the most demanding reasoning and analysis tasks.","contextLength":200000,"outputMax":64000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/anthropic/claude-4.5-opus","docsJson":"https://api.aimlapi.com/docs-json?model=anthropic%2Fclaude-opus-4.5&endpoint=anthropic%2Fmessages"},"type":"anthropic/messages","aliases":["claude-opus-4.5","anthropic/claude-opus-4-5","claude-opus-4-5"],"tags":["playground:chat","tier:tier_2"]},{"id":"anthropic/claude-haiku-4.5","info":{"releasedAt":"2025-10-16","name":"Claude 4.5 Haiku","developer":"Anthropic","description":"Claude 4.5 Haiku is a fast, lightweight model optimized for quick responses and high-throughput applications.","contextLength":200000,"outputMax":64000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/anthropic/claude-4.5-haiku","docsJson":"https://api.aimlapi.com/docs-json?model=anthropic%2Fclaude-haiku-4.5&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["claude-haiku-4.5","claude-haiku-4-5"],"tags":["playground:chat","tier:tier_2"]},{"id":"anthropic/claude-haiku-4.5","info":{"releasedAt":"2025-10-16","name":"Claude 4.5 Haiku","developer":"Anthropic","description":"Claude 4.5 Haiku is a fast, lightweight model optimized for quick responses and high-throughput applications.","contextLength":200000,"outputMax":64000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/anthropic/claude-4.5-haiku","docsJson":"https://api.aimlapi.com/docs-json?model=anthropic%2Fclaude-haiku-4.5&endpoint=anthropic%2Fmessages"},"type":"anthropic/messages","aliases":["claude-haiku-4.5","claude-haiku-4-5"],"tags":["playground:chat","tier:tier_2"]},{"id":"anthropic/claude-sonnet-4.5","info":{"releasedAt":"2025-10-01","name":"Claude 4.5 Sonnet","developer":"Anthropic","description":"Claude 4.5 Sonnet offers a balance of intelligence and speed for diverse enterprise and coding tasks.","contextLength":200000,"outputMax":64000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/anthropic/claude-4-5-sonnet","docsJson":"https://api.aimlapi.com/docs-json?model=anthropic%2Fclaude-sonnet-4.5&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["claude-sonnet-4.5","claude-sonnet-4-5"],"tags":["playground:chat","tier:tier_2"]},{"id":"anthropic/claude-sonnet-4.5","info":{"releasedAt":"2025-10-01","name":"Claude 4.5 Sonnet","developer":"Anthropic","description":"Claude 4.5 Sonnet offers a balance of intelligence and speed for diverse enterprise and coding tasks.","contextLength":200000,"outputMax":64000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/anthropic/claude-4-5-sonnet","docsJson":"https://api.aimlapi.com/docs-json?model=anthropic%2Fclaude-sonnet-4.5&endpoint=anthropic%2Fmessages"},"type":"anthropic/messages","aliases":["claude-sonnet-4.5","claude-sonnet-4-5"],"tags":["playground:chat","tier:tier_2"]},{"id":"anthropic/claude-opus-4.1","info":{"releasedAt":"2025-09-30","name":"Claude 4.1 Opus","developer":"Anthropic","description":"Claude 4.1 Opus is an enhanced version of Claude 4 Opus with improved reasoning and instruction-following capabilities.","contextLength":200000,"outputMax":32000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/anthropic/claude-opus-4.1","docsJson":"https://api.aimlapi.com/docs-json?model=anthropic%2Fclaude-opus-4.1&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["claude-opus-4.1","claude-opus-4-1-latest","claude-opus-4-1","anthropic/claude-opus-4.1-20250805"],"tags":["playground:chat","tier:tier_2"]},{"id":"anthropic/claude-opus-4.1","info":{"releasedAt":"2025-09-30","name":"Claude 4.1 Opus","developer":"Anthropic","description":"Claude 4.1 Opus is an enhanced version of Claude 4 Opus with improved reasoning and instruction-following capabilities.","contextLength":200000,"outputMax":32000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/anthropic/claude-opus-4.1","docsJson":"https://api.aimlapi.com/docs-json?model=anthropic%2Fclaude-opus-4.1&endpoint=anthropic%2Fmessages"},"type":"anthropic/messages","aliases":["claude-opus-4.1","claude-opus-4-1-latest","claude-opus-4-1","anthropic/claude-opus-4.1-20250805"],"tags":["playground:chat","tier:tier_2"]},{"id":"anthropic/claude-opus-4","info":{"releasedAt":"2025-05-22","name":"Claude Opus 4","developer":"Anthropic","contextLength":200000,"outputMax":32000,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=anthropic%2Fclaude-opus-4&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["claude-opus-4"],"tags":["playground:chat","tier:tier_2"]},{"id":"anthropic/claude-opus-4","info":{"releasedAt":"2025-05-22","name":"Claude Opus 4","developer":"Anthropic","contextLength":200000,"outputMax":32000,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=anthropic%2Fclaude-opus-4&endpoint=anthropic%2Fmessages"},"type":"anthropic/messages","aliases":["claude-opus-4"],"tags":["playground:chat","tier:tier_2"]},{"id":"anthropic/claude-sonnet-4","info":{"releasedAt":"2025-05-22","name":"Claude Sonnet 4","developer":"Anthropic","contextLength":1000000,"outputMax":64000,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=anthropic%2Fclaude-sonnet-4&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["claude-sonnet-4"],"tags":["playground:chat","tier:tier_2"]},{"id":"anthropic/claude-sonnet-4","info":{"releasedAt":"2025-05-22","name":"Claude Sonnet 4","developer":"Anthropic","contextLength":1000000,"outputMax":64000,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=anthropic%2Fclaude-sonnet-4&endpoint=anthropic%2Fmessages"},"type":"anthropic/messages","aliases":["claude-sonnet-4"],"tags":["playground:chat","tier:tier_2"]},{"id":"anthropic/claude-3-haiku","info":{"releasedAt":"2024-03-13","name":"Claude 3 Haiku","developer":"Anthropic","contextLength":200000,"outputMax":4096,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=anthropic%2Fclaude-3-haiku&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["claude-3-haiku"],"tags":["playground:chat","tier:tier_2"]},{"id":"anthropic/claude-3-haiku","info":{"releasedAt":"2024-03-13","name":"Claude 3 Haiku","developer":"Anthropic","contextLength":200000,"outputMax":4096,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=anthropic%2Fclaude-3-haiku&endpoint=anthropic%2Fmessages"},"type":"anthropic/messages","aliases":["claude-3-haiku"],"tags":["playground:chat","tier:tier_2"]},{"id":"anthropic/claude-opus-4.1","info":{"releasedAt":"2025-09-30","name":"Claude 4.1 Opus","developer":"Anthropic","description":"Claude 4.1 Opus is an enhanced version of Claude 4 Opus with improved reasoning and instruction-following capabilities.","contextLength":200000,"outputMax":32000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/anthropic/claude-opus-4.1","docsJson":"https://api.aimlapi.com/docs-json?model=anthropic%2Fclaude-opus-4.1&endpoint=anthropic%2Fbatches"},"type":"anthropic/batches","aliases":["claude-opus-4.1","claude-opus-4-1-latest","claude-opus-4-1","anthropic/claude-opus-4.1-20250805"],"tags":["playground:chat","tier:tier_2"]},{"id":"anthropic/claude-opus-4.1","info":{"releasedAt":"2025-09-30","name":"Claude 4.1 Opus","developer":"Anthropic","description":"Claude 4.1 Opus is an enhanced version of Claude 4 Opus with improved reasoning and instruction-following capabilities.","contextLength":200000,"outputMax":32000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/anthropic/claude-opus-4.1","docsJson":"https://api.aimlapi.com/docs-json?model=anthropic%2Fclaude-opus-4.1&endpoint=anthropic%2Fbatches-status"},"type":"anthropic/batches-status","aliases":["claude-opus-4.1","claude-opus-4-1-latest","claude-opus-4-1","anthropic/claude-opus-4.1-20250805"],"tags":["playground:chat","tier:tier_2"]},{"id":"anthropic/claude-opus-4.1","info":{"releasedAt":"2025-09-30","name":"Claude 4.1 Opus","developer":"Anthropic","description":"Claude 4.1 Opus is an enhanced version of Claude 4 Opus with improved reasoning and instruction-following capabilities.","contextLength":200000,"outputMax":32000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/anthropic/claude-opus-4.1","docsJson":"https://api.aimlapi.com/docs-json?model=anthropic%2Fclaude-opus-4.1&endpoint=anthropic%2Fbatches-cancel"},"type":"anthropic/batches-cancel","aliases":["claude-opus-4.1","claude-opus-4-1-latest","claude-opus-4-1","anthropic/claude-opus-4.1-20250805"],"tags":["playground:chat","tier:tier_2"]},{"id":"anthropic/claude-sonnet-4.5","info":{"releasedAt":"2025-10-01","name":"Claude 4.5 Sonnet","developer":"Anthropic","description":"Claude 4.5 Sonnet offers a balance of intelligence and speed for diverse enterprise and coding tasks.","contextLength":200000,"outputMax":64000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/anthropic/claude-4-5-sonnet","docsJson":"https://api.aimlapi.com/docs-json?model=anthropic%2Fclaude-sonnet-4.5&endpoint=anthropic%2Fbatches"},"type":"anthropic/batches","aliases":["claude-sonnet-4.5","claude-sonnet-4-5"],"tags":["playground:chat","tier:tier_2"]},{"id":"anthropic/claude-sonnet-4.5","info":{"releasedAt":"2025-10-01","name":"Claude 4.5 Sonnet","developer":"Anthropic","description":"Claude 4.5 Sonnet offers a balance of intelligence and speed for diverse enterprise and coding tasks.","contextLength":200000,"outputMax":64000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/anthropic/claude-4-5-sonnet","docsJson":"https://api.aimlapi.com/docs-json?model=anthropic%2Fclaude-sonnet-4.5&endpoint=anthropic%2Fbatches-status"},"type":"anthropic/batches-status","aliases":["claude-sonnet-4.5","claude-sonnet-4-5"],"tags":["playground:chat","tier:tier_2"]},{"id":"anthropic/claude-sonnet-4.5","info":{"releasedAt":"2025-10-01","name":"Claude 4.5 Sonnet","developer":"Anthropic","description":"Claude 4.5 Sonnet offers a balance of intelligence and speed for diverse enterprise and coding tasks.","contextLength":200000,"outputMax":64000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/anthropic/claude-4-5-sonnet","docsJson":"https://api.aimlapi.com/docs-json?model=anthropic%2Fclaude-sonnet-4.5&endpoint=anthropic%2Fbatches-cancel"},"type":"anthropic/batches-cancel","aliases":["claude-sonnet-4.5","claude-sonnet-4-5"],"tags":["playground:chat","tier:tier_2"]},{"id":"anthropic/claude-haiku-4.5","info":{"releasedAt":"2025-10-16","name":"Claude 4.5 Haiku","developer":"Anthropic","description":"Claude 4.5 Haiku is a fast, lightweight model optimized for quick responses and high-throughput applications.","contextLength":200000,"outputMax":64000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/anthropic/claude-4.5-haiku","docsJson":"https://api.aimlapi.com/docs-json?model=anthropic%2Fclaude-haiku-4.5&endpoint=anthropic%2Fbatches"},"type":"anthropic/batches","aliases":["claude-haiku-4.5","claude-haiku-4-5"],"tags":["playground:chat","tier:tier_2"]},{"id":"anthropic/claude-haiku-4.5","info":{"releasedAt":"2025-10-16","name":"Claude 4.5 Haiku","developer":"Anthropic","description":"Claude 4.5 Haiku is a fast, lightweight model optimized for quick responses and high-throughput applications.","contextLength":200000,"outputMax":64000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/anthropic/claude-4.5-haiku","docsJson":"https://api.aimlapi.com/docs-json?model=anthropic%2Fclaude-haiku-4.5&endpoint=anthropic%2Fbatches-status"},"type":"anthropic/batches-status","aliases":["claude-haiku-4.5","claude-haiku-4-5"],"tags":["playground:chat","tier:tier_2"]},{"id":"anthropic/claude-haiku-4.5","info":{"releasedAt":"2025-10-16","name":"Claude 4.5 Haiku","developer":"Anthropic","description":"Claude 4.5 Haiku is a fast, lightweight model optimized for quick responses and high-throughput applications.","contextLength":200000,"outputMax":64000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/anthropic/claude-4.5-haiku","docsJson":"https://api.aimlapi.com/docs-json?model=anthropic%2Fclaude-haiku-4.5&endpoint=anthropic%2Fbatches-cancel"},"type":"anthropic/batches-cancel","aliases":["claude-haiku-4.5","claude-haiku-4-5"],"tags":["playground:chat","tier:tier_2"]},{"id":"anthropic/claude-opus-4.5","info":{"releasedAt":"2025-11-25","name":"Claude 4.5 Opus","developer":"Anthropic","description":"Claude 4.5 Opus is Anthropic's flagship model for the most demanding reasoning and analysis tasks.","contextLength":200000,"outputMax":64000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/anthropic/claude-4.5-opus","docsJson":"https://api.aimlapi.com/docs-json?model=anthropic%2Fclaude-opus-4.5&endpoint=anthropic%2Fbatches"},"type":"anthropic/batches","aliases":["claude-opus-4.5","anthropic/claude-opus-4-5","claude-opus-4-5"],"tags":["playground:chat","tier:tier_2"]},{"id":"anthropic/claude-opus-4.5","info":{"releasedAt":"2025-11-25","name":"Claude 4.5 Opus","developer":"Anthropic","description":"Claude 4.5 Opus is Anthropic's flagship model for the most demanding reasoning and analysis tasks.","contextLength":200000,"outputMax":64000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/anthropic/claude-4.5-opus","docsJson":"https://api.aimlapi.com/docs-json?model=anthropic%2Fclaude-opus-4.5&endpoint=anthropic%2Fbatches-status"},"type":"anthropic/batches-status","aliases":["claude-opus-4.5","anthropic/claude-opus-4-5","claude-opus-4-5"],"tags":["playground:chat","tier:tier_2"]},{"id":"anthropic/claude-opus-4.5","info":{"releasedAt":"2025-11-25","name":"Claude 4.5 Opus","developer":"Anthropic","description":"Claude 4.5 Opus is Anthropic's flagship model for the most demanding reasoning and analysis tasks.","contextLength":200000,"outputMax":64000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/anthropic/claude-4.5-opus","docsJson":"https://api.aimlapi.com/docs-json?model=anthropic%2Fclaude-opus-4.5&endpoint=anthropic%2Fbatches-cancel"},"type":"anthropic/batches-cancel","aliases":["claude-opus-4.5","anthropic/claude-opus-4-5","claude-opus-4-5"],"tags":["playground:chat","tier:tier_2"]},{"id":"anthropic/claude-sonnet-4.6","info":{"releasedAt":"2026-02-18","name":"Claude 4.6 Sonnet","developer":"Anthropic","description":"Claude 4.6 Sonnet is a highly capable model balancing performance and efficiency for everyday AI tasks.","contextLength":200000,"outputMax":64000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/anthropic/claude-4.6-sonnet","docsJson":"https://api.aimlapi.com/docs-json?model=anthropic%2Fclaude-sonnet-4.6&endpoint=anthropic%2Fbatches"},"type":"anthropic/batches","aliases":["claude-sonnet-4.6","claude-sonnet-4-6","anthropic/claude-sonnet-4-6-20260218"],"tags":["playground:chat","tier:tier_2"]},{"id":"anthropic/claude-sonnet-4.6","info":{"releasedAt":"2026-02-18","name":"Claude 4.6 Sonnet","developer":"Anthropic","description":"Claude 4.6 Sonnet is a highly capable model balancing performance and efficiency for everyday AI tasks.","contextLength":200000,"outputMax":64000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/anthropic/claude-4.6-sonnet","docsJson":"https://api.aimlapi.com/docs-json?model=anthropic%2Fclaude-sonnet-4.6&endpoint=anthropic%2Fbatches-status"},"type":"anthropic/batches-status","aliases":["claude-sonnet-4.6","claude-sonnet-4-6","anthropic/claude-sonnet-4-6-20260218"],"tags":["playground:chat","tier:tier_2"]},{"id":"anthropic/claude-sonnet-4.6","info":{"releasedAt":"2026-02-18","name":"Claude 4.6 Sonnet","developer":"Anthropic","description":"Claude 4.6 Sonnet is a highly capable model balancing performance and efficiency for everyday AI tasks.","contextLength":200000,"outputMax":64000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/anthropic/claude-4.6-sonnet","docsJson":"https://api.aimlapi.com/docs-json?model=anthropic%2Fclaude-sonnet-4.6&endpoint=anthropic%2Fbatches-cancel"},"type":"anthropic/batches-cancel","aliases":["claude-sonnet-4.6","claude-sonnet-4-6","anthropic/claude-sonnet-4-6-20260218"],"tags":["playground:chat","tier:tier_2"]},{"id":"anthropic/claude-opus-4.7","info":{"releasedAt":"2026-04-16","name":"Claude 4.7 Opus","developer":"Anthropic","description":"","contextLength":1000000,"outputMax":128000,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=anthropic%2Fclaude-opus-4.7&endpoint=anthropic%2Fbatches"},"type":"anthropic/batches","aliases":["claude-opus-4.7","claude-opus-4-7","anthropic/claude-opus-4-7"],"tags":["playground:chat","tier:tier_2","playground:code"]},{"id":"anthropic/claude-opus-4.7","info":{"releasedAt":"2026-04-16","name":"Claude 4.7 Opus","developer":"Anthropic","description":"","contextLength":1000000,"outputMax":128000,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=anthropic%2Fclaude-opus-4.7&endpoint=anthropic%2Fbatches-status"},"type":"anthropic/batches-status","aliases":["claude-opus-4.7","claude-opus-4-7","anthropic/claude-opus-4-7"],"tags":["playground:chat","tier:tier_2"]},{"id":"anthropic/claude-opus-4.7","info":{"releasedAt":"2026-04-16","name":"Claude 4.7 Opus","developer":"Anthropic","description":"","contextLength":1000000,"outputMax":128000,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=anthropic%2Fclaude-opus-4.7&endpoint=anthropic%2Fbatches-cancel"},"type":"anthropic/batches-cancel","aliases":["claude-opus-4.7","claude-opus-4-7","anthropic/claude-opus-4-7"],"tags":["playground:chat","tier:tier_2"]},{"id":"anthropic/claude-opus-4.8","info":{"releasedAt":"2026-05-28","name":"Claude 4.8 Opus","developer":"Anthropic","description":"Claude 4.8 Opus is Anthropic's most capable model designed for complex reasoning and agentic coding workflows. Features a 1M token context window, adaptive thinking, and top-tier performance across multilingual tasks, long-context handling, and vision.","contextLength":1000000,"outputMax":128000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/anthropic/claude-4.8-opus","isHottest":true,"docsJson":"https://api.aimlapi.com/docs-json?model=anthropic%2Fclaude-opus-4.8&endpoint=anthropic%2Fbatches"},"type":"anthropic/batches","aliases":["claude-opus-4.8","claude-opus-4-8","anthropic/claude-opus-4-8"],"tags":["playground:chat","tier:tier_2","playground:code"]},{"id":"anthropic/claude-opus-4.8","info":{"releasedAt":"2026-05-28","name":"Claude 4.8 Opus","developer":"Anthropic","description":"Claude 4.8 Opus is Anthropic's most capable model designed for complex reasoning and agentic coding workflows. Features a 1M token context window, adaptive thinking, and top-tier performance across multilingual tasks, long-context handling, and vision.","contextLength":1000000,"outputMax":128000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/anthropic/claude-4.8-opus","isHottest":true,"docsJson":"https://api.aimlapi.com/docs-json?model=anthropic%2Fclaude-opus-4.8&endpoint=anthropic%2Fbatches-status"},"type":"anthropic/batches-status","aliases":["claude-opus-4.8","claude-opus-4-8","anthropic/claude-opus-4-8"],"tags":["playground:chat","tier:tier_2"]},{"id":"anthropic/claude-opus-4.8","info":{"releasedAt":"2026-05-28","name":"Claude 4.8 Opus","developer":"Anthropic","description":"Claude 4.8 Opus is Anthropic's most capable model designed for complex reasoning and agentic coding workflows. Features a 1M token context window, adaptive thinking, and top-tier performance across multilingual tasks, long-context handling, and vision.","contextLength":1000000,"outputMax":128000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/anthropic/claude-4.8-opus","isHottest":true,"docsJson":"https://api.aimlapi.com/docs-json?model=anthropic%2Fclaude-opus-4.8&endpoint=anthropic%2Fbatches-cancel"},"type":"anthropic/batches-cancel","aliases":["claude-opus-4.8","claude-opus-4-8","anthropic/claude-opus-4-8"],"tags":["playground:chat","tier:tier_2"]},{"id":"anthropic/claude-fable-latest","info":{"releasedAt":"2026-06-09","name":"Claude Fable Latest","developer":"Anthropic","contextLength":1000000,"outputMax":128000,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=anthropic%2Fclaude-fable-latest&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["claude-fable-latest"],"tags":["playground:chat","tier:tier_2"]},{"id":"anthropic/claude-fable-latest","info":{"releasedAt":"2026-06-09","name":"Claude Fable Latest","developer":"Anthropic","contextLength":1000000,"outputMax":128000,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=anthropic%2Fclaude-fable-latest&endpoint=anthropic%2Fmessages"},"type":"anthropic/messages","aliases":["claude-fable-latest"],"tags":["playground:chat","tier:tier_2"]},{"id":"anthropic/claude-haiku-latest","info":{"releasedAt":"2026-04-27","name":"Claude Haiku Latest","developer":"Anthropic","contextLength":200000,"outputMax":64000,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=anthropic%2Fclaude-haiku-latest&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["claude-haiku-latest"],"tags":["playground:chat","tier:tier_2"]},{"id":"anthropic/claude-haiku-latest","info":{"releasedAt":"2026-04-27","name":"Claude Haiku Latest","developer":"Anthropic","contextLength":200000,"outputMax":64000,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=anthropic%2Fclaude-haiku-latest&endpoint=anthropic%2Fmessages"},"type":"anthropic/messages","aliases":["claude-haiku-latest"],"tags":["playground:chat","tier:tier_2"]},{"id":"anthropic/claude-sonnet-latest","info":{"releasedAt":"2026-04-27","name":"Claude Sonnet Latest","developer":"Anthropic","contextLength":1000000,"outputMax":128000,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=anthropic%2Fclaude-sonnet-latest&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["claude-sonnet-latest"],"tags":["playground:chat","tier:tier_2"]},{"id":"anthropic/claude-sonnet-latest","info":{"releasedAt":"2026-04-27","name":"Claude Sonnet Latest","developer":"Anthropic","contextLength":1000000,"outputMax":128000,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=anthropic%2Fclaude-sonnet-latest&endpoint=anthropic%2Fmessages"},"type":"anthropic/messages","aliases":["claude-sonnet-latest"],"tags":["playground:chat","tier:tier_2"]},{"id":"anthropic/claude-opus-latest","info":{"releasedAt":"2026-04-21","name":"Claude Opus Latest","developer":"Anthropic","contextLength":1000000,"outputMax":128000,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=anthropic%2Fclaude-opus-latest&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["claude-opus-latest"],"tags":["playground:chat","tier:tier_2"]},{"id":"anthropic/claude-opus-latest","info":{"releasedAt":"2026-04-21","name":"Claude Opus Latest","developer":"Anthropic","contextLength":1000000,"outputMax":128000,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=anthropic%2Fclaude-opus-latest&endpoint=anthropic%2Fmessages"},"type":"anthropic/messages","aliases":["claude-opus-latest"],"tags":["playground:chat","tier:tier_2"]},{"id":"bytedance/seedance-1-0-pro","info":{"releasedAt":"2025-12-29","developer":"ByteDance","description":"ByteDance Seedance 1.0 Pro generates high-quality videos from text prompts with enhanced detail and consistency.","name":"Seedance 1.0 Pro","url":"","docsUrl":"https://docs.aimlapi.com/api-references/video-models/bytedance/seedance-1.0-pro-text-to-video","docsJson":"https://api.aimlapi.com/docs-json?model=bytedance%2Fseedance-1-0-pro&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":[],"tags":["playground:video","tier:tier_2"]},{"id":"bytedance/seedance-1-0-pro-fast","info":{"releasedAt":"2025-12-29","developer":"ByteDance","description":"ByteDance Seedance 1.0 Pro Fast delivers high-quality video generation with reduced processing time.","name":"Seedance 1.0 Pro Fast","url":"","docsUrl":"https://docs.aimlapi.com/api-references/video-models/bytedance/seedance-1.0-pro-fast","docsJson":"https://api.aimlapi.com/docs-json?model=bytedance%2Fseedance-1-0-pro-fast&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":[],"tags":["playground:video","tier:tier_2"]},{"id":"bytedance/seedance-1-5-pro","info":{"releasedAt":"2026-04-03","developer":"ByteDance","description":"","name":"Seedance 1.5 Pro","url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=bytedance%2Fseedance-1-5-pro&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":[],"tags":["playground:video","tier:tier_2"]},{"id":"bytedance/dreamina-seedance-2-0","info":{"releasedAt":"2026-04-07","name":"Seedance 2.0","developer":"ByteDance","description":"","url":"","docsUrl":"","isHottest":true,"docsJson":"https://api.aimlapi.com/docs-json?model=bytedance%2Fdreamina-seedance-2-0&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":[],"tags":["playground:video","tier:tier_2"]},{"id":"bytedance/dreamina-seedance-2-0-fast","info":{"releasedAt":"2026-04-07","name":"Seedance 2.0 Fast","developer":"ByteDance","description":"","url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=bytedance%2Fdreamina-seedance-2-0-fast&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":[],"tags":["playground:video","tier:tier_2"]},{"id":"bytedance/dreamina-seedance-2-0-mini","info":{"releasedAt":"2026-06-25","name":"Seedance 2.0 Mini","developer":"ByteDance","description":"","url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=bytedance%2Fdreamina-seedance-2-0-mini&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":[],"tags":["playground:video","tier:tier_2"]},{"id":"bytedance/seedream-4-5","info":{"releasedAt":"2025-12-04","developer":"ByteDance","description":"ByteDance Seedream 4.5 is an advanced text-to-image model with improved prompt adherence and visual quality.","name":"Seedream 4.5","url":"","docsUrl":"https://docs.aimlapi.com/api-references/image-models/bytedance/seedream-4-5","docsJson":"https://api.aimlapi.com/docs-json?model=bytedance%2Fseedream-4-5&endpoint=openai%2Fimage-generations"},"type":"openai/image-generations","aliases":[],"tags":["playground:image","tier:tier_2"]},{"id":"bytedance/seedream-5-0-lite","info":{"releasedAt":"2026-03-02","developer":"ByteDance","description":"Seedream 5.0 Lite Preview is a text-to-image model by ByteDance optimized for fast image generation with API-friendly workflows.","name":"Seedream 5.0 Lite Preview","url":"","docsUrl":"https://docs.aimlapi.com/api-references/image-models/bytedance","docsJson":"https://api.aimlapi.com/docs-json?model=bytedance%2Fseedream-5-0-lite&endpoint=openai%2Fimage-generations"},"type":"openai/image-generations","aliases":[],"tags":["playground:image","tier:tier_2"]},{"id":"bytedance/dola-seedream-5-0-pro","info":{"releasedAt":"2026-07-08","developer":"ByteDance","description":"Seedream 5.0 Pro is ByteDance flagship text-to-image model with high-resolution output up to 2048x2048 (up to ~2.7K at 16:9) and multi-image reference support.","name":"Seedream 5.0 Pro","url":"","docsUrl":"https://docs.aimlapi.com/api-references/image-models/bytedance","docsJson":"https://api.aimlapi.com/docs-json?model=bytedance%2Fdola-seedream-5-0-pro&endpoint=openai%2Fimage-generations"},"type":"openai/image-generations","aliases":[],"tags":["playground:image","tier:tier_2"]},{"id":"bytedance/seed-1-8","info":{"releasedAt":"2026-01-12","name":"Seed 1.8","developer":"ByteDance","description":"ByteDance Seed 1.8 is a large language model with a 256K context window optimized for long-context reasoning and generation.","contextLength":256000,"outputMax":224000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/bytedance/seed-1.8","docsJson":"https://api.aimlapi.com/docs-json?model=bytedance%2Fseed-1-8&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":[],"tags":["playground:chat","tier:tier_2"]},{"id":"bytedance/seed-2-0-pro","info":{"releasedAt":"2026-04-24","name":"Dola-Seed 2.0 Pro","developer":"ByteDance","description":"","contextLength":256000,"outputMax":128000,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=bytedance%2Fseed-2-0-pro&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":[],"tags":["playground:chat","tier:tier_2"]},{"id":"bytedance/seed-2-0-lite","info":{"releasedAt":"2026-04-24","name":"Dola-Seed 2.0 Lite","developer":"ByteDance","description":"","contextLength":256000,"outputMax":128000,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=bytedance%2Fseed-2-0-lite&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":[],"tags":["playground:chat","tier:tier_2"]},{"id":"bytedance/seed-2-0-mini","info":{"releasedAt":"2026-04-24","name":"Dola-Seed 2.0 Mini","developer":"ByteDance","description":"","contextLength":256000,"outputMax":128000,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=bytedance%2Fseed-2-0-mini&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":[],"tags":["playground:chat","tier:tier_2"]},{"id":"bytedance/seed-2-0-code-preview","info":{"releasedAt":"2026-04-24","name":"Dola-Seed 2.0 Code","developer":"ByteDance","description":"","contextLength":256000,"outputMax":128000,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=bytedance%2Fseed-2-0-code-preview&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":[],"tags":["playground:chat","tier:tier_2","playground:code"]},{"id":"bytedance/seed-audio-1-0","info":{"releasedAt":"2026-06-29","name":"Seed Audio 1.0","developer":"ByteDance","description":"Seed Audio 1.0 is a non-streaming audio generation model for speech, sound effects, timbre control, and reference-guided audio creation.","url":"","docsUrl":"https://docs.byteplus.com/en/docs/byteplusvoice/seedaudio-01","docsJson":"https://api.aimlapi.com/docs-json?model=bytedance%2Fseed-audio-1-0&endpoint=internal%2Ftext-to-speech"},"type":"internal/text-to-speech","aliases":["bytedance/seed-audio-1.0"],"tags":["playground:tts","tier:tier_2"]},{"id":"bytedance/dreamina-creative-upscale","info":{"releasedAt":"2026-06-04","developer":"ByteDance","description":"Dreamina Creative Upscale is a Seedream-based super-resolution model that enhances AIGC and low-quality images, enriching texture and detail while preserving structure, with 2K/4K output.","name":"Dreamina Creative Upscale","url":"","docsUrl":"https://docs.aimlapi.com/api-references/image-models/bytedance","docsJson":"https://api.aimlapi.com/docs-json?model=bytedance%2Fdreamina-creative-upscale&endpoint=openai%2Fimage-generations"},"type":"openai/image-generations","aliases":[],"tags":["playground:image","tier:tier_2"]},{"id":"bytedance/seedance-1-0-pro-t2v","info":{"releasedAt":"2025-12-29","developer":"ByteDance","description":"ByteDance Seedance 1.0 Pro generates high-quality videos from text prompts with enhanced detail and consistency.","name":"Seedance 1.0 Pro","url":"","docsUrl":"https://docs.aimlapi.com/api-references/video-models/bytedance/seedance-1.0-pro-text-to-video","docsJson":"https://api.aimlapi.com/docs-json?model=bytedance%2Fseedance-1-0-pro-t2v&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":[],"tags":["playground:video","tier:tier_2"]},{"id":"bytedance/seedance-1-0-pro-i2v","info":{"releasedAt":"2025-12-29","developer":"ByteDance","description":"ByteDance Seedance 1.0 Pro generates high-quality videos from text prompts with enhanced detail and consistency.","name":"Seedance 1.0 Pro","url":"","docsUrl":"https://docs.aimlapi.com/api-references/video-models/bytedance/seedance-1.0-pro-text-to-video","docsJson":"https://api.aimlapi.com/docs-json?model=bytedance%2Fseedance-1-0-pro-i2v&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":[],"tags":["playground:video","tier:tier_2"]},{"id":"bytedance/seedream-5-0-lite-preview","info":{"releasedAt":"2026-03-02","developer":"ByteDance","description":"Seedream 5.0 Lite Preview is a text-to-image model by ByteDance optimized for fast image generation with API-friendly workflows.","name":"Seedream 5.0 Lite Preview","url":"","docsUrl":"https://docs.aimlapi.com/api-references/image-models/bytedance","docsJson":"https://api.aimlapi.com/docs-json?model=bytedance%2Fseedream-5-0-lite-preview&endpoint=openai%2Fimage-generations"},"type":"openai/image-generations","aliases":[],"tags":["playground:image","tier:tier_2"]},{"id":"bytedance/seedream-5-0-pro","info":{"releasedAt":"2026-07-08","developer":"ByteDance","description":"Seedream 5.0 Pro is ByteDance flagship text-to-image model with high-resolution output up to 2048x2048 (up to ~2.7K at 16:9) and multi-image reference support.","name":"Seedream 5.0 Pro","url":"","docsUrl":"https://docs.aimlapi.com/api-references/image-models/bytedance","docsJson":"https://api.aimlapi.com/docs-json?model=bytedance%2Fseedream-5-0-pro&endpoint=openai%2Fimage-generations"},"type":"openai/image-generations","aliases":[],"tags":["playground:image","tier:tier_2"]},{"id":"bytedance/seedance-2-0-fast","info":{"releasedAt":"2026-04-07","name":"Seedance 2.0 Fast","developer":"ByteDance","description":"","url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=bytedance%2Fseedance-2-0-fast&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":["bytedance/seedance-2.0/fast/image-to-video","bytedance/seedance-2.0/fast/reference-to-video","bytedance/seedance-2.0/fast/text-to-video"],"tags":["playground:video","tier:tier_2"]},{"id":"bytedance/seedance-2-0","info":{"releasedAt":"2026-04-07","name":"Seedance 2.0","developer":"ByteDance","description":"","url":"","docsUrl":"","isHottest":true,"docsJson":"https://api.aimlapi.com/docs-json?model=bytedance%2Fseedance-2-0&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":["bytedance/seedance-2.0/image-to-video","bytedance/seedance-2.0/reference-to-video","bytedance/seedance-2.0/text-to-video"],"tags":["playground:video","tier:tier_2"]},{"id":"bytedance/seedance-2-0-mini","info":{"releasedAt":"2026-06-25","name":"Seedance 2.0 Mini","developer":"ByteDance","description":"","url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=bytedance%2Fseedance-2-0-mini&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":[],"tags":["playground:video","tier:tier_2"]},{"id":"bytedance/dola-seed-2-0-pro","info":{"releasedAt":"2026-04-24","name":"Dola-Seed 2.0 Pro","developer":"ByteDance","description":"","contextLength":256000,"outputMax":128000,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=bytedance%2Fdola-seed-2-0-pro&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":[],"tags":["playground:chat","tier:tier_2"]},{"id":"bytedance/dola-seed-2-0-lite","info":{"releasedAt":"2026-04-24","name":"Dola-Seed 2.0 Lite","developer":"ByteDance","description":"","contextLength":256000,"outputMax":128000,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=bytedance%2Fdola-seed-2-0-lite&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":[],"tags":["playground:chat","tier:tier_2"]},{"id":"bytedance/dola-seed-2-0-mini","info":{"releasedAt":"2026-04-24","name":"Dola-Seed 2.0 Mini","developer":"ByteDance","description":"","contextLength":256000,"outputMax":128000,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=bytedance%2Fdola-seed-2-0-mini&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":[],"tags":["playground:chat","tier:tier_2"]},{"id":"bytedance/dola-seed-2-0-code","info":{"releasedAt":"2026-04-24","name":"Dola-Seed 2.0 Code","developer":"ByteDance","description":"","contextLength":256000,"outputMax":128000,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=bytedance%2Fdola-seed-2-0-code&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":[],"tags":["playground:chat","tier:tier_2","playground:code"]},{"id":"elevenlabs/eleven_music","info":{"releasedAt":"2025-12-05","name":"Eleven Music v1","developer":"Elevenlabs","description":"ElevenLabs Music v1 generates original music tracks from text prompts with diverse style and genre support.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/music-models/elevenlabs/eleven_music","docsJson":"https://api.aimlapi.com/docs-json?model=elevenlabs%2Feleven_music&endpoint=internal%2Faudio-generations%2Fsubmit"},"type":"internal/audio-generations/submit","aliases":[],"tags":["playground:audio","tier:tier_2"]},{"id":"elevenlabs/eleven_multilingual_v2","info":{"releasedAt":"2026-01-05","name":"Eleven Multilingual v2","developer":"Elevenlabs","description":"ElevenLabs Multilingual v2 delivers natural-sounding text-to-speech in 29 languages with expressive voice cloning.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/speech-models/text-to-speech/elevenlabs/eleven_multilingual_v2","docsJson":"https://api.aimlapi.com/docs-json?model=elevenlabs%2Feleven_multilingual_v2&endpoint=internal%2Ftext-to-speech"},"type":"internal/text-to-speech","aliases":[],"tags":["playground:tts","tier:tier_2"]},{"id":"elevenlabs/eleven_turbo_v2_5","info":{"releasedAt":"2026-01-05","name":"Eleven Turbo v2.5","developer":"Elevenlabs","description":"ElevenLabs Turbo v2.5 provides ultra-low-latency text-to-speech generation optimized for real-time conversational AI.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/speech-models/text-to-speech/elevenlabs/eleven_turbo_v2_5","docsJson":"https://api.aimlapi.com/docs-json?model=elevenlabs%2Feleven_turbo_v2_5&endpoint=internal%2Ftext-to-speech"},"type":"internal/text-to-speech","aliases":[],"tags":["playground:tts","tier:tier_2"]},{"id":"elevenlabs/v3_alpha","info":{"releasedAt":"2026-01-05","name":"Eleven v3 Alpha","developer":"Elevenlabs","description":"ElevenLabs v3 Alpha is an experimental next-generation TTS model with enhanced expressiveness and voice quality.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/speech-models/voice-chat/elevenlabs/v3_alpha","docsJson":"https://api.aimlapi.com/docs-json?model=elevenlabs%2Fv3_alpha&endpoint=internal%2Ftext-to-speech"},"type":"internal/text-to-speech","aliases":[],"tags":["playground:tts","tier:tier_2"]},{"id":"deepseek/deepseek-reasoner","info":{"releasedAt":"2025-08-28","name":"DeepSeek R1","developer":"DeepSeek AI","description":"DeepSeek R1 excels in reasoning tasks with advanced features like chain-of-thought processing and efficient parameter activation","contextLength":128000,"outputMax":127000,"url":"https://aimlapi.com/models/deepseek-r1-api","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/deepseek/deepseek-r1","docsJson":"https://api.aimlapi.com/docs-json?model=deepseek%2Fdeepseek-reasoner&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["deepseek-reasoner"],"tags":["playground:chat","tier:tier_2"]},{"id":"deepseek/deepseek-chat","info":{"releasedAt":"2025-08-28","name":"DeepSeek V3","developer":"DeepSeek AI","description":"DeepSeek-V3 is an advanced LLM with efficient architecture and high performance across various natural language tasks.","contextLength":128000,"outputMax":124000,"url":"https://aimlapi.com/models/deepseek-v3","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/deepseek/deepseek-chat","docsJson":"https://api.aimlapi.com/docs-json?model=deepseek%2Fdeepseek-chat&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["deepseek-chat"],"tags":["playground:chat","tier:tier_2"]},{"id":"deepseek/deepseek-v4-flash","info":{"releasedAt":"2026-04-24","name":"DeepSeek V4 Flash","developer":"DeepSeek AI","description":"DeepSeek V4 Flash and Pro are large language models for chat and reasoning tasks with up to 1M context length. They support both standard and thinking modes, enabling efficient responses or deeper reasoning workflows.","contextLength":1000000,"outputMax":384000,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=deepseek%2Fdeepseek-v4-flash&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["deepseek-v4-flash","deepseek-chat","deepseek/deepseek-chat"],"tags":["playground:chat","tier:tier_2"]},{"id":"deepseek/deepseek-v4-pro","info":{"releasedAt":"2026-04-24","name":"DeepSeek V4 Pro","developer":"DeepSeek AI","description":"DeepSeek V4 Flash and Pro are large language models for chat and reasoning tasks with up to 1M context length. They support both standard and thinking modes, enabling efficient responses or deeper reasoning workflows.","contextLength":1000000,"outputMax":384000,"url":"","docsUrl":"","isHottest":true,"docsJson":"https://api.aimlapi.com/docs-json?model=deepseek%2Fdeepseek-v4-pro&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["deepseek-v4-pro"],"tags":["playground:chat","tier:tier_2","playground:code"]},{"id":"deepseek/deepseek-chat-v3.1","info":{"releasedAt":"2025-08-28","name":"DeepSeek V3.1","developer":"DeepSeek AI","description":"DeepSeek-V3.1 is the latest advanced LLM with improved architecture and performance across various natural language tasks.","contextLength":128000,"outputMax":8000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/deepseek/deepseek-chat-v3.1","docsJson":"https://api.aimlapi.com/docs-json?model=deepseek%2Fdeepseek-chat-v3.1&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":[],"tags":["playground:chat","tier:tier_2","playground:code"]},{"id":"deepseek/deepseek-non-reasoner-v3.1-terminus","info":{"releasedAt":"2025-08-28","name":"DeepSeek V3.1","developer":"DeepSeek AI","description":"DeepSeek-V3.1 is the latest advanced LLM with improved architecture and performance across various natural language tasks.","contextLength":128000,"outputMax":8000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/deepseek/deepseek-chat-v3.1","docsJson":"https://api.aimlapi.com/docs-json?model=deepseek%2Fdeepseek-non-reasoner-v3.1-terminus&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["deepseek-non-reasoner-v3.1-terminus"],"tags":["playground:chat","tier:tier_2","playground:code"]},{"id":"deepseek/deepseek-reasoner-v3.1-terminus","info":{"releasedAt":"2025-08-28","name":"DeepSeek V3.1","developer":"DeepSeek AI","description":"DeepSeek-V3.1 is the latest advanced LLM with improved architecture and performance across various natural language tasks.","contextLength":128000,"outputMax":8000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/deepseek/deepseek-chat-v3.1","docsJson":"https://api.aimlapi.com/docs-json?model=deepseek%2Fdeepseek-reasoner-v3.1-terminus&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["deepseek-reasoner-v3.1-terminus"],"tags":["playground:chat","tier:tier_2","playground:code"]},{"id":"deepseek/deepseek-r1","info":{"releasedAt":"2025-08-28","name":"DeepSeek Reasoner V3.1","developer":"DeepSeek AI","description":"DeepSeek Reasoner V3.1 excels in reasoning tasks with advanced chain-of-thought processing and the latest improvements in parameter activation.","contextLength":128000,"outputMax":64000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/deepseek/deepseek-reasoner-v3.1","docsJson":"https://api.aimlapi.com/docs-json?model=deepseek%2Fdeepseek-r1&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["deepseek/deepseek-reasoner-v3.1","deepseek-reasoner"],"tags":["playground:chat","tier:tier_2","playground:code"]},{"id":"deepseek/deepseek-non-thinking-v3.2-exp","info":{"releasedAt":"2025-10-03","name":"DeepSeek V3.2 Exp","developer":"DeepSeek AI","description":"DeepSeek-V3.2-Exp is an experimental variant of DeepSeek-V3.2 with extended context and non-thinking mode for fast responses.","contextLength":128000,"outputMax":64000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/deepseek/deepseek-reasoner-v3.2-exp-non-thinking","docsJson":"https://api.aimlapi.com/docs-json?model=deepseek%2Fdeepseek-non-thinking-v3.2-exp&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["deepseek-non-thinking-v3.2-exp"],"tags":["playground:chat","tier:tier_2"]},{"id":"deepseek/deepseek-thinking-v3.2-exp","info":{"releasedAt":"2025-10-03","name":"DeepSeek V3.2 Exp","developer":"DeepSeek AI","description":"DeepSeek-V3.2-Exp is an experimental variant of DeepSeek-V3.2 with extended context and non-thinking mode for fast responses.","contextLength":128000,"outputMax":64000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/deepseek/deepseek-reasoner-v3.2-exp-non-thinking","docsJson":"https://api.aimlapi.com/docs-json?model=deepseek%2Fdeepseek-thinking-v3.2-exp&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["deepseek-thinking-v3.2-exp-v2"],"tags":["playground:chat","tier:tier_2"]},{"id":"meituan/longcat-2.0","info":{"releasedAt":"2026-06-30","name":"LongCat-2.0","developer":"Meituan","description":"LongCat-2.0 is Meituan's trillion-parameter agentic MoE model with a 1M-token context window and up to 128K output tokens. It supports native tool calling and multi-step reasoning.","contextLength":1000000,"outputMax":128000,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=meituan%2Flongcat-2.0&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["longcat-2.0"],"tags":["playground:chat","tier:tier_2"]},{"id":"google/gemini-2.5-flash","info":{"releasedAt":"2025-09-09","name":"Gemini 2.5 Flash","developer":"Google","description":"Gemini 2.5 Flash is a powerful AI model developed by Google, designed to handle complex tasks with high accuracy and efficiency and has thinking capabilities.","contextLength":1000000,"outputMax":65536,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/google/gemini-2.5-flash","docsJson":"https://api.aimlapi.com/docs-json?model=google%2Fgemini-2.5-flash&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["gemini-2.5-flash"],"tags":["playground:chat","tier:tier_2"]},{"id":"google/gemini-3-flash-preview","info":{"releasedAt":"2025-12-17","name":"Gemini 3 Flash Preview","developer":"Google","description":"Gemini 3 Flash Preview is a fast, efficient variant of Gemini 3 designed for low-latency multimodal applications.","contextLength":1000000,"outputMax":65536,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/google/gemini-3-flash-preview","docsJson":"https://api.aimlapi.com/docs-json?model=google%2Fgemini-3-flash-preview&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["gemini-3-flash-preview"],"tags":["playground:chat","tier:tier_2"]},{"id":"google/gemini-3.5-flash","info":{"releasedAt":"2026-05-19","name":"Gemini 3.5 Flash","developer":"Google","description":"Gemini 3.5 Flash is a multimodal reasoning model from Google optimized for fast inference and agentic workflows. Supports text, image, audio and video understanding with large context window and strong coding capabilities.","contextLength":1048576,"outputMax":65536,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/google/gemini-3-5-flash","isHottest":true,"docsJson":"https://api.aimlapi.com/docs-json?model=google%2Fgemini-3.5-flash&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["gemini-3.5-flash"],"tags":["playground:chat","tier:tier_2"]},{"id":"google/gemini-2.5-flash-lite","info":{"releasedAt":"2025-09-09","name":"Gemini 2.5 Flash Lite Preview","developer":"Google","description":"Gemini 2.5 Flash Lite Preview is a lightweight AI model developed by Google, optimized for quick responses and efficient processing, making it ideal for tasks requiring minimal latency and resource consumption","contextLength":1000000,"outputMax":1048576,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/google/gemini-2.5-flash-lite-preview","docsJson":"https://api.aimlapi.com/docs-json?model=google%2Fgemini-2.5-flash-lite&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["gemini-2.5-flash-lite"],"tags":["playground:chat","tier:tier_2"]},{"id":"google/gemini-3.1-flash-lite","info":{"releasedAt":"2026-05-08","name":"Gemini 3.1 Flash Lite","developer":"Google","description":"Gemini 3.1 Flash Lite is a cost-efficient multimodal model designed for high-volume tasks such as translation, lightweight reasoning, and simple agent workflows.","contextLength":1000000,"outputMax":65536,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=google%2Fgemini-3.1-flash-lite&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["gemini-3.1-flash-lite"],"tags":["playground:chat","tier:tier_2"]},{"id":"google/gemini-2.5-pro","info":{"releasedAt":"2025-09-09","name":"Gemini 2.5 Pro","developer":"Google","description":"Gemini Pro 2.5 is Google's most advanced reasoning AI model designed for complex tasks, showcasing strong reasoning and coding capabilities. It leads various benchmarks, indicating its enhanced performance.","contextLength":1000000,"outputMax":65536,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/google/gemini-2.5-pro","docsJson":"https://api.aimlapi.com/docs-json?model=google%2Fgemini-2.5-pro&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["gemini-2.5-pro"],"tags":["playground:chat","tier:tier_2","playground:code"]},{"id":"google/gemini-3.1-pro-preview","info":{"releasedAt":"2026-02-25","name":"Gemini 3.1 Pro Preview","developer":"Google","description":"A frontier reasoning model optimized for software engineering and agentic workflows with 1M token context.","contextLength":1000000,"outputMax":65536,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/google/gemini-3-1-pro-preview","docsJson":"https://api.aimlapi.com/docs-json?model=google%2Fgemini-3.1-pro-preview&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["gemini-3.1-pro-preview","gemini-3-1-pro-preview","google/gemini-3-1-pro-preview"],"tags":["playground:chat","tier:tier_2","playground:code"]},{"id":"google/gemma-4-26b-a4b-it-maas","info":{"releasedAt":"2026-06-23","name":"Gemma 4 26B A4B IT","developer":"Google","description":"Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts open model from Google.","contextLength":262144,"outputMax":128000,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=google%2Fgemma-4-26b-a4b-it-maas&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["gemma-4-26b-a4b-it-maas"],"tags":["playground:chat","tier:tier_2"]},{"id":"google/text-multilingual-embedding-002","info":{"releasedAt":"2025-12-13","name":"Text Multilingual Embedding 002","developer":"Google","description":"Google's multilingual embedding model 002 supports cross-lingual semantic search and similarity across multiple languages.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/embedding-models/google/text-multilingual-embedding-002","contextLength":2000,"docsJson":"https://api.aimlapi.com/docs-json?model=google%2Ftext-multilingual-embedding-002&endpoint=openai%2Fembeddings"},"type":"openai/embeddings","aliases":["text-multilingual-embedding-002"],"tags":["playground:embeddings","tier:tier_2"]},{"id":"google/imagen-3.0-generate-002","info":{"releasedAt":"2025-10-13","name":"Imagen 3.0","developer":"Google","description":"Imagen 3: Google's high-quality text-to-image model with enhanced realism and understanding.","url":"https://aimlapi.com/models/imagen-3-api","docsUrl":"https://docs.aimlapi.com/api-references/image-models/google/imagen-3.0","docsJson":"https://api.aimlapi.com/docs-json?model=google%2Fimagen-3.0-generate-002&endpoint=openai%2Fimage-generations"},"type":"openai/image-generations","aliases":["imagen-3.0-generate-002"],"tags":["playground:image","tier:tier_2"]},{"id":"google/imagen-4.0-generate-001","info":{"releasedAt":"2025-10-13","name":"Imagen 4.0 Generate","developer":"Google","description":"Imagen 4.0 Generate: Google's high-quality text-to-image model with enhanced realism and understanding.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/image-models/google/imagen-4-generate","docsJson":"https://api.aimlapi.com/docs-json?model=google%2Fimagen-4.0-generate-001&endpoint=openai%2Fimage-generations"},"type":"openai/image-generations","aliases":["imagen-4.0-generate-001"],"tags":["playground:image","tier:tier_2"]},{"id":"google/imagen-4.0-fast-generate-001","info":{"releasedAt":"2025-10-13","name":"Imagen 4.0 Fast Generate","developer":"Google","description":"Imagen 4.0 Fast Generate: Google's fast text-to-image model with enhanced realism and understanding.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/image-models/google/imagen-4-fast-generate","docsJson":"https://api.aimlapi.com/docs-json?model=google%2Fimagen-4.0-fast-generate-001&endpoint=openai%2Fimage-generations"},"type":"openai/image-generations","aliases":["imagen-4.0-fast-generate-001"],"tags":["playground:image","tier:tier_2"]},{"id":"google/imagen-4.0-ultra-generate-001","info":{"releasedAt":"2025-10-13","name":"Imagen 4.0 Ultra Generate","developer":"Google","description":"Imagen 4.0 Ultra Generate: Google's high-quality text-to-image model with enhanced realism and understanding.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/image-models/google/imagen-4-ultra-generate","docsJson":"https://api.aimlapi.com/docs-json?model=google%2Fimagen-4.0-ultra-generate-001&endpoint=openai%2Fimage-generations"},"type":"openai/image-generations","aliases":["imagen-4.0-ultra-generate-001"],"tags":["playground:image","tier:tier_2"]},{"id":"google/gemini-3-pro-image-preview","info":{"releasedAt":"2026-02-23","name":"Gemini 3 Pro Image","developer":"Google","description":"Gemini 3 Pro Image is a text-to-image model that generates images from text descriptions.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/image-models/google/gemini-3-pro-image-preview","docsJson":"https://api.aimlapi.com/docs-json?model=google%2Fgemini-3-pro-image-preview&endpoint=openai%2Fimage-generations"},"type":"openai/image-generations","aliases":["gemini-3-pro-image-preview","google/nano-banana-pro"],"tags":["playground:image","tier:tier_2"]},{"id":"google/nano-banana-pro","info":{"releasedAt":"2026-02-27","name":"Nano Banana Pro","developer":"Google","description":"Nano Banana Pro is a text-to-image model that generates images from text descriptions.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/image-models/google/gemini-3-pro-image-preview","docsJson":"https://api.aimlapi.com/docs-json?model=google%2Fnano-banana-pro&endpoint=openai%2Fimage-generations"},"type":"openai/image-generations","aliases":["nano-banana-pro"],"tags":["playground:image","tier:tier_2"]},{"id":"google/gemini-3-pro-image-preview-edit","info":{"releasedAt":"2026-02-23","name":"Gemini 3 Pro Image Edit","developer":"Google","description":"Gemini 3 Pro Image Edit is an image-to-image model that edits images based on text prompts.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/image-models/google/gemini-3-pro-image-preview-edit","docsJson":"https://api.aimlapi.com/docs-json?model=google%2Fgemini-3-pro-image-preview-edit&endpoint=openai%2Fimage-generations"},"type":"openai/image-generations","aliases":["gemini-3-pro-image-preview-edit","google/nano-banana-pro-edit"],"tags":["playground:image","tier:tier_2"]},{"id":"google/nano-banana-pro-edit","info":{"releasedAt":"2026-02-27","name":"Nano Banana Pro Edit","developer":"Google","description":"Nano Banana Pro Edit is an image-to-image model that edits images based on text prompts.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/image-models/google/gemini-3-pro-image-preview-edit","docsJson":"https://api.aimlapi.com/docs-json?model=google%2Fnano-banana-pro-edit&endpoint=openai%2Fimage-generations"},"type":"openai/image-generations","aliases":["nano-banana-pro-edit"],"tags":["playground:image","tier:tier_2"]},{"id":"google/gemini-2.5-flash-image","info":{"releasedAt":"2026-02-23","name":"Gemini 2.5 Flash Image","developer":"Google","description":"Gemini 2.5 Flash Image is a text-to-image model powered by Gemini 2.5 Flash for fast, high-quality image generation.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/image-models/google/gemini-2.5-flash-image","docsJson":"https://api.aimlapi.com/docs-json?model=google%2Fgemini-2.5-flash-image&endpoint=openai%2Fimage-generations"},"type":"openai/image-generations","aliases":["gemini-2.5-flash-image","google/nano-banana"],"tags":["playground:image","tier:tier_2"]},{"id":"google/nano-banana","info":{"releasedAt":"2026-02-27","name":"Nano Banana","developer":"Google","description":"","url":"","docsUrl":"https://docs.aimlapi.com/api-references/image-models/google/gemini-2.5-flash-image","docsJson":"https://api.aimlapi.com/docs-json?model=google%2Fnano-banana&endpoint=openai%2Fimage-generations"},"type":"openai/image-generations","aliases":["nano-banana"],"tags":["playground:image","tier:tier_2"]},{"id":"google/gemini-2.5-flash-image-edit","info":{"releasedAt":"2026-02-23","name":"Gemini 2.5 Flash Image Edit","developer":"Google","description":"Gemini 2.5 Flash Image Edit enables text-guided image editing powered by Google's Gemini 2.5 Flash model.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/image-models/google/gemini-2.5-flash-image-edit","docsJson":"https://api.aimlapi.com/docs-json?model=google%2Fgemini-2.5-flash-image-edit&endpoint=openai%2Fimage-generations"},"type":"openai/image-generations","aliases":["gemini-2.5-flash-image-edit","google/nano-banana-edit"],"tags":["playground:image","tier:tier_2"]},{"id":"google/gemini-3.1-flash-image-preview","info":{"releasedAt":"2026-02-27","name":"Nano Banana 2","developer":"Google","description":"Nano Banana 2 is a compact text-to-image model from Google optimized for fast image generation.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/image-models/google/gemini-3.1-flash-image","isHottest":true,"docsJson":"https://api.aimlapi.com/docs-json?model=google%2Fgemini-3.1-flash-image-preview&endpoint=openai%2Fimage-generations"},"type":"openai/image-generations","aliases":["gemini-3.1-flash-image-preview"],"tags":["playground:image","tier:tier_2"]},{"id":"google/gemini-3.1-flash-lite-image","info":{"name":"Nano Banana 2 Lite","developer":"Google","description":"Nano Banana 2 Lite is a cost-efficient text-to-image model from Google, a lighter and cheaper variant of Nano Banana 2 for high-volume image generation.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/image-models/google/gemini-3.1-flash-lite-image","isHottest":true,"docsJson":"https://api.aimlapi.com/docs-json?model=google%2Fgemini-3.1-flash-lite-image&endpoint=openai%2Fimage-generations"},"type":"openai/image-generations","aliases":["gemini-3.1-flash-lite-image"],"tags":["playground:image","tier:tier_2"]},{"id":"google/veo-2.0-generate-001","info":{"releasedAt":"2025-11-25","name":"Veo 2 Text-to-Video","description":"Veo2: Google's advanced text-to-video model","developer":"Google","url":"https://aimlapi.com/models/veo-2-text-to-video-api","docsUrl":"https://docs.aimlapi.com/api-references/video-models/google/veo2-text-to-video","docsJson":"https://api.aimlapi.com/docs-json?model=google%2Fveo-2.0-generate-001&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":["veo-2.0-generate-001"],"tags":["playground:video","tier:tier_2"]},{"id":"google/veo-3.0-fast-generate-001","info":{"releasedAt":"2025-11-25","name":"Veo 3 Text to Video Fast","description":"Veo3 Fast generates videos from text prompts at faster speeds, optimized for high-throughput creative workflows.","developer":"Google","url":"","docsUrl":"https://docs.aimlapi.com/api-references/video-models/google/veo-3-fast-text-to-video","docsJson":"https://api.aimlapi.com/docs-json?model=google%2Fveo-3.0-fast-generate-001&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":["veo-3.0-fast-generate-001"],"tags":["playground:video","tier:tier_2"]},{"id":"google/veo-3.0-generate-001","info":{"releasedAt":"2025-11-25","name":"Veo 3 Text to Video","description":"Veo3 is Google's advanced video generation model that creates high-quality videos with synchronized audio from text.","developer":"Google","url":"","docsUrl":"https://docs.aimlapi.com/api-references/video-models/google/veo3-text-to-video","docsJson":"https://api.aimlapi.com/docs-json?model=google%2Fveo-3.0-generate-001&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":["veo-3.0-generate-001"],"tags":["playground:video","tier:tier_2"]},{"id":"google/veo-3.1-lite-generate-001","info":{"releasedAt":"2026-04-06","name":"Veo 3.1 Lite Generate Preview","description":"","developer":"Google","url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=google%2Fveo-3.1-lite-generate-001&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":["veo-3.1-lite-generate-001"],"tags":["playground:video","tier:tier_2"]},{"id":"google/veo-3.1-generate-001","info":{"releasedAt":"2026-05-27","name":"Veo 3.1","description":"","developer":"Google","url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=google%2Fveo-3.1-generate-001&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":["veo-3.1-generate-001"],"tags":["playground:video","tier:tier_2"]},{"id":"google/veo-3.1-fast-generate-001","info":{"releasedAt":"2026-05-27","name":"Veo 3.1 Fast","description":"","developer":"Google","url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=google%2Fveo-3.1-fast-generate-001&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":["veo-3.1-fast-generate-001"],"tags":["playground:video","tier:tier_2"]},{"id":"google/gemini-omni-flash-preview","info":{"name":"Gemini Omni Flash Preview","description":"Gemini Omni Flash Preview is Google's multimodal video generation and editing model for text-to-video, image-to-video, reference-to-video, and edit workflows.","developer":"Google","url":"","docsUrl":"https://docs.aimlapi.com/api-references/video-models/google/gemini-omni-flash-preview","isHottest":true,"docsJson":"https://api.aimlapi.com/docs-json?model=google%2Fgemini-omni-flash-preview&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":["gemini-omni-flash-preview"],"tags":["playground:video","tier:tier_2"]},{"id":"google/gc-document-ai","info":{"releasedAt":"2025-12-16","name":"GC Document AI","developer":"Google","description":"Google Cloud Document AI extracts structured data and text from documents using optical character recognition and AI.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/vision-models/ocr-optical-character-recognition/google/google-ocr","docsJson":"https://api.aimlapi.com/docs-json?model=google%2Fgc-document-ai&endpoint=internal%2Foptical-character-recognition"},"type":"internal/optical-character-recognition","aliases":["gc-document-ai"],"tags":["playground:ocr","tier:tier_2"]},{"id":"google/gemma-3n-e4b-it","info":{"releasedAt":"2025-09-09","name":"Gemma 3n 4B","developer":"Google","description":"Gemma 3n 4B is an ultra-efficient next-generation Gemma model optimized for on-device multimodal applications.","contextLength":8192,"outputMax":2048,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/google/gemma-3n-4b","docsJson":"https://api.aimlapi.com/docs-json?model=google%2Fgemma-3n-e4b-it&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["gemma-3n-e4b-it"],"tags":["playground:chat","tier:tier_1"]},{"id":"google/gemma-3-4b-it","info":{"releasedAt":"2025-09-09","name":"Gemma 3 4B","developer":"Google","description":"Gemma 3 4B is a lightweight open language model from Google, suitable for on-device deployment and efficient inference.","contextLength":131000,"outputMax":32768,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/google/gemma-3","docsJson":"https://api.aimlapi.com/docs-json?model=google%2Fgemma-3-4b-it&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["gemma-3-4b-it"],"tags":["playground:chat","tier:tier_1"]},{"id":"google/gemma-3-12b-it","info":{"releasedAt":"2025-09-09","name":"Gemma 3 12B","developer":"Google","description":"Gemma 3 12B is a mid-size open language model from Google offering a balance of capability and efficiency.","contextLength":131000,"outputMax":96000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/google/gemma-3","docsJson":"https://api.aimlapi.com/docs-json?model=google%2Fgemma-3-12b-it&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["gemma-3-12b-it"],"tags":["playground:chat","tier:tier_1"]},{"id":"google/gemma-3-27b-it","info":{"releasedAt":"2025-09-09","name":"Gemma 3 27B","developer":"Google","description":"Gemma 3 27B is Google's largest Gemma open model, delivering strong reasoning and text generation capabilities.","contextLength":128000,"outputMax":131072,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/google/gemma-3","docsJson":"https://api.aimlapi.com/docs-json?model=google%2Fgemma-3-27b-it&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["gemma-3-27b-it"],"tags":["playground:chat","tier:tier_2"]},{"id":"google/gemma-4-31b-it","info":{"releasedAt":"2026-04-03","name":"Gemma 4 31B Instruct","developer":"Google","description":"","contextLength":256000,"outputMax":262144,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=google%2Fgemma-4-31b-it&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["gemma-4-31b-it"],"tags":["playground:chat","tier:tier_2"]},{"id":"google/gemma-4-26b-a4b-it","info":{"releasedAt":"2026-06-23","name":"Gemma 4 26B A4B IT","developer":"Google","description":"Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts open model from Google.","contextLength":262144,"outputMax":128000,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=google%2Fgemma-4-26b-a4b-it&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["gemma-4-26b-a4b-it"],"tags":["playground:chat","tier:tier_2"]},{"id":"google/gemini-3.1-flash-lite-image","info":{"releasedAt":"2026-06-30","name":"Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image)","developer":"Google","contextLength":65536,"outputMax":66000,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=google%2Fgemini-3.1-flash-lite-image&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["gemini-3.1-flash-lite-image"],"tags":["playground:chat","tier:tier_2"]},{"id":"google/gemini-3.1-flash-image","info":{"releasedAt":"2026-06-18","name":"Nano Banana 2 (Gemini 3.1 Flash Image)","developer":"Google","contextLength":131072,"outputMax":32768,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=google%2Fgemini-3.1-flash-image&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["gemini-3.1-flash-image"],"tags":["playground:chat","tier:tier_2"]},{"id":"google/gemini-3-pro-image","info":{"releasedAt":"2026-06-18","name":"Nano Banana Pro (Gemini 3 Pro Image)","developer":"Google","contextLength":65536,"outputMax":32768,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=google%2Fgemini-3-pro-image&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["gemini-3-pro-image"],"tags":["playground:chat","tier:tier_2"]},{"id":"google/gemini-3.1-flash-lite-preview","info":{"releasedAt":"2026-04-06","name":"Gemini 3.1 Flash Lite Preview","developer":"Google","description":"","contextLength":1000000,"outputMax":65536,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=google%2Fgemini-3.1-flash-lite-preview&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["gemini-3.1-flash-lite-preview"],"tags":["playground:chat","tier:tier_2"]},{"id":"google/gemini-3.1-flash-image-preview","info":{"releasedAt":"2026-02-26","name":"Nano Banana 2 (Gemini 3.1 Flash Image Preview)","developer":"Google","contextLength":131072,"outputMax":32768,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=google%2Fgemini-3.1-flash-image-preview&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["gemini-3.1-flash-image-preview"],"tags":["playground:chat","tier:tier_2"]},{"id":"google/gemini-3.1-pro-preview-customtools","info":{"releasedAt":"2026-02-25","name":"Gemini 3.1 Pro Preview Custom Tools","developer":"Google","contextLength":1048756,"outputMax":65536,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=google%2Fgemini-3.1-pro-preview-customtools&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["gemini-3.1-pro-preview-customtools"],"tags":["playground:chat","tier:tier_2"]},{"id":"google/gemini-3-pro-image-preview","info":{"releasedAt":"2025-11-20","name":"Nano Banana Pro (Gemini 3 Pro Image Preview)","developer":"Google","contextLength":65536,"outputMax":32768,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=google%2Fgemini-3-pro-image-preview&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["gemini-3-pro-image-preview","google/nano-banana-pro"],"tags":["playground:chat","tier:tier_2"]},{"id":"google/gemini-2.5-flash-image","info":{"releasedAt":"2025-10-07","name":"Nano Banana (Gemini 2.5 Flash Image)","developer":"Google","contextLength":32768,"outputMax":32768,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=google%2Fgemini-2.5-flash-image&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["gemini-2.5-flash-image","google/nano-banana"],"tags":["playground:chat","tier:tier_2"]},{"id":"google/gemini-2.5-pro-preview","info":{"releasedAt":"2025-06-05","name":"Gemini 2.5 Pro Preview 06-05","developer":"Google","contextLength":1048576,"outputMax":65536,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=google%2Fgemini-2.5-pro-preview&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["gemini-2.5-pro-preview"],"tags":["playground:chat","tier:tier_2"]},{"id":"google/gemini-2.5-pro-preview-05-06","info":{"releasedAt":"2025-05-07","name":"Gemini 2.5 Pro Preview 05-06","developer":"Google","contextLength":1048576,"outputMax":65535,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=google%2Fgemini-2.5-pro-preview-05-06&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["gemini-2.5-pro-preview-05-06"],"tags":["playground:chat","tier:tier_2"]},{"id":"google/gemma-2-27b-it","info":{"releasedAt":"2024-07-13","name":"Gemma 2 27B","developer":"Google","contextLength":8192,"outputMax":2048,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=google%2Fgemma-2-27b-it&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["gemma-2-27b-it"],"tags":["playground:chat","tier:tier_2"]},{"id":"google/gemini-2.5-flash-lite-preview","info":{"releasedAt":"2025-09-09","name":"Gemini 2.5 Flash Lite Preview","developer":"Google","description":"Gemini 2.5 Flash Lite Preview is a lightweight AI model developed by Google, optimized for quick responses and efficient processing, making it ideal for tasks requiring minimal latency and resource consumption","contextLength":1000000,"outputMax":1048576,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/google/gemini-2.5-flash-lite-preview","docsJson":"https://api.aimlapi.com/docs-json?model=google%2Fgemini-2.5-flash-lite-preview&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["gemini-2.5-flash-lite-preview"],"tags":["playground:chat","tier:tier_2"]},{"id":"google/gemini-3-1-flash-lite-preview","info":{"releasedAt":"2026-04-06","name":"Gemini 3.1 Flash Lite Preview","developer":"Google","description":"","contextLength":1000000,"outputMax":65536,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=google%2Fgemini-3-1-flash-lite-preview&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":[],"tags":["playground:chat","tier:tier_2"]},{"id":"google/gemini-3-5-flash","info":{"releasedAt":"2026-05-19","name":"Gemini 3.5 Flash","developer":"Google","description":"Gemini 3.5 Flash is a multimodal reasoning model from Google optimized for fast inference and agentic workflows. Supports text, image, audio and video understanding with large context window and strong coding capabilities.","contextLength":1048576,"outputMax":65536,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/google/gemini-3-5-flash","isHottest":true,"docsJson":"https://api.aimlapi.com/docs-json?model=google%2Fgemini-3-5-flash&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["gemini-3-5-flash"],"tags":["playground:chat","tier:tier_2"]},{"id":"google/gemini-3-1-flash-lite","info":{"releasedAt":"2026-05-08","name":"Gemini 3.1 Flash Lite","developer":"Google","description":"Gemini 3.1 Flash Lite is a cost-efficient multimodal model designed for high-volume tasks such as translation, lightweight reasoning, and simple agent workflows.","contextLength":1000000,"outputMax":65536,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=google%2Fgemini-3-1-flash-lite&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":[],"tags":["playground:chat","tier:tier_2"]},{"id":"google/gemini-pro-latest","info":{"releasedAt":"2026-04-27","name":"Gemini Pro Latest","developer":"Google","contextLength":1048576,"outputMax":65536,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=google%2Fgemini-pro-latest&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["gemini-pro-latest"],"tags":["playground:chat","tier:tier_2"]},{"id":"google/gemini-flash-latest","info":{"releasedAt":"2026-04-27","name":"Gemini Flash Latest","developer":"Google","contextLength":1048576,"outputMax":65536,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=google%2Fgemini-flash-latest&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["gemini-flash-latest"],"tags":["playground:chat","tier:tier_2"]},{"id":"google/imagen4/preview","info":{"releasedAt":"2025-10-13","name":"Imagen 4.0 Generate","developer":"Google","description":"Imagen 4.0 Generate: Google's high-quality text-to-image model with enhanced realism and understanding.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/image-models/google/imagen-4-generate","docsJson":"https://api.aimlapi.com/docs-json?model=google%2Fimagen4%2Fpreview&endpoint=openai%2Fimage-generations"},"type":"openai/image-generations","aliases":[],"tags":["playground:image","tier:tier_2"]},{"id":"google/gemini-3-1-flash-image-preview","info":{"releasedAt":"2026-02-27","name":"Nano Banana 2","developer":"Google","description":"Nano Banana 2 is a compact text-to-image model from Google optimized for fast image generation.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/image-models/google/gemini-3.1-flash-image","isHottest":true,"docsJson":"https://api.aimlapi.com/docs-json?model=google%2Fgemini-3-1-flash-image-preview&endpoint=openai%2Fimage-generations"},"type":"openai/image-generations","aliases":["google/nano-banana-2"],"tags":["playground:image","tier:tier_2"]},{"id":"google/gemini-3-1-flash-lite-image","info":{"name":"Nano Banana 2 Lite","developer":"Google","description":"Nano Banana 2 Lite is a cost-efficient text-to-image model from Google, a lighter and cheaper variant of Nano Banana 2 for high-volume image generation.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/image-models/google/gemini-3.1-flash-lite-image","isHottest":true,"docsJson":"https://api.aimlapi.com/docs-json?model=google%2Fgemini-3-1-flash-lite-image&endpoint=openai%2Fimage-generations"},"type":"openai/image-generations","aliases":["google/nano-banana-2-lite","google/nano-banana-lite"],"tags":["playground:image","tier:tier_2"]},{"id":"google/veo-3.1-t2v","info":{"releasedAt":"2026-05-27","name":"Veo 3.1","description":"","developer":"Google","url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=google%2Fveo-3.1-t2v&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":[],"tags":["playground:video","tier:tier_2"]},{"id":"google/veo-3.1-i2v","info":{"releasedAt":"2026-05-27","name":"Veo 3.1","description":"","developer":"Google","url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=google%2Fveo-3.1-i2v&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":[],"tags":["playground:video","tier:tier_2"]},{"id":"google/veo-3.1-t2v-fast","info":{"releasedAt":"2026-05-27","name":"Veo 3.1 Fast","description":"","developer":"Google","url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=google%2Fveo-3.1-t2v-fast&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":[],"tags":["playground:video","tier:tier_2"]},{"id":"google/veo-3.1-i2v-fast","info":{"releasedAt":"2026-05-27","name":"Veo 3.1 Fast","description":"","developer":"Google","url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=google%2Fveo-3.1-i2v-fast&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":[],"tags":["playground:video","tier:tier_2"]},{"id":"google/veo-3.1-first-last-image-to-video","info":{"releasedAt":"2026-05-27","name":"Veo 3.1","description":"","developer":"Google","url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=google%2Fveo-3.1-first-last-image-to-video&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":[],"tags":["playground:video","tier:tier_2"]},{"id":"google/veo-3.1-reference-to-video","info":{"releasedAt":"2025-11-24","name":"Veo 3.1 Reference to Video","description":"Veo 3.1 creates videos guided by reference images for consistent character and scene appearance.","developer":"Google","url":"","docsUrl":"https://docs.aimlapi.com/api-references/video-models/google/veo-3-1-reference-to-video","docsJson":"https://api.aimlapi.com/docs-json?model=google%2Fveo-3.1-reference-to-video&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":[],"tags":["playground:video","tier:tier_2"]},{"id":"google/veo-3.1-first-last-image-to-video-fast","info":{"releasedAt":"2026-05-27","name":"Veo 3.1 Fast","description":"","developer":"Google","url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=google%2Fveo-3.1-first-last-image-to-video-fast&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":[],"tags":["playground:video","tier:tier_2"]},{"id":"google/veo3-1-extend-video","info":{"releasedAt":"2026-05-27","name":"Veo 3.1","description":"","developer":"Google","url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=google%2Fveo3-1-extend-video&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":[],"tags":["playground:video","tier:tier_2"]},{"id":"google/veo3-1-fast-extend-video","info":{"releasedAt":"2026-05-27","name":"Veo 3.1 Fast","description":"","developer":"Google","url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=google%2Fveo3-1-fast-extend-video&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":[],"tags":["playground:video","tier:tier_2"]},{"id":"google/veo2","info":{"releasedAt":"2025-11-25","name":"Veo 2 Text-to-Video","description":"Veo2: Google's advanced text-to-video model","developer":"Google","url":"https://aimlapi.com/models/veo-2-text-to-video-api","docsUrl":"https://docs.aimlapi.com/api-references/video-models/google/veo2-text-to-video","docsJson":"https://api.aimlapi.com/docs-json?model=google%2Fveo2&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":["veo2"],"tags":["playground:video","tier:tier_2"]},{"id":"google/veo2-image-to-video","info":{"releasedAt":"2025-11-25","name":"Veo 2 Image to Video","description":"Veo2 Image-to-Video: Google's AI transforming still images into dynamic videos","developer":"Google","url":"https://aimlapi.com/models/veo-2-image-to-video-api","docsUrl":"https://docs.aimlapi.com/api-references/video-models/google/veo2-image-to-video","docsJson":"https://api.aimlapi.com/docs-json?model=google%2Fveo2-image-to-video&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":["veo2/image-to-video"],"tags":["playground:video","tier:tier_2"]},{"id":"google/veo3","info":{"releasedAt":"2025-11-25","name":"Veo 3 Text to Video","description":"Veo3 is Google's advanced video generation model that creates high-quality videos with synchronized audio from text.","developer":"Google","url":"","docsUrl":"https://docs.aimlapi.com/api-references/video-models/google/veo3-text-to-video","docsJson":"https://api.aimlapi.com/docs-json?model=google%2Fveo3&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":[],"tags":["playground:video","tier:tier_2"]},{"id":"google/veo-3.0-i2v","info":{"releasedAt":"2025-11-25","name":"Veo 3 Image to Video","description":"Veo3 image-to-video animates still images into high-quality videos with synchronized audio generation.","developer":"Google","url":"","docsUrl":"https://docs.aimlapi.com/api-references/video-models/google/veo-3-image-to-video","docsJson":"https://api.aimlapi.com/docs-json?model=google%2Fveo-3.0-i2v&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":[],"tags":["playground:video","tier:tier_2"]},{"id":"google/veo-3.0-fast","info":{"releasedAt":"2025-11-25","name":"Veo 3 Text to Video Fast","description":"Veo3 Fast generates videos from text prompts at faster speeds, optimized for high-throughput creative workflows.","developer":"Google","url":"","docsUrl":"https://docs.aimlapi.com/api-references/video-models/google/veo-3-fast-text-to-video","docsJson":"https://api.aimlapi.com/docs-json?model=google%2Fveo-3.0-fast&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":[],"tags":["playground:video","tier:tier_2"]},{"id":"google/veo-3.0-i2v-fast","info":{"releasedAt":"2025-11-25","name":"Veo 3 Image to Video Fast","description":"Veo3 Fast animates images into videos at faster speeds, optimized for rapid iteration and cost-efficiency.","developer":"Google","url":"","docsUrl":"https://docs.aimlapi.com/api-references/video-models/google/veo-3-fast-image-to-video","docsJson":"https://api.aimlapi.com/docs-json?model=google%2Fveo-3.0-i2v-fast&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":[],"tags":["playground:video","tier:tier_2"]},{"id":"google/veo-3-1-lite-generate-preview","info":{"releasedAt":"2026-04-06","name":"Veo 3.1 Lite Generate Preview","description":"","developer":"Google","url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=google%2Fveo-3-1-lite-generate-preview&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":[],"tags":["playground:video","tier:tier_2"]},{"id":"meta/muse-spark-1.1","info":{"releasedAt":"2026-07-09","name":"Muse Spark 1.1","developer":"Meta","contextLength":1048576,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=meta%2Fmuse-spark-1.1&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["muse-spark-1.1"],"tags":["playground:chat","tier:tier_2"]},{"id":"meta-llama/Llama-3.3-70B-Instruct-Turbo","info":{"releasedAt":"2025-09-30","name":"Llama 3.3 70B Instruct Turbo","developer":"Meta","description":"Meta Llama 3.3 70B Instruct Turbo is an advanced language model optimized for instruction-following tasks with high efficiency and performance.","contextLength":128000,"outputMax":127000,"url":"https://aimlapi.com/models/meta-llama-3-3-70b-instruct-turbo-api","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/meta/llama-3.3-70b-instruct-turbo","docsJson":"https://api.aimlapi.com/docs-json?model=meta-llama%2FLlama-3.3-70B-Instruct-Turbo&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":[],"tags":["playground:chat","tier:tier_2"]},{"id":"meta-llama/llama-3.3-70b-versatile","info":{"releasedAt":"2025-09-30","name":"Llama 3.3 70B Versatile","developer":"Meta","description":"Llama-3.3-70B-Versatile is Meta's advanced multilingual large language model, optimized for a wide range of natural language processing tasks. With 70 billion parameters, it offers high performance across various benchmarks while maintaining efficiency suitable for diverse applications.","contextLength":131072,"outputMax":32768,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/meta/llama-3.3-70b-versatile","docsJson":"https://api.aimlapi.com/docs-json?model=meta-llama%2Fllama-3.3-70b-versatile&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["llama-3.3-70b-versatile"],"tags":["playground:chat","tier:tier_2"]},{"id":"mistralai/mistral-nemo","info":{"releasedAt":"2025-09-09","name":"Mistral NeMo","developer":"Mistral AI","description":"Mistral-Nemo is a powerful multilingual language model with advanced capabilities.","contextLength":128000,"outputMax":131072,"url":"https://aimlapi.com/models/mistral-nemo-api","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/mistral-ai/mistral-nemo","docsJson":"https://api.aimlapi.com/docs-json?model=mistralai%2Fmistral-nemo&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["mistral-nemo"],"tags":["playground:chat","tier:tier_2"]},{"id":"mistralai/mistral-medium-3-5","info":{"releasedAt":"2026-04-30","name":"Medium 3.5","developer":"Mistral AI","contextLength":262144,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=mistralai%2Fmistral-medium-3-5&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["mistral-medium-3-5"],"tags":["playground:chat","tier:tier_2"]},{"id":"mistralai/mistral-small-2603","info":{"releasedAt":"2026-03-16","name":"Small 4","developer":"Mistral AI","contextLength":262144,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=mistralai%2Fmistral-small-2603&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["mistral-small-2603"],"tags":["playground:chat","tier:tier_2"]},{"id":"mistralai/devstral-2512","info":{"releasedAt":"2025-12-09","name":"Devstral 2 2512","developer":"Mistral AI","contextLength":262144,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=mistralai%2Fdevstral-2512&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["devstral-2512"],"tags":["playground:chat","tier:tier_2"]},{"id":"mistralai/ministral-14b-2512","info":{"releasedAt":"2025-12-02","name":"Ministral 3 14B 2512","developer":"Mistral AI","contextLength":262144,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=mistralai%2Fministral-14b-2512&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["ministral-14b-2512"],"tags":["playground:chat","tier:tier_2"]},{"id":"mistralai/ministral-8b-2512","info":{"releasedAt":"2025-12-02","name":"Ministral 3 8B 2512","developer":"Mistral AI","contextLength":262144,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=mistralai%2Fministral-8b-2512&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["ministral-8b-2512"],"tags":["playground:chat","tier:tier_2"]},{"id":"mistralai/ministral-3b-2512","info":{"releasedAt":"2025-12-02","name":"Ministral 3 3B 2512","developer":"Mistral AI","contextLength":131072,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=mistralai%2Fministral-3b-2512&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["ministral-3b-2512"],"tags":["playground:chat","tier:tier_2"]},{"id":"mistralai/mistral-large-2512","info":{"releasedAt":"2025-12-01","name":"Large 3 2512","developer":"Mistral AI","contextLength":262144,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=mistralai%2Fmistral-large-2512&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["mistral-large-2512"],"tags":["playground:chat","tier:tier_2"]},{"id":"mistralai/voxtral-small-24b-2507","info":{"releasedAt":"2025-10-30","name":"Voxtral Small 24B 2507","developer":"Mistral AI","contextLength":32000,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=mistralai%2Fvoxtral-small-24b-2507&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["voxtral-small-24b-2507"],"tags":["playground:chat","tier:tier_2"]},{"id":"mistralai/mistral-medium-3.1","info":{"releasedAt":"2025-08-13","name":"Medium 3.1","developer":"Mistral AI","contextLength":131072,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=mistralai%2Fmistral-medium-3.1&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["mistral-medium-3.1"],"tags":["playground:chat","tier:tier_2"]},{"id":"mistralai/codestral-2508","info":{"releasedAt":"2025-08-01","name":"Codestral 2508","developer":"Mistral AI","contextLength":256000,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=mistralai%2Fcodestral-2508&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["codestral-2508"],"tags":["playground:chat","tier:tier_2"]},{"id":"mistralai/mistral-small-3.2-24b-instruct","info":{"releasedAt":"2025-06-20","name":"Small 3.2 24B","developer":"Mistral AI","contextLength":128000,"outputMax":16384,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=mistralai%2Fmistral-small-3.2-24b-instruct&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["mistral-small-3.2-24b-instruct"],"tags":["playground:chat","tier:tier_2"]},{"id":"mistralai/mistral-medium-3","info":{"releasedAt":"2025-05-07","name":"Medium 3","developer":"Mistral AI","contextLength":131072,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=mistralai%2Fmistral-medium-3&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["mistral-medium-3"],"tags":["playground:chat","tier:tier_2"]},{"id":"mistralai/mistral-small-3.1-24b-instruct","info":{"releasedAt":"2025-03-17","name":"Small 3.1 24B","developer":"Mistral AI","contextLength":128000,"outputMax":128000,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=mistralai%2Fmistral-small-3.1-24b-instruct&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["mistral-small-3.1-24b-instruct"],"tags":["playground:chat","tier:tier_2"]},{"id":"mistralai/mistral-saba","info":{"releasedAt":"2025-02-17","name":"Saba","developer":"Mistral AI","contextLength":32768,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=mistralai%2Fmistral-saba&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["mistral-saba"],"tags":["playground:chat","tier:tier_2"]},{"id":"mistralai/mistral-small-24b-instruct-2501","info":{"releasedAt":"2025-01-30","name":"Small 3","developer":"Mistral AI","contextLength":32768,"outputMax":16384,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=mistralai%2Fmistral-small-24b-instruct-2501&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["mistral-small-24b-instruct-2501"],"tags":["playground:chat","tier:tier_2"]},{"id":"mistralai/mistral-large-2407","info":{"releasedAt":"2024-11-19","name":"Large 2407","developer":"Mistral AI","contextLength":131072,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=mistralai%2Fmistral-large-2407&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["mistral-large-2407"],"tags":["playground:chat","tier:tier_2"]},{"id":"mistralai/mixtral-8x22b-instruct","info":{"releasedAt":"2024-04-17","name":"Mixtral 8x22B Instruct","developer":"Mistral AI","contextLength":65536,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=mistralai%2Fmixtral-8x22b-instruct&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["mixtral-8x22b-instruct"],"tags":["playground:chat","tier:tier_2"]},{"id":"mistralai/mistral-large","info":{"releasedAt":"2024-02-26","name":"Large","developer":"Mistral AI","contextLength":128000,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=mistralai%2Fmistral-large&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["mistral-large"],"tags":["playground:chat","tier:tier_2"]},{"id":"alibaba/glm-5.2","info":{"releasedAt":"2026-06-16","name":"GLM 5.2","developer":"Zhipu AI","description":"GLM-5.2 is Zhipu AI flagship MoE LLM with a 1M-token context window, optimized for agentic coding, tool use, reasoning, and long-context tasks.","contextLength":1000000,"outputMax":131072,"url":"","docsUrl":"","isHottest":true,"docsJson":"https://api.aimlapi.com/docs-json?model=alibaba%2Fglm-5.2&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["glm-5.2"],"tags":["playground:chat","tier:tier_2"]},{"id":"alibaba/glm-5.2-fast-preview","info":{"releasedAt":"2026-07-10","name":"GLM 5.2 Fast Preview","developer":"Zhipu AI","description":"A latency-optimized GLM-5.2 preview with the same 1M-token context window and 1.5–2× higher output throughput for real-time chat, agents, and coding.","contextLength":1000000,"outputMax":131072,"url":"","docsUrl":"https://help.aliyun.com/en/model-studio/fast-mode","docsJson":"https://api.aimlapi.com/docs-json?model=alibaba%2Fglm-5.2-fast-preview&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["glm-5.2-fast-preview"],"tags":["playground:chat","tier:tier_2"]},{"id":"alibaba/qwen-max","info":{"releasedAt":"2025-09-09","name":"Qwen Max","developer":"Alibaba Cloud","description":"Qwen Max: powerful AI, excels in stability, competes globally.","contextLength":32000,"outputMax":8192,"url":"https://aimlapi.com/models/qwen-max-api","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/alibaba-cloud/qwen-max","docsJson":"https://api.aimlapi.com/docs-json?model=alibaba%2Fqwen-max&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["qwen-max"],"tags":["playground:chat","tier:tier_2"]},{"id":"alibaba/qwen-plus","info":{"releasedAt":"2025-09-09","name":"Qwen Plus","developer":"Alibaba Cloud","description":"Qwen-Plus: Alibaba's advanced multilingual model with enhanced reasoning and instruction-following capabilities.","contextLength":131000,"outputMax":16384,"url":"https://aimlapi.com/models/qwen-plus-api","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/alibaba-cloud/qwen-plus","docsJson":"https://api.aimlapi.com/docs-json?model=alibaba%2Fqwen-plus&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["qwen-plus"],"tags":["playground:chat","tier:tier_2"]},{"id":"alibaba/qwen-turbo","info":{"releasedAt":"2025-09-09","name":"Qwen Turbo","developer":"Alibaba Cloud","description":"Qwen Turbo: optimizes AI agent speed, integrates with RAG, large context window.","contextLength":1000000,"outputMax":16384,"url":"https://aimlapi.com/models/qwen-turbo-api","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/alibaba-cloud/qwen-turbo","docsJson":"https://api.aimlapi.com/docs-json?model=alibaba%2Fqwen-turbo&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["qwen-turbo"],"tags":["playground:chat","tier:tier_2"]},{"id":"alibaba/qwen3-32b","info":{"releasedAt":"2025-09-09","name":"Qwen3 32B","developer":"Alibaba Cloud","description":"Alibaba's Qwen 3 32B is a multilingual model with instruction-following capabilities and enhanced reasoning.","contextLength":131000,"outputMax":16384,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/alibaba-cloud/qwen3-32b","docsJson":"https://api.aimlapi.com/docs-json?model=alibaba%2Fqwen3-32b&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["qwen3-32b"],"tags":["playground:chat","tier:tier_2"]},{"id":"alibaba/qwen3-235b-a22b-thinking-2507","info":{"releasedAt":"2025-09-09","name":"Qwen3 Thinking 2507","developer":"Alibaba Cloud","description":"Alibaba's Qwen 3 thinking 2507 is a multilingual reasoning model with knowledge augmentation, and creative capabilities.","contextLength":32000,"outputMax":16000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/alibaba-cloud/qwen3-235b-a22b-thinking-2507","docsJson":"https://api.aimlapi.com/docs-json?model=alibaba%2Fqwen3-235b-a22b-thinking-2507&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["qwen3-235b-a22b-thinking-2507"],"tags":["playground:chat","tier:tier_2","playground:code"]},{"id":"alibaba/qwen3.5-flash","info":{"releasedAt":"2026-04-21","name":"Qwen3.5 Flash","developer":"Alibaba Cloud","description":"Qwen Max: powerful AI, excels in stability, competes globally.","contextLength":1000000,"outputMax":65536,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=alibaba%2Fqwen3.5-flash&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["qwen3.5-flash"],"tags":["playground:chat","tier:tier_2"]},{"id":"alibaba/qwen3.5-plus","info":{"releasedAt":"2026-02-20","name":"Qwen3.5 Plus","developer":"Alibaba Cloud","description":"Qwen3.5-Plus is a commercial large language model by Alibaba Cloud designed for long-context text generation and enterprise-grade conversational AI. Supports up to 1M tokens per request with production-ready API stability.","contextLength":1000000,"outputMax":65536,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/alibaba-cloud/qwen3.5-plus","docsJson":"https://api.aimlapi.com/docs-json?model=alibaba%2Fqwen3.5-plus&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["qwen3.5-plus"],"tags":["playground:chat","tier:tier_2"]},{"id":"alibaba/qwen3-coder-480b-a35b-instruct","info":{"releasedAt":"2025-09-09","name":"Qwen3 Coder","developer":"Alibaba Cloud","description":"Alibaba's Qwen 3 Coder is a powerful coding agent.","contextLength":262000,"outputMax":65536,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/alibaba-cloud/qwen3-coder-480b-a35b-instruct","docsJson":"https://api.aimlapi.com/docs-json?model=alibaba%2Fqwen3-coder-480b-a35b-instruct&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["qwen3-coder-480b-a35b-instruct"],"tags":["playground:chat","tier:tier_2","playground:code"]},{"id":"alibaba/qwen3-next-80b-a3b-thinking","info":{"releasedAt":"2025-09-30","name":"Qwen3 Next 80B A3B Thinking","developer":"Alibaba Cloud","description":"Alibaba's Qwen 3 Next 80B A3B Thinking is a multilingual reasoning model with advanced chain-of-thought capabilities.","contextLength":126976,"outputMax":81920,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/alibaba-cloud/qwen3-next-80b-a3b-thinking","docsJson":"https://api.aimlapi.com/docs-json?model=alibaba%2Fqwen3-next-80b-a3b-thinking&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["qwen3-next-80b-a3b-thinking"],"tags":["playground:chat","tier:tier_2","playground:code"]},{"id":"alibaba/qwen3-next-80b-a3b-instruct","info":{"releasedAt":"2025-09-30","name":"Qwen3 Next 80B A3B Instruct","developer":"Alibaba Cloud","description":"Alibaba's Qwen 3 Next 80B A3B Instruct is a multilingual model with enhanced instruction-following capabilities.","contextLength":129024,"outputMax":16384,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/alibaba-cloud/qwen3-next-80b-a3b-instruct","docsJson":"https://api.aimlapi.com/docs-json?model=alibaba%2Fqwen3-next-80b-a3b-instruct&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["qwen3-next-80b-a3b-instruct"],"tags":["playground:chat","tier:tier_2","playground:code"]},{"id":"alibaba/qwen3-max-preview","info":{"releasedAt":"2025-09-30","name":"Qwen3 Max Preview","developer":"Alibaba Cloud","description":"Alibaba's Qwen 3 Max Preview is a multilingual model with instruction-following capabilities and enhanced reasoning.","contextLength":252000,"outputMax":32768,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/alibaba-cloud/qwen3-max-preview","docsJson":"https://api.aimlapi.com/docs-json?model=alibaba%2Fqwen3-max-preview&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["qwen3-max-preview"],"tags":["playground:chat","tier:tier_2"]},{"id":"alibaba/qwen3-max","info":{"releasedAt":"2025-09-30","name":"Qwen3 Max Instruct","developer":"Alibaba Cloud","description":"Alibaba's Qwen 3 Max Instruct is the most powerful model in the Qwen 3 series.","contextLength":262144,"outputMax":65536,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/alibaba-cloud/qwen3-max-instruct","docsJson":"https://api.aimlapi.com/docs-json?model=alibaba%2Fqwen3-max&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["qwen3-max"],"tags":["playground:chat","tier:tier_2"]},{"id":"alibaba/qwen3-vl-plus","info":{"releasedAt":"2025-10-19","name":"Qwen3 VL Plus","developer":"Alibaba Cloud","description":"Alibaba's Qwen 3 VL Plus is a powerful vision-language model with hybrid thinking capabilities. Supports image understanding with up to 16,384 tokens per image and high-resolution mode for detailed analysis.","contextLength":262144,"outputMax":32768,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/alibaba-cloud","docsJson":"https://api.aimlapi.com/docs-json?model=alibaba%2Fqwen3-vl-plus&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["qwen3-vl-plus"],"tags":["playground:chat","tier:tier_2"]},{"id":"alibaba/qwen3-vl-flash","info":{"releasedAt":"2025-10-19","name":"Qwen3 VL Flash","developer":"Alibaba Cloud","description":"Alibaba's Qwen 3 VL Flash is a fast and cost-effective vision-language model with hybrid thinking capabilities. Supports image understanding with up to 16,384 tokens per image and high-resolution mode for detailed analysis.","contextLength":262144,"outputMax":32768,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/alibaba-cloud","docsJson":"https://api.aimlapi.com/docs-json?model=alibaba%2Fqwen3-vl-flash&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["qwen3-vl-flash"],"tags":["playground:chat","tier:tier_2"]},{"id":"alibaba/qwen3-vl-32b-thinking","info":{"releasedAt":"2025-11-11","name":"Qwen3 VL 32B Thinking","developer":"Alibaba Cloud","description":"Alibaba's Qwen 3 VL 32B Thinking is a powerful vision-language model with hybrid thinking capabilities.","contextLength":126000,"outputMax":32768,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/alibaba-cloud/qwen3-vl-32b-thinking","docsJson":"https://api.aimlapi.com/docs-json?model=alibaba%2Fqwen3-vl-32b-thinking&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["qwen3-vl-32b-thinking"],"tags":["playground:chat","tier:tier_2"]},{"id":"alibaba/qwen3-vl-32b-instruct","info":{"releasedAt":"2025-11-11","name":"Qwen3 VL 32B Instruct","developer":"Alibaba Cloud","description":"Alibaba's Qwen 3 VL 32B Instruct is a powerful vision-language model with hybrid instruction-following capabilities.","contextLength":126000,"outputMax":32768,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/alibaba-cloud/qwen3-vl-32b-instruct","docsJson":"https://api.aimlapi.com/docs-json?model=alibaba%2Fqwen3-vl-32b-instruct&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["qwen3-vl-32b-instruct"],"tags":["playground:chat","tier:tier_2"]},{"id":"alibaba/qwen3-omni-30b-a3b-captioner","info":{"releasedAt":"2025-11-14","name":"Qwen3 Omni Captioner","developer":"Alibaba Cloud","description":"Qwen3-Omni-Captioner automatically generates accurate and comprehensive descriptions for complex audio, including speech, ambient sounds, music, and sound effects. The model can identify speaker emotions, musical elements, and is suitable for audio content analysis, security audits, and audio editing. Supports audio input up to 40 minutes (1 second = 25 tokens).","contextLength":65536,"outputMax":32768,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/alibaba-cloud/qwen3-omni-30b-a3b-captioner","docsJson":"https://api.aimlapi.com/docs-json?model=alibaba%2Fqwen3-omni-30b-a3b-captioner&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["qwen3-omni-30b-a3b-captioner"],"tags":["tier:tier_2","playground:chat_audio"]},{"id":"alibaba/qwen3.5-omni-plus","info":{"releasedAt":"2026-04-24","name":"Qwen3.5 Omni Plus","developer":"Alibaba Cloud","description":"","contextLength":256000,"outputMax":192000,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=alibaba%2Fqwen3.5-omni-plus&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["qwen3.5-omni-plus"],"tags":["playground:chat","tier:tier_2"]},{"id":"alibaba/qwen3.5-omni-flash","info":{"releasedAt":"2026-04-24","name":"Qwen3.5 Omni Flash","developer":"Alibaba Cloud","description":"","contextLength":256000,"outputMax":192000,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=alibaba%2Fqwen3.5-omni-flash&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["qwen3.5-omni-flash"],"tags":["playground:chat","tier:tier_2"]},{"id":"alibaba/qwen3.6-max-preview","info":{"releasedAt":"2026-04-21","name":"Qwen3.6 Max Preview","developer":"Alibaba Cloud","description":"Qwen3.6-Max-Preview — a high-capability reasoning model by Alibaba Cloud designed for complex tasks and long-form problem solving. It provides strong reasoning performance and high accuracy for advanced use cases.","contextLength":262144,"outputMax":65536,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/alibaba-cloud/qwen3.6-max-preview","docsJson":"https://api.aimlapi.com/docs-json?model=alibaba%2Fqwen3.6-max-preview&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["qwen3.6-max-preview"],"tags":["playground:chat","tier:tier_2"]},{"id":"alibaba/qwen3.7-max","info":{"releasedAt":"2026-05-21","name":"Qwen3.7 Max","developer":"Alibaba Cloud","description":"Qwen3.7-Max is Alibaba’s flagship reasoning and agentic LLM optimized for coding, productivity, long-context understanding and autonomous workflows. Text input and text output only. Supports function calling, explicit context cache and advanced reasoning capabilities.","contextLength":1000000,"outputMax":65536,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/alibaba-cloud/qwen3.7-max","isHottest":true,"docsJson":"https://api.aimlapi.com/docs-json?model=alibaba%2Fqwen3.7-max&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["qwen3.7-max"],"tags":["playground:chat","tier:tier_2","playground:code"]},{"id":"alibaba/qwen3.7-plus","info":{"releasedAt":"2026-06-01","name":"Qwen3.7-Plus","developer":"Alibaba Cloud","description":"Qwen3.7-Plus is a multimodal agent model that unifies vision and language into a single agent foundation. It delivers strong vision-language capabilities while retaining agentic strength in coding, tool use, and productivity workflows — including GUI understanding, visual Q&A, and full-modality input for complex software engineering tasks.","contextLength":1000000,"outputMax":65536,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/alibaba-cloud/qwen3.7-plus","docsJson":"https://api.aimlapi.com/docs-json?model=alibaba%2Fqwen3.7-plus&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["qwen3.7-plus"],"tags":["playground:chat","tier:tier_2","playground:code"]},{"id":"alibaba/qwen3.6-plus","info":{"releasedAt":"2026-04-21","name":"Qwen3.6 Plus","developer":"Alibaba Cloud","description":"Qwen3.6-Plus — a balanced general-purpose model by Alibaba Cloud optimized for performance, cost, and speed. Suitable for a wide range of chat and generation tasks.","contextLength":1000000,"outputMax":65536,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/alibaba-cloud/qwen3.6-plus","docsJson":"https://api.aimlapi.com/docs-json?model=alibaba%2Fqwen3.6-plus&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["qwen3.6-plus"],"tags":["playground:chat","tier:tier_2"]},{"id":"alibaba/qwen3.6-flash","info":{"releasedAt":"2026-04-21","name":"Qwen3.6 Flash","developer":"Alibaba Cloud","description":"Qwen3.6-Flash — a lightweight and cost-efficient model by Alibaba Cloud designed for simple tasks and high-throughput applications. It offers fast response times with lower cost.","contextLength":1000000,"outputMax":65536,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/alibaba-cloud/qwen3.6-flash","docsJson":"https://api.aimlapi.com/docs-json?model=alibaba%2Fqwen3.6-flash&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["qwen3.6-flash"],"tags":["playground:chat","tier:tier_2"]},{"id":"alibaba/qwen3.6-27b","info":{"releasedAt":"2026-04-23","name":"Qwen3.6 27B","developer":"Alibaba Cloud","description":"","contextLength":256000,"outputMax":252000,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=alibaba%2Fqwen3.6-27b&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["qwen3.6-27b"],"tags":["playground:chat","tier:tier_2"]},{"id":"alibaba/qwen3.6-35b-a3b","info":{"releasedAt":"2026-04-23","name":"Qwen3.6 35B A3B","developer":"Alibaba Cloud","description":"","contextLength":256000,"outputMax":252000,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=alibaba%2Fqwen3.6-35b-a3b&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["qwen3.6-35b-a3b"],"tags":["playground:chat","tier:tier_2"]},{"id":"alibaba/text-embedding-v4","info":{"releasedAt":"2025-12-13","name":"Qwen Text Embedding v4","developer":"Alibaba Cloud","description":"Advanced text embedding model from the Qwen3-Embedding series with support for custom dimensions (64-2048) and over 100 languages. Ideal for semantic search, clustering, and classification tasks.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/embedding-models/alibaba-cloud/qwen-text-embedding-v4","contextLength":8192,"docsJson":"https://api.aimlapi.com/docs-json?model=alibaba%2Ftext-embedding-v4&endpoint=openai%2Fembeddings"},"type":"openai/embeddings","aliases":["text-embedding-v4"],"tags":["playground:embeddings","tier:tier_2"]},{"id":"alibaba/text-embedding-v3","info":{"releasedAt":"2025-12-13","name":"Qwen Text Embedding v3","developer":"Alibaba Cloud","description":"High-quality text embedding model with support for custom dimensions (512-1024) and over 50 languages. Suitable for semantic search, recommendation systems, and text analysis.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/embedding-models/alibaba-cloud/qwen-text-embedding-v3","contextLength":8192,"docsJson":"https://api.aimlapi.com/docs-json?model=alibaba%2Ftext-embedding-v3&endpoint=openai%2Fembeddings"},"type":"openai/embeddings","aliases":["text-embedding-v3"],"tags":["playground:embeddings","tier:tier_2"]},{"id":"alibaba/qwen-image-edit","info":{"releasedAt":"2025-10-13","developer":"Alibaba Cloud","description":"Qwen image editing model for modifying existing images based on text prompts","name":"Qwen Image Edit","url":"","docsUrl":"https://docs.aimlapi.com/api-references/image-models/alibaba-cloud/qwen-image-edit","docsJson":"https://api.aimlapi.com/docs-json?model=alibaba%2Fqwen-image-edit&endpoint=openai%2Fimage-generations"},"type":"openai/image-generations","aliases":["qwen-image-edit"],"tags":["playground:image","tier:tier_2"]},{"id":"alibaba/qwen-image","info":{"releasedAt":"2026-02-05","name":"Qwen Image","developer":"Alibaba Cloud","description":"General-purpose image generation model with multiple artistic styles and strong complex text rendering.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/image-models/alibaba-cloud/qwen-image","docsJson":"https://api.aimlapi.com/docs-json?model=alibaba%2Fqwen-image&endpoint=openai%2Fimage-generations"},"type":"openai/image-generations","aliases":["qwen-image"],"tags":["playground:image","tier:tier_2"]},{"id":"alibaba/wan2.5-t2i-preview","info":{"releasedAt":"2025-11-13","developer":"Alibaba Cloud","description":"Wan 2.5 preview text-to-image model with no single-side length limit.","name":"Wan 2.5 Preview","url":"","docsUrl":"https://docs.aimlapi.com/api-references/image-models/alibaba-cloud/wan2.5-t2i-preview","docsJson":"https://api.aimlapi.com/docs-json?model=alibaba%2Fwan2.5-t2i-preview&endpoint=openai%2Fimage-generations"},"type":"openai/image-generations","aliases":["wan2.5-t2i-preview"],"tags":["playground:image","tier:tier_2"]},{"id":"alibaba/wan2.2-t2i-plus","info":{"releasedAt":"2025-11-13","developer":"Alibaba Cloud","description":"Wan 2.2 Professional Edition text-to-image model with improved stability and success rate compared to the 2.1 model.","name":"Wan 2.2 Plus","url":"","docsUrl":"https://docs.aimlapi.com/api-references/image-models/alibaba-cloud/wan2.2-t2i-plus","docsJson":"https://api.aimlapi.com/docs-json?model=alibaba%2Fwan2.2-t2i-plus&endpoint=openai%2Fimage-generations"},"type":"openai/image-generations","aliases":["wan2.2-t2i-plus"],"tags":["playground:image","tier:tier_2"]},{"id":"alibaba/wan2.2-t2i-flash","info":{"releasedAt":"2025-11-13","developer":"Alibaba Cloud","description":"Wan 2.2 Flash Edition text-to-image model - 50% faster than the 2.1 model.","name":"Wan 2.2 Flash","url":"","docsUrl":"https://docs.aimlapi.com/api-references/image-models/alibaba-cloud/wan2.2-t2i-flash","docsJson":"https://api.aimlapi.com/docs-json?model=alibaba%2Fwan2.2-t2i-flash&endpoint=openai%2Fimage-generations"},"type":"openai/image-generations","aliases":["wan2.2-t2i-flash"],"tags":["playground:image","tier:tier_2"]},{"id":"alibaba/qwen-image-2.0","info":{"releasedAt":"2026-04-21","developer":"Alibaba Cloud","description":"","name":"Qwen Image 2.0","url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=alibaba%2Fqwen-image-2.0&endpoint=openai%2Fimage-generations"},"type":"openai/image-generations","aliases":["qwen-image-2.0"],"tags":["playground:image","tier:tier_2"]},{"id":"alibaba/qwen-image-2.0-pro","info":{"releasedAt":"2026-04-21","developer":"Alibaba Cloud","description":"","name":"Qwen Image 2.0 Pro","url":"","docsUrl":"","isHottest":true,"docsJson":"https://api.aimlapi.com/docs-json?model=alibaba%2Fqwen-image-2.0-pro&endpoint=openai%2Fimage-generations"},"type":"openai/image-generations","aliases":["qwen-image-2.0-pro"],"tags":["playground:image","tier:tier_2"]},{"id":"alibaba/wan2.6-image","info":{"releasedAt":"2025-12-18","developer":"Alibaba Cloud","description":"Wan 2.6 is a next-generation text-to-image model from Alibaba Cloud with enhanced visual quality and detail.","name":"Wan 2.6 Image","url":"","docsUrl":"https://docs.aimlapi.com/api-references/image-models/alibaba-cloud/wan-2-6-image","docsJson":"https://api.aimlapi.com/docs-json?model=alibaba%2Fwan2.6-image&endpoint=openai%2Fimage-generations"},"type":"openai/image-generations","aliases":["wan2.6-image"],"tags":["playground:image","tier:tier_2"]},{"id":"alibaba/wan2.7-image","info":{"releasedAt":"2026-04-06","developer":"Alibaba Cloud","description":"Wan 2.7 is a next-generation text-to-image model from Alibaba Cloud with enhanced visual quality and detail.","name":"Wan 2.7 Image","url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=alibaba%2Fwan2.7-image&endpoint=openai%2Fimage-generations"},"type":"openai/image-generations","aliases":["wan2.7-image"],"tags":["playground:image","tier:tier_2"]},{"id":"alibaba/wan2.7-image-pro","info":{"releasedAt":"2026-04-06","developer":"Alibaba Cloud","description":"Wan 2.7 Pro is a next-generation text-to-image model from Alibaba Cloud with enhanced visual quality and detail.","name":"Wan 2.7 Pro Image","url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=alibaba%2Fwan2.7-image-pro&endpoint=openai%2Fimage-generations"},"type":"openai/image-generations","aliases":["wan2.7-image-pro"],"tags":["playground:image","tier:tier_2"]},{"id":"alibaba/z-image-turbo","info":{"releasedAt":"2025-12-02","name":"Z-Image Turbo","developer":"Alibaba Cloud","description":"Lightweight image model for fast generation with Chinese and English text rendering.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/image-models/alibaba-cloud/z-image-turbo","docsJson":"https://api.aimlapi.com/docs-json?model=alibaba%2Fz-image-turbo&endpoint=openai%2Fimage-generations"},"type":"openai/image-generations","aliases":["z-image-turbo"],"tags":["playground:image","tier:tier_2"]},{"id":"alibaba/wan2.1-t2v-plus","info":{"releasedAt":"2025-11-20","developer":"Alibaba Cloud","description":"Wan 2.1 Plus is a high-quality text-to-video model from Alibaba Cloud for diverse creative video generation.","name":"Wan 2.1 Plus Text to Video","url":"","docsUrl":"https://docs.aimlapi.com/api-references/video-models/alibaba-cloud/wan-2.1-plus-text-to-video","docsJson":"https://api.aimlapi.com/docs-json?model=alibaba%2Fwan2.1-t2v-plus&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":["wan2.1-t2v-plus"],"tags":["playground:video","tier:tier_2"]},{"id":"alibaba/wan2.1-t2v-turbo","info":{"releasedAt":"2025-11-20","developer":"Alibaba Cloud","description":"Wan 2.1 Turbo is a fast text-to-video model from Alibaba Cloud optimized for speed without sacrificing quality.","name":"Wan 2.1 Turbo Text to Video","url":"","docsUrl":"https://docs.aimlapi.com/api-references/video-models/alibaba-cloud/wan-2.1-turbo-text-to-video","docsJson":"https://api.aimlapi.com/docs-json?model=alibaba%2Fwan2.1-t2v-turbo&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":["wan2.1-t2v-turbo"],"tags":["playground:video","tier:tier_2"]},{"id":"alibaba/wan2.2-i2v-plus","info":{"releasedAt":"2025-11-20","developer":"Alibaba Cloud","description":"Wan 2.2 Plus Image-to-Video generates high-quality videos from input images with improved stability.","name":"Wan 2.2 Plus Image to Video","url":"","docsUrl":"https://docs.aimlapi.com/api-references/video-models/alibaba-cloud","docsJson":"https://api.aimlapi.com/docs-json?model=alibaba%2Fwan2.2-i2v-plus&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":["wan2.2-i2v-plus"],"tags":["playground:video","tier:tier_2"]},{"id":"alibaba/wan2.2-t2v-plus","info":{"releasedAt":"2025-11-20","developer":"Alibaba Cloud","description":"Wan 2.2 Plus Text-to-Video generates high-quality videos from text prompts with improved stability and coherence.","name":"Wan 2.2 Plus Text to Video","url":"","docsUrl":"https://docs.aimlapi.com/api-references/video-models/alibaba-cloud/wan-2.2-plus-text-to-video","docsJson":"https://api.aimlapi.com/docs-json?model=alibaba%2Fwan2.2-t2v-plus&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":["wan2.2-t2v-plus"],"tags":["playground:video","tier:tier_2"]},{"id":"alibaba/wan2.5-t2v-preview","info":{"releasedAt":"2025-11-20","developer":"Alibaba Cloud","description":"Generate high-quality videos from text prompts using Alibaba Cloud's WAN 2.5 text-to-video model with support for 480p, 720p, and 1080p resolutions.","name":"Wan 2.5 Preview Text to Video","url":"","docsUrl":"https://docs.aimlapi.com/api-references/video-models/alibaba-cloud/wan-2.5-preview-text-to-video","docsJson":"https://api.aimlapi.com/docs-json?model=alibaba%2Fwan2.5-t2v-preview&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":["wan2.5-t2v-preview"],"tags":["playground:video","tier:tier_2"]},{"id":"alibaba/wan2.5-i2v-preview","info":{"releasedAt":"2025-11-20","developer":"Alibaba Cloud","description":"Generate high-quality videos from images using Alibaba Cloud's WAN 2.5 image-to-video model with support for 480p, 720p, and 1080p resolutions.","name":"Wan 2.5 Preview Image to Video","url":"","docsUrl":"https://docs.aimlapi.com/api-references/video-models/alibaba-cloud/wan-2.5-preview-image-to-video","docsJson":"https://api.aimlapi.com/docs-json?model=alibaba%2Fwan2.5-i2v-preview&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":["wan2.5-i2v-preview"],"tags":["playground:video","tier:tier_2"]},{"id":"alibaba/wan2.6-t2v","info":{"releasedAt":"2025-12-18","developer":"Alibaba Cloud","description":"Wan 2.6 Text-to-Video generates high-quality videos from text descriptions with advanced motion modeling.","name":"Wan 2.6 Text to Video","url":"","docsUrl":"https://docs.aimlapi.com/api-references/video-models/alibaba-cloud/wan-2.6-text-to-video","docsJson":"https://api.aimlapi.com/docs-json?model=alibaba%2Fwan2.6-t2v&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":["wan2.6-t2v"],"tags":["playground:video","tier:tier_2"]},{"id":"alibaba/wan2.6-i2v","info":{"releasedAt":"2025-12-18","developer":"Alibaba Cloud","description":"Wan 2.6 Image-to-Video animates still images into smooth, high-quality videos with advanced motion modeling.","name":"Wan 2.6 Image to Video","url":"","docsUrl":"https://docs.aimlapi.com/api-references/video-models/alibaba-cloud/wan-2.6-image-to-video","docsJson":"https://api.aimlapi.com/docs-json?model=alibaba%2Fwan2.6-i2v&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":["wan2.6-i2v"],"tags":["playground:video","tier:tier_2"]},{"id":"alibaba/wan2.6-i2v-flash","info":{"releasedAt":"2026-02-02","developer":"Alibaba Cloud","description":"Wan 2.6 Image-to-Video Flash is a faster variant of Wan 2.6 I2V for rapid video generation.","name":"Wan 2.6 Image to Video Flash","url":"","docsUrl":"https://docs.aimlapi.com/api-references/video-models/alibaba-cloud/wan-2.6-flash-image-to-video","docsJson":"https://api.aimlapi.com/docs-json?model=alibaba%2Fwan2.6-i2v-flash&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":["wan2.6-i2v-flash"],"tags":["playground:video","tier:tier_2"]},{"id":"alibaba/wan2.6-r2v","info":{"releasedAt":"2025-12-18","developer":"Alibaba Cloud","description":"Wan 2.6 Reference-to-Video generates videos guided by reference images for consistent character and scene appearance.","name":"Wan 2.6 Reference to Video","url":"","docsUrl":"https://docs.aimlapi.com/api-references/video-models/alibaba-cloud/wan-2.6-reference-to-video","docsJson":"https://api.aimlapi.com/docs-json?model=alibaba%2Fwan2.6-r2v&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":["wan2.6-r2v"],"tags":["playground:video","tier:tier_2"]},{"id":"alibaba/wan2.7-t2v","info":{"releasedAt":"2026-04-28","developer":"Alibaba Cloud","description":"Wan 2.7 T2V — a text-to-video model by Alibaba Cloud that generates multi-shot videos from prompts. It supports cinematic visuals, prompt control, and audio integration.","name":"Wan 2.7 Text to Video","url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=alibaba%2Fwan2.7-t2v&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":["wan2.7-t2v"],"tags":["playground:video","tier:tier_2"]},{"id":"alibaba/wan2.7-i2v","info":{"releasedAt":"2026-04-28","developer":"Alibaba Cloud","description":"Wan 2.7 I2V — an image-to-video model by Alibaba Cloud that generates videos from input images. It supports first-frame, first-and-last-frame, and continuation workflows.","name":"Wan 2.7 Image to Video","url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=alibaba%2Fwan2.7-i2v&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":["wan2.7-i2v"],"tags":["playground:video","tier:tier_2"]},{"id":"alibaba/wan2.7-r2v","info":{"releasedAt":"2026-04-28","developer":"Alibaba Cloud","description":"Wan 2.7 R2V — a reference-to-video model by Alibaba Cloud that generates videos using reference images or videos. It enables character, motion, and style transfer.","name":"Wan 2.7 Reference to Video","url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=alibaba%2Fwan2.7-r2v&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":["wan2.7-r2v"],"tags":["playground:video","tier:tier_2"]},{"id":"alibaba/custom:happyhorse-1.0","info":{"releasedAt":"2026-04-27","developer":"Alibaba Cloud","description":"","name":"Happy Horse","url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=alibaba%2Fcustom%3Ahappyhorse-1.0&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":["custom:happyhorse-1.0"],"tags":["playground:video","tier:tier_2"]},{"id":"alibaba/happyhorse-1.0-t2v","info":{"releasedAt":"2026-04-27","developer":"Alibaba Cloud","description":"","name":"Happy Horse","url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=alibaba%2Fhappyhorse-1.0-t2v&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":["happyhorse-1.0-t2v"],"tags":["playground:video","tier:tier_2"]},{"id":"alibaba/happyhorse-1.0-i2v","info":{"releasedAt":"2026-04-27","developer":"Alibaba Cloud","description":"","name":"Happy Horse","url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=alibaba%2Fhappyhorse-1.0-i2v&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":["happyhorse-1.0-i2v"],"tags":["playground:video","tier:tier_2"]},{"id":"alibaba/happyhorse-1.0-r2v","info":{"releasedAt":"2026-04-27","developer":"Alibaba Cloud","description":"","name":"Happy Horse","url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=alibaba%2Fhappyhorse-1.0-r2v&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":["happyhorse-1.0-r2v"],"tags":["playground:video","tier:tier_2"]},{"id":"alibaba/happyhorse-1.0-video-edit","info":{"releasedAt":"2026-04-27","developer":"Alibaba Cloud","description":"","name":"Happy Horse","url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=alibaba%2Fhappyhorse-1.0-video-edit&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":["happyhorse-1.0-video-edit"],"tags":["playground:video","tier:tier_2"]},{"id":"alibaba/custom:happyhorse-1.1","info":{"releasedAt":"2026-06-22","developer":"Alibaba Cloud","description":"Happy Horse 1.1 is Alibaba Cloud's video generation family with highly realistic, fluid, and detailed motion. It automatically routes to text-to-video, image-to-video, or reference-to-video based on the inputs you provide.","name":"Happy Horse 1.1","url":"","docsUrl":"","isHottest":true,"docsJson":"https://api.aimlapi.com/docs-json?model=alibaba%2Fcustom%3Ahappyhorse-1.1&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":["custom:happyhorse-1.1"],"tags":["playground:video","tier:tier_2"]},{"id":"alibaba/happyhorse-1.1-t2v","info":{"releasedAt":"2026-06-22","developer":"Alibaba Cloud","description":"Happy Horse 1.1 is Alibaba Cloud's video generation family with highly realistic, fluid, and detailed motion. It automatically routes to text-to-video, image-to-video, or reference-to-video based on the inputs you provide.","name":"Happy Horse 1.1","url":"","docsUrl":"","isHottest":true,"docsJson":"https://api.aimlapi.com/docs-json?model=alibaba%2Fhappyhorse-1.1-t2v&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":["happyhorse-1.1-t2v"],"tags":["playground:video","tier:tier_2"]},{"id":"alibaba/happyhorse-1.1-i2v","info":{"releasedAt":"2026-06-22","developer":"Alibaba Cloud","description":"Happy Horse 1.1 is Alibaba Cloud's video generation family with highly realistic, fluid, and detailed motion. It automatically routes to text-to-video, image-to-video, or reference-to-video based on the inputs you provide.","name":"Happy Horse 1.1","url":"","docsUrl":"","isHottest":true,"docsJson":"https://api.aimlapi.com/docs-json?model=alibaba%2Fhappyhorse-1.1-i2v&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":["happyhorse-1.1-i2v"],"tags":["playground:video","tier:tier_2"]},{"id":"alibaba/happyhorse-1.1-r2v","info":{"releasedAt":"2026-06-22","developer":"Alibaba Cloud","description":"Happy Horse 1.1 is Alibaba Cloud's video generation family with highly realistic, fluid, and detailed motion. It automatically routes to text-to-video, image-to-video, or reference-to-video based on the inputs you provide.","name":"Happy Horse 1.1","url":"","docsUrl":"","isHottest":true,"docsJson":"https://api.aimlapi.com/docs-json?model=alibaba%2Fhappyhorse-1.1-r2v&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":["happyhorse-1.1-r2v"],"tags":["playground:video","tier:tier_2"]},{"id":"alibaba/qwen3-tts-flash","info":{"releasedAt":"2026-01-05","name":"Qwen3 TTS Flash","developer":"Alibaba Cloud","description":"Qwen3-TTS offers 17 voices and supports multiple languages and dialects including Chinese. The system can adapt its tone and smoothly process complex text.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/speech-models/text-to-speech/alibaba-cloud/qwen3-tts-flash","docsJson":"https://api.aimlapi.com/docs-json?model=alibaba%2Fqwen3-tts-flash&endpoint=internal%2Ftext-to-speech"},"type":"internal/text-to-speech","aliases":["qwen3-tts-flash"],"tags":["playground:tts","tier:tier_2"]},{"id":"zhipu/glm-5-2","info":{"releasedAt":"2026-06-16","name":"GLM 5.2","developer":"Zhipu AI","description":"GLM-5.2 is Zhipu AI flagship MoE LLM with a 1M-token context window, optimized for agentic coding, tool use, reasoning, and long-context tasks.","contextLength":1000000,"outputMax":131072,"url":"","docsUrl":"","isHottest":true,"docsJson":"https://api.aimlapi.com/docs-json?model=zhipu%2Fglm-5-2&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":[],"tags":["playground:chat","tier:tier_2"]},{"id":"zhipu/glm-5-2-fast-preview","info":{"releasedAt":"2026-07-10","name":"GLM 5.2 Fast Preview","developer":"Zhipu AI","description":"A latency-optimized GLM-5.2 preview with the same 1M-token context window and 1.5–2× higher output throughput for real-time chat, agents, and coding.","contextLength":1000000,"outputMax":131072,"url":"","docsUrl":"https://help.aliyun.com/en/model-studio/fast-mode","docsJson":"https://api.aimlapi.com/docs-json?model=zhipu%2Fglm-5-2-fast-preview&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":[],"tags":["playground:chat","tier:tier_2"]},{"id":"alibaba/qwen3.5-plus-20260218","info":{"releasedAt":"2026-02-20","name":"Qwen3.5 Plus","developer":"Alibaba Cloud","description":"Qwen3.5-Plus is a commercial large language model by Alibaba Cloud designed for long-context text generation and enterprise-grade conversational AI. Supports up to 1M tokens per request with production-ready API stability.","contextLength":1000000,"outputMax":65536,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/alibaba-cloud/qwen3.5-plus","docsJson":"https://api.aimlapi.com/docs-json?model=alibaba%2Fqwen3.5-plus-20260218&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["qwen3.5-plus"],"tags":["playground:chat","tier:tier_2"]},{"id":"alibaba/wan2.2-vace-fun-a14b-depth","info":{"releasedAt":"2025-11-24","name":"Wan 2.2 Vace Depth","developer":"Alibaba Cloud","description":"Generate videos from depth maps using Alibaba WAN-2.2-VACE model.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/video-models/alibaba-cloud/wan2.2-vace-fun-a14b-depth-image-to-video","docsJson":"https://api.aimlapi.com/docs-json?model=alibaba%2Fwan2.2-vace-fun-a14b-depth&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":[],"tags":["playground:video","tier:tier_2"]},{"id":"alibaba/wan2.2-vace-fun-a14b-pose","info":{"releasedAt":"2025-11-24","name":"Wan 2.2 Vace Pose","developer":"Alibaba Cloud","description":"Generate pose-guided videos using Alibaba WAN-2.2-VACE model.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/video-models/alibaba-cloud/wan2.2-vace-fun-a14b-pose-image-to-video","docsJson":"https://api.aimlapi.com/docs-json?model=alibaba%2Fwan2.2-vace-fun-a14b-pose&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":[],"tags":["playground:video","tier:tier_2"]},{"id":"alibaba/wan2.2-vace-fun-a14b-inpainting","info":{"releasedAt":"2025-11-24","name":"Wan 2.2 Vace Inpainting","developer":"Alibaba Cloud","description":"Generate inpainted videos using Alibaba WAN-2.2-VACE model.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/video-models/alibaba-cloud/wan2.2-vace-fun-a14b-inpainting-image-to-video","docsJson":"https://api.aimlapi.com/docs-json?model=alibaba%2Fwan2.2-vace-fun-a14b-inpainting&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":[],"tags":["playground:video","tier:tier_2"]},{"id":"alibaba/wan2.2-vace-fun-a14b-outpainting","info":{"releasedAt":"2025-11-24","name":"Wan 2.2 Vace Outpainting","developer":"Alibaba Cloud","description":"Generate outpainted videos using Alibaba WAN-2.2-VACE model.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/video-models/alibaba-cloud/wan2.2-vace-fun-a14b-outpainting-image-to-video","docsJson":"https://api.aimlapi.com/docs-json?model=alibaba%2Fwan2.2-vace-fun-a14b-outpainting&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":[],"tags":["playground:video","tier:tier_2"]},{"id":"alibaba/wan2.2-vace-fun-a14b-reframe","info":{"releasedAt":"2025-11-24","name":"Wan 2.2 Vace Reframe","developer":"Alibaba Cloud","description":"Generate reframed videos using Alibaba WAN-2.2-VACE model.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/video-models/alibaba-cloud/wan2.2-vace-fun-a14b-reframe-image-to-video","docsJson":"https://api.aimlapi.com/docs-json?model=alibaba%2Fwan2.2-vace-fun-a14b-reframe&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":[],"tags":["playground:video","tier:tier_2"]},{"id":"alibaba/wan2.2-14b-animate-move","info":{"releasedAt":"2025-11-24","name":"Wan 2.2 14B Animate Move","developer":"Alibaba Cloud","description":"Generate animated videos from video and image using Alibaba WAN-2.2-14B move model.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/video-models/alibaba-cloud/wan-2.2-14b-animate-move-image-to-video","docsJson":"https://api.aimlapi.com/docs-json?model=alibaba%2Fwan2.2-14b-animate-move&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":[],"tags":["playground:video","tier:tier_2"]},{"id":"alibaba/wan2.2-14b-animate-replace","info":{"releasedAt":"2025-11-24","name":"Wan 2.2 14B Animate Replace","developer":"Alibaba Cloud","description":"Generate animated videos from video and image using Alibaba WAN-2.2-14B replace model.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/video-models/alibaba-cloud/wan-2.2-14b-animate-replace-image-to-video","docsJson":"https://api.aimlapi.com/docs-json?model=alibaba%2Fwan2.2-14b-animate-replace&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":[],"tags":["playground:video","tier:tier_2"]},{"id":"alibaba/z-image-turbo-lora","info":{"releasedAt":"2025-12-02","name":"Z-Image Turbo LoRA","developer":"Alibaba Cloud","description":"Z-Image Turbo LoRA extends the Z-Image Turbo model with custom style and subject fine-tuning via LoRA adapters.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/image-models/alibaba-cloud/z-image-turbo-lora","docsJson":"https://api.aimlapi.com/docs-json?model=alibaba%2Fz-image-turbo-lora&endpoint=openai%2Fimage-generations"},"type":"openai/image-generations","aliases":[],"tags":["playground:image","tier:tier_2"]},{"id":"alibaba/qwen-text-embedding-v4","info":{"releasedAt":"2025-12-13","name":"Qwen Text Embedding v4","developer":"Alibaba Cloud","description":"Advanced text embedding model from the Qwen3-Embedding series with support for custom dimensions (64-2048) and over 100 languages. Ideal for semantic search, clustering, and classification tasks.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/embedding-models/alibaba-cloud/qwen-text-embedding-v4","contextLength":8192,"docsJson":"https://api.aimlapi.com/docs-json?model=alibaba%2Fqwen-text-embedding-v4&endpoint=openai%2Fembeddings"},"type":"openai/embeddings","aliases":[],"tags":["playground:embeddings","tier:tier_2"]},{"id":"alibaba/qwen-text-embedding-v3","info":{"releasedAt":"2025-12-13","name":"Qwen Text Embedding v3","developer":"Alibaba Cloud","description":"High-quality text embedding model with support for custom dimensions (512-1024) and over 50 languages. Suitable for semantic search, recommendation systems, and text analysis.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/embedding-models/alibaba-cloud/qwen-text-embedding-v3","contextLength":8192,"docsJson":"https://api.aimlapi.com/docs-json?model=alibaba%2Fqwen-text-embedding-v3&endpoint=openai%2Fembeddings"},"type":"openai/embeddings","aliases":[],"tags":["playground:embeddings","tier:tier_2"]},{"id":"alibaba/wan-2-6-t2v","info":{"releasedAt":"2025-12-18","developer":"Alibaba Cloud","description":"Wan 2.6 Text-to-Video generates high-quality videos from text descriptions with advanced motion modeling.","name":"Wan 2.6 Text to Video","url":"","docsUrl":"https://docs.aimlapi.com/api-references/video-models/alibaba-cloud/wan-2.6-text-to-video","docsJson":"https://api.aimlapi.com/docs-json?model=alibaba%2Fwan-2-6-t2v&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":[],"tags":["playground:video","tier:tier_2"]},{"id":"alibaba/wan-2-6-i2v","info":{"releasedAt":"2025-12-18","developer":"Alibaba Cloud","description":"Wan 2.6 Image-to-Video animates still images into smooth, high-quality videos with advanced motion modeling.","name":"Wan 2.6 Image to Video","url":"","docsUrl":"https://docs.aimlapi.com/api-references/video-models/alibaba-cloud/wan-2.6-image-to-video","docsJson":"https://api.aimlapi.com/docs-json?model=alibaba%2Fwan-2-6-i2v&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":[],"tags":["playground:video","tier:tier_2"]},{"id":"alibaba/wan-2-6-image-to-video-flash","info":{"releasedAt":"2026-02-02","developer":"Alibaba Cloud","description":"Wan 2.6 Image-to-Video Flash is a faster variant of Wan 2.6 I2V for rapid video generation.","name":"Wan 2.6 Image to Video Flash","url":"","docsUrl":"https://docs.aimlapi.com/api-references/video-models/alibaba-cloud/wan-2.6-flash-image-to-video","docsJson":"https://api.aimlapi.com/docs-json?model=alibaba%2Fwan-2-6-image-to-video-flash&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":[],"tags":["playground:video","tier:tier_2"]},{"id":"alibaba/wan-2-6-r2v","info":{"releasedAt":"2025-12-18","developer":"Alibaba Cloud","description":"Wan 2.6 Reference-to-Video generates videos guided by reference images for consistent character and scene appearance.","name":"Wan 2.6 Reference to Video","url":"","docsUrl":"https://docs.aimlapi.com/api-references/video-models/alibaba-cloud/wan-2.6-reference-to-video","docsJson":"https://api.aimlapi.com/docs-json?model=alibaba%2Fwan-2-6-r2v&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":[],"tags":["playground:video","tier:tier_2"]},{"id":"alibaba/wan-2-6-image","info":{"releasedAt":"2025-12-18","developer":"Alibaba Cloud","description":"Wan 2.6 is a next-generation text-to-image model from Alibaba Cloud with enhanced visual quality and detail.","name":"Wan 2.6 Image","url":"","docsUrl":"https://docs.aimlapi.com/api-references/image-models/alibaba-cloud/wan-2-6-image","docsJson":"https://api.aimlapi.com/docs-json?model=alibaba%2Fwan-2-6-image&endpoint=openai%2Fimage-generations"},"type":"openai/image-generations","aliases":[],"tags":["playground:image","tier:tier_2"]},{"id":"alibaba/wan-2-7-image","info":{"releasedAt":"2026-04-06","developer":"Alibaba Cloud","description":"Wan 2.7 is a next-generation text-to-image model from Alibaba Cloud with enhanced visual quality and detail.","name":"Wan 2.7 Image","url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=alibaba%2Fwan-2-7-image&endpoint=openai%2Fimage-generations"},"type":"openai/image-generations","aliases":[],"tags":["playground:image","tier:tier_2"]},{"id":"alibaba/wan-2-7-image-pro","info":{"releasedAt":"2026-04-06","developer":"Alibaba Cloud","description":"Wan 2.7 Pro is a next-generation text-to-image model from Alibaba Cloud with enhanced visual quality and detail.","name":"Wan 2.7 Pro Image","url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=alibaba%2Fwan-2-7-image-pro&endpoint=openai%2Fimage-generations"},"type":"openai/image-generations","aliases":[],"tags":["playground:image","tier:tier_2"]},{"id":"alibaba/wan-2-7-t2v","info":{"releasedAt":"2026-04-28","developer":"Alibaba Cloud","description":"Wan 2.7 T2V — a text-to-video model by Alibaba Cloud that generates multi-shot videos from prompts. It supports cinematic visuals, prompt control, and audio integration.","name":"Wan 2.7 Text to Video","url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=alibaba%2Fwan-2-7-t2v&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":["wan2.7-t2v"],"tags":["playground:video","tier:tier_2"]},{"id":"alibaba/wan-2-7-i2v","info":{"releasedAt":"2026-04-28","developer":"Alibaba Cloud","description":"Wan 2.7 I2V — an image-to-video model by Alibaba Cloud that generates videos from input images. It supports first-frame, first-and-last-frame, and continuation workflows.","name":"Wan 2.7 Image to Video","url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=alibaba%2Fwan-2-7-i2v&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":["wan2.7-i2v"],"tags":["playground:video","tier:tier_2"]},{"id":"alibaba/wan-2-7-r2v","info":{"releasedAt":"2026-04-28","developer":"Alibaba Cloud","description":"Wan 2.7 R2V — a reference-to-video model by Alibaba Cloud that generates videos using reference images or videos. It enables character, motion, and style transfer.","name":"Wan 2.7 Reference to Video","url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=alibaba%2Fwan-2-7-r2v&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":["wan2.7-r2v"],"tags":["playground:video","tier:tier_2"]},{"id":"alibaba/qwen-image-2-0","info":{"releasedAt":"2026-04-21","developer":"Alibaba Cloud","description":"","name":"Qwen Image 2.0","url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=alibaba%2Fqwen-image-2-0&endpoint=openai%2Fimage-generations"},"type":"openai/image-generations","aliases":[],"tags":["playground:image","tier:tier_2"]},{"id":"alibaba/qwen-image-2-0-pro","info":{"releasedAt":"2026-04-21","developer":"Alibaba Cloud","description":"","name":"Qwen Image 2.0 Pro","url":"","docsUrl":"","isHottest":true,"docsJson":"https://api.aimlapi.com/docs-json?model=alibaba%2Fqwen-image-2-0-pro&endpoint=openai%2Fimage-generations"},"type":"openai/image-generations","aliases":[],"tags":["playground:image","tier:tier_2"]},{"id":"alibaba/happyhorse-1-0","info":{"releasedAt":"2026-04-27","developer":"Alibaba Cloud","description":"","name":"Happy Horse","url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=alibaba%2Fhappyhorse-1-0&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":[],"tags":["playground:video","tier:tier_2"]},{"id":"alibaba/happyhorse-1-1","info":{"releasedAt":"2026-06-22","developer":"Alibaba Cloud","description":"Happy Horse 1.1 is Alibaba Cloud's video generation family with highly realistic, fluid, and detailed motion. It automatically routes to text-to-video, image-to-video, or reference-to-video based on the inputs you provide.","name":"Happy Horse 1.1","url":"","docsUrl":"","isHottest":true,"docsJson":"https://api.aimlapi.com/docs-json?model=alibaba%2Fhappyhorse-1-1&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":[],"tags":["playground:video","tier:tier_2"]},{"id":"alibaba/happyhorse-1-1-t2v","info":{"releasedAt":"2026-06-22","developer":"Alibaba Cloud","description":"Happy Horse 1.1 is Alibaba Cloud's video generation family with highly realistic, fluid, and detailed motion. It automatically routes to text-to-video, image-to-video, or reference-to-video based on the inputs you provide.","name":"Happy Horse 1.1","url":"","docsUrl":"","isHottest":true,"docsJson":"https://api.aimlapi.com/docs-json?model=alibaba%2Fhappyhorse-1-1-t2v&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":[],"tags":["playground:video","tier:tier_2"]},{"id":"alibaba/happyhorse-1-1-i2v","info":{"releasedAt":"2026-06-22","developer":"Alibaba Cloud","description":"Happy Horse 1.1 is Alibaba Cloud's video generation family with highly realistic, fluid, and detailed motion. It automatically routes to text-to-video, image-to-video, or reference-to-video based on the inputs you provide.","name":"Happy Horse 1.1","url":"","docsUrl":"","isHottest":true,"docsJson":"https://api.aimlapi.com/docs-json?model=alibaba%2Fhappyhorse-1-1-i2v&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":[],"tags":["playground:video","tier:tier_2"]},{"id":"alibaba/happyhorse-1-1-r2v","info":{"releasedAt":"2026-06-22","developer":"Alibaba Cloud","description":"Happy Horse 1.1 is Alibaba Cloud's video generation family with highly realistic, fluid, and detailed motion. It automatically routes to text-to-video, image-to-video, or reference-to-video based on the inputs you provide.","name":"Happy Horse 1.1","url":"","docsUrl":"","isHottest":true,"docsJson":"https://api.aimlapi.com/docs-json?model=alibaba%2Fhappyhorse-1-1-r2v&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":[],"tags":["playground:video","tier:tier_2"]},{"id":"Qwen/Qwen2.5-7B-Instruct-Turbo","info":{"releasedAt":"2025-09-30","name":"Qwen2.5 7B Instruct Turbo","developer":"Alibaba Cloud","description":"Qwen 2.5 7B Instruct Turbo excels in coding and instruction following.","contextLength":32000,"outputMax":31000,"url":"https://aimlapi.com/models/qwen-2-5-7b-instruct-api","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/alibaba-cloud/qwen2.5-7b-instruct-turbo","docsJson":"https://api.aimlapi.com/docs-json?model=Qwen%2FQwen2.5-7B-Instruct-Turbo&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":[],"tags":["playground:chat","tier:tier_2"]},{"id":"Qwen/Qwen3-235B-A22B-Thinking-2507","info":{"releasedAt":"2025-09-30","name":"Qwen3 Next 80B A3B Thinking","developer":"Alibaba Cloud","description":"Alibaba's Qwen 3 Next 80B A3B Thinking is a multilingual reasoning model with advanced chain-of-thought capabilities.","contextLength":126976,"outputMax":81920,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/alibaba-cloud/qwen3-next-80b-a3b-thinking","docsJson":"https://api.aimlapi.com/docs-json?model=Qwen%2FQwen3-235B-A22B-Thinking-2507&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":[],"tags":["playground:chat","tier:tier_2","playground:code"]},{"id":"Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8","info":{"releasedAt":"2025-09-09","name":"Qwen3 Coder","developer":"Alibaba Cloud","description":"Alibaba's Qwen 3 Coder is a powerful coding agent.","contextLength":262000,"outputMax":65536,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/alibaba-cloud/qwen3-coder-480b-a35b-instruct","docsJson":"https://api.aimlapi.com/docs-json?model=Qwen%2FQwen3-Coder-480B-A35B-Instruct-FP8&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":[],"tags":["playground:chat","tier:tier_2","playground:code"]},{"id":"minimax/MiniMax-Text-01","info":{"releasedAt":"2025-09-09","contextLength":1000000,"outputMax":40000,"description":"MiniMax-Text-01 excels in long-context processing with advanced features like hybrid attention mechanisms and open-source accessibility.","name":"Text 01","developer":"Minimax AI","url":"https://aimlapi.com/models/minimax-text-01-api","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/minimax/text-01","docsJson":"https://api.aimlapi.com/docs-json?model=minimax%2FMiniMax-Text-01&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["MiniMax-Text-01"],"tags":["playground:chat","tier:tier_2"]},{"id":"minimax/m1","info":{"releasedAt":"2025-09-09","contextLength":1000000,"outputMax":40960,"description":"MiniMax-M1 is a powerful reasoning model with a 1M token context window, delivering strong performance on complex tasks.","name":"MiniMax M1","developer":"Minimax AI","url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/minimax/m1","docsJson":"https://api.aimlapi.com/docs-json?model=minimax%2Fm1&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["MiniMax-M1"],"tags":["playground:chat","tier:tier_2"]},{"id":"minimax/m2","info":{"releasedAt":"2025-11-04","contextLength":1000000,"outputMax":40960,"description":"MiniMax-M2 is an advanced large language model with 1M token context for extended reasoning and generation.","name":"MiniMax M2","developer":"Minimax AI","url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/minimax/m2","docsJson":"https://api.aimlapi.com/docs-json?model=minimax%2Fm2&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["MiniMax-M2"],"tags":["playground:chat","tier:tier_2"]},{"id":"minimax/m2-her","info":{"releasedAt":"2026-04-14","contextLength":64000,"outputMax":2048,"description":"","name":"MiniMax M2-her","developer":"Minimax AI","url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=minimax%2Fm2-her&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["MiniMax M2-her"],"tags":["playground:chat","tier:tier_2"]},{"id":"minimax/m2-1","info":{"releasedAt":"2025-12-23","contextLength":204000,"outputMax":204000,"description":"MiniMax-M2.1 is an updated Minimax model with a 200K context window optimized for conversational and reasoning tasks.","name":"MiniMax M2.1","developer":"Minimax AI","url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/minimax/m2-1","docsJson":"https://api.aimlapi.com/docs-json?model=minimax%2Fm2-1&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["MiniMax-M2.1"],"tags":["playground:chat","tier:tier_2"]},{"id":"minimax/m2-1-highspeed","info":{"releasedAt":"2026-04-14","contextLength":204800,"outputMax":204800,"description":"","name":"MiniMax M2.1 Highspeed","developer":"Minimax AI","url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=minimax%2Fm2-1-highspeed&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["MiniMax-M2.1-Highspeed"],"tags":["playground:chat","tier:tier_2"]},{"id":"minimax/m2-5-20260218","info":{"releasedAt":"2026-02-19","contextLength":204800,"outputMax":204800,"description":"MiniMax-M2.5 is a general-purpose large language model by MiniMax designed for text generation and conversational AI use cases.","name":"MiniMax M2.5","developer":"Minimax AI","url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/minimax/m2-5","docsJson":"https://api.aimlapi.com/docs-json?model=minimax%2Fm2-5-20260218&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["MiniMax-M2.5"],"tags":["playground:chat","tier:tier_2"]},{"id":"minimax/minimax-m3","info":{"releasedAt":"2026-06-01","contextLength":524288,"outputMax":524288,"description":"MiniMax M3 is a large-context reasoning model from MiniMax. Supports up to 1M context tokens and is optimized for long-document understanding, coding workflows, agent tasks, and complex multi-step reasoning.","name":"MiniMax M3","developer":"Minimax AI","url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/minimax/m3","isHottest":true,"docsJson":"https://api.aimlapi.com/docs-json?model=minimax%2Fminimax-m3&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["MiniMax-M3"],"tags":["playground:chat","tier:tier_2","playground:code"]},{"id":"minimax/m2-7-20260402","info":{"releasedAt":"2026-04-02","contextLength":204800,"outputMax":204800,"description":"","name":"MiniMax M2.7","developer":"Minimax AI","url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=minimax%2Fm2-7-20260402&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["MiniMax-M2.7"],"tags":["playground:chat","tier:tier_2","playground:code"]},{"id":"minimax/m2-7-highspeed","info":{"releasedAt":"2026-04-14","contextLength":204800,"outputMax":204800,"description":"","name":"MiniMax M2.7 Highspeed","developer":"Minimax AI","url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=minimax%2Fm2-7-highspeed&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["MiniMax-M2.7-Highspeed"],"tags":["playground:chat","tier:tier_2"]},{"id":"minimax/m2-5-highspeed-20260218","info":{"releasedAt":"2026-02-19","contextLength":204800,"outputMax":204800,"description":"MiniMax-M2.5 Highspeed is a low-latency, high-throughput version of MiniMax-M2.5 optimized for real-time applications.","name":"MiniMax M2.5 Highspeed","developer":"Minimax AI","url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/minimax/m2-5-highspeed","docsJson":"https://api.aimlapi.com/docs-json?model=minimax%2Fm2-5-highspeed-20260218&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["MiniMax-M2.5-Highspeed"],"tags":["playground:chat","tier:tier_2"]},{"id":"video-01","info":{"releasedAt":"2025-11-28","name":"Video 01","developer":"Minimax AI","description":"Minimax Video-01 generates high-quality videos from text prompts or image using advanced AI techniques for diverse creative applications.","url":"https://aimlapi.com/models/minimax-video-01-api","docsUrl":"https://docs.aimlapi.com/api-references/video-models/minimax/video-01","docsJson":"https://api.aimlapi.com/docs-json?model=video-01&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":[],"tags":["playground:video","tier:tier_2"]},{"id":"video-01-live2d","info":{"releasedAt":"2025-11-28","name":"Video 01 Live2D","developer":"Minimax AI","description":"Minimax Video-01 generates high-quality videos from text prompts or image using advanced AI techniques for diverse creative applications.","url":"https://aimlapi.com/models/minimax-video-01-api","docsUrl":"https://docs.aimlapi.com/api-references/video-models/minimax/video-01-live2d","docsJson":"https://api.aimlapi.com/docs-json?model=video-01-live2d&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":[],"tags":["playground:video","tier:tier_2"]},{"id":"minimax/hailuo-02","info":{"releasedAt":"2025-11-28","name":"Hailuo 02","developer":"Minimax AI","description":"Hailuo 02 is MiniMax's second-generation video model offering improved visual quality and motion coherence.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/video-models/minimax/hailuo-02","docsJson":"https://api.aimlapi.com/docs-json?model=minimax%2Fhailuo-02&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":[],"tags":["playground:video","tier:tier_2"]},{"id":"minimax/hailuo-2.3","info":{"releasedAt":"2025-11-28","name":"Hailuo 2.3","developer":"Minimax AI","description":"Hailuo 2.3 is an advanced video generation model from MiniMax with enhanced realism and prompt fidelity.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/video-models/minimax/hailuo-2.3","docsJson":"https://api.aimlapi.com/docs-json?model=minimax%2Fhailuo-2.3&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":[],"tags":["playground:video","tier:tier_2"]},{"id":"minimax/hailuo-2.3-fast","info":{"releasedAt":"2025-11-28","name":"Hailuo 2.3 Fast","developer":"Minimax AI","description":"Hailuo 2.3 Fast is a speed-optimized variant of Hailuo 2.3 for rapid video generation workflows.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/video-models/minimax/hailuo-2.3-fast","docsJson":"https://api.aimlapi.com/docs-json?model=minimax%2Fhailuo-2.3-fast&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":[],"tags":["playground:video","tier:tier_2"]},{"id":"minimax/music-1.5","info":{"releasedAt":"2025-12-05","description":"MiniMax Music 1.5 provides enhanced music generation quality with refined control over composition styles.","name":"MiniMax Music 1.5","developer":"Minimax AI","url":"","docsUrl":"https://docs.aimlapi.com/api-references/music-models/minimax/music-1.5","docsJson":"https://api.aimlapi.com/docs-json?model=minimax%2Fmusic-1.5&endpoint=internal%2Faudio-generations%2Fsubmit"},"type":"internal/audio-generations/submit","aliases":[],"tags":["playground:audio","tier:tier_2"]},{"id":"minimax/music-2.0","info":{"releasedAt":"2025-12-05","description":"MiniMax Music 2.0 delivers superior music generation quality and offers improved control over composition styles.","name":"MiniMax Music 2.0","developer":"Minimax AI","url":"","docsUrl":"https://docs.aimlapi.com/api-references/music-models/minimax/music-2.0","docsJson":"https://api.aimlapi.com/docs-json?model=minimax%2Fmusic-2.0&endpoint=internal%2Faudio-generations%2Fsubmit"},"type":"internal/audio-generations/submit","aliases":[],"tags":["playground:audio","tier:tier_2"]},{"id":"minimax/music-2.6","info":{"releasedAt":"2026-04-13","description":"MiniMax Music 2.6 — a music generation model that creates up to 5-minute audio tracks from text prompts. Optimized for fast generation and consistent musical structure.","name":"MiniMax Music 2.6","developer":"Minimax AI","url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=minimax%2Fmusic-2.6&endpoint=internal%2Faudio-generations%2Fsubmit"},"type":"internal/audio-generations/submit","aliases":[],"tags":["playground:audio","tier:tier_2"]},{"id":"minimax/music-cover","info":{"releasedAt":"2026-04-15","description":"MiniMax Music Cover — an audio-to-audio music generation model that creates cover versions from reference audio. Supports style transformation while preserving the original structure and melody.","name":"MiniMax Music Cover","developer":"Minimax AI","url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=minimax%2Fmusic-cover&endpoint=internal%2Faudio-generations%2Fsubmit"},"type":"internal/audio-generations/submit","aliases":[],"tags":["playground:audio","tier:tier_2"]},{"id":"minimax/speech-2.5-turbo-preview","info":{"releasedAt":"2026-01-05","name":"Speech 2.5 Turbo Preview","developer":"Minimax AI","description":"The brand new Turbo model. Ultimate Value, 40 Languages - supports synchronous text-to-speech audio generation with 100+ existing voices and multiple audio specifications.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/speech-models/voice-chat/minimax/speech-2.5-turbo-preview","docsJson":"https://api.aimlapi.com/docs-json?model=minimax%2Fspeech-2.5-turbo-preview&endpoint=internal%2Ftext-to-speech"},"type":"internal/text-to-speech","aliases":[],"tags":["playground:tts","tier:tier_2"]},{"id":"minimax/speech-2.5-hd-preview","info":{"releasedAt":"2026-01-05","name":"Speech 2.5 HD Preview","developer":"Minimax AI","description":"The brand new HD model. Ultimate Similarity, Ultra-High Quality - supports synchronous text-to-speech audio generation with superior rhythm and stability.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/speech-models/voice-chat/minimax/speech-2.5-hd-preview","docsJson":"https://api.aimlapi.com/docs-json?model=minimax%2Fspeech-2.5-hd-preview&endpoint=internal%2Ftext-to-speech"},"type":"internal/text-to-speech","aliases":[],"tags":["playground:tts","tier:tier_2"]},{"id":"minimax/speech-2.6-hd","info":{"releasedAt":"2026-01-05","name":"Speech 2.6 HD","developer":"Minimax AI","description":"MiniMax Speech 2.6 HD delivers ultra-high-quality text-to-speech audio with superior naturalness and voice similarity.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/speech-models/voice-chat/minimax/speech-2.6-hd","docsJson":"https://api.aimlapi.com/docs-json?model=minimax%2Fspeech-2.6-hd&endpoint=internal%2Ftext-to-speech"},"type":"internal/text-to-speech","aliases":[],"tags":["playground:tts","tier:tier_2"]},{"id":"minimax/speech-2.6-turbo","info":{"releasedAt":"2026-01-05","name":"Speech 2.6 Turbo","developer":"Minimax AI","description":"MiniMax Speech 2.6 Turbo is a low-latency text-to-speech model for real-time voice applications across 40 languages.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/speech-models/voice-chat/minimax/speech-2.6-turbo","docsJson":"https://api.aimlapi.com/docs-json?model=minimax%2Fspeech-2.6-turbo&endpoint=internal%2Ftext-to-speech"},"type":"internal/text-to-speech","aliases":[],"tags":["playground:tts","tier:tier_2"]},{"id":"minimax/speech-2.8-turbo","info":{"releasedAt":"2026-04-13","name":"Speech 2.8 Turbo","developer":"Minimax AI","description":"MiniMax Speech 2.8 — text-to-speech model for generating natural-sounding speech from text. Supports multiple quality modes (turbo and hd) optimized for latency or audio fidelity.","url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=minimax%2Fspeech-2.8-turbo&endpoint=internal%2Ftext-to-speech"},"type":"internal/text-to-speech","aliases":[],"tags":["playground:tts","tier:tier_2"]},{"id":"minimax/speech-2.8-hd","info":{"releasedAt":"2026-04-13","name":"Speech 2.8 HD","developer":"Minimax AI","description":"MiniMax Speech 2.8 — text-to-speech model for generating natural-sounding speech from text. Supports multiple quality modes (turbo and hd) optimized for latency or audio fidelity.","url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=minimax%2Fspeech-2.8-hd&endpoint=internal%2Ftext-to-speech"},"type":"internal/text-to-speech","aliases":[],"tags":["playground:tts","tier:tier_2"]},{"id":"moonshot/kimi-k2-5","info":{"releasedAt":"2026-02-06","name":"Kimi K2.5","developer":"Moonshot","description":"Kimi k2.5 is a powerful agentic model by Moonshot AI with strong coding and tool-use capabilities.","contextLength":262144,"outputMax":131000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/moonshot/kimi-k2-5","docsJson":"https://api.aimlapi.com/docs-json?model=moonshot%2Fkimi-k2-5&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["kimi-k2-5"],"tags":["playground:chat","tier:tier_2"]},{"id":"moonshot/kimi-k2-6","info":{"releasedAt":"2026-04-20","name":"Kimi K2.6","developer":"Moonshot","description":"","contextLength":262000,"outputMax":260000,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=moonshot%2Fkimi-k2-6&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":[],"tags":["playground:chat","tier:tier_2","playground:code"]},{"id":"moonshot/kimi-k2-7-code","info":{"releasedAt":"2026-06-12","name":"Kimi K2.7 Code","developer":"Moonshot","description":"Agentic coding model from Moonshot with extended reasoning and tool use.","contextLength":262144,"outputMax":260000,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=moonshot%2Fkimi-k2-7-code&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["kimi-k2-7-code"],"tags":["playground:chat","tier:tier_2","playground:code"]},{"id":"moonshot/kimi-k2-7-code-highspeed","info":{"releasedAt":"2026-06-22","name":"Kimi K2.7 Code Highspeed","developer":"Moonshot","description":"High-throughput variant of Kimi K2.7 Code from Moonshot — the same agentic coding model with extended reasoning and tool use, served at higher speed.","contextLength":262144,"outputMax":260000,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=moonshot%2Fkimi-k2-7-code-highspeed&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["kimi-k2-7-code-highspeed"],"tags":["playground:chat","tier:tier_2","playground:code"]},{"id":"moonshot/kimi-k3","info":{"name":"Kimi K3","developer":"Moonshot","description":"Kimi K3 is a multimodal model from Moonshot AI accepting text and image input.","contextLength":1048576,"url":"","docsUrl":"","isHottest":true,"docsJson":"https://api.aimlapi.com/docs-json?model=moonshot%2Fkimi-k3&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["kimi-k3","moonshotai/kimi-k3"],"tags":["playground:chat","tier:tier_2","playground:code"]},{"id":"anthracite-org/magnum-v4-72b","info":{"releasedAt":"2025-09-09","name":"Magnum v4 72B","developer":"Anthracite","description":"Magnum V4 is a powerful language model optimized for high-quality text generation tasks.","contextLength":32000,"outputMax":16384,"url":"https://aimlapi.com/models/magnum-v4-72b-api","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/anthracite/magnum-v4","docsJson":"https://api.aimlapi.com/docs-json?model=anthracite-org%2Fmagnum-v4-72b&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["magnum-v4-72b"],"tags":["playground:chat","tier:tier_2"]},{"id":"gryphe/mythomax-l2-13b","info":{"releasedAt":"2025-12-09","name":"MythoMax 13B","developer":"Gryphe","description":"One of the highest performing and most popular fine-tunes of Llama 2 13B, with rich descriptions and roleplay.","contextLength":4096,"outputMax":4096,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/gryphe/mythomax-l2-13b","docsJson":"https://api.aimlapi.com/docs-json?model=gryphe%2Fmythomax-l2-13b&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["mythomax-l2-13b"],"tags":["playground:chat","tier:tier_2"]},{"id":"baidu/ernie-4.5-vl-424b-a47b","info":{"releasedAt":"2026-01-12","name":"Ernie 4.5 VL 424B A47B","developer":"Baidu","description":"High-capacity vision-language Ernie 4.5 VL 424B A47B for demanding multimodal workflows.","contextLength":123000,"outputMax":123000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/baidu/ernie-4.5-vl-424b-a47b","docsJson":"https://api.aimlapi.com/docs-json?model=baidu%2Fernie-4.5-vl-424b-a47b&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["baidu/ernie-4-5-vl-424b-a47b"],"tags":["playground:chat","tier:tier_2"]},{"id":"baidu/ernie-5.0","info":{"releasedAt":"2026-06-30","name":"ERNIE 5.0","developer":"Baidu","description":"ERNIE 5.0 is Baidu’s unified foundation model supporting text generation, visual understanding, and deep-thinking reasoning, with a 128K context window.","contextLength":128000,"outputMax":65536,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=baidu%2Fernie-5.0&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["ernie-5.0"],"tags":["playground:chat","tier:tier_2"]},{"id":"nvidia/nemotron-3-nano-30b-a3b","info":{"releasedAt":"2026-04-30","name":"Nemotron 3 Nano 30B A3B","developer":"Nvidia","description":"NVIDIA Nemotron 3 Nano 30B A3B is a lightweight MoE language model from the Nemotron 3 family, designed for efficient and scalable text generation and agent workflows with strong compute efficiency.","contextLength":262144,"outputMax":228000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/nvidia/nemotron-3-nano-30b-a3b","docsJson":"https://api.aimlapi.com/docs-json?model=nvidia%2Fnemotron-3-nano-30b-a3b&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["nemotron-3-nano-30b-a3b"],"tags":["playground:chat","tier:tier_2"]},{"id":"nvidia/nemotron-3-super-120b-a12b","info":{"releasedAt":"2026-04-30","name":"Nemotron 3 Super 120B A12B","developer":"Nvidia","description":"NVIDIA Nemotron 3 Super 120B A12B is the high-capacity MoE variant of the Nemotron 3 family, delivering strong reasoning and long-context performance for demanding text generation and agent workflows while preserving MoE compute efficiency.","contextLength":262144,"outputMax":262144,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/nvidia/nemotron-3-super-120b-a12b","docsJson":"https://api.aimlapi.com/docs-json?model=nvidia%2Fnemotron-3-super-120b-a12b&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["nemotron-3-super-120b-a12b"],"tags":["playground:chat","tier:tier_2"]},{"id":"nvidia/nemotron-3-ultra-550b-a55b","info":{"releasedAt":"2026-06-04","name":"Nemotron 3 Ultra 550B A55B","developer":"Nvidia","description":"NVIDIA Nemotron 3 Ultra is a reasoning and orchestration model built on a hybrid Transformer-Mamba Mixture-of-Experts architecture, optimized for complex reasoning, long-context analysis, and agent workflows with up to 1M context length.","contextLength":1000000,"outputMax":32768,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/nvidia/nemotron-3-ultra-550b-a55b","docsJson":"https://api.aimlapi.com/docs-json?model=nvidia%2Fnemotron-3-ultra-550b-a55b&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["nemotron-3-ultra-550b-a55b"],"tags":["playground:chat","tier:tier_2"]},{"id":"nvidia/llama-3.3-nemotron-super-49b-v1.5","info":{"releasedAt":"2025-10-10","name":"Llama 3.3 Nemotron Super 49B V1.5","developer":"Nvidia","contextLength":131072,"outputMax":16384,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=nvidia%2Fllama-3.3-nemotron-super-49b-v1.5&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["llama-3.3-nemotron-super-49b-v1.5"],"tags":["playground:chat","tier:tier_2"]},{"id":"nousresearch/hermes-4-405b","info":{"releasedAt":"2025-10-02","name":"Hermes 4 405B","developer":"NousResearch","description":"Hermes 4 is a large-scale reasoning model built on Meta-Llama-3.1-405B with hybrid reasoning mode. It can choose to deliberate internally with <think>...</think> traces or respond directly, offering flexibility between speed and depth. Supports structured outputs, JSON mode, function calling, and tool use.","contextLength":131072,"outputMax":16000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/nousresearch/hermes-4-405b","docsJson":"https://api.aimlapi.com/docs-json?model=nousresearch%2Fhermes-4-405b&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["hermes-4-405b"],"tags":["playground:chat","tier:tier_2"]},{"id":"nousresearch/hermes-4-70b","info":{"releasedAt":"2025-08-26","name":"Hermes 4 70B","developer":"NousResearch","contextLength":131072,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=nousresearch%2Fhermes-4-70b&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["hermes-4-70b"],"tags":["playground:chat","tier:tier_2"]},{"id":"nousresearch/hermes-3-llama-3.1-70b","info":{"releasedAt":"2024-08-18","name":"Hermes 3 70B Instruct","developer":"NousResearch","contextLength":131072,"outputMax":16384,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=nousresearch%2Fhermes-3-llama-3.1-70b&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["hermes-3-llama-3.1-70b"],"tags":["playground:chat","tier:tier_2"]},{"id":"nousresearch/hermes-3-llama-3.1-405b","info":{"releasedAt":"2024-08-16","name":"Hermes 3 405B Instruct","developer":"NousResearch","contextLength":131072,"outputMax":16384,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=nousresearch%2Fhermes-3-llama-3.1-405b&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["hermes-3-llama-3.1-405b"],"tags":["playground:chat","tier:tier_2"]},{"id":"cohere/command-a","info":{"releasedAt":"2025-09-09","name":"Command A","developer":"Cohere","description":"Command A is a powerful LLM with advanced capabilities for enterprise applications.","contextLength":256000,"outputMax":256000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/cohere/command-a","docsJson":"https://api.aimlapi.com/docs-json?model=cohere%2Fcommand-a&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["command-a"],"tags":["playground:chat","tier:tier_2"]},{"id":"cohere/command-r7b-12-2024","info":{"releasedAt":"2024-12-14","name":"Command R7B (12-2024)","developer":"Cohere","contextLength":128000,"outputMax":4000,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=cohere%2Fcommand-r7b-12-2024&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["command-r7b-12-2024"],"tags":["playground:chat","tier:tier_2"]},{"id":"cohere/command-r-08-2024","info":{"releasedAt":"2024-08-30","name":"Command R (08-2024)","developer":"Cohere","contextLength":128000,"outputMax":4000,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=cohere%2Fcommand-r-08-2024&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["command-r-08-2024"],"tags":["playground:chat","tier:tier_2"]},{"id":"cohere/command-r-plus-08-2024","info":{"releasedAt":"2024-08-30","name":"Command R+ (08-2024)","developer":"Cohere","contextLength":128000,"outputMax":4000,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=cohere%2Fcommand-r-plus-08-2024&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["command-r-plus-08-2024"],"tags":["playground:chat","tier:tier_2"]},{"id":"perplexity/sonar","info":{"releasedAt":"2025-09-09","name":"Sonar","developer":"Perplexity","description":"Perplexity Sonar is a fast search-augmented language model grounded in real-time web data for up-to-date answers.","contextLength":128000,"outputMax":100000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/perplexity/sonar","docsJson":"https://api.aimlapi.com/docs-json?model=perplexity%2Fsonar&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["sonar"],"tags":["playground:chat","tier:tier_2"]},{"id":"perplexity/sonar-pro","info":{"releasedAt":"2025-09-09","name":"Sonar Pro","developer":"Perplexity","description":"Perplexity Sonar Pro is an advanced search-augmented language model with deeper reasoning and broader web coverage.","contextLength":200000,"outputMax":100000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/perplexity/sonar-pro","docsJson":"https://api.aimlapi.com/docs-json?model=perplexity%2Fsonar-pro&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["sonar-pro"],"tags":["playground:chat","tier:tier_2"]},{"id":"x-ai/grok-3-beta","info":{"releasedAt":"2025-09-09","name":"Grok 3 Beta","developer":"X AI","description":"Grok 3 Beta is xAI's advanced language model with strong reasoning and broad knowledge capabilities.","contextLength":131000,"outputMax":130000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/xai/grok-3-beta","docsJson":"https://api.aimlapi.com/docs-json?model=x-ai%2Fgrok-3-beta&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["grok-3"],"tags":["playground:chat","tier:tier_2"]},{"id":"x-ai/grok-3-mini-beta","info":{"releasedAt":"2025-09-09","name":"Grok 3 Beta Mini","developer":"X AI","description":"Grok 3 Beta Mini is a compact, efficient variant of Grok 3 optimized for speed and cost-effective inference.","contextLength":131000,"outputMax":130000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/xai/grok-3-mini-beta","docsJson":"https://api.aimlapi.com/docs-json?model=x-ai%2Fgrok-3-mini-beta&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["grok-3-mini"],"tags":["playground:chat","tier:tier_2"]},{"id":"x-ai/grok-4-fast-reasoning","info":{"releasedAt":"2025-09-30","name":"Grok 4 Fast Reasoning","developer":"X AI","description":"Grok 4 Fast with always-on reasoning for complex problem-solving tasks.","contextLength":2000000,"outputMax":1999000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/xai/grok-4-fast-reasoning","docsJson":"https://api.aimlapi.com/docs-json?model=x-ai%2Fgrok-4-fast-reasoning&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["grok-4-fast-reasoning"],"tags":["playground:chat","tier:tier_2"]},{"id":"x-ai/grok-4-fast-non-reasoning","info":{"releasedAt":"2025-09-30","name":"Grok 4 Fast Non-Reasoning","developer":"X AI","description":"Grok 4 Fast without reasoning for faster responses and lower latency.","contextLength":2000000,"outputMax":1999000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/xai/grok-4-fast-non-reasoning","docsJson":"https://api.aimlapi.com/docs-json?model=x-ai%2Fgrok-4-fast-non-reasoning&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["grok-4-fast-non-reasoning"],"tags":["playground:chat","tier:tier_2"]},{"id":"x-ai/grok-4-1-fast-reasoning","info":{"releasedAt":"2025-11-20","name":"Grok 4.1 Fast Reasoning","developer":"X AI","description":"Grok 4.1 Fast is a frontier multimodal model optimized for high-performance agentic tool calling with advanced reasoning capabilities.","contextLength":2000000,"outputMax":1999000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/xai/grok-4-1-fast-reasoning","docsJson":"https://api.aimlapi.com/docs-json?model=x-ai%2Fgrok-4-1-fast-reasoning&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["grok-4-1-fast-reasoning"],"tags":["playground:chat","tier:tier_2"]},{"id":"x-ai/grok-4-1-fast-non-reasoning","info":{"releasedAt":"2025-11-20","name":"Grok 4.1 Fast Non-Reasoning","developer":"X AI","description":"Grok 4.1 Fast without reasoning for faster responses and lower latency in high-performance agentic applications.","contextLength":2000000,"outputMax":1999000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/xai/grok-4-1-fast-non-reasoning","docsJson":"https://api.aimlapi.com/docs-json?model=x-ai%2Fgrok-4-1-fast-non-reasoning&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["grok-4-1-fast-non-reasoning"],"tags":["playground:chat","tier:tier_2"]},{"id":"x-ai/grok-4-3","info":{"releasedAt":"2026-05-05","name":"Grok 4.3","developer":"X AI","description":"Grok 4.3 is a large language model by xAI for text generation and reasoning tasks. Supports up to 1M context tokens and is optimized for conversational AI and analytical workflows.","contextLength":1000000,"outputMax":1000000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/xai/grok-4-3","docsJson":"https://api.aimlapi.com/docs-json?model=x-ai%2Fgrok-4-3&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["grok-4-3"],"tags":["playground:chat","tier:tier_2"]},{"id":"x-ai/grok-4-3","info":{"releasedAt":"2026-05-05","name":"Grok 4.3","developer":"X AI","description":"Grok 4.3 is a large language model by xAI for text generation and reasoning tasks. Supports up to 1M context tokens and is optimized for conversational AI and analytical workflows.","contextLength":1000000,"outputMax":1000000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/xai/grok-4-3","docsJson":"https://api.aimlapi.com/docs-json?model=x-ai%2Fgrok-4-3&endpoint=openai%2Fresponses%2Fsubmit"},"type":"openai/responses/submit","aliases":["grok-4-3"],"tags":["playground:chat","tier:tier_2"]},{"id":"x-ai/grok-4-5","info":{"releasedAt":"2026-07-08","name":"Grok 4.5","developer":"X AI","description":"Grok 4.5 is a large language model by xAI for text generation and reasoning tasks, with a 500K token context window and prompt caching support.","contextLength":500000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/xai/grok-4-5","isHottest":true,"docsJson":"https://api.aimlapi.com/docs-json?model=x-ai%2Fgrok-4-5&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["grok-4-5"],"tags":["playground:chat","tier:tier_2"]},{"id":"x-ai/grok-4-20-0309-reasoning","info":{"releasedAt":"2026-04-09","name":"Grok 4.20 Reasoning","developer":"X AI","description":"Grok 4.20 Reasoning — a large language model designed for advanced reasoning tasks. It excels at multi-step problem solving, logical analysis, and complex instruction following.","contextLength":2000000,"outputMax":1999000,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=x-ai%2Fgrok-4-20-0309-reasoning&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["grok-4-20-0309-reasoning"],"tags":["playground:chat","tier:tier_2"]},{"id":"x-ai/grok-4-20-0309-non-reasoning","info":{"releasedAt":"2026-04-09","name":"Grok 4.20 Non-Reasoning","developer":"X AI","description":"Grok 4.20 Non-Reasoning — a general-purpose language model optimized for standard text generation and conversational tasks, without extended reasoning capabilities.","contextLength":2000000,"outputMax":1999000,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=x-ai%2Fgrok-4-20-0309-non-reasoning&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["grok-4-20-0309-non-reasoning"],"tags":["playground:chat","tier:tier_2"]},{"id":"x-ai/grok-code-fast-1","info":{"releasedAt":"2025-09-30","name":"Grok Code Fast 1","developer":"X AI","description":"A speedy and economical reasoning model that excels at agentic coding with function calling and structured outputs.","contextLength":256000,"outputMax":255000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/xai/grok-code-fast-1","docsJson":"https://api.aimlapi.com/docs-json?model=x-ai%2Fgrok-code-fast-1&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["grok-code-fast-1"],"tags":["playground:chat","tier:tier_2","playground:code"]},{"id":"x-ai/grok-build-0-1","info":{"releasedAt":"2026-06-02","name":"Grok Build 0.1","developer":"X AI","description":"Grok Build 0.1 is a coding and agentic model from xAI for software development workflows, tool usage, structured reasoning, and multi-step task execution.","url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=x-ai%2Fgrok-build-0-1&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["xai/grok-build-0-1","grok-build-0-1"],"tags":["playground:chat","tier:tier_2","playground:code"]},{"id":"x-ai/grok-imagine-image","info":{"releasedAt":"2026-03-03","name":"Grok Imagine Image","developer":"X AI","description":"Grok Imagine Image is a lightweight text-to-image model by xAI optimized for fast and cost-efficient image generation.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/image-models/xai","docsJson":"https://api.aimlapi.com/docs-json?model=x-ai%2Fgrok-imagine-image&endpoint=openai%2Fimage-generations"},"type":"openai/image-generations","aliases":["grok-imagine-image-2026-03-02"],"tags":["playground:image","tier:tier_2"]},{"id":"x-ai/grok-imagine-image-pro","info":{"releasedAt":"2026-03-03","name":"Grok Imagine Image Pro","developer":"X AI","description":"Grok Imagine Image Pro is an advanced text-to-image model by xAI designed for high-quality image generation with improved detail and prompt fidelity.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/image-models/xai","docsJson":"https://api.aimlapi.com/docs-json?model=x-ai%2Fgrok-imagine-image-pro&endpoint=openai%2Fimage-generations"},"type":"openai/image-generations","aliases":[],"tags":["playground:image","tier:tier_2"]},{"id":"x-ai/grok-imagine-video","info":{"releasedAt":"2026-06-01","name":"Grok Imagine Video","developer":"X AI","description":"Grok Imagine Video is an image-to-video generation model by xAI that transforms static images into short animated video clips with coherent motion and visual consistency.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/video-models/xai","docsJson":"https://api.aimlapi.com/docs-json?model=x-ai%2Fgrok-imagine-video&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":["xai/grok-imagine-video"],"tags":["playground:video","tier:tier_2"]},{"id":"x-ai/grok-imagine-video-1.5-preview","info":{"releasedAt":"2026-06-01","name":"Grok Imagine Video 1.5 Preview","developer":"X AI","description":"Grok Imagine Video 1.5 Preview is an image-to-video generation model by xAI for transforming images into animated video sequences, suited for social content, visual concepts and motion generation.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/video-models/xai","docsJson":"https://api.aimlapi.com/docs-json?model=x-ai%2Fgrok-imagine-video-1.5-preview&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":["xai/grok-imagine-video-1.5-preview"],"tags":["playground:video","tier:tier_2"]},{"id":"zhipu/glm-4.5","info":{"releasedAt":"2025-09-09","name":"GLM 4.5","developer":"Zhipu AI","description":"Advanced version of GLM-4.5 with enhanced capabilities and web search integration","contextLength":128000,"outputMax":98000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/zhipu/glm-4.5","docsJson":"https://api.aimlapi.com/docs-json?model=zhipu%2Fglm-4.5&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["glm-4.5"],"tags":["playground:chat","tier:tier_2"]},{"id":"zhipu/glm-4.5-air","info":{"releasedAt":"2025-09-09","name":"GLM 4.5 Air","developer":"Zhipu AI","description":"Lightweight version of GLM-4.5 for cost-effective applications","contextLength":128000,"outputMax":98000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/zhipu/glm-4.5-air","docsJson":"https://api.aimlapi.com/docs-json?model=zhipu%2Fglm-4.5-air&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["glm-4.5-air"],"tags":["playground:chat","tier:tier_2"]},{"id":"zhipu/glm-4.6","info":{"releasedAt":"2025-10-02","name":"GLM 4.6","developer":"Zhipu AI","description":"Advanced version of GLM-4.6 with web search integration and enhanced capabilities","contextLength":200000,"outputMax":128000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/zhipu/glm-4.6","docsJson":"https://api.aimlapi.com/docs-json?model=zhipu%2Fglm-4.6&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["glm-4.6"],"tags":["playground:chat","tier:tier_2"]},{"id":"zhipu/glm-4.7","info":{"releasedAt":"2025-12-23","name":"GLM 4.7","developer":"Zhipu AI","description":"GLM-4.7 is Zhipu AI flagship text LLM optimized for agentic coding and stable multi-step reasoning, supporting long-context workflows.","contextLength":200000,"outputMax":128000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/zhipu/glm-4.7","docsJson":"https://api.aimlapi.com/docs-json?model=zhipu%2Fglm-4.7&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["glm-4.7"],"tags":["playground:chat","tier:tier_2"]},{"id":"zhipu/glm-5","info":{"releasedAt":"2026-02-12","name":"GLM 5","developer":"Zhipu AI","description":"GLM-5 is Zhipu AI next-generation 745B MoE LLM for high-quality text generation and reasoning, optimized for chat, long-form content, and instruction-following tasks.","contextLength":200000,"outputMax":128000,"url":"","docsUrl":"https://docs.aimlapi.com/api-references/text-models-llm/zhipu/glm-5","docsJson":"https://api.aimlapi.com/docs-json?model=zhipu%2Fglm-5&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["glm-5"],"tags":["playground:chat","tier:tier_2"]},{"id":"zhipu/glm-5.1","info":{"releasedAt":"2026-04-08","name":"GLM 5.1","developer":"Zhipu AI","description":"","contextLength":200000,"outputMax":128000,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=zhipu%2Fglm-5.1&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["glm-5.1"],"tags":["playground:chat","tier:tier_2"]},{"id":"zhipu/glm-5.2","info":{"releasedAt":"2026-06-16","name":"GLM 5.2","developer":"Zhipu AI","description":"GLM-5.2 is Zhipu AI flagship MoE LLM with a 1M-token context window, optimized for agentic coding, tool use, reasoning, and long-context tasks.","contextLength":1000000,"outputMax":131072,"url":"","docsUrl":"","isHottest":true,"docsJson":"https://api.aimlapi.com/docs-json?model=zhipu%2Fglm-5.2&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["glm-5.2"],"tags":["playground:chat","tier:tier_2"]},{"id":"zhipu/glm-ocr","info":{"releasedAt":"2026-02-09","name":"GLM-OCR","developer":"Zhipu AI","description":"GLM-OCR is a document understanding model for extracting text and structured content from images and documents.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/vision-models/ocr-optical-character-recognition/zhipu/glm-ocr","docsJson":"https://api.aimlapi.com/docs-json?model=zhipu%2Fglm-ocr&endpoint=internal%2Foptical-character-recognition"},"type":"internal/optical-character-recognition","aliases":["glm-ocr"],"tags":["playground:ocr","tier:tier_2"]},{"id":"zhipu/glm-5-1","info":{"releasedAt":"2026-04-08","name":"GLM 5.1","developer":"Zhipu AI","description":"","contextLength":200000,"outputMax":128000,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=zhipu%2Fglm-5-1&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":[],"tags":["playground:chat","tier:tier_2"]},{"id":"reve/create-image","info":{"releasedAt":"2025-10-13","name":"Reve Image Create","developer":"Reve AI","description":"Create images from a text description using Reve AI's advanced image generation model.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/image-models/reve/reve-create-image","docsJson":"https://api.aimlapi.com/docs-json?model=reve%2Fcreate-image&endpoint=openai%2Fimage-generations"},"type":"openai/image-generations","aliases":[],"tags":["playground:image","tier:tier_2"]},{"id":"reve/edit-image","info":{"releasedAt":"2025-10-13","name":"Reve Image Edit","developer":"Reve AI","description":"Edit images based on a text description using Reve AI's image editing capabilities.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/image-models/reve/reve-edit-image","docsJson":"https://api.aimlapi.com/docs-json?model=reve%2Fedit-image&endpoint=openai%2Fimage-generations"},"type":"openai/image-generations","aliases":[],"tags":["playground:image","tier:tier_2"]},{"id":"reve/remix-edit-image","info":{"releasedAt":"2025-10-13","name":"Reve Image Remix","developer":"Reve AI","description":"Create images from a text description and reference images using Reve AI's remix capabilities.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/image-models/reve/reve-remix-edit-image","docsJson":"https://api.aimlapi.com/docs-json?model=reve%2Fremix-edit-image&endpoint=openai%2Fimage-generations"},"type":"openai/image-generations","aliases":[],"tags":["playground:image","tier:tier_2"]},{"id":"topaz-labs/sharpen","info":{"releasedAt":"2025-11-17","developer":"Topaz Labs","description":"Sharpening model for enhancing image clarity and reducing blur","name":"Sharpen","url":"","docsUrl":"https://docs.aimlapi.com/api-references/image-models/topaz-labs/sharpen","docsJson":"https://api.aimlapi.com/docs-json?model=topaz-labs%2Fsharpen&endpoint=openai%2Fimage-generations"},"type":"openai/image-generations","aliases":["sharpen"],"tags":["playground:image","tier:tier_2"]},{"id":"topaz-labs/sharpen-gen","info":{"releasedAt":"2025-11-17","developer":"Topaz Labs","description":"Topaz Sharpen Generative uses AI to intelligently recover fine detail and sharpness in images using generative techniques.","name":"Sharpen Generative","url":"","docsUrl":"https://docs.aimlapi.com/api-references/image-models/topaz-labs/sharpen-generative","docsJson":"https://api.aimlapi.com/docs-json?model=topaz-labs%2Fsharpen-gen&endpoint=openai%2Fimage-generations"},"type":"openai/image-generations","aliases":["sharpen-gen"],"tags":["playground:image","tier:tier_2"]},{"id":"kling-video/v1/standard/image-to-video","info":{"releasedAt":"2025-11-28","name":"Kling 1.0 Standard Image to Video","developer":"Kling AI","description":"Kling AI Image-to-Video generates high-quality videos from images using advanced AI techniques for dynamic visual storytelling.","url":"https://aimlapi.com/models/kling-ai-image-to-video","docsUrl":"https://docs.aimlapi.com/api-references/video-models/kling-ai/v1-standard-image-to-video","docsJson":"https://api.aimlapi.com/docs-json?model=kling-video%2Fv1%2Fstandard%2Fimage-to-video&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":[],"tags":["playground:video","tier:tier_2"]},{"id":"kling-video/v1/standard/text-to-video","info":{"releasedAt":"2025-11-28","name":"Kling 1.0 Standard Text to Video","developer":"Kling AI","description":"Kling AI Text-to-Video generates high-quality videos from text prompts using advanced AI techniques for dynamic visual storytelling.","url":"https://aimlapi.com/models/kling-ai-text-to-video-api","docsUrl":"https://docs.aimlapi.com/api-references/video-models/kling-ai/v1-standard-text-to-video","docsJson":"https://api.aimlapi.com/docs-json?model=kling-video%2Fv1%2Fstandard%2Ftext-to-video&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":[],"tags":["playground:video","tier:tier_2"]},{"id":"kling-video/v1/pro/image-to-video","info":{"releasedAt":"2025-11-28","name":"Kling 1.0 Pro Image to Video","developer":"Kling AI","description":"Kling AI Image-to-Video generates high-quality videos from images using advanced AI techniques for dynamic visual storytelling.","url":"https://aimlapi.com/models/kling-ai-image-to-video","docsUrl":"https://docs.aimlapi.com/api-references/video-models/kling-ai/v1-pro-image-to-video","docsJson":"https://api.aimlapi.com/docs-json?model=kling-video%2Fv1%2Fpro%2Fimage-to-video&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":[],"tags":["playground:video","tier:tier_2"]},{"id":"kling-video/v1/pro/text-to-video","info":{"releasedAt":"2025-11-28","name":"Kling 1.0 Pro Text to Video","developer":"Kling AI","description":"Kling AI Text-to-Video generates high-quality videos from text prompts using advanced AI techniques for dynamic visual storytelling.","url":"https://aimlapi.com/models/kling-ai-text-to-video-api","docsUrl":"https://docs.aimlapi.com/api-references/video-models/kling-ai/v1-pro-text-to-video","docsJson":"https://api.aimlapi.com/docs-json?model=kling-video%2Fv1%2Fpro%2Ftext-to-video&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":[],"tags":["playground:video","tier:tier_2"]},{"id":"kling-video/v1.5/pro/image-to-video","info":{"releasedAt":"2025-11-28","name":"Kling 1.5 Pro Image to Video","developer":"Kling AI","description":"Kling AI 1.5 Image-to-Video generates high-quality videos from images using advanced AI techniques for dynamic visual storytelling.","url":"https://aimlapi.com/models/kling-ai-image-to-video","docsUrl":"https://docs.aimlapi.com/api-references/video-models/kling-ai","docsJson":"https://api.aimlapi.com/docs-json?model=kling-video%2Fv1.5%2Fpro%2Fimage-to-video&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":[],"tags":["playground:video","tier:tier_2"]},{"id":"kling-video/v1.5/pro/text-to-video","info":{"releasedAt":"2025-11-28","name":"Kling 1.5 Pro Text to Video","developer":"Kling AI","description":"Kling AI 1.5 Text-to-Video generates high-quality videos from text prompts using advanced AI techniques for dynamic visual storytelling.","url":"https://aimlapi.com/models/kling-ai-text-to-video-api","docsUrl":"https://docs.aimlapi.com/api-references/video-models/kling-ai","docsJson":"https://api.aimlapi.com/docs-json?model=kling-video%2Fv1.5%2Fpro%2Ftext-to-video&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":[],"tags":["playground:video","tier:tier_2"]},{"id":"kling-video/v1.6/standard/text-to-video","info":{"releasedAt":"2025-11-24","name":"Kling 1.6 Standard Text to Video","developer":"Kling AI","description":"Kling 1.6 enhances video generation with improved prompt adherence and dynamic visuals for diverse creative applications.","url":"https://aimlapi.com/models/kling-1-6-standard","docsUrl":"https://docs.aimlapi.com/api-references/video-models/kling-ai/v1.6-standard-text-to-video","docsJson":"https://api.aimlapi.com/docs-json?model=kling-video%2Fv1.6%2Fstandard%2Ftext-to-video&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":[],"tags":["playground:video","tier:tier_2"]},{"id":"kling-video/v1.6/standard/image-to-video","info":{"releasedAt":"2025-11-24","name":"Kling 1.6 Standard Image to Video","developer":"Kling AI","description":"Kling 1.6 enhances video generation with improved prompt adherence and dynamic visuals for diverse creative applications.","url":"https://aimlapi.com/models/kling-1-6-standard","docsUrl":"https://docs.aimlapi.com/api-references/video-models/kling-ai/v1.6-standart-image-to-video","docsJson":"https://api.aimlapi.com/docs-json?model=kling-video%2Fv1.6%2Fstandard%2Fimage-to-video&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":[],"tags":["playground:video","tier:tier_2"]},{"id":"kling-video/v1.6/pro/image-to-video","info":{"releasedAt":"2025-11-28","name":"Kling 1.6 Pro Image to Video","developer":"Kling AI","description":"Kling 1.6 enhances video generation with improved prompt adherence and dynamic visuals for diverse creative applications.","url":"https://aimlapi.com/models/kling-1-6-pro-api","docsUrl":"https://docs.aimlapi.com/api-references/video-models/kling-ai/v1.6-pro-image-to-video","docsJson":"https://api.aimlapi.com/docs-json?model=kling-video%2Fv1.6%2Fpro%2Fimage-to-video&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":[],"tags":["playground:video","tier:tier_2"]},{"id":"kling-video/v1.6/pro/text-to-video","info":{"releasedAt":"2025-11-28","name":"Kling 1.6 Pro Text to Video","developer":"Kling AI","description":"Kling 1.6 Pro text-to-video generates high-quality videos from text prompts with enhanced motion and visual fidelity.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/video-models/kling-ai/v1.6-pro-text-to-video","docsJson":"https://api.aimlapi.com/docs-json?model=kling-video%2Fv1.6%2Fpro%2Ftext-to-video&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":[],"tags":["playground:video","tier:tier_2"]},{"id":"klingai/kling-video-v1.6-pro-effects","info":{"releasedAt":"2025-11-28","name":"Kling 1.6 Pro Effects","developer":"Kling AI","description":"Kling 1.6 Pro Effects applies cinematic visual effects to videos using advanced AI motion control.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/video-models/kling-ai/v1.6-pro-effects","docsJson":"https://api.aimlapi.com/docs-json?model=klingai%2Fkling-video-v1.6-pro-effects&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":[],"tags":["playground:video","tier:tier_2"]},{"id":"klingai/kling-video-v1.6-standard-effects","info":{"releasedAt":"2025-11-28","name":"Kling 1.6 Standard Effects","developer":"Kling AI","description":"Kling 1.6 Standard Effects applies AI-driven visual effects to videos at a cost-effective quality tier.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/video-models/kling-ai/v1.6-standard-effects","docsJson":"https://api.aimlapi.com/docs-json?model=klingai%2Fkling-video-v1.6-standard-effects&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":[],"tags":["playground:video","tier:tier_2"]},{"id":"kling-video/v1.6/standard/multi-image-to-video","info":{"releasedAt":"2025-11-28","name":"Kling 1.6 Standard Multi Image to Video","developer":"Kling AI","description":"Kling 1.6 multi-image-to-video creates dynamic videos from multiple input images with enhanced temporal consistency and natural transitions.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/video-models/kling-ai/v1.6-standard-multi-image-to-video","docsJson":"https://api.aimlapi.com/docs-json?model=kling-video%2Fv1.6%2Fstandard%2Fmulti-image-to-video&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":[],"tags":["playground:video","tier:tier_2"]},{"id":"klingai/v2-master-image-to-video","info":{"releasedAt":"2025-11-28","name":"Kling 2.0 Master Image to Video","developer":"Kling AI","description":"Kling 2.0 Master generates high-fidelity videos from images with state-of-the-art motion realism.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/video-models/kling-ai/v2-master-image-to-video","docsJson":"https://api.aimlapi.com/docs-json?model=klingai%2Fv2-master-image-to-video&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":[],"tags":["playground:video","tier:tier_2"]},{"id":"klingai/v2-master-text-to-video","info":{"releasedAt":"2025-11-28","name":"Kling 2.0 Master Text to Video","developer":"Kling AI","description":"Kling 2.0 Master generates high-fidelity videos from text prompts with state-of-the-art motion realism.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/video-models/kling-ai/v2-master-text-to-video","docsJson":"https://api.aimlapi.com/docs-json?model=klingai%2Fv2-master-text-to-video&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":[],"tags":["playground:video","tier:tier_2"]},{"id":"kling-video/v2.1/standard/image-to-video","info":{"releasedAt":"2025-11-28","name":"Kling 2.1 Standard Image to Video","developer":"Kling AI","description":"Kling 2.1 enhances video generation with improved prompt adherence for diverse creative applications.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/video-models/kling-ai/v2.1-standard-image-to-video","docsJson":"https://api.aimlapi.com/docs-json?model=kling-video%2Fv2.1%2Fstandard%2Fimage-to-video&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":[],"tags":["playground:video","tier:tier_2"]},{"id":"klingai/v2.1-master-image-to-video","info":{"releasedAt":"2025-11-28","name":"Kling 2.1 Master Image to Video","developer":"Kling AI","description":"Kling 2.1 Master image-to-video generates high-fidelity videos with the highest motion quality in the Kling 2.1 lineup.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/video-models/kling-ai/v2.1-master-image-to-video","docsJson":"https://api.aimlapi.com/docs-json?model=klingai%2Fv2.1-master-image-to-video&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":[],"tags":["playground:video","tier:tier_2"]},{"id":"klingai/v2.1-master-text-to-video","info":{"releasedAt":"2025-11-28","name":"Kling 2.1 Master Text to Video","developer":"Kling AI","description":"Kling 2.1 Master text-to-video generates premium videos from text with the highest quality in the Kling 2.1 series.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/video-models/kling-ai/v2.1-master-text-to-video","docsJson":"https://api.aimlapi.com/docs-json?model=klingai%2Fv2.1-master-text-to-video&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":[],"tags":["playground:video","tier:tier_2"]},{"id":"kling-video/v2.1/pro/image-to-video","info":{"releasedAt":"2025-11-28","name":"Kling 2.1 Pro Image to Video","developer":"Kling AI","description":"Kling 2.1 enhances video generation with improved prompt adherence for diverse creative applications.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/video-models/kling-ai/v2.1-pro-image-to-video","docsJson":"https://api.aimlapi.com/docs-json?model=kling-video%2Fv2.1%2Fpro%2Fimage-to-video&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":[],"tags":["playground:video","tier:tier_2"]},{"id":"klingai/v2.5-turbo/pro/image-to-video","info":{"releasedAt":"2025-11-24","name":"Kling 2.5 Turbo Pro Image to Video","developer":"Kling AI","description":"Kling 2.5 Turbo Pro generates high-quality videos from images with improved motion quality and faster processing.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/video-models/kling-ai/v2.5-turbo-pro-image-to-video","docsJson":"https://api.aimlapi.com/docs-json?model=klingai%2Fv2.5-turbo%2Fpro%2Fimage-to-video&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":[],"tags":["playground:video","tier:tier_2"]},{"id":"klingai/v2.5-turbo/pro/text-to-video","info":{"releasedAt":"2025-11-24","name":"Kling 2.5 Turbo Pro Text to Video","developer":"Kling AI","description":"Kling 2.5 Turbo Pro generates high-quality videos from text prompts with improved motion and faster processing.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/video-models/kling-ai/v2.5-turbo-pro-text-to-video","docsJson":"https://api.aimlapi.com/docs-json?model=klingai%2Fv2.5-turbo%2Fpro%2Ftext-to-video&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":[],"tags":["playground:video","tier:tier_2"]},{"id":"klingai/avatar-standard","info":{"releasedAt":"2025-11-24","name":"Kling Avatar Standard","developer":"Kling AI","description":"Kling Avatar creates dynamic videos from avatar reference images with audio synchronization using standard mode for cost-effective generation.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/video-models/kling-ai/avatar-standard","docsJson":"https://api.aimlapi.com/docs-json?model=klingai%2Favatar-standard&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":[],"tags":["playground:video","tier:tier_2"]},{"id":"klingai/avatar-pro","info":{"releasedAt":"2025-11-24","name":"Kling Avatar Professional","developer":"Kling AI","description":"Kling Avatar creates dynamic videos from avatar reference images with audio synchronization using professional mode for higher quality and longer duration.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/video-models/kling-ai/avatar-pro","docsJson":"https://api.aimlapi.com/docs-json?model=klingai%2Favatar-pro&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":[],"tags":["playground:video","tier:tier_2"]},{"id":"klingai/image-o1","info":{"releasedAt":"2025-12-03","name":"Kling Image O1","developer":"Kling AI","description":"Kling Image O1 applies reasoning-enhanced AI to generate highly accurate and detailed images from text prompts.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/image-models/kling-ai/image-o1","docsJson":"https://api.aimlapi.com/docs-json?model=klingai%2Fimage-o1&endpoint=openai%2Fimage-generations"},"type":"openai/image-generations","aliases":[],"tags":["playground:image","tier:tier_2"]},{"id":"klingai/video-o1-image-to-video","info":{"releasedAt":"2025-12-03","name":"Kling Video O1 Image to Video","developer":"Kling AI","description":"Kling Video O1 applies reasoning-enhanced video generation from images for more accurate motion and scene understanding.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/video-models/kling-ai/video-o1-image-to-video","docsJson":"https://api.aimlapi.com/docs-json?model=klingai%2Fvideo-o1-image-to-video&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":[],"tags":["playground:video","tier:tier_2"]},{"id":"klingai/video-o1-reference-to-video","info":{"releasedAt":"2025-12-03","name":"Kling Video O1 Reference to Video","developer":"Kling AI","description":"Kling Video O1 Reference-to-Video creates videos that maintain consistent appearance from reference images using AI reasoning.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/video-models/kling-ai/video-o1-reference-to-video","docsJson":"https://api.aimlapi.com/docs-json?model=klingai%2Fvideo-o1-reference-to-video&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":[],"tags":["playground:video","tier:tier_2"]},{"id":"klingai/video-o1-video-to-video-edit","info":{"releasedAt":"2025-12-03","name":"Kling Video O1 Video to Video Edit","developer":"Kling AI","description":"Kling Video O1 Video-to-Video Edit applies AI-driven edits to existing videos with reasoning-enhanced accuracy.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/video-models/kling-ai/video-o1-video-to-video-edit","docsJson":"https://api.aimlapi.com/docs-json?model=klingai%2Fvideo-o1-video-to-video-edit&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":[],"tags":["playground:video","tier:tier_2"]},{"id":"klingai/video-o1-video-to-video-reference","info":{"releasedAt":"2025-12-03","name":"Kling O1 Video to Video Reference","developer":"Kling AI","description":"Kling Video O1 Video-to-Video Reference generates new videos guided by both an input video and reference images.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/video-models/kling-ai/video-o1-video-to-video-reference","docsJson":"https://api.aimlapi.com/docs-json?model=klingai%2Fvideo-o1-video-to-video-reference&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":[],"tags":["playground:video","tier:tier_2"]},{"id":"klingai/video-v2-6-pro-image-to-video","info":{"releasedAt":"2025-12-03","name":"Kling 2.6 Pro Image to Video","developer":"Kling AI","description":"Kling 2.6 Pro image-to-video delivers next-generation video quality from images with advanced motion control.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/video-models/kling-ai/video-v2.6-pro-image-to-video","docsJson":"https://api.aimlapi.com/docs-json?model=klingai%2Fvideo-v2-6-pro-image-to-video&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":[],"tags":["playground:video","tier:tier_2"]},{"id":"klingai/video-v2-6-pro-text-to-video","info":{"releasedAt":"2025-12-03","name":"Kling 2.6 Pro Text to Video","developer":"Kling AI","description":"Kling 2.6 Pro text-to-video delivers next-generation video quality from text prompts with advanced motion control.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/video-models/kling-ai/video-v2-6-pro-text-to-video","docsJson":"https://api.aimlapi.com/docs-json?model=klingai%2Fvideo-v2-6-pro-text-to-video&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":[],"tags":["playground:video","tier:tier_2"]},{"id":"klingai/video-v2-6-motion-control","info":{"releasedAt":"2026-06-10","name":"Kling 2.6 Motion Control","developer":"Kling AI","description":"Kling 2.6 Motion Control transfers motion from a reference video onto a character image, with selectable std/pro generation modes.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/video-models/kling-ai/video-v2.6-motion-control","docsJson":"https://api.aimlapi.com/docs-json?model=klingai%2Fvideo-v2-6-motion-control&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":[],"tags":["playground:video","tier:tier_2"]},{"id":"klingai/video-v3-standard-text-to-video","info":{"releasedAt":"2026-02-05","name":"Kling 3.0 Standard Text to Video","description":"Kling 3.0 Standard text-to-video generates high-quality videos from text prompts with improved temporal consistency.","developer":"Kling AI","url":"","docsUrl":"https://docs.aimlapi.com/api-references/video-models/kling-ai/v3-standard-text-to-video","docsJson":"https://api.aimlapi.com/docs-json?model=klingai%2Fvideo-v3-standard-text-to-video&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":[],"tags":["playground:video","tier:tier_2"]},{"id":"klingai/video-v3-standard-image-to-video","info":{"releasedAt":"2026-02-05","name":"Kling 3.0 Standard Image to Video","description":"Kling 3.0 Standard image-to-video animates images into smooth, high-quality videos with improved temporal consistency.","developer":"Kling AI","url":"","docsUrl":"https://docs.aimlapi.com/api-references/video-models/kling-ai/v3-standard-image-to-video","docsJson":"https://api.aimlapi.com/docs-json?model=klingai%2Fvideo-v3-standard-image-to-video&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":[],"tags":["playground:video","tier:tier_2"]},{"id":"klingai/video-v3-pro-text-to-video","info":{"releasedAt":"2026-02-05","name":"Kling 3.0 Pro Text to Video","description":"Kling 3.0 Pro text-to-video generates premium videos from text prompts with the highest quality in the Kling 3.0 series.","developer":"Kling AI","url":"","docsUrl":"https://docs.aimlapi.com/api-references/video-models/kling-ai/v3-pro-text-to-video","isHottest":true,"docsJson":"https://api.aimlapi.com/docs-json?model=klingai%2Fvideo-v3-pro-text-to-video&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":[],"tags":["playground:video","tier:tier_2"]},{"id":"klingai/video-v3-pro-image-to-video","info":{"releasedAt":"2026-02-05","name":"Kling 3.0 Pro Image to Video","description":"Kling 3.0 Pro image-to-video generates premium videos from images with the highest quality in the Kling 3.0 series.","developer":"Kling AI","url":"","docsUrl":"https://docs.aimlapi.com/api-references/video-models/kling-ai/v3-pro-image-to-video","docsJson":"https://api.aimlapi.com/docs-json?model=klingai%2Fvideo-v3-pro-image-to-video&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":[],"tags":["playground:video","tier:tier_2"]},{"id":"klingai/video-v3-standard-turbo-text-to-video","info":{"releasedAt":"2026-06-17","name":"Kling 3.0 Standard Turbo Text to Video","description":"Kling 3.0 Turbo Standard text-to-video turns prompts into fast, cost-efficient 720p videos with native audio.","developer":"Kling AI","url":"","docsUrl":"https://docs.aimlapi.com/api-references/video-models/kling-ai/v3-standard-turbo-text-to-video","docsJson":"https://api.aimlapi.com/docs-json?model=klingai%2Fvideo-v3-standard-turbo-text-to-video&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":[],"tags":["playground:video","tier:tier_2"]},{"id":"klingai/video-v3-standard-turbo-image-to-video","info":{"releasedAt":"2026-06-17","name":"Kling 3.0 Standard Turbo Image to Video","description":"Kling 3.0 Turbo Standard image-to-video animates first and last frame reference images into fast, cost-efficient 720p videos with native audio.","developer":"Kling AI","url":"","docsUrl":"https://docs.aimlapi.com/api-references/video-models/kling-ai/v3-standard-turbo-image-to-video","docsJson":"https://api.aimlapi.com/docs-json?model=klingai%2Fvideo-v3-standard-turbo-image-to-video&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":[],"tags":["playground:video","tier:tier_2"]},{"id":"klingai/video-v3-turbo-pro-text-to-video","info":{"releasedAt":"2026-06-17","name":"Kling 3.0 Turbo Pro Text to Video","description":"Kling 3.0 Turbo Pro text-to-video generates high-quality 1080p videos with improved lipsync and multishot generation capabilities.","developer":"Kling AI","url":"","docsUrl":"https://docs.aimlapi.com/api-references/video-models/kling-ai/v3-turbo-pro-text-to-video","docsJson":"https://api.aimlapi.com/docs-json?model=klingai%2Fvideo-v3-turbo-pro-text-to-video&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":[],"tags":["playground:video","tier:tier_2"]},{"id":"klingai/video-v3-turbo-pro-image-to-video","info":{"releasedAt":"2026-06-17","name":"Kling 3.0 Turbo Pro Image to Video","description":"Kling 3.0 Turbo Pro image-to-video generates high-quality 1080p videos from images with improved lipsync and multishot generation capabilities.","developer":"Kling AI","url":"","docsUrl":"https://docs.aimlapi.com/api-references/video-models/kling-ai/v3-turbo-pro-image-to-video","docsJson":"https://api.aimlapi.com/docs-json?model=klingai%2Fvideo-v3-turbo-pro-image-to-video&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":[],"tags":["playground:video","tier:tier_2"]},{"id":"klingai/video-v3-motion-control","info":{"releasedAt":"2026-06-10","name":"Kling 3.0 Motion Control","developer":"Kling AI","description":"Kling 3.0 Motion Control transfers motion from a reference video onto a character image at Kling 3.0 fidelity, with selectable std/pro generation modes.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/video-models/kling-ai/v3-motion-control","docsJson":"https://api.aimlapi.com/docs-json?model=klingai%2Fvideo-v3-motion-control&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":[],"tags":["playground:video","tier:tier_2"]},{"id":"pixverse/v5/text-to-video","info":{"releasedAt":"2025-11-05","name":"Pixverse v5 Text to Video","developer":"Pixverse","description":"Create dynamic videos from text prompts using PixVerse v5 advanced text-to-video AI technology.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/video-models/pixverse/v5-text-to-video","docsJson":"https://api.aimlapi.com/docs-json?model=pixverse%2Fv5%2Ftext-to-video&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":[],"tags":["playground:video","tier:tier_2"]},{"id":"pixverse/v5/image-to-video","info":{"releasedAt":"2025-11-05","name":"Pixverse v5 Image to Video","developer":"Pixverse","description":"Generate high-quality videos from images using PixVerse v5 with advanced AI video generation.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/video-models/pixverse/v5-5-image-to-video","docsJson":"https://api.aimlapi.com/docs-json?model=pixverse%2Fv5%2Fimage-to-video&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":[],"tags":["playground:video","tier:tier_2"]},{"id":"pixverse/v5/transition","info":{"releasedAt":"2025-11-05","name":"Pixverse v5 Transition","developer":"Pixverse","description":"Create seamless transitions between images using PixVerse v5 with advanced AI techniques.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/video-models/pixverse/v5-transition","docsJson":"https://api.aimlapi.com/docs-json?model=pixverse%2Fv5%2Ftransition&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":[],"tags":["playground:video","tier:tier_2"]},{"id":"pixverse/lip-sync","info":{"releasedAt":"2025-11-05","name":"Pixverse Lip Sync","developer":"Pixverse","description":"PixVerse Lip Sync generates videos with synchronized lip movements from audio and face image inputs.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/video-models/pixverse/lip-sync","docsJson":"https://api.aimlapi.com/docs-json?model=pixverse%2Flip-sync&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":[],"tags":["playground:video","tier:tier_2"]},{"id":"pixverse/v5.5/text-to-video","info":{"releasedAt":"2025-12-08","name":"Pixverse v5.5 Text to Video","developer":"Pixverse","description":"Create dynamic videos from text prompts using PixVerse v5.5 with audio-visual synchronization and multi-shot camera control.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/video-models/pixverse/v5-5-text-to-video","docsJson":"https://api.aimlapi.com/docs-json?model=pixverse%2Fv5.5%2Ftext-to-video&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":["pixverse/v5-5-text-to-video"],"tags":["playground:video","tier:tier_2"]},{"id":"pixverse/v5.5/image-to-video","info":{"releasedAt":"2025-12-08","name":"Pixverse v5.5 Image to Video","developer":"Pixverse","description":"Generate high-quality videos from images using PixVerse v5.5 with audio-visual synchronization and multi-shot camera control.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/video-models/pixverse/v5-5-image-to-video","docsJson":"https://api.aimlapi.com/docs-json?model=pixverse%2Fv5.5%2Fimage-to-video&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":["pixverse/v5-5-image-to-video"],"tags":["playground:video","tier:tier_2"]},{"id":"luma/ray-2","info":{"releasedAt":"2025-12-02","name":"Luma Dream Machine Ray-2","developer":"Luma AI","description":"Luma Ray-2 generates high-quality videos from text prompts or images with advanced AI techniques.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/video-models/luma-ai/luma-ray-2","docsJson":"https://api.aimlapi.com/docs-json?model=luma%2Fray-2&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":["ray-2"],"tags":["playground:video","tier:tier_2"]},{"id":"luma/ray-flash-2","info":{"releasedAt":"2025-12-02","name":"Luma Dream Machine Ray-Flash-2","developer":"Luma AI","description":"Luma Ray-Flash-2 is a faster, more cost-effective model for video generation.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/video-models/luma-ai/luma-ray-flash-2","docsJson":"https://api.aimlapi.com/docs-json?model=luma%2Fray-flash-2&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":["ray-flash-2"],"tags":["playground:video","tier:tier_2"]},{"id":"luma/uni-1","info":{"releasedAt":"2026-03-23","name":"Luma Uni-1","developer":"Luma AI","description":"Luma Uni-1 generates and edits images from text prompts with support for up to 9 reference images, styles, and web-search grounding.","url":"","docsUrl":"https://docs.agents.lumalabs.ai/guides/model/","docsJson":"https://api.aimlapi.com/docs-json?model=luma%2Funi-1&endpoint=openai%2Fimage-generations"},"type":"openai/image-generations","aliases":[],"tags":["playground:image","tier:tier_2"]},{"id":"luma/uni-1-max","info":{"releasedAt":"2026-03-23","name":"Luma Uni-1 Max","developer":"Luma AI","description":"Luma Uni-1 Max is the higher-quality image generation and editing variant of Uni-1 with the same parameters.","url":"","docsUrl":"https://docs.agents.lumalabs.ai/guides/model/","docsJson":"https://api.aimlapi.com/docs-json?model=luma%2Funi-1-max&endpoint=openai%2Fimage-generations"},"type":"openai/image-generations","aliases":[],"tags":["playground:image","tier:tier_2"]},{"id":"luma/ray-3.2","info":{"releasedAt":"2026-06-09","name":"Luma Ray-3.2","developer":"Luma AI","description":"Luma Ray-3.2 generates, edits, and reframes videos from text or images with HDR output, multi-keyframe control, and seamless looping.","url":"","docsUrl":"https://docs.agents.lumalabs.ai/guides/model/","docsJson":"https://api.aimlapi.com/docs-json?model=luma%2Fray-3.2&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":[],"tags":["playground:video","tier:tier_2"]},{"id":"runway/gen3a_turbo","info":{"releasedAt":"2025-12-04","developer":"Runway ML","description":"Runway Gen-3 Turbo generates high-quality videos from images quickly and efficiently, enhancing creative workflows","name":"Gen 3a Turbo","url":"https://aimlapi.com/models/runway-gen-3-turbo","docsUrl":"https://docs.aimlapi.com/api-references/video-models/runway/gen3a_turbo","docsJson":"https://api.aimlapi.com/docs-json?model=runway%2Fgen3a_turbo&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":["gen3a_turbo"],"tags":["playground:video","tier:tier_2"]},{"id":"runway/gen4_turbo","info":{"releasedAt":"2025-12-04","developer":"Runway ML","description":"Runway Gen-4 Turbo generates high-quality videos from images and text with fast processing and improved motion consistency.","name":"Gen 4 Turbo","url":"","docsUrl":"https://docs.aimlapi.com/api-references/video-models/runway/gen4_turbo","docsJson":"https://api.aimlapi.com/docs-json?model=runway%2Fgen4_turbo&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":["gen4_turbo"],"tags":["playground:video","tier:tier_2"]},{"id":"runway/gen4_aleph","info":{"releasedAt":"2025-12-04","developer":"Runway ML","description":"Runway Gen-4 Aleph is an advanced video generation model with enhanced realism and creative control.","name":"Gen 4 Aleph","url":"","docsUrl":"https://docs.aimlapi.com/api-references/video-models/runway/gen4_aleph","docsJson":"https://api.aimlapi.com/docs-json?model=runway%2Fgen4_aleph&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":["gen4_aleph"],"tags":["playground:video","tier:tier_2"]},{"id":"runway/act_two","info":{"releasedAt":"2025-12-04","developer":"Runway ML","description":"Runway Act Two creates expressive, full-body performance videos by transferring motion from a driving video to a subject.","name":"Runway Act Two","url":"","docsUrl":"https://docs.aimlapi.com/api-references/video-models/runway/act_two","docsJson":"https://api.aimlapi.com/docs-json?model=runway%2Fact_two&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":["act_two"],"tags":["playground:video","tier:tier_2"]},{"id":"magic/image-to-3d","info":{"releasedAt":"2025-12-08","developer":"Magic Inc","description":"Magic Inc image-to-3D model generates 3D assets from single 2D images for game, VR, and design workflows.","name":"Magic Image to 3D","url":"","docsUrl":"https://docs.aimlapi.com/api-references/3d-generating-models","docsJson":"https://api.aimlapi.com/docs-json?model=magic%2Fimage-to-3d&endpoint=openai%2Fimage-generations"},"type":"openai/image-generations","aliases":[],"tags":["tier:tier_2","playground:image_3d"]},{"id":"magic/text-to-video","info":{"releasedAt":"2025-12-26","developer":"Magic Inc","description":"Magic Inc text-to-video model generates dynamic videos from text descriptions using advanced AI techniques.","name":"Magic Text to Video","url":"","docsUrl":"https://docs.aimlapi.com/api-references/video-models/magic/text-to-video","docsJson":"https://api.aimlapi.com/docs-json?model=magic%2Ftext-to-video&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":[],"tags":["playground:video","tier:tier_2"]},{"id":"magic/image-to-video","info":{"releasedAt":"2025-12-26","developer":"Magic Inc","description":"Magic Inc image-to-video model animates still images into smooth, coherent videos.","name":"Magic Image to Video","url":"","docsUrl":"https://docs.aimlapi.com/api-references/video-models/magic/image-to-video","docsJson":"https://api.aimlapi.com/docs-json?model=magic%2Fimage-to-video&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":[],"tags":["playground:video","tier:tier_2"]},{"id":"magic/video-to-video","info":{"releasedAt":"2025-12-26","developer":"Magic Inc","description":"Magic Inc video-to-video model transforms and enhances existing videos using AI-driven style and motion editing.","name":"Magic Video to Video","url":"","docsUrl":"https://docs.aimlapi.com/api-references/video-models/magic/video-to-video","docsJson":"https://api.aimlapi.com/docs-json?model=magic%2Fvideo-to-video&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":[],"tags":["playground:video","tier:tier_2"]},{"id":"mistral/labs-leanstral-1-5","info":{"releasedAt":"2026-06-30","name":"Leanstral 1.5","developer":"Mistral AI","description":"Leanstral 1.5 is a Lean 4 formal proof engineering model optimized for automated theorem proving and autoformalization.","contextLength":256000,"url":"","docsUrl":"https://docs.mistral.ai/models/model-cards/leanstral-1-5","docsJson":"https://api.aimlapi.com/docs-json?model=mistral%2Flabs-leanstral-1-5&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["labs-leanstral-1-5"],"tags":["playground:chat","tier:tier_2","playground:code"]},{"id":"mistral/mistral-ocr-latest","info":{"releasedAt":"2025-12-16","name":"Mistral OCR","developer":"Mistral AI","description":"Mistral OCR is a document understanding model for extracting text and structured content from PDFs and images.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/vision-models/ocr-optical-character-recognition/mistral-ai/mistral-ocr-latest","docsJson":"https://api.aimlapi.com/docs-json?model=mistral%2Fmistral-ocr-latest&endpoint=internal%2Foptical-character-recognition"},"type":"internal/optical-character-recognition","aliases":["mistral-ocr-latest"],"tags":["playground:ocr","tier:tier_2"]},{"id":"mistral/mistral-ocr-2512","info":{"releasedAt":"2026-06-16","name":"Mistral OCR 3","developer":"Mistral AI","description":"Mistral OCR 3 is a document understanding model that extracts text and embedded images from PDFs and images with high fidelity, producing markdown output with HTML-based table reconstruction. Fully backward compatible with Mistral OCR 2.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/vision-models/ocr-optical-character-recognition/mistral-ai/mistral-ocr-2512","docsJson":"https://api.aimlapi.com/docs-json?model=mistral%2Fmistral-ocr-2512&endpoint=internal%2Foptical-character-recognition"},"type":"internal/optical-character-recognition","aliases":["mistral-ocr-2512"],"tags":["playground:ocr","tier:tier_2"]},{"id":"mistral/mistral-ocr-4-0","info":{"releasedAt":"2026-06-23","name":"Mistral OCR 4","developer":"Mistral AI","description":"Mistral OCR 4 is Mistral's most advanced document extraction and understanding model, adding native paragraph-level bounding box extraction and structural block labels on top of high-fidelity text, table, and image extraction from PDFs and images. Fully backward compatible with Mistral OCR 3.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/vision-models/ocr-optical-character-recognition/mistral-ai/mistral-ocr-4-0","docsJson":"https://api.aimlapi.com/docs-json?model=mistral%2Fmistral-ocr-4-0&endpoint=internal%2Foptical-character-recognition"},"type":"internal/optical-character-recognition","aliases":["mistral-ocr-4-0"],"tags":["playground:ocr","tier:tier_2"]},{"id":"mistral/leanstral-1-5","info":{"releasedAt":"2026-06-30","name":"Leanstral 1.5","developer":"Mistral AI","description":"Leanstral 1.5 is a Lean 4 formal proof engineering model optimized for automated theorem proving and autoformalization.","contextLength":256000,"url":"","docsUrl":"https://docs.mistral.ai/models/model-cards/leanstral-1-5","docsJson":"https://api.aimlapi.com/docs-json?model=mistral%2Fleanstral-1-5&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["leanstral-1-5","labs-leanstral-1-5","mistral/labs-leanstral-1-5"],"tags":["playground:chat","tier:tier_2","playground:code"]},{"id":"mistral/mistral-ocr-3","info":{"releasedAt":"2026-06-16","name":"Mistral OCR 3","developer":"Mistral AI","description":"Mistral OCR 3 is a document understanding model that extracts text and embedded images from PDFs and images with high fidelity, producing markdown output with HTML-based table reconstruction. Fully backward compatible with Mistral OCR 2.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/vision-models/ocr-optical-character-recognition/mistral-ai/mistral-ocr-2512","docsJson":"https://api.aimlapi.com/docs-json?model=mistral%2Fmistral-ocr-3&endpoint=internal%2Foptical-character-recognition"},"type":"internal/optical-character-recognition","aliases":["mistral-ocr-3"],"tags":["playground:ocr","tier:tier_2"]},{"id":"mistral/mistral-ocr-4","info":{"releasedAt":"2026-06-23","name":"Mistral OCR 4","developer":"Mistral AI","description":"Mistral OCR 4 is Mistral's most advanced document extraction and understanding model, adding native paragraph-level bounding box extraction and structural block labels on top of high-fidelity text, table, and image extraction from PDFs and images. Fully backward compatible with Mistral OCR 3.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/vision-models/ocr-optical-character-recognition/mistral-ai/mistral-ocr-4-0","docsJson":"https://api.aimlapi.com/docs-json?model=mistral%2Fmistral-ocr-4&endpoint=internal%2Foptical-character-recognition"},"type":"internal/optical-character-recognition","aliases":["mistral-ocr-4"],"tags":["playground:ocr","tier:tier_2"]},{"id":"deepgram/nova-2-general","info":{"releasedAt":"2025-12-30","name":"Nova-2 General","developer":"Deepgram","description":"Nova-2: Advanced, versatile ASR model for diverse transcription needs.","url":"https://aimlapi.com/models/deepgram-nova-2","docsUrl":"https://docs.aimlapi.com/api-references/speech-models/speech-to-text/deepgram/nova-2","docsJson":"https://api.aimlapi.com/docs-json?model=deepgram%2Fnova-2-general&endpoint=internal%2Fspeech-to-text%2Fsubmit"},"type":"internal/speech-to-text/submit","aliases":["nova-2-general","#g1_nova-2-general"],"tags":["playground:stt","tier:tier_2"]},{"id":"deepgram/nova-2-meeting","info":{"releasedAt":"2025-12-30","name":"Nova-2 Meeting","developer":"Deepgram","description":"Nova-2: Advanced, versatile ASR model for diverse transcription needs.","url":"https://aimlapi.com/models/deepgram-nova-2","docsUrl":"https://docs.aimlapi.com/api-references/speech-models/speech-to-text/deepgram/nova-2","docsJson":"https://api.aimlapi.com/docs-json?model=deepgram%2Fnova-2-meeting&endpoint=internal%2Fspeech-to-text%2Fsubmit"},"type":"internal/speech-to-text/submit","aliases":["nova-2-meeting","#g1_nova-2-meeting"],"tags":["playground:stt","tier:tier_2"]},{"id":"deepgram/nova-2-phonecall","info":{"releasedAt":"2025-12-30","name":"Nova-2 Phonecall","developer":"Deepgram","description":"Nova-2: Advanced, versatile ASR model for diverse transcription needs.","url":"https://aimlapi.com/models/deepgram-nova-2","docsUrl":"https://docs.aimlapi.com/api-references/speech-models/speech-to-text/deepgram/nova-2","docsJson":"https://api.aimlapi.com/docs-json?model=deepgram%2Fnova-2-phonecall&endpoint=internal%2Fspeech-to-text%2Fsubmit"},"type":"internal/speech-to-text/submit","aliases":["nova-2-phonecall","#g1_nova-2-phonecall"],"tags":["playground:stt","tier:tier_2"]},{"id":"deepgram/nova-2-voicemail","info":{"releasedAt":"2025-12-30","name":"Nova-2 Voicemail","developer":"Deepgram","description":"Nova-2: Advanced, versatile ASR model for diverse transcription needs.","url":"https://aimlapi.com/models/deepgram-nova-2","docsUrl":"https://docs.aimlapi.com/api-references/speech-models/speech-to-text/deepgram/nova-2","docsJson":"https://api.aimlapi.com/docs-json?model=deepgram%2Fnova-2-voicemail&endpoint=internal%2Fspeech-to-text%2Fsubmit"},"type":"internal/speech-to-text/submit","aliases":["nova-2-voicemail","#g1_nova-2-voicemail"],"tags":["playground:stt","tier:tier_2"]},{"id":"deepgram/nova-2-finance","info":{"releasedAt":"2025-12-30","name":"Nova-2 Finance","developer":"Deepgram","description":"Nova-2: Advanced, versatile ASR model for diverse transcription needs.","url":"https://aimlapi.com/models/deepgram-nova-2","docsUrl":"https://docs.aimlapi.com/api-references/speech-models/speech-to-text/deepgram/nova-2","docsJson":"https://api.aimlapi.com/docs-json?model=deepgram%2Fnova-2-finance&endpoint=internal%2Fspeech-to-text%2Fsubmit"},"type":"internal/speech-to-text/submit","aliases":["nova-2-finance","#g1_nova-2-finance"],"tags":["playground:stt","tier:tier_2"]},{"id":"deepgram/nova-2-conversationalai","info":{"releasedAt":"2025-12-30","name":"Nova-2 Conversational AI","developer":"Deepgram","description":"Nova-2: Advanced, versatile ASR model for diverse transcription needs.","url":"https://aimlapi.com/models/deepgram-nova-2","docsUrl":"https://docs.aimlapi.com/api-references/speech-models/speech-to-text/deepgram/nova-2","docsJson":"https://api.aimlapi.com/docs-json?model=deepgram%2Fnova-2-conversationalai&endpoint=internal%2Fspeech-to-text%2Fsubmit"},"type":"internal/speech-to-text/submit","aliases":["nova-2-conversationalai","#g1_nova-2-conversationalai"],"tags":["playground:stt","tier:tier_2"]},{"id":"deepgram/nova-2-video","info":{"releasedAt":"2025-12-30","name":"Nova-2 Video","developer":"Deepgram","description":"Nova-2: Advanced, versatile ASR model for diverse transcription needs.","url":"https://aimlapi.com/models/deepgram-nova-2","docsUrl":"https://docs.aimlapi.com/api-references/speech-models/speech-to-text/deepgram/nova-2","docsJson":"https://api.aimlapi.com/docs-json?model=deepgram%2Fnova-2-video&endpoint=internal%2Fspeech-to-text%2Fsubmit"},"type":"internal/speech-to-text/submit","aliases":["nova-2-video","#g1_nova-2-video"],"tags":["playground:stt","tier:tier_2"]},{"id":"deepgram/nova-2-medical","info":{"releasedAt":"2025-12-30","name":"Nova-2 Medical","developer":"Deepgram","description":"Nova-2: Advanced, versatile ASR model for diverse transcription needs.","url":"https://aimlapi.com/models/deepgram-nova-2","docsUrl":"https://docs.aimlapi.com/api-references/speech-models/speech-to-text/deepgram/nova-2","docsJson":"https://api.aimlapi.com/docs-json?model=deepgram%2Fnova-2-medical&endpoint=internal%2Fspeech-to-text%2Fsubmit"},"type":"internal/speech-to-text/submit","aliases":["nova-2-medical","#g1_nova-2-medical"],"tags":["playground:stt","tier:tier_2"]},{"id":"deepgram/nova-2-drivethru","info":{"releasedAt":"2025-12-30","name":"Nova-2 Drive Thru","developer":"Deepgram","description":"Nova-2: Advanced, versatile ASR model for diverse transcription needs.","url":"https://aimlapi.com/models/deepgram-nova-2","docsUrl":"https://docs.aimlapi.com/api-references/speech-models/speech-to-text/deepgram/nova-2","docsJson":"https://api.aimlapi.com/docs-json?model=deepgram%2Fnova-2-drivethru&endpoint=internal%2Fspeech-to-text%2Fsubmit"},"type":"internal/speech-to-text/submit","aliases":["nova-2-drivethru","#g1_nova-2-drivethru"],"tags":["playground:stt","tier:tier_2"]},{"id":"deepgram/nova-2-automotive","info":{"releasedAt":"2025-12-30","name":"Nova-2 Automotive","developer":"Deepgram","description":"Nova-2: Advanced, versatile ASR model for diverse transcription needs.","url":"https://aimlapi.com/models/deepgram-nova-2","docsUrl":"https://docs.aimlapi.com/api-references/speech-models/speech-to-text/deepgram/nova-2","docsJson":"https://api.aimlapi.com/docs-json?model=deepgram%2Fnova-2-automotive&endpoint=internal%2Fspeech-to-text%2Fsubmit"},"type":"internal/speech-to-text/submit","aliases":["nova-2-automotive","#g1_nova-2-automotive"],"tags":["playground:stt","tier:tier_2"]},{"id":"deepgram/nova-3","info":{"releasedAt":"2026-06-04","name":"Nova-3","developer":"Deepgram","description":"Nova-3: Deepgram next-generation ASR model with improved accuracy and multilingual support.","url":"https://aimlapi.com/models/deepgram-nova-3","docsUrl":"https://docs.aimlapi.com/api-references/speech-models/speech-to-text/deepgram/nova-3","docsJson":"https://api.aimlapi.com/docs-json?model=deepgram%2Fnova-3&endpoint=internal%2Fspeech-to-text%2Fsubmit"},"type":"internal/speech-to-text/submit","aliases":["nova-3","#g1_nova-3"],"tags":["playground:stt","tier:tier_2"]},{"id":"deepgram/nova-3-general","info":{"releasedAt":"2026-06-04","name":"Nova-3 General","developer":"Deepgram","description":"Nova-3: Deepgram next-generation ASR model with improved accuracy and multilingual support.","url":"https://aimlapi.com/models/deepgram-nova-3","docsUrl":"https://docs.aimlapi.com/api-references/speech-models/speech-to-text/deepgram/nova-3","docsJson":"https://api.aimlapi.com/docs-json?model=deepgram%2Fnova-3-general&endpoint=internal%2Fspeech-to-text%2Fsubmit"},"type":"internal/speech-to-text/submit","aliases":["nova-3-general","#g1_nova-3-general"],"tags":["playground:stt","tier:tier_2"]},{"id":"deepgram/nova-3-medical","info":{"releasedAt":"2026-06-04","name":"Nova-3 Medical","developer":"Deepgram","description":"Nova-3 Medical: Deepgram next-generation ASR specialized for medical and healthcare terminology.","url":"https://aimlapi.com/models/deepgram-nova-3","docsUrl":"https://docs.aimlapi.com/api-references/speech-models/speech-to-text/deepgram/nova-3","docsJson":"https://api.aimlapi.com/docs-json?model=deepgram%2Fnova-3-medical&endpoint=internal%2Fspeech-to-text%2Fsubmit"},"type":"internal/speech-to-text/submit","aliases":["nova-3-medical","#g1_nova-3-medical"],"tags":["playground:stt","tier:tier_2"]},{"id":"deepgram/whisper-large","info":{"releasedAt":"2025-12-30","name":"Whisper Large","developer":"Deepgram","description":"Whisper: Multilingual speech recognition model, robust, versatile, open-source.","url":"https://aimlapi.com/models/whisper","docsUrl":"https://docs.aimlapi.com/api-references/speech-models/speech-to-text/deepgram/nova-2","docsJson":"https://api.aimlapi.com/docs-json?model=deepgram%2Fwhisper-large&endpoint=internal%2Fspeech-to-text%2Fsubmit"},"type":"internal/speech-to-text/submit","aliases":["whisper-large","#g1_whisper-large"],"tags":["playground:stt","tier:tier_2"]},{"id":"deepgram/whisper-medium","info":{"releasedAt":"2025-12-30","name":"Whisper Medium","developer":"Deepgram","description":"Whisper: Multilingual speech recognition model, robust, versatile, open-source.","url":"https://aimlapi.com/models/whisper","docsUrl":"https://docs.aimlapi.com/api-references/speech-models/speech-to-text/deepgram/nova-2","docsJson":"https://api.aimlapi.com/docs-json?model=deepgram%2Fwhisper-medium&endpoint=internal%2Fspeech-to-text%2Fsubmit"},"type":"internal/speech-to-text/submit","aliases":["whisper-medium","#g1_whisper-medium"],"tags":["playground:stt","tier:tier_2"]},{"id":"deepgram/whisper-small","info":{"releasedAt":"2025-12-30","name":"Whisper Small","developer":"Deepgram","description":"Whisper: Multilingual speech recognition model, robust, versatile, open-source.","url":"https://aimlapi.com/models/whisper","docsUrl":"https://docs.aimlapi.com/api-references/speech-models/speech-to-text/deepgram/nova-2","docsJson":"https://api.aimlapi.com/docs-json?model=deepgram%2Fwhisper-small&endpoint=internal%2Fspeech-to-text%2Fsubmit"},"type":"internal/speech-to-text/submit","aliases":["whisper-small","#g1_whisper-small"],"tags":["playground:stt","tier:tier_2"]},{"id":"deepgram/whisper-tiny","info":{"releasedAt":"2025-12-30","name":"Whisper Tiny","developer":"Deepgram","description":"Whisper: Multilingual speech recognition model, robust, versatile, open-source.","url":"https://aimlapi.com/models/whisper","docsUrl":"https://docs.aimlapi.com/api-references/speech-models/speech-to-text/deepgram/nova-2","docsJson":"https://api.aimlapi.com/docs-json?model=deepgram%2Fwhisper-tiny&endpoint=internal%2Fspeech-to-text%2Fsubmit"},"type":"internal/speech-to-text/submit","aliases":["whisper-tiny","#g1_whisper-tiny"],"tags":["playground:stt","tier:tier_2"]},{"id":"deepgram/whisper-base","info":{"releasedAt":"2025-12-30","name":"Whisper Base","developer":"Deepgram","description":"Whisper: Multilingual speech recognition model, robust, versatile, open-source.","url":"https://aimlapi.com/models/whisper","docsUrl":"https://docs.aimlapi.com/api-references/speech-models/speech-to-text/deepgram/nova-2","docsJson":"https://api.aimlapi.com/docs-json?model=deepgram%2Fwhisper-base&endpoint=internal%2Fspeech-to-text%2Fsubmit"},"type":"internal/speech-to-text/submit","aliases":["whisper-base","#g1_whisper-base"],"tags":["playground:stt","tier:tier_2"]},{"id":"deepgram/aura","info":{"releasedAt":"2026-06-26","name":"Aura","developer":"Deepgram","description":"Aura is a real-time TTS model with human-like voices for conversational AI applications. Pick a voice via the `voice` parameter.","url":"https://aimlapi.com/models/aura","docsUrl":"https://docs.aimlapi.com/api-references/speech-models/text-to-speech/deepgram/aura","docsJson":"https://api.aimlapi.com/docs-json?model=deepgram%2Faura&endpoint=internal%2Ftext-to-speech"},"type":"internal/text-to-speech","aliases":["aura","aura-asteria-en","deepgram/aura-asteria-en","#g1_aura-asteria-en","aura-hera-en","deepgram/aura-hera-en","#g1_aura-hera-en","aura-luna-en","deepgram/aura-luna-en","#g1_aura-luna-en","aura-stella-en","deepgram/aura-stella-en","#g1_aura-stella-en","aura-athena-en","deepgram/aura-athena-en","#g1_aura-athena-en","aura-zeus-en","deepgram/aura-zeus-en","#g1_aura-zeus-en","aura-orion-en","deepgram/aura-orion-en","#g1_aura-orion-en","aura-arcas-en","deepgram/aura-arcas-en","#g1_aura-arcas-en","aura-perseus-en","deepgram/aura-perseus-en","#g1_aura-perseus-en","aura-angus-en","deepgram/aura-angus-en","#g1_aura-angus-en","aura-orpheus-en","deepgram/aura-orpheus-en","#g1_aura-orpheus-en","aura-helios-en","deepgram/aura-helios-en","#g1_aura-helios-en"],"tags":["playground:tts","tier:tier_2"]},{"id":"deepgram/aura-2","info":{"releasedAt":"2026-06-26","name":"Aura-2","developer":"Deepgram","description":"Aura-2 is the next-generation real-time TTS model with human-like voices for conversational AI applications. Pick a voice via the `voice` parameter.","url":"https://aimlapi.com/models/aura","docsUrl":"https://docs.aimlapi.com/api-references/speech-models/text-to-speech/deepgram/aura","docsJson":"https://api.aimlapi.com/docs-json?model=deepgram%2Faura-2&endpoint=internal%2Ftext-to-speech"},"type":"internal/text-to-speech","aliases":["aura-2","aura-2-amalthea-en","deepgram/aura-2-amalthea-en","#g1_aura-2-amalthea-en","aura-2-andromeda-en","deepgram/aura-2-andromeda-en","#g1_aura-2-andromeda-en","aura-2-apollo-en","deepgram/aura-2-apollo-en","#g1_aura-2-apollo-en","aura-2-arcas-en","deepgram/aura-2-arcas-en","#g1_aura-2-arcas-en","aura-2-aries-en","deepgram/aura-2-aries-en","#g1_aura-2-aries-en","aura-2-asteria-en","deepgram/aura-2-asteria-en","#g1_aura-2-asteria-en","aura-2-athena-en","deepgram/aura-2-athena-en","#g1_aura-2-athena-en","aura-2-atlas-en","deepgram/aura-2-atlas-en","#g1_aura-2-atlas-en","aura-2-aurora-en","deepgram/aura-2-aurora-en","#g1_aura-2-aurora-en","aura-2-callista-en","deepgram/aura-2-callista-en","#g1_aura-2-callista-en","aura-2-cora-en","deepgram/aura-2-cora-en","#g1_aura-2-cora-en","aura-2-cordelia-en","deepgram/aura-2-cordelia-en","#g1_aura-2-cordelia-en","aura-2-delia-en","deepgram/aura-2-delia-en","#g1_aura-2-delia-en","aura-2-draco-en","deepgram/aura-2-draco-en","#g1_aura-2-draco-en","aura-2-electra-en","deepgram/aura-2-electra-en","#g1_aura-2-electra-en","aura-2-harmonia-en","deepgram/aura-2-harmonia-en","#g1_aura-2-harmonia-en","aura-2-helena-en","deepgram/aura-2-helena-en","#g1_aura-2-helena-en","aura-2-hera-en","deepgram/aura-2-hera-en","#g1_aura-2-hera-en","aura-2-hermes-en","deepgram/aura-2-hermes-en","#g1_aura-2-hermes-en","aura-2-hyperion-en","deepgram/aura-2-hyperion-en","#g1_aura-2-hyperion-en","aura-2-iris-en","deepgram/aura-2-iris-en","#g1_aura-2-iris-en","aura-2-janus-en","deepgram/aura-2-janus-en","#g1_aura-2-janus-en","aura-2-juno-en","deepgram/aura-2-juno-en","#g1_aura-2-juno-en","aura-2-jupiter-en","deepgram/aura-2-jupiter-en","#g1_aura-2-jupiter-en","aura-2-luna-en","deepgram/aura-2-luna-en","#g1_aura-2-luna-en","aura-2-mars-en","deepgram/aura-2-mars-en","#g1_aura-2-mars-en","aura-2-minerva-en","deepgram/aura-2-minerva-en","#g1_aura-2-minerva-en","aura-2-neptune-en","deepgram/aura-2-neptune-en","#g1_aura-2-neptune-en","aura-2-odysseus-en","deepgram/aura-2-odysseus-en","#g1_aura-2-odysseus-en","aura-2-ophelia-en","deepgram/aura-2-ophelia-en","#g1_aura-2-ophelia-en","aura-2-orion-en","deepgram/aura-2-orion-en","#g1_aura-2-orion-en","aura-2-orpheus-en","deepgram/aura-2-orpheus-en","#g1_aura-2-orpheus-en","aura-2-pandora-en","deepgram/aura-2-pandora-en","#g1_aura-2-pandora-en","aura-2-phoebe-en","deepgram/aura-2-phoebe-en","#g1_aura-2-phoebe-en","aura-2-pluto-en","deepgram/aura-2-pluto-en","#g1_aura-2-pluto-en","aura-2-saturn-en","deepgram/aura-2-saturn-en","#g1_aura-2-saturn-en","aura-2-selene-en","deepgram/aura-2-selene-en","#g1_aura-2-selene-en","aura-2-thalia-en","deepgram/aura-2-thalia-en","#g1_aura-2-thalia-en","aura-2-theia-en","deepgram/aura-2-theia-en","#g1_aura-2-theia-en","aura-2-vesta-en","deepgram/aura-2-vesta-en","#g1_aura-2-vesta-en","aura-2-zeus-en","deepgram/aura-2-zeus-en","#g1_aura-2-zeus-en","aura-2-celeste-es","deepgram/aura-2-celeste-es","#g1_aura-2-celeste-es","aura-2-estrella-es","deepgram/aura-2-estrella-es","#g1_aura-2-estrella-es","aura-2-nestor-es","deepgram/aura-2-nestor-es","#g1_aura-2-nestor-es"],"tags":["playground:tts","tier:tier_2"]},{"id":"aai/slam-1","info":{"releasedAt":"2025-12-30","name":"Slam 1","developer":"AssemblyAI","description":"AssemblyAI's most customizable model for transcription (English only).","url":"","docsUrl":"https://docs.aimlapi.com/api-references/speech-models/speech-to-text/assembly-ai/slam-1","docsJson":"https://api.aimlapi.com/docs-json?model=aai%2Fslam-1&endpoint=internal%2Fspeech-to-text%2Fsubmit"},"type":"internal/speech-to-text/submit","aliases":["slam-1"],"tags":["playground:stt","tier:tier_2"]},{"id":"aai/universal","info":{"releasedAt":"2025-12-30","name":"Universal","developer":"AssemblyAI","description":"AssemblyAI's fastest, most robust model with broad language support.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/speech-models/speech-to-text/assembly-ai/universal","docsJson":"https://api.aimlapi.com/docs-json?model=aai%2Funiversal&endpoint=internal%2Fspeech-to-text%2Fsubmit"},"type":"internal/speech-to-text/submit","aliases":["universal"],"tags":["playground:stt","tier:tier_2"]},{"id":"hume/octave-2","info":{"releasedAt":"2026-01-05","name":"Octave 2","developer":"Hume AI","description":"High-quality text-to-speech model with emotional expression capabilities","url":"","docsUrl":"https://docs.aimlapi.com/api-references/speech-models/text-to-speech/hume-ai","docsJson":"https://api.aimlapi.com/docs-json?model=hume%2Foctave-2&endpoint=internal%2Ftext-to-speech"},"type":"internal/text-to-speech","aliases":["octave-2"],"tags":["playground:tts","tier:tier_2"]},{"id":"inworld/tts-1","info":{"releasedAt":"2026-01-05","name":"Inworld TTS 1","developer":"Inworld AI","description":"High-quality text-to-speech model with natural-sounding voices","url":"","docsUrl":"https://docs.aimlapi.com/api-references/speech-models/text-to-speech/inworld/tts-1","docsJson":"https://api.aimlapi.com/docs-json?model=inworld%2Ftts-1&endpoint=internal%2Ftext-to-speech"},"type":"internal/text-to-speech","aliases":[],"tags":["playground:tts","tier:tier_2"]},{"id":"inworld/tts-1-max","info":{"releasedAt":"2026-01-05","name":"Inworld TTS 1 Max","developer":"Inworld AI","description":"Premium text-to-speech model with ultra-realistic speech generation","url":"","docsUrl":"https://docs.aimlapi.com/api-references/speech-models/text-to-speech/inworld/tts-1-max","docsJson":"https://api.aimlapi.com/docs-json?model=inworld%2Ftts-1-max&endpoint=internal%2Ftext-to-speech"},"type":"internal/text-to-speech","aliases":[],"tags":["playground:tts","tier:tier_2"]},{"id":"inworld/tts-1-5-max","info":{"releasedAt":"2026-02-04","name":"Inworld TTS 1.5 Max","developer":"Inworld AI","description":"Text-to-speech model focused on maximum voice stability and expressiveness, suitable for high-quality production and narrative use cases.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/speech-models/text-to-speech/inworld/tts-1-5-max","docsJson":"https://api.aimlapi.com/docs-json?model=inworld%2Ftts-1-5-max&endpoint=internal%2Ftext-to-speech"},"type":"internal/text-to-speech","aliases":[],"tags":["playground:tts","tier:tier_2"]},{"id":"inworld/tts-1-5-mini","info":{"releasedAt":"2026-02-04","name":"Inworld TTS 1.5 Mini","developer":"Inworld AI","description":"Low-latency text-to-speech model optimized for real-time and high-throughput scenarios while maintaining high audio quality.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/speech-models/text-to-speech/inworld/tts-1-5-mini","docsJson":"https://api.aimlapi.com/docs-json?model=inworld%2Ftts-1-5-mini&endpoint=internal%2Ftext-to-speech"},"type":"internal/text-to-speech","aliases":[],"tags":["playground:tts","tier:tier_2"]},{"id":"xiaomi/mimo-v2.5","info":{"releasedAt":"2026-04-23","name":"MiMo V2.5","developer":"Xiaomi","description":"MiMo-V2.5 — a native omnimodal model by Xiaomi for text, image, audio, and video understanding. It delivers strong agentic performance at lower cost, making it suitable for general-purpose AI applications.","contextLength":1000000,"outputMax":128000,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=xiaomi%2Fmimo-v2.5&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["mimo-v2.5"],"tags":["playground:chat","tier:tier_2"]},{"id":"xiaomi/mimo-v2.5-pro","info":{"releasedAt":"2026-04-23","name":"MiMo V2.5 Pro","developer":"Xiaomi","description":"MiMo-V2.5-Pro — a flagship reasoning model by Xiaomi designed for complex agentic workflows, long-horizon tasks, and advanced software engineering scenarios with a 1M token context window.","contextLength":1000000,"outputMax":128000,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=xiaomi%2Fmimo-v2.5-pro&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["mimo-v2.5-pro"],"tags":["playground:chat","tier:tier_2"]},{"id":"stepfun/step-3.7-flash","info":{"releasedAt":"2026-06-01","name":"Step 3.7 Flash","developer":"StepFun","description":"Step 3.7 Flash is a multimodal Mixture-of-Experts model from StepFun with text, image, and video understanding. It supports a 256K context window and is optimized for fast inference, reasoning, agent workflows, and long-context productivity tasks.","contextLength":256000,"outputMax":256000,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=stepfun%2Fstep-3.7-flash&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["step-3.7-flash"],"tags":["playground:chat","tier:tier_2"]},{"id":"sakana/fugu-ultra","info":{"releasedAt":"2026-06-24","name":"Fugu Ultra","developer":"Sakana AI","description":"Fugu Ultra is the higher-performance model in Sakana AI's Fugu family. Rather than a standard monolithic language model, it is a learned multi-agent orchestration system: a model trained to route tasks across a swappable pool of underlying models and to recursively call instances of itself. It is optimized for complex, multi-step reasoning, coding, and agentic workflows, with orchestration tokens billed as standard input/output tokens.","contextLength":1000000,"outputMax":128000,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=sakana%2Ffugu-ultra&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["fugu-ultra"],"tags":["playground:chat","tier:tier_2"]},{"id":"microsoft/mai-image-2.5","info":{"releasedAt":"2026-06-03","name":"MAI-Image 2.5","developer":"Microsoft","description":"MAI-Image 2.5 is an image generation model from Microsoft, served via Azure AI Foundry. It produces photorealistic and artistic images from text prompts with support for multiple aspect ratios.","url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=microsoft%2Fmai-image-2.5&endpoint=openai%2Fimage-generations"},"type":"openai/image-generations","aliases":[],"tags":["playground:image","tier:tier_2"]},{"id":"microsoft/mai-transcribe-1.5","info":{"releasedAt":"2026-06-03","name":"MAI-Transcribe 1.5","developer":"Microsoft","description":"MAI-Transcribe 1.5 is a fast speech-to-text model from Microsoft, powered by Azure AI Speech. It supports 100+ BCP-47 locales with automatic language detection and punctuation restoration.","url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=microsoft%2Fmai-transcribe-1.5&endpoint=internal%2Fspeech-to-text%2Fsubmit"},"type":"internal/speech-to-text/submit","aliases":[],"tags":["playground:stt","tier:tier_2"]},{"id":"microsoft/mai-voice-2","info":{"releasedAt":"2026-06-03","name":"MAI-Voice 2","developer":"Microsoft","description":"MAI-Voice 2 is a high-fidelity, expressive text-to-speech model from Microsoft, powered by Azure AI Speech. It synthesizes natural-sounding speech across multiple languages with support for a wide range of neural voices.","url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=microsoft%2Fmai-voice-2&endpoint=internal%2Ftext-to-speech"},"type":"internal/text-to-speech","aliases":[],"tags":["playground:tts","tier:tier_2"]},{"id":"tencent/hy3","info":{"releasedAt":"2026-07-06","name":"Hy3","developer":"Tencent","contextLength":262144,"outputMax":131072,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=tencent%2Fhy3&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["hy3"],"tags":["playground:chat","tier:tier_2"]},{"id":"flux/schnell","info":{"releasedAt":"2025-10-13","name":"Flux Schnell","developer":"Black Forest Labs","description":"FLUX.1 [schnell] is a cutting-edge text-to-image model for developers.","url":"https://aimlapi.com/models/flux-1-schnell-api","docsUrl":"https://docs.aimlapi.com/api-references/image-models/flux/flux-schnell","docsJson":"https://api.aimlapi.com/docs-json?model=flux%2Fschnell&endpoint=openai%2Fimage-generations"},"type":"openai/image-generations","aliases":[],"tags":["playground:image","tier:tier_2"]},{"id":"flux-pro","info":{"releasedAt":"2025-10-13","name":"Flux Pro","developer":"Black Forest Labs","description":"FLUX.1 [pro]: The ultimate AI image generation model for professionals.","url":"https://aimlapi.com/models/flux-1-pro-api","docsUrl":"https://docs.aimlapi.com/api-references/image-models/flux/flux-pro","docsJson":"https://api.aimlapi.com/docs-json?model=flux-pro&endpoint=openai%2Fimage-generations"},"type":"openai/image-generations","aliases":[],"tags":["playground:image","tier:tier_2"]},{"id":"flux/srpo","info":{"releasedAt":"2025-10-13","name":"Flux SRPO","developer":"Black Forest Labs","description":"FLUX.1 SRPO is an advanced image generation model optimized for superior quality and performance.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/image-models/flux/flux-srpo-text-to-image","docsJson":"https://api.aimlapi.com/docs-json?model=flux%2Fsrpo&endpoint=openai%2Fimage-generations"},"type":"openai/image-generations","aliases":[],"tags":["playground:image","tier:tier_2"]},{"id":"flux-realism","info":{"releasedAt":"2025-10-13","name":"Flux Realism","developer":"Black Forest Labs","description":"FLUX Realism LoRA generates photorealistic images from text prompts, enhancing creative possibilities.","url":"https://aimlapi.com/models/flux-realism-lora-api","docsUrl":"https://docs.aimlapi.com/api-references/image-models/flux/flux-realism","docsJson":"https://api.aimlapi.com/docs-json?model=flux-realism&endpoint=openai%2Fimage-generations"},"type":"openai/image-generations","aliases":[],"tags":["playground:image","tier:tier_2"]},{"id":"flux-2","info":{"releasedAt":"2025-11-26","name":"Flux 2","developer":"Black Forest Labs","description":"FLUX 2 is the next-generation text-to-image model from Black Forest Labs with improved quality and prompt adherence.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/image-models/flux/flux-2","docsJson":"https://api.aimlapi.com/docs-json?model=flux-2&endpoint=openai%2Fimage-generations"},"type":"openai/image-generations","aliases":[],"tags":["playground:image","tier:tier_2"]},{"id":"flux-2/lora","info":{"releasedAt":"2025-11-26","name":"Flux 2 LoRA","developer":"Black Forest Labs","description":"FLUX 2 with LoRA support for custom style and subject fine-tuning in text-to-image generation.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/image-models/flux/flux-2-lora","docsJson":"https://api.aimlapi.com/docs-json?model=flux-2%2Flora&endpoint=openai%2Fimage-generations"},"type":"openai/image-generations","aliases":[],"tags":["playground:image","tier:tier_2"]},{"id":"flux-2/lora/edit","info":{"releasedAt":"2025-11-26","name":"Flux 2 LoRA Edit","developer":"Black Forest Labs","description":"FLUX 2 Edit with LoRA support for fine-tuned, style-consistent image editing.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/image-models/flux/flux-2-lora-edit","docsJson":"https://api.aimlapi.com/docs-json?model=flux-2%2Flora%2Fedit&endpoint=openai%2Fimage-generations"},"type":"openai/image-generations","aliases":[],"tags":["playground:image","tier:tier_2"]},{"id":"flux-2-pro","info":{"releasedAt":"2025-11-26","name":"Flux 2 Pro","developer":"Black Forest Labs","description":"FLUX 2 Pro delivers professional-grade text-to-image generation with the highest quality output from Black Forest Labs.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/image-models/flux/flux-2-pro","isHottest":true,"docsJson":"https://api.aimlapi.com/docs-json?model=flux-2-pro&endpoint=openai%2Fimage-generations"},"type":"openai/image-generations","aliases":[],"tags":["playground:image","tier:tier_2"]},{"id":"flux-2-pro/edit","info":{"releasedAt":"2025-11-26","name":"Flux 2 Pro","developer":"Black Forest Labs","description":"FLUX 2 Pro delivers professional-grade text-to-image generation with the highest quality output from Black Forest Labs.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/image-models/flux/flux-2-pro","isHottest":true,"docsJson":"https://api.aimlapi.com/docs-json?model=flux-2-pro%2Fedit&endpoint=openai%2Fimage-generations"},"type":"openai/image-generations","aliases":[],"tags":["playground:image","tier:tier_2"]},{"id":"flux-2-max","info":{"releasedAt":"2025-12-17","name":"Flux 2 Max","developer":"Black Forest Labs","description":"FLUX 2 Max is the maximum-capability text-to-image model from Black Forest Labs for the highest visual fidelity.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/image-models/flux","docsJson":"https://api.aimlapi.com/docs-json?model=flux-2-max&endpoint=openai%2Fimage-generations"},"type":"openai/image-generations","aliases":[],"tags":["playground:image","tier:tier_2"]},{"id":"flux-2-max/edit","info":{"releasedAt":"2025-12-17","name":"Flux 2 Max","developer":"Black Forest Labs","description":"FLUX 2 Max is the maximum-capability text-to-image model from Black Forest Labs for the highest visual fidelity.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/image-models/flux","docsJson":"https://api.aimlapi.com/docs-json?model=flux-2-max%2Fedit&endpoint=openai%2Fimage-generations"},"type":"openai/image-generations","aliases":[],"tags":["playground:image","tier:tier_2"]},{"id":"flux-pro/kontext/text-to-image","info":{"releasedAt":"2025-10-13","name":"Flux Kontext Pro","developer":"Black Forest Labs","description":"FLUX.1 Kontext Pro generates images from text with advanced contextual understanding for consistent character and style.","url":"https://aimlapi.com/models/flux-1-kontext-pro","docsUrl":"https://docs.aimlapi.com/api-references/image-models/flux/flux-kontext-pro-text-to-image","docsJson":"https://api.aimlapi.com/docs-json?model=flux-pro%2Fkontext%2Ftext-to-image&endpoint=openai%2Fimage-generations"},"type":"openai/image-generations","aliases":[],"tags":["playground:image","tier:tier_2"]},{"id":"flux-pro/kontext","info":{"releasedAt":"2025-10-13","name":"Flux Kontext Pro","developer":"Black Forest Labs","description":"FLUX.1 Kontext Pro generates images from text with advanced contextual understanding for consistent character and style.","url":"https://aimlapi.com/models/flux-1-kontext-pro","docsUrl":"https://docs.aimlapi.com/api-references/image-models/flux/flux-kontext-pro-text-to-image","docsJson":"https://api.aimlapi.com/docs-json?model=flux-pro%2Fkontext&endpoint=openai%2Fimage-generations"},"type":"openai/image-generations","aliases":[],"tags":["playground:image","tier:tier_2"]},{"id":"flux-pro/kontext/max/text-to-image","info":{"releasedAt":"2025-10-13","name":"Flux Kontext Max","developer":"Black Forest Labs","description":"FLUX.1 Kontext Max is the highest-capability Kontext model for complex text-to-image tasks with maximum fidelity.","url":"https://aimlapi.com/models/flux-1-kontext-max","docsUrl":"https://docs.aimlapi.com/api-references/image-models/flux/flux-kontext-max-text-to-image","docsJson":"https://api.aimlapi.com/docs-json?model=flux-pro%2Fkontext%2Fmax%2Ftext-to-image&endpoint=openai%2Fimage-generations"},"type":"openai/image-generations","aliases":[],"tags":["playground:image","tier:tier_2"]},{"id":"flux-pro/kontext/max","info":{"releasedAt":"2025-10-13","name":"Flux Kontext Max","developer":"Black Forest Labs","description":"FLUX.1 Kontext Max is the highest-capability Kontext model for complex text-to-image tasks with maximum fidelity.","url":"https://aimlapi.com/models/flux-1-kontext-max","docsUrl":"https://docs.aimlapi.com/api-references/image-models/flux/flux-kontext-max-text-to-image","docsJson":"https://api.aimlapi.com/docs-json?model=flux-pro%2Fkontext%2Fmax&endpoint=openai%2Fimage-generations"},"type":"openai/image-generations","aliases":[],"tags":["playground:image","tier:tier_2"]},{"id":"flux/dev","info":{"releasedAt":"2025-08-18","name":"Flux Dev","developer":"Black Forest Labs","description":"FLUX.1 [dev] is an advanced image generation model by Black Forest Labs.","url":"https://aimlapi.com/models/flux-1-dev-api","docsUrl":"https://docs.aimlapi.com/api-references/image-models/flux/flux-dev","docsJson":"https://api.aimlapi.com/docs-json?model=flux%2Fdev&endpoint=openai%2Fimage-generations"},"type":"openai/image-generations","aliases":[],"tags":["playground:image","tier:tier_2"]},{"id":"flux/dev/image-to-image","info":{"releasedAt":"2025-08-18","name":"Flux Dev","developer":"Black Forest Labs","description":"FLUX.1 [dev] is an advanced image generation model by Black Forest Labs.","url":"https://aimlapi.com/models/flux-1-dev-api","docsUrl":"https://docs.aimlapi.com/api-references/image-models/flux/flux-dev","docsJson":"https://api.aimlapi.com/docs-json?model=flux%2Fdev%2Fimage-to-image&endpoint=openai%2Fimage-generations"},"type":"openai/image-generations","aliases":[],"tags":["playground:image","tier:tier_2"]},{"id":"stable-diffusion-v3-medium","info":{"releasedAt":"2025-10-13","name":"Stable Diffusion v3 Medium","developer":"Stability AI","description":"Enhanced Stable Diffusion 3 text-to-image model with improved text quality, efficiency and understanding","url":"https://aimlapi.com/models/stable-diffusion-3-api","docsUrl":"https://docs.aimlapi.com/api-references/image-models/stability-ai/stable-diffusion-v3-medium","docsJson":"https://api.aimlapi.com/docs-json?model=stable-diffusion-v3-medium&endpoint=openai%2Fimage-generations"},"type":"openai/image-generations","aliases":[],"tags":["playground:image","tier:tier_2"]},{"id":"stable-diffusion-v35-large","info":{"releasedAt":"2025-10-13","name":"Stable Diffusion v3.5 Large","developer":"Stability AI","description":"Stable Diffusion 3.5 Large enhances image generation with advanced architecture and diverse outputs.","url":"https://aimlapi.com/models/stable-diffusion-3-5-large-api","docsUrl":"https://docs.aimlapi.com/api-references/image-models/stability-ai/stable-diffusion-v35-large","docsJson":"https://api.aimlapi.com/docs-json?model=stable-diffusion-v35-large&endpoint=openai%2Fimage-generations"},"type":"openai/image-generations","aliases":[],"tags":["playground:image","tier:tier_2"]},{"id":"uso","info":{"releasedAt":"2025-10-13","name":"USO Image to Image","developer":"ByteDance","description":"USO is an advanced image-to-image model for style transfer and image transformation.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/image-models/bytedance/uso","docsJson":"https://api.aimlapi.com/docs-json?model=uso&endpoint=openai%2Fimage-generations"},"type":"openai/image-generations","aliases":[],"tags":["playground:image","tier:tier_2"]},{"id":"bytedance/seedream/v4/edit","info":{"releasedAt":"2025-10-13","name":"Seedream 4.0 Image to Image","developer":"ByteDance","description":"Edit images using ByteDance's SeedDream 4 model.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/image-models/bytedance/seedream-v4-edit-image-to-image","docsJson":"https://api.aimlapi.com/docs-json?model=bytedance%2Fseedream%2Fv4%2Fedit&endpoint=openai%2Fimage-generations"},"type":"openai/image-generations","aliases":[],"tags":["playground:image","tier:tier_2"]},{"id":"bytedance/seedream/v4/text-to-image","info":{"releasedAt":"2025-10-13","name":"Seedream 4.0 Text to Image","developer":"ByteDance","description":"Generate images using ByteDance's SeedDream 4 text-to-image model.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/image-models/bytedance/seedream-v4-text-to-image","docsJson":"https://api.aimlapi.com/docs-json?model=bytedance%2Fseedream%2Fv4%2Ftext-to-image&endpoint=openai%2Fimage-generations"},"type":"openai/image-generations","aliases":[],"tags":["playground:image","tier:tier_2"]},{"id":"hunyuan-image/v3/text-to-image","info":{"releasedAt":"2025-10-13","name":"Hunyuan Image V3","developer":"Tencent","description":"Hunyuan Image V3 is an advanced text-to-image model that generates high-quality images from text prompts.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/image-models/tencent/hunyuan-image-v3-text-to-image","docsJson":"https://api.aimlapi.com/docs-json?model=hunyuan-image%2Fv3%2Ftext-to-image&endpoint=openai%2Fimage-generations"},"type":"openai/image-generations","aliases":[],"tags":["playground:image","tier:tier_2"]},{"id":"qwen-image","info":{"releasedAt":"2026-02-05","name":"Qwen Image","developer":"Alibaba Cloud","description":"General-purpose image generation model with multiple artistic styles and strong complex text rendering.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/image-models/alibaba-cloud/qwen-image","docsJson":"https://api.aimlapi.com/docs-json?model=qwen-image&endpoint=openai%2Fimage-generations"},"type":"openai/image-generations","aliases":[],"tags":["playground:image","tier:tier_2"]},{"id":"recraft-v3","info":{"releasedAt":"2025-10-13","name":"Recraft v3","developer":"Recraft AI","description":"State-of-the-art AI image generator with superior text and vector capabilities.","url":"https://aimlapi.com/models/recraft-v3","docsUrl":"https://docs.aimlapi.com/api-references/image-models/recraftai/recraft-v3","docsJson":"https://api.aimlapi.com/docs-json?model=recraft-v3&endpoint=openai%2Fimage-generations"},"type":"openai/image-generations","aliases":[],"tags":["playground:image","tier:tier_2"]},{"id":"triposr","info":{"releasedAt":"2025-10-13","name":"TripoSR","developer":"Tripo AI","description":"TripoSR: Fast, transformer-based 3D reconstruction model from single RGB images.","url":"https://aimlapi.com/models/stable-tripo-sr-api","docsUrl":"https://docs.aimlapi.com/api-references/3d-generating-models/stability-ai/triposr","docsJson":"https://api.aimlapi.com/docs-json?model=triposr&endpoint=openai%2Fimage-generations"},"type":"openai/image-generations","aliases":[],"tags":["tier:tier_2","playground:image_3d"]},{"id":"gemini-25-flash-image","info":{"releasedAt":"2026-02-23","name":"Gemini 2.5 Flash Image","developer":"Google","description":"Gemini 2.5 Flash Image is a text-to-image model powered by Gemini 2.5 Flash for fast, high-quality image generation.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/image-models/google/gemini-2.5-flash-image","docsJson":"https://api.aimlapi.com/docs-json?model=gemini-25-flash-image&endpoint=openai%2Fimage-generations"},"type":"openai/image-generations","aliases":[],"tags":["playground:image","tier:tier_2"]},{"id":"gemini-25-flash-image/edit","info":{"releasedAt":"2026-02-23","name":"Gemini 2.5 Flash Image Edit","developer":"Google","description":"Gemini 2.5 Flash Image Edit enables text-guided image editing powered by Google's Gemini 2.5 Flash model.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/image-models/google/gemini-2.5-flash-image-edit","docsJson":"https://api.aimlapi.com/docs-json?model=gemini-25-flash-image%2Fedit&endpoint=openai%2Fimage-generations"},"type":"openai/image-generations","aliases":[],"tags":["playground:image","tier:tier_2"]},{"id":"gemini-3-pro-image-preview","info":{"releasedAt":"2026-02-23","name":"Gemini 3 Pro Image","developer":"Google","description":"Gemini 3 Pro Image is a text-to-image model that generates images from text descriptions.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/image-models/google/gemini-3-pro-image-preview","docsJson":"https://api.aimlapi.com/docs-json?model=gemini-3-pro-image-preview&endpoint=openai%2Fimage-generations"},"type":"openai/image-generations","aliases":[],"tags":["playground:image","tier:tier_2"]},{"id":"gemini-3-pro-image-preview/edit","info":{"releasedAt":"2026-06-11","name":"Gemini 3 Pro Image Edit","developer":"Google","description":"Gemini 3 Pro Image Edit is an image-to-image model that edits images based on text prompts.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/image-models/google/gemini-3-pro-image-preview","docsJson":"https://api.aimlapi.com/docs-json?model=gemini-3-pro-image-preview%2Fedit&endpoint=openai%2Fimage-generations"},"type":"openai/image-generations","aliases":[],"tags":["playground:image","tier:tier_2"]},{"id":"lyria2","info":{"releasedAt":"2025-12-05","name":"Lyria 2","developer":"Google","description":"Lyria 2 is Google's advanced music generation model capable of creating high-quality, diverse musical compositions from text.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/music-models/google/lyria-2","docsJson":"https://api.aimlapi.com/docs-json?model=lyria2&endpoint=internal%2Faudio-generations%2Fsubmit"},"type":"internal/audio-generations/submit","aliases":[],"tags":["playground:audio","tier:tier_2"]},{"id":"hunyuan-part","info":{"releasedAt":"2025-11-17","name":"Hunyuan Part","developer":"Tencent","description":"Tencent Hunyuan Part is a 3D generation model for creating detailed 3D assets from text or image inputs.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/3d-generating-models/tencent/hunyuan-part","docsJson":"https://api.aimlapi.com/docs-json?model=hunyuan-part&endpoint=openai%2Fimage-generations"},"type":"openai/image-generations","aliases":[],"tags":["tier:tier_2","playground:image_3d"]},{"id":"z-image/turbo","info":{"releasedAt":"2025-12-02","name":"Z-Image Turbo","developer":"Alibaba Cloud","description":"Lightweight image model for fast generation with Chinese and English text rendering.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/image-models/alibaba-cloud/z-image-turbo","docsJson":"https://api.aimlapi.com/docs-json?model=z-image%2Fturbo&endpoint=openai%2Fimage-generations"},"type":"openai/image-generations","aliases":[],"tags":["playground:image","tier:tier_2"]},{"id":"z-image/turbo/lora","info":{"releasedAt":"2025-12-02","name":"Z-Image Turbo LoRA","developer":"Alibaba Cloud","description":"Z-Image Turbo LoRA extends the Z-Image Turbo model with custom style and subject fine-tuning via LoRA adapters.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/image-models/alibaba-cloud/z-image-turbo-lora","docsJson":"https://api.aimlapi.com/docs-json?model=z-image%2Fturbo%2Flora&endpoint=openai%2Fimage-generations"},"type":"openai/image-generations","aliases":[],"tags":["playground:image","tier:tier_2"]},{"id":"kling-image/o1","info":{"releasedAt":"2025-12-03","name":"Kling Image O1","developer":"Kling AI","description":"Kling Image O1 applies reasoning-enhanced AI to generate highly accurate and detailed images from text prompts.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/image-models/kling-ai/image-o1","docsJson":"https://api.aimlapi.com/docs-json?model=kling-image%2Fo1&endpoint=openai%2Fimage-generations"},"type":"openai/image-generations","aliases":[],"tags":["playground:image","tier:tier_2"]},{"id":"minimax-music","info":{"releasedAt":"2025-12-05","name":"MiniMax Music","developer":"Minimax AI","description":"MiniMax Music generates original music tracks from text descriptions with diverse genre and style support.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/music-models/minimax/minimax-music-legacy","docsJson":"https://api.aimlapi.com/docs-json?model=minimax-music&endpoint=internal%2Faudio-generations%2Fsubmit"},"type":"internal/audio-generations/submit","aliases":[],"tags":["playground:audio","tier:tier_2"]},{"id":"stable-audio","info":{"releasedAt":"2025-12-05","name":"Stable Audio","developer":"Stability AI","description":"Stable Audio generates high-quality audio from text prompts with innovative features like audio transformation and extensive creative control.","url":"https://aimlapi.com/models/stable-audio","docsUrl":"https://docs.aimlapi.com/api-references/music-models/stability-ai/stable-audio","docsJson":"https://api.aimlapi.com/docs-json?model=stable-audio&endpoint=internal%2Faudio-generations%2Fsubmit"},"type":"internal/audio-generations/submit","aliases":[],"tags":["playground:audio","tier:tier_2"]},{"id":"kling-video/v2.5-turbo/pro/image-to-video","info":{"releasedAt":"2025-11-24","name":"Kling 2.5 Turbo Pro Image to Video","developer":"Kling AI","description":"Kling 2.5 Turbo Pro generates high-quality videos from images with improved motion quality and faster processing.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/video-models/kling-ai/v2.5-turbo-pro-image-to-video","docsJson":"https://api.aimlapi.com/docs-json?model=kling-video%2Fv2.5-turbo%2Fpro%2Fimage-to-video&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":[],"tags":["playground:video","tier:tier_2"]},{"id":"kling-video/v2.5-turbo/pro/text-to-video","info":{"releasedAt":"2025-11-24","name":"Kling 2.5 Turbo Pro Text to Video","developer":"Kling AI","description":"Kling 2.5 Turbo Pro generates high-quality videos from text prompts with improved motion and faster processing.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/video-models/kling-ai/v2.5-turbo-pro-text-to-video","docsJson":"https://api.aimlapi.com/docs-json?model=kling-video%2Fv2.5-turbo%2Fpro%2Ftext-to-video&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":[],"tags":["playground:video","tier:tier_2"]},{"id":"kling-video/v1/standard/ai-avatar","info":{"releasedAt":"2025-11-24","name":"Kling Avatar Standard","developer":"Kling AI","description":"Kling Avatar creates dynamic videos from avatar reference images with audio synchronization using standard mode for cost-effective generation.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/video-models/kling-ai/avatar-standard","docsJson":"https://api.aimlapi.com/docs-json?model=kling-video%2Fv1%2Fstandard%2Fai-avatar&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":[],"tags":["playground:video","tier:tier_2"]},{"id":"kling-video/v1/pro/ai-avatar","info":{"releasedAt":"2025-11-24","name":"Kling Avatar Professional","developer":"Kling AI","description":"Kling Avatar creates dynamic videos from avatar reference images with audio synchronization using professional mode for higher quality and longer duration.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/video-models/kling-ai/avatar-pro","docsJson":"https://api.aimlapi.com/docs-json?model=kling-video%2Fv1%2Fpro%2Fai-avatar&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":[],"tags":["playground:video","tier:tier_2"]},{"id":"kling-video/o1/image-to-video","info":{"releasedAt":"2025-12-03","name":"Kling Video O1 Image to Video","developer":"Kling AI","description":"Kling Video O1 applies reasoning-enhanced video generation from images for more accurate motion and scene understanding.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/video-models/kling-ai/video-o1-image-to-video","docsJson":"https://api.aimlapi.com/docs-json?model=kling-video%2Fo1%2Fimage-to-video&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":[],"tags":["playground:video","tier:tier_2"]},{"id":"kling-video/o1/reference-to-video","info":{"releasedAt":"2025-12-03","name":"Kling Video O1 Reference to Video","developer":"Kling AI","description":"Kling Video O1 Reference-to-Video creates videos that maintain consistent appearance from reference images using AI reasoning.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/video-models/kling-ai/video-o1-reference-to-video","docsJson":"https://api.aimlapi.com/docs-json?model=kling-video%2Fo1%2Freference-to-video&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":[],"tags":["playground:video","tier:tier_2"]},{"id":"kling-video/o1/video-to-video/edit","info":{"releasedAt":"2025-12-03","name":"Kling Video O1 Video to Video Edit","developer":"Kling AI","description":"Kling Video O1 Video-to-Video Edit applies AI-driven edits to existing videos with reasoning-enhanced accuracy.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/video-models/kling-ai/video-o1-video-to-video-edit","docsJson":"https://api.aimlapi.com/docs-json?model=kling-video%2Fo1%2Fvideo-to-video%2Fedit&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":[],"tags":["playground:video","tier:tier_2"]},{"id":"kling-video/o1/video-to-video/reference","info":{"releasedAt":"2025-12-03","name":"Kling O1 Video to Video Reference","developer":"Kling AI","description":"Kling Video O1 Video-to-Video Reference generates new videos guided by both an input video and reference images.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/video-models/kling-ai/video-o1-video-to-video-reference","docsJson":"https://api.aimlapi.com/docs-json?model=kling-video%2Fo1%2Fvideo-to-video%2Freference&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":[],"tags":["playground:video","tier:tier_2"]},{"id":"kling-video/v2.6/pro/text-to-video","info":{"releasedAt":"2025-12-03","name":"Kling 2.6 Pro Text to Video","developer":"Kling AI","description":"Kling 2.6 Pro text-to-video delivers next-generation video quality from text prompts with advanced motion control.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/video-models/kling-ai/video-v2-6-pro-text-to-video","docsJson":"https://api.aimlapi.com/docs-json?model=kling-video%2Fv2.6%2Fpro%2Ftext-to-video&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":[],"tags":["playground:video","tier:tier_2"]},{"id":"kling-video/v2.6/pro/image-to-video","info":{"releasedAt":"2025-12-03","name":"Kling 2.6 Pro Image to Video","developer":"Kling AI","description":"Kling 2.6 Pro image-to-video delivers next-generation video quality from images with advanced motion control.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/video-models/kling-ai/video-v2.6-pro-image-to-video","docsJson":"https://api.aimlapi.com/docs-json?model=kling-video%2Fv2.6%2Fpro%2Fimage-to-video&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":[],"tags":["playground:video","tier:tier_2"]},{"id":"kling-video/v2/master/image-to-video","info":{"releasedAt":"2025-11-28","name":"Kling 2.0 Master Image to Video","developer":"Kling AI","description":"Kling 2.0 Master generates high-fidelity videos from images with state-of-the-art motion realism.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/video-models/kling-ai/v2-master-image-to-video","docsJson":"https://api.aimlapi.com/docs-json?model=kling-video%2Fv2%2Fmaster%2Fimage-to-video&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":[],"tags":["playground:video","tier:tier_2"]},{"id":"kling-video/v2/master/text-to-video","info":{"releasedAt":"2025-11-28","name":"Kling 2.0 Master Text to Video","developer":"Kling AI","description":"Kling 2.0 Master generates high-fidelity videos from text prompts with state-of-the-art motion realism.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/video-models/kling-ai/v2-master-text-to-video","docsJson":"https://api.aimlapi.com/docs-json?model=kling-video%2Fv2%2Fmaster%2Ftext-to-video&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":[],"tags":["playground:video","tier:tier_2"]},{"id":"kling-video/v2.1/master/image-to-video","info":{"releasedAt":"2025-11-28","name":"Kling 2.1 Master Image to Video","developer":"Kling AI","description":"Kling 2.1 Master image-to-video generates high-fidelity videos with the highest motion quality in the Kling 2.1 lineup.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/video-models/kling-ai/v2.1-master-image-to-video","docsJson":"https://api.aimlapi.com/docs-json?model=kling-video%2Fv2.1%2Fmaster%2Fimage-to-video&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":[],"tags":["playground:video","tier:tier_2"]},{"id":"kling-video/v2.1/master/text-to-video","info":{"releasedAt":"2025-11-28","name":"Kling 2.1 Master Text to Video","developer":"Kling AI","description":"Kling 2.1 Master text-to-video generates premium videos from text with the highest quality in the Kling 2.1 series.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/video-models/kling-ai/v2.1-master-text-to-video","docsJson":"https://api.aimlapi.com/docs-json?model=kling-video%2Fv2.1%2Fmaster%2Ftext-to-video&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":[],"tags":["playground:video","tier:tier_2"]},{"id":"kling-video/v3/standard/text-to-video","info":{"releasedAt":"2026-02-05","name":"Kling 3.0 Standard Text to Video","description":"Kling 3.0 Standard text-to-video generates high-quality videos from text prompts with improved temporal consistency.","developer":"Kling AI","url":"","docsUrl":"https://docs.aimlapi.com/api-references/video-models/kling-ai/v3-standard-text-to-video","docsJson":"https://api.aimlapi.com/docs-json?model=kling-video%2Fv3%2Fstandard%2Ftext-to-video&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":[],"tags":["playground:video","tier:tier_2"]},{"id":"kling-video/v3/standard/image-to-video","info":{"releasedAt":"2026-02-05","name":"Kling 3.0 Standard Image to Video","description":"Kling 3.0 Standard image-to-video animates images into smooth, high-quality videos with improved temporal consistency.","developer":"Kling AI","url":"","docsUrl":"https://docs.aimlapi.com/api-references/video-models/kling-ai/v3-standard-image-to-video","docsJson":"https://api.aimlapi.com/docs-json?model=kling-video%2Fv3%2Fstandard%2Fimage-to-video&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":[],"tags":["playground:video","tier:tier_2"]},{"id":"kling-video/v3/pro/text-to-video","info":{"releasedAt":"2026-02-05","name":"Kling 3.0 Pro Text to Video","description":"Kling 3.0 Pro text-to-video generates premium videos from text prompts with the highest quality in the Kling 3.0 series.","developer":"Kling AI","url":"","docsUrl":"https://docs.aimlapi.com/api-references/video-models/kling-ai/v3-pro-text-to-video","isHottest":true,"docsJson":"https://api.aimlapi.com/docs-json?model=kling-video%2Fv3%2Fpro%2Ftext-to-video&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":[],"tags":["playground:video","tier:tier_2"]},{"id":"kling-video/v3/pro/image-to-video","info":{"releasedAt":"2026-02-05","name":"Kling 3.0 Pro Image to Video","description":"Kling 3.0 Pro image-to-video generates premium videos from images with the highest quality in the Kling 3.0 series.","developer":"Kling AI","url":"","docsUrl":"https://docs.aimlapi.com/api-references/video-models/kling-ai/v3-pro-image-to-video","docsJson":"https://api.aimlapi.com/docs-json?model=kling-video%2Fv3%2Fpro%2Fimage-to-video&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":[],"tags":["playground:video","tier:tier_2"]},{"id":"kling-video/v3/turbo/standard/text-to-video","info":{"releasedAt":"2026-06-17","name":"Kling 3.0 Standard Turbo Text to Video","description":"Kling 3.0 Turbo Standard text-to-video turns prompts into fast, cost-efficient 720p videos with native audio.","developer":"Kling AI","url":"","docsUrl":"https://docs.aimlapi.com/api-references/video-models/kling-ai/v3-standard-turbo-text-to-video","docsJson":"https://api.aimlapi.com/docs-json?model=kling-video%2Fv3%2Fturbo%2Fstandard%2Ftext-to-video&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":[],"tags":["playground:video","tier:tier_2"]},{"id":"kling-video/v3/turbo/standard/image-to-video","info":{"releasedAt":"2026-06-17","name":"Kling 3.0 Standard Turbo Image to Video","description":"Kling 3.0 Turbo Standard image-to-video animates first and last frame reference images into fast, cost-efficient 720p videos with native audio.","developer":"Kling AI","url":"","docsUrl":"https://docs.aimlapi.com/api-references/video-models/kling-ai/v3-standard-turbo-image-to-video","docsJson":"https://api.aimlapi.com/docs-json?model=kling-video%2Fv3%2Fturbo%2Fstandard%2Fimage-to-video&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":[],"tags":["playground:video","tier:tier_2"]},{"id":"kling-video/v3/turbo/pro/text-to-video","info":{"releasedAt":"2026-06-17","name":"Kling 3.0 Turbo Pro Text to Video","description":"Kling 3.0 Turbo Pro text-to-video generates high-quality 1080p videos with improved lipsync and multishot generation capabilities.","developer":"Kling AI","url":"","docsUrl":"https://docs.aimlapi.com/api-references/video-models/kling-ai/v3-turbo-pro-text-to-video","docsJson":"https://api.aimlapi.com/docs-json?model=kling-video%2Fv3%2Fturbo%2Fpro%2Ftext-to-video&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":[],"tags":["playground:video","tier:tier_2"]},{"id":"kling-video/v3/turbo/pro/image-to-video","info":{"releasedAt":"2026-06-17","name":"Kling 3.0 Turbo Pro Image to Video","description":"Kling 3.0 Turbo Pro image-to-video generates high-quality 1080p videos from images with improved lipsync and multishot generation capabilities.","developer":"Kling AI","url":"","docsUrl":"https://docs.aimlapi.com/api-references/video-models/kling-ai/v3-turbo-pro-image-to-video","docsJson":"https://api.aimlapi.com/docs-json?model=kling-video%2Fv3%2Fturbo%2Fpro%2Fimage-to-video&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":[],"tags":["playground:video","tier:tier_2"]},{"id":"veo3.1","info":{"releasedAt":"2025-11-24","name":"Veo 3.1 Text to Video","description":"Veo 3.1 generates high-quality videos with audio from text prompts using Google's latest video generation model.","developer":"Google","url":"","docsUrl":"https://docs.aimlapi.com/api-references/video-models/google/veo-3-1-text-to-video","isHottest":true,"docsJson":"https://api.aimlapi.com/docs-json?model=veo3.1&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":[],"tags":["playground:video","tier:tier_2"]},{"id":"veo3.1/image-to-video","info":{"releasedAt":"2025-11-24","name":"Veo 3.1 Image to Video","description":"Veo 3.1 animates still images into high-quality videos with audio using Google's latest generation model.","developer":"Google","url":"","docsUrl":"https://docs.aimlapi.com/api-references/video-models/google/veo-3-1-image-to-video","docsJson":"https://api.aimlapi.com/docs-json?model=veo3.1%2Fimage-to-video&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":[],"tags":["playground:video","tier:tier_2"]},{"id":"veo3.1/first-last-frame-to-video","info":{"releasedAt":"2025-11-24","name":"Veo 3.1 First Last Frame to Video","description":"Veo 3.1 generates smooth videos by interpolating between provided first and last frame images.","developer":"Google","url":"","docsUrl":"https://docs.aimlapi.com/api-references/video-models/google/veo-3-1-first-last-image-to-video","docsJson":"https://api.aimlapi.com/docs-json?model=veo3.1%2Ffirst-last-frame-to-video&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":[],"tags":["playground:video","tier:tier_2"]},{"id":"veo3.1/reference-to-video","info":{"releasedAt":"2025-11-24","name":"Veo 3.1 Reference to Video","description":"Veo 3.1 creates videos guided by reference images for consistent character and scene appearance.","developer":"Google","url":"","docsUrl":"https://docs.aimlapi.com/api-references/video-models/google/veo-3-1-reference-to-video","docsJson":"https://api.aimlapi.com/docs-json?model=veo3.1%2Freference-to-video&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":[],"tags":["playground:video","tier:tier_2"]},{"id":"veo3.1/fast","info":{"releasedAt":"2025-11-24","name":"Veo 3.1 Text to Video Fast","description":"Veo 3.1 Fast is a speed-optimized variant of Veo 3.1 text-to-video for rapid generation at reduced cost.","developer":"Google","url":"","docsUrl":"https://docs.aimlapi.com/api-references/video-models/google/veo-3-1-text-to-video-fast","docsJson":"https://api.aimlapi.com/docs-json?model=veo3.1%2Ffast&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":[],"tags":["playground:video","tier:tier_2"]},{"id":"veo3.1/fast/image-to-video","info":{"releasedAt":"2025-11-24","name":"Veo 3.1 Image to Video Fast","description":"Veo 3.1 Fast image-to-video provides faster animation of images into videos at reduced cost.","developer":"Google","url":"","docsUrl":"https://docs.aimlapi.com/api-references/video-models/google/veo-3-1-image-to-video-fast","docsJson":"https://api.aimlapi.com/docs-json?model=veo3.1%2Ffast%2Fimage-to-video&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":[],"tags":["playground:video","tier:tier_2"]},{"id":"veo3.1/fast/first-last-frame-to-video","info":{"releasedAt":"2025-11-24","name":"Veo 3.1 First Last Frame to Video Fast","description":"Veo 3.1 Fast first-last-frame interpolation for rapid video generation between two keyframes.","developer":"Google","url":"","docsUrl":"https://docs.aimlapi.com/api-references/video-models/google/veo-3-1-first-last-image-to-video-fast","docsJson":"https://api.aimlapi.com/docs-json?model=veo3.1%2Ffast%2Ffirst-last-frame-to-video&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":[],"tags":["playground:video","tier:tier_2"]},{"id":"veo3.1/extend-video","info":{"releasedAt":"2025-12-23","name":"Veo 3.1 Extend Video","description":"Veo 3.1 Extend Video is a video extension (video-to-video) model for continuing an existing clip, with optional audio generation.","developer":"Google","url":"","docsUrl":"https://docs.aimlapi.com/api-references/video-models/google/veo-3.1-extend-video","docsJson":"https://api.aimlapi.com/docs-json?model=veo3.1%2Fextend-video&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":[],"tags":["playground:video","tier:tier_2"]},{"id":"veo3.1/fast/extend-video","info":{"releasedAt":"2025-12-23","name":"Veo 3.1 Fast Extend Video","description":"Veo 3.1 Fast Extend Video provides the same extend workflow at lower cost and faster iteration, also supporting audio on/off modes.","developer":"Google","url":"","docsUrl":"https://docs.aimlapi.com/api-references/video-models/google/veo-3.1-fast-extend-video","docsJson":"https://api.aimlapi.com/docs-json?model=veo3.1%2Ffast%2Fextend-video&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":[],"tags":["playground:video","tier:tier_2"]},{"id":"veo3.1/lite/image-to-video","info":{"releasedAt":"2026-04-06","name":"Veo 3.1 Lite Generate Preview","description":"","developer":"Google","url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=veo3.1%2Flite%2Fimage-to-video&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":[],"tags":["playground:video","tier:tier_2"]},{"id":"veo3.1/lite/first-last-frame-to-video","info":{"releasedAt":"2026-04-06","name":"Veo 3.1 Lite Generate Preview","description":"","developer":"Google","url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=veo3.1%2Flite%2Ffirst-last-frame-to-video&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":[],"tags":["playground:video","tier:tier_2"]},{"id":"veo3.1/lite","info":{"releasedAt":"2026-04-06","name":"Veo 3.1 Lite Generate Preview","description":"","developer":"Google","url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=veo3.1%2Flite&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":[],"tags":["playground:video","tier:tier_2"]},{"id":"bytedance/omnihuman","info":{"releasedAt":"2025-11-24","name":"OmniHuman Image to Video","developer":"ByteDance","description":"Generate incredibly accurate videos of human beings speaking a dialogue using ByteDance's OmniHuman model.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/video-models/bytedance/omnihuman","docsJson":"https://api.aimlapi.com/docs-json?model=bytedance%2Fomnihuman&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":[],"tags":["playground:video","tier:tier_2"]},{"id":"bytedance/omnihuman/v1.5","info":{"releasedAt":"2025-11-24","name":"OmniHuman v1.5","developer":"ByteDance","description":"OmniHuman v1.5 generates realistic videos of human figures with improved motion naturalness and facial accuracy.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/video-models/bytedance/omnihuman-1.5","docsJson":"https://api.aimlapi.com/docs-json?model=bytedance%2Fomnihuman%2Fv1.5&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":[],"tags":["playground:video","tier:tier_2"]},{"id":"hunyuan-video-foley","info":{"releasedAt":"2025-11-24","name":"Hunyuan Video Foley","developer":"Tencent","description":"Generate foley audio for videos using Tencent Hunyuan Video Foley model. Adds realistic sound effects synchronized with video content.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/video-models/tencent/hunyuan-video-foley","docsJson":"https://api.aimlapi.com/docs-json?model=hunyuan-video-foley&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":[],"tags":["playground:video","tier:tier_2"]},{"id":"wan-22-vace-fun-a14b/depth","info":{"releasedAt":"2025-11-24","name":"Wan 2.2 Vace Depth","developer":"Alibaba Cloud","description":"Generate videos from depth maps using Alibaba WAN-2.2-VACE model.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/video-models/alibaba-cloud/wan2.2-vace-fun-a14b-depth-image-to-video","docsJson":"https://api.aimlapi.com/docs-json?model=wan-22-vace-fun-a14b%2Fdepth&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":[],"tags":["playground:video","tier:tier_2"]},{"id":"wan-22-vace-fun-a14b/pose","info":{"releasedAt":"2025-11-24","name":"Wan 2.2 Vace Pose","developer":"Alibaba Cloud","description":"Generate pose-guided videos using Alibaba WAN-2.2-VACE model.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/video-models/alibaba-cloud/wan2.2-vace-fun-a14b-pose-image-to-video","docsJson":"https://api.aimlapi.com/docs-json?model=wan-22-vace-fun-a14b%2Fpose&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":[],"tags":["playground:video","tier:tier_2"]},{"id":"wan-22-vace-fun-a14b/inpainting","info":{"releasedAt":"2025-11-24","name":"Wan 2.2 Vace Inpainting","developer":"Alibaba Cloud","description":"Generate inpainted videos using Alibaba WAN-2.2-VACE model.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/video-models/alibaba-cloud/wan2.2-vace-fun-a14b-inpainting-image-to-video","docsJson":"https://api.aimlapi.com/docs-json?model=wan-22-vace-fun-a14b%2Finpainting&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":[],"tags":["playground:video","tier:tier_2"]},{"id":"wan-22-vace-fun-a14b/outpainting","info":{"releasedAt":"2025-11-24","name":"Wan 2.2 Vace Outpainting","developer":"Alibaba Cloud","description":"Generate outpainted videos using Alibaba WAN-2.2-VACE model.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/video-models/alibaba-cloud/wan2.2-vace-fun-a14b-outpainting-image-to-video","docsJson":"https://api.aimlapi.com/docs-json?model=wan-22-vace-fun-a14b%2Foutpainting&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":[],"tags":["playground:video","tier:tier_2"]},{"id":"wan-22-vace-fun-a14b/reframe","info":{"releasedAt":"2025-11-24","name":"Wan 2.2 Vace Reframe","developer":"Alibaba Cloud","description":"Generate reframed videos using Alibaba WAN-2.2-VACE model.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/video-models/alibaba-cloud/wan2.2-vace-fun-a14b-reframe-image-to-video","docsJson":"https://api.aimlapi.com/docs-json?model=wan-22-vace-fun-a14b%2Freframe&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":[],"tags":["playground:video","tier:tier_2"]},{"id":"wan/v2.2-14b/animate/move","info":{"releasedAt":"2025-11-24","name":"Wan 2.2 14B Animate Move","developer":"Alibaba Cloud","description":"Generate animated videos from video and image using Alibaba WAN-2.2-14B move model.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/video-models/alibaba-cloud/wan-2.2-14b-animate-move-image-to-video","docsJson":"https://api.aimlapi.com/docs-json?model=wan%2Fv2.2-14b%2Fanimate%2Fmove&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":[],"tags":["playground:video","tier:tier_2"]},{"id":"wan/v2.2-14b/animate/replace","info":{"releasedAt":"2025-11-24","name":"Wan 2.2 14B Animate Replace","developer":"Alibaba Cloud","description":"Generate animated videos from video and image using Alibaba WAN-2.2-14B replace model.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/video-models/alibaba-cloud/wan-2.2-14b-animate-replace-image-to-video","docsJson":"https://api.aimlapi.com/docs-json?model=wan%2Fv2.2-14b%2Fanimate%2Freplace&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":[],"tags":["playground:video","tier:tier_2"]},{"id":"kandinsky5/text-to-video","info":{"releasedAt":"2025-11-24","name":"Kandinsky5 Text to Video","developer":"Sber AI","description":"Kandinsky5 text-to-video model generates high-quality videos from text prompts. $0.10 for 5s, $0.20 for 10s.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/video-models/sber-ai/kandinsky5-text-to-video","docsJson":"https://api.aimlapi.com/docs-json?model=kandinsky5%2Ftext-to-video&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":[],"tags":["playground:video","tier:tier_2"]},{"id":"kandinsky5/text-to-video/distill","info":{"releasedAt":"2025-11-24","name":"Kandinsky5 Text to Video Distill","developer":"Sber AI","description":"Kandinsky5 distilled text-to-video model for faster generation. $0.05 for 5s, $0.10 for 10s.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/video-models/sber-ai/kandinsky5-distill-text-to-video","docsJson":"https://api.aimlapi.com/docs-json?model=kandinsky5%2Ftext-to-video%2Fdistill&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":[],"tags":["playground:video","tier:tier_2"]},{"id":"krea-wan-14b/text-to-video","info":{"releasedAt":"2025-11-24","name":"Krea WAN 14B Text to Video","developer":"Krea","description":"Krea WAN 14B Text to Video generates high-quality videos from text using the 14B parameter WAN model.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/video-models/krea/krea-wan-14b-text-to-video","docsJson":"https://api.aimlapi.com/docs-json?model=krea-wan-14b%2Ftext-to-video&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":[],"tags":["playground:video","tier:tier_2"]},{"id":"krea-wan-14b/video-to-video","info":{"releasedAt":"2025-11-24","name":"Krea WAN 14B Video to Video","developer":"Krea","description":"Krea WAN 14B Video to Video transforms and re-renders existing videos with AI-driven style and motion control.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/video-models/krea/krea-wan-14b-video-to-video","docsJson":"https://api.aimlapi.com/docs-json?model=krea-wan-14b%2Fvideo-to-video&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":[],"tags":["playground:video","tier:tier_2"]},{"id":"ltxv-2","info":{"releasedAt":"2025-11-24","name":"LTXV 2","developer":"LTXV","description":"Generate high-quality videos from text prompts or images using LTXV 2 model with support for multiple resolutions and frame rates.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/video-models/ltxv/ltxv-2","docsJson":"https://api.aimlapi.com/docs-json?model=ltxv-2&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":[],"tags":["playground:video","tier:tier_2"]},{"id":"ltxv-2/image-to-video","info":{"releasedAt":"2025-11-24","name":"LTXV 2","developer":"LTXV","description":"Generate high-quality videos from text prompts or images using LTXV 2 model with support for multiple resolutions and frame rates.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/video-models/ltxv/ltxv-2","docsJson":"https://api.aimlapi.com/docs-json?model=ltxv-2%2Fimage-to-video&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":[],"tags":["playground:video","tier:tier_2"]},{"id":"ltxv-2/text-to-video","info":{"releasedAt":"2025-11-24","name":"LTXV 2","developer":"LTXV","description":"Generate high-quality videos from text prompts or images using LTXV 2 model with support for multiple resolutions and frame rates.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/video-models/ltxv/ltxv-2","docsJson":"https://api.aimlapi.com/docs-json?model=ltxv-2%2Ftext-to-video&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":[],"tags":["playground:video","tier:tier_2"]},{"id":"ltxv-2/fast","info":{"releasedAt":"2025-11-24","name":"LTXV 2 Fast","developer":"LTXV","description":"Generate high-quality videos from text prompts or images using LTXV 2 fast model with support for multiple resolutions and frame rates at faster speeds.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/video-models/ltxv/ltxv-2-fast","docsJson":"https://api.aimlapi.com/docs-json?model=ltxv-2%2Ffast&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":[],"tags":["playground:video","tier:tier_2"]},{"id":"ltxv-2/image-to-video/fast","info":{"releasedAt":"2025-11-24","name":"LTXV 2 Fast","developer":"LTXV","description":"Generate high-quality videos from text prompts or images using LTXV 2 fast model with support for multiple resolutions and frame rates at faster speeds.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/video-models/ltxv/ltxv-2-fast","docsJson":"https://api.aimlapi.com/docs-json?model=ltxv-2%2Fimage-to-video%2Ffast&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":[],"tags":["playground:video","tier:tier_2"]},{"id":"ltxv-2/text-to-video/fast","info":{"releasedAt":"2025-11-24","name":"LTXV 2 Fast","developer":"LTXV","description":"Generate high-quality videos from text prompts or images using LTXV 2 fast model with support for multiple resolutions and frame rates at faster speeds.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/video-models/ltxv/ltxv-2-fast","docsJson":"https://api.aimlapi.com/docs-json?model=ltxv-2%2Ftext-to-video%2Ffast&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":[],"tags":["playground:video","tier:tier_2"]},{"id":"vibevoice/7b","info":{"releasedAt":"2026-01-05","name":"VibeVoice 7B","developer":"Microsoft","description":"VibeVoice 7B is a high-quality text-to-speech model that supports multi-speaker dialogue generation with natural-sounding voices.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/speech-models/text-to-speech/microsoft/vibevoice-7b","docsJson":"https://api.aimlapi.com/docs-json?model=vibevoice%2F7b&endpoint=internal%2Ftext-to-speech"},"type":"internal/text-to-speech","aliases":[],"tags":["playground:tts","tier:tier_2"]},{"id":"vibevoice","info":{"releasedAt":"2026-01-05","name":"VibeVoice 1.5B","developer":"Microsoft","description":"VibeVoice 1.5B is an efficient text-to-speech model that supports multi-speaker dialogue generation with natural-sounding voices.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/speech-models/text-to-speech/microsoft/vibevoice-1.5b","docsJson":"https://api.aimlapi.com/docs-json?model=vibevoice&endpoint=internal%2Ftext-to-speech"},"type":"internal/text-to-speech","aliases":[],"tags":["playground:tts","tier:tier_2"]},{"id":"flux/kontext-max/text-to-image","info":{"releasedAt":"2025-10-13","name":"Flux Kontext Max","developer":"Black Forest Labs","description":"FLUX.1 Kontext Max is the highest-capability Kontext model for complex text-to-image tasks with maximum fidelity.","url":"https://aimlapi.com/models/flux-1-kontext-max","docsUrl":"https://docs.aimlapi.com/api-references/image-models/flux/flux-kontext-max-text-to-image","docsJson":"https://api.aimlapi.com/docs-json?model=flux%2Fkontext-max%2Ftext-to-image&endpoint=openai%2Fimage-generations"},"type":"openai/image-generations","aliases":[],"tags":["playground:image","tier:tier_2"]},{"id":"flux/kontext-pro/text-to-image","info":{"releasedAt":"2025-10-13","name":"Flux Kontext Pro","developer":"Black Forest Labs","description":"FLUX.1 Kontext Pro generates images from text with advanced contextual understanding for consistent character and style.","url":"https://aimlapi.com/models/flux-1-kontext-pro","docsUrl":"https://docs.aimlapi.com/api-references/image-models/flux/flux-kontext-pro-text-to-image","docsJson":"https://api.aimlapi.com/docs-json?model=flux%2Fkontext-pro%2Ftext-to-image&endpoint=openai%2Fimage-generations"},"type":"openai/image-generations","aliases":[],"tags":["playground:image","tier:tier_2"]},{"id":"flux/kontext-max/image-to-image","info":{"releasedAt":"2025-10-13","name":"Flux Kontext Max","developer":"Black Forest Labs","description":"FLUX.1 Kontext Max is the highest-capability Kontext model for complex text-to-image tasks with maximum fidelity.","url":"https://aimlapi.com/models/flux-1-kontext-max","docsUrl":"https://docs.aimlapi.com/api-references/image-models/flux/flux-kontext-max-text-to-image","docsJson":"https://api.aimlapi.com/docs-json?model=flux%2Fkontext-max%2Fimage-to-image&endpoint=openai%2Fimage-generations"},"type":"openai/image-generations","aliases":[],"tags":["playground:image","tier:tier_2"]},{"id":"flux/kontext-pro/image-to-image","info":{"releasedAt":"2025-10-13","name":"Flux Kontext Pro","developer":"Black Forest Labs","description":"FLUX.1 Kontext Pro generates images from text with advanced contextual understanding for consistent character and style.","url":"https://aimlapi.com/models/flux-1-kontext-pro","docsUrl":"https://docs.aimlapi.com/api-references/image-models/flux/flux-kontext-pro-text-to-image","docsJson":"https://api.aimlapi.com/docs-json?model=flux%2Fkontext-pro%2Fimage-to-image&endpoint=openai%2Fimage-generations"},"type":"openai/image-generations","aliases":[],"tags":["playground:image","tier:tier_2"]},{"id":"blackforestlabs/flux-2","info":{"releasedAt":"2025-11-26","name":"Flux 2","developer":"Black Forest Labs","description":"FLUX 2 is the next-generation text-to-image model from Black Forest Labs with improved quality and prompt adherence.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/image-models/flux/flux-2","docsJson":"https://api.aimlapi.com/docs-json?model=blackforestlabs%2Fflux-2&endpoint=openai%2Fimage-generations"},"type":"openai/image-generations","aliases":[],"tags":["playground:image","tier:tier_2"]},{"id":"blackforestlabs/flux-2-lora","info":{"releasedAt":"2025-11-26","name":"Flux 2 LoRA","developer":"Black Forest Labs","description":"FLUX 2 with LoRA support for custom style and subject fine-tuning in text-to-image generation.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/image-models/flux/flux-2-lora","docsJson":"https://api.aimlapi.com/docs-json?model=blackforestlabs%2Fflux-2-lora&endpoint=openai%2Fimage-generations"},"type":"openai/image-generations","aliases":[],"tags":["playground:image","tier:tier_2"]},{"id":"blackforestlabs/flux-2-lora-edit","info":{"releasedAt":"2025-11-26","name":"Flux 2 LoRA Edit","developer":"Black Forest Labs","description":"FLUX 2 Edit with LoRA support for fine-tuned, style-consistent image editing.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/image-models/flux/flux-2-lora-edit","docsJson":"https://api.aimlapi.com/docs-json?model=blackforestlabs%2Fflux-2-lora-edit&endpoint=openai%2Fimage-generations"},"type":"openai/image-generations","aliases":[],"tags":["playground:image","tier:tier_2"]},{"id":"blackforestlabs/flux-2-pro-edit","info":{"releasedAt":"2025-11-26","name":"Flux 2 Pro","developer":"Black Forest Labs","description":"FLUX 2 Pro delivers professional-grade text-to-image generation with the highest quality output from Black Forest Labs.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/image-models/flux/flux-2-pro","isHottest":true,"docsJson":"https://api.aimlapi.com/docs-json?model=blackforestlabs%2Fflux-2-pro-edit&endpoint=openai%2Fimage-generations"},"type":"openai/image-generations","aliases":[],"tags":["playground:image","tier:tier_2"]},{"id":"blackforestlabs/flux-2-max-edit","info":{"releasedAt":"2025-12-17","name":"Flux 2 Max","developer":"Black Forest Labs","description":"FLUX 2 Max is the maximum-capability text-to-image model from Black Forest Labs for the highest visual fidelity.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/image-models/flux","docsJson":"https://api.aimlapi.com/docs-json?model=blackforestlabs%2Fflux-2-max-edit&endpoint=openai%2Fimage-generations"},"type":"openai/image-generations","aliases":[],"tags":["playground:image","tier:tier_2"]},{"id":"bytedance/uso","info":{"releasedAt":"2025-10-13","name":"USO Image to Image","developer":"ByteDance","description":"USO is an advanced image-to-image model for style transfer and image transformation.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/image-models/bytedance/uso","docsJson":"https://api.aimlapi.com/docs-json?model=bytedance%2Fuso&endpoint=openai%2Fimage-generations"},"type":"openai/image-generations","aliases":[],"tags":["playground:image","tier:tier_2"]},{"id":"bytedance/seedream-v4-edit","info":{"releasedAt":"2025-10-13","name":"Seedream 4.0 Image to Image","developer":"ByteDance","description":"Edit images using ByteDance's SeedDream 4 model.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/image-models/bytedance/seedream-v4-edit-image-to-image","docsJson":"https://api.aimlapi.com/docs-json?model=bytedance%2Fseedream-v4-edit&endpoint=openai%2Fimage-generations"},"type":"openai/image-generations","aliases":[],"tags":["playground:image","tier:tier_2"]},{"id":"bytedance/seedream-v4-text-to-image","info":{"releasedAt":"2025-10-13","name":"Seedream 4.0 Text to Image","developer":"ByteDance","description":"Generate images using ByteDance's SeedDream 4 text-to-image model.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/image-models/bytedance/seedream-v4-text-to-image","docsJson":"https://api.aimlapi.com/docs-json?model=bytedance%2Fseedream-v4-text-to-image&endpoint=openai%2Fimage-generations"},"type":"openai/image-generations","aliases":[],"tags":["playground:image","tier:tier_2"]},{"id":"hunyuan/hunyuan-image-v3-text-to-image","info":{"releasedAt":"2025-10-13","name":"Hunyuan Image V3","developer":"Tencent","description":"Hunyuan Image V3 is an advanced text-to-image model that generates high-quality images from text prompts.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/image-models/tencent/hunyuan-image-v3-text-to-image","docsJson":"https://api.aimlapi.com/docs-json?model=hunyuan%2Fhunyuan-image-v3-text-to-image&endpoint=openai%2Fimage-generations"},"type":"openai/image-generations","aliases":[],"tags":["playground:image","tier:tier_2"]},{"id":"tencent/hunyuan-part","info":{"releasedAt":"2025-11-17","name":"Hunyuan Part","developer":"Tencent","description":"Tencent Hunyuan Part is a 3D generation model for creating detailed 3D assets from text or image inputs.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/3d-generating-models/tencent/hunyuan-part","docsJson":"https://api.aimlapi.com/docs-json?model=tencent%2Fhunyuan-part&endpoint=openai%2Fimage-generations"},"type":"openai/image-generations","aliases":[],"tags":["tier:tier_2","playground:image_3d"]},{"id":"google/lyria2","info":{"releasedAt":"2025-12-05","name":"Lyria 2","developer":"Google","description":"Lyria 2 is Google's advanced music generation model capable of creating high-quality, diverse musical compositions from text.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/music-models/google/lyria-2","docsJson":"https://api.aimlapi.com/docs-json?model=google%2Flyria2&endpoint=internal%2Faudio-generations%2Fsubmit"},"type":"internal/audio-generations/submit","aliases":[],"tags":["playground:audio","tier:tier_2"]},{"id":"veed/fabric-1.0","info":{"releasedAt":"2025-11-24","name":"VEED Fabric-1.0","developer":"VEED","description":"Generate high-quality videos from image and audio inputs using VEED Fabric-1.0 model.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/video-models/veed/fabric-1.0","docsJson":"https://api.aimlapi.com/docs-json?model=veed%2Ffabric-1.0&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":[],"tags":["playground:video","tier:tier_2"]},{"id":"veed/fabric-1.0/fast","info":{"releasedAt":"2025-11-24","name":"VEED Fabric-1.0 Fast","developer":"VEED","description":"Generate high-quality videos from image and audio inputs with faster processing using VEED Fabric-1.0 Fast model.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/video-models/veed/fabric-1.0-fast","docsJson":"https://api.aimlapi.com/docs-json?model=veed%2Ffabric-1.0%2Ffast&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":[],"tags":["playground:video","tier:tier_2"]},{"id":"tencent/hunyuan-video-foley","info":{"releasedAt":"2025-11-24","name":"Hunyuan Video Foley","developer":"Tencent","description":"Generate foley audio for videos using Tencent Hunyuan Video Foley model. Adds realistic sound effects synchronized with video content.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/video-models/tencent/hunyuan-video-foley","docsJson":"https://api.aimlapi.com/docs-json?model=tencent%2Fhunyuan-video-foley&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":[],"tags":["playground:video","tier:tier_2"]},{"id":"sber-ai/kandinsky5-t2v","info":{"releasedAt":"2025-11-24","name":"Kandinsky5 Text to Video","developer":"Sber AI","description":"Kandinsky5 text-to-video model generates high-quality videos from text prompts. $0.10 for 5s, $0.20 for 10s.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/video-models/sber-ai/kandinsky5-text-to-video","docsJson":"https://api.aimlapi.com/docs-json?model=sber-ai%2Fkandinsky5-t2v&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":[],"tags":["playground:video","tier:tier_2"]},{"id":"sber-ai/kandinsky5-distill-t2v","info":{"releasedAt":"2025-11-24","name":"Kandinsky5 Text to Video Distill","developer":"Sber AI","description":"Kandinsky5 distilled text-to-video model for faster generation. $0.05 for 5s, $0.10 for 10s.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/video-models/sber-ai/kandinsky5-distill-text-to-video","docsJson":"https://api.aimlapi.com/docs-json?model=sber-ai%2Fkandinsky5-distill-t2v&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":[],"tags":["playground:video","tier:tier_2"]},{"id":"krea/krea-wan-14b/text-to-video","info":{"releasedAt":"2025-11-24","name":"Krea WAN 14B Text to Video","developer":"Krea","description":"Krea WAN 14B Text to Video generates high-quality videos from text using the 14B parameter WAN model.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/video-models/krea/krea-wan-14b-text-to-video","docsJson":"https://api.aimlapi.com/docs-json?model=krea%2Fkrea-wan-14b%2Ftext-to-video&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":[],"tags":["playground:video","tier:tier_2"]},{"id":"krea/krea-wan-14b/video-to-video","info":{"releasedAt":"2025-11-24","name":"Krea WAN 14B Video to Video","developer":"Krea","description":"Krea WAN 14B Video to Video transforms and re-renders existing videos with AI-driven style and motion control.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/video-models/krea/krea-wan-14b-video-to-video","docsJson":"https://api.aimlapi.com/docs-json?model=krea%2Fkrea-wan-14b%2Fvideo-to-video&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":[],"tags":["playground:video","tier:tier_2"]},{"id":"ltxv/ltxv-2","info":{"releasedAt":"2025-11-24","name":"LTXV 2","developer":"LTXV","description":"Generate high-quality videos from text prompts or images using LTXV 2 model with support for multiple resolutions and frame rates.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/video-models/ltxv/ltxv-2","docsJson":"https://api.aimlapi.com/docs-json?model=ltxv%2Fltxv-2&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":[],"tags":["playground:video","tier:tier_2"]},{"id":"ltxv/ltxv-2-fast","info":{"releasedAt":"2025-11-24","name":"LTXV 2 Fast","developer":"LTXV","description":"Generate high-quality videos from text prompts or images using LTXV 2 fast model with support for multiple resolutions and frame rates at faster speeds.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/video-models/ltxv/ltxv-2-fast","docsJson":"https://api.aimlapi.com/docs-json?model=ltxv%2Fltxv-2-fast&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":[],"tags":["playground:video","tier:tier_2"]},{"id":"microsoft/vibevoice-7b","info":{"releasedAt":"2026-01-05","name":"VibeVoice 7B","developer":"Microsoft","description":"VibeVoice 7B is a high-quality text-to-speech model that supports multi-speaker dialogue generation with natural-sounding voices.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/speech-models/text-to-speech/microsoft/vibevoice-7b","docsJson":"https://api.aimlapi.com/docs-json?model=microsoft%2Fvibevoice-7b&endpoint=internal%2Ftext-to-speech"},"type":"internal/text-to-speech","aliases":[],"tags":["playground:tts","tier:tier_2"]},{"id":"microsoft/vibevoice-1.5b","info":{"releasedAt":"2026-01-05","name":"VibeVoice 1.5B","developer":"Microsoft","description":"VibeVoice 1.5B is an efficient text-to-speech model that supports multi-speaker dialogue generation with natural-sounding voices.","url":"","docsUrl":"https://docs.aimlapi.com/api-references/speech-models/text-to-speech/microsoft/vibevoice-1.5b","docsJson":"https://api.aimlapi.com/docs-json?model=microsoft%2Fvibevoice-1.5b&endpoint=internal%2Ftext-to-speech"},"type":"internal/text-to-speech","aliases":[],"tags":["playground:tts","tier:tier_2"]},{"id":"blackforestlabs/flux-2-pro","info":{"releasedAt":"2026-06-12","name":"FLUX.2 Pro","developer":"Black Forest Labs","description":"Professional FLUX.2 image generation and editing with strong prompt adherence.","url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=blackforestlabs%2Fflux-2-pro&endpoint=openai%2Fimage-generations"},"type":"openai/image-generations","aliases":[],"tags":["playground:image","tier:tier_2"]},{"id":"blackforestlabs/flux-2-pro-preview","info":{"releasedAt":"2026-06-12","name":"FLUX.2 Pro Preview","developer":"Black Forest Labs","description":"Preview release of the FLUX.2 Pro image model.","url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=blackforestlabs%2Fflux-2-pro-preview&endpoint=openai%2Fimage-generations"},"type":"openai/image-generations","aliases":[],"tags":["playground:image","tier:tier_2"]},{"id":"blackforestlabs/flux-2-max","info":{"releasedAt":"2026-06-12","name":"FLUX.2 Max","developer":"Black Forest Labs","description":"Highest-quality FLUX.2 model for detailed image generation and editing.","url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=blackforestlabs%2Fflux-2-max&endpoint=openai%2Fimage-generations"},"type":"openai/image-generations","aliases":[],"tags":["playground:image","tier:tier_2"]},{"id":"blackforestlabs/flux-2-flex","info":{"releasedAt":"2026-06-12","name":"FLUX.2 Flex","developer":"Black Forest Labs","description":"Configurable FLUX.2 model balancing quality, latency, and control.","url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=blackforestlabs%2Fflux-2-flex&endpoint=openai%2Fimage-generations"},"type":"openai/image-generations","aliases":[],"tags":["playground:image","tier:tier_2"]},{"id":"blackforestlabs/flux-2-klein-9b","info":{"releasedAt":"2026-06-12","name":"FLUX.2 Klein 9B","developer":"Black Forest Labs","description":"Compact 9B FLUX.2 model for efficient image generation.","url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=blackforestlabs%2Fflux-2-klein-9b&endpoint=openai%2Fimage-generations"},"type":"openai/image-generations","aliases":[],"tags":["playground:image","tier:tier_2"]},{"id":"blackforestlabs/flux-2-klein-9b-preview","info":{"releasedAt":"2026-06-12","name":"FLUX.2 Klein 9B Preview","developer":"Black Forest Labs","description":"Preview release of the compact FLUX.2 Klein 9B model.","url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=blackforestlabs%2Fflux-2-klein-9b-preview&endpoint=openai%2Fimage-generations"},"type":"openai/image-generations","aliases":[],"tags":["playground:image","tier:tier_2"]},{"id":"blackforestlabs/flux-2-klein-4b","info":{"releasedAt":"2026-06-12","name":"FLUX.2 Klein 4B","developer":"Black Forest Labs","description":"Compact 4B FLUX.2 model optimized for efficient generation.","url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=blackforestlabs%2Fflux-2-klein-4b&endpoint=openai%2Fimage-generations"},"type":"openai/image-generations","aliases":[],"tags":["playground:image","tier:tier_2"]},{"id":"blackforestlabs/flux-outpainting","info":{"releasedAt":"2026-06-12","name":"FLUX Outpainting","developer":"Black Forest Labs","description":"Extends an image beyond its original canvas.","url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=blackforestlabs%2Fflux-outpainting&endpoint=openai%2Fimage-generations"},"type":"openai/image-generations","aliases":[],"tags":["playground:image","tier:tier_2"]},{"id":"blackforestlabs/flux-erase","info":{"releasedAt":"2026-06-12","name":"FLUX Erase","developer":"Black Forest Labs","description":"Removes masked content from an image.","url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=blackforestlabs%2Fflux-erase&endpoint=openai%2Fimage-generations"},"type":"openai/image-generations","aliases":[],"tags":["playground:image","tier:tier_2"]},{"id":"blackforestlabs/flux-vto","info":{"releasedAt":"2026-06-12","name":"FLUX Virtual Try-On","developer":"Black Forest Labs","description":"Generates virtual clothing try-on images.","url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=blackforestlabs%2Fflux-vto&endpoint=openai%2Fimage-generations"},"type":"openai/image-generations","aliases":[],"tags":["playground:image","tier:tier_2"]},{"id":"blackforestlabs/flux-kontext-pro","info":{"releasedAt":"2026-06-12","name":"FLUX.1 Kontext Pro","developer":"Black Forest Labs","description":"Context-aware image generation and editing model.","url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=blackforestlabs%2Fflux-kontext-pro&endpoint=openai%2Fimage-generations"},"type":"openai/image-generations","aliases":[],"tags":["playground:image","tier:tier_2"]},{"id":"blackforestlabs/flux-kontext-max","info":{"releasedAt":"2026-06-12","name":"FLUX.1 Kontext Max","developer":"Black Forest Labs","description":"Highest-capability Kontext image generation and editing model.","url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=blackforestlabs%2Fflux-kontext-max&endpoint=openai%2Fimage-generations"},"type":"openai/image-generations","aliases":[],"tags":["playground:image","tier:tier_2"]},{"id":"blackforestlabs/flux-pro-1.1","info":{"releasedAt":"2026-06-12","name":"FLUX 1.1 Pro","developer":"Black Forest Labs","description":"Professional FLUX 1.1 text-to-image model.","url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=blackforestlabs%2Fflux-pro-1.1&endpoint=openai%2Fimage-generations"},"type":"openai/image-generations","aliases":[],"tags":["playground:image","tier:tier_2"]},{"id":"blackforestlabs/flux-pro-1.1-ultra","info":{"releasedAt":"2026-06-12","name":"FLUX 1.1 Pro Ultra","developer":"Black Forest Labs","description":"High-resolution FLUX 1.1 Pro image generation model.","url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=blackforestlabs%2Fflux-pro-1.1-ultra&endpoint=openai%2Fimage-generations"},"type":"openai/image-generations","aliases":[],"tags":["playground:image","tier:tier_2"]},{"id":"blackforestlabs/flux-dev","info":{"releasedAt":"2026-06-12","name":"FLUX.1 Dev","developer":"Black Forest Labs","description":"Development-oriented FLUX.1 image generation model.","url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=blackforestlabs%2Fflux-dev&endpoint=openai%2Fimage-generations"},"type":"openai/image-generations","aliases":[],"tags":["playground:image","tier:tier_2"]},{"id":"blackforestlabs/flux-fill","info":{"releasedAt":"2026-06-12","name":"FLUX.1 Fill","developer":"Black Forest Labs","description":"FLUX.1 inpainting and masked image filling model.","url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=blackforestlabs%2Fflux-fill&endpoint=openai%2Fimage-generations"},"type":"openai/image-generations","aliases":[],"tags":["playground:image","tier:tier_2"]},{"id":"blackforestlabs/flux-expand","info":{"releasedAt":"2026-06-12","name":"FLUX.1 Expand","developer":"Black Forest Labs","description":"FLUX.1 image expansion and outpainting model.","url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=blackforestlabs%2Fflux-expand&endpoint=openai%2Fimage-generations"},"type":"openai/image-generations","aliases":[],"tags":["playground:image","tier:tier_2"]},{"id":"beeble/switchx-video-to-video","info":{"releasedAt":"2026-06-15","name":"SwitchX Video to Video","developer":"Beeble","description":"SwitchX is a video-to-video compositing model by Beeble that replaces a scene element while preserving the original subject, with automatic subject detection and seamless relighting to match a reference image. Does not support tools/function calling.","url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=beeble%2Fswitchx-video-to-video&endpoint=internal%2Fvideo-generations%2Fsubmit"},"type":"internal/video-generations/submit","aliases":["switchx-video-to-video"],"tags":["playground:video","tier:tier_2"]},{"id":"beeble/switchx-image-to-image","info":{"releasedAt":"2026-06-15","name":"SwitchX Image to Image","developer":"Beeble","description":"SwitchX is an image-to-image compositing model by Beeble that replaces a scene element while preserving the original subject, with automatic subject detection and seamless relighting to match a reference image. Does not support tools/function calling.","url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=beeble%2Fswitchx-image-to-image&endpoint=openai%2Fimage-generations"},"type":"openai/image-generations","aliases":["switchx-image-to-image"],"tags":["playground:image","tier:tier_2"]},{"id":"ai21/jamba-large-1.7","info":{"releasedAt":"2025-08-08","name":"Jamba Large 1.7","developer":"AI21","contextLength":256000,"outputMax":4096,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=ai21%2Fjamba-large-1.7&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["jamba-large-1.7"],"tags":["playground:chat","tier:tier_2"]},{"id":"aion-labs/aion-3.0-mini","info":{"releasedAt":"2026-07-07","name":"Aion-3.0-Mini","developer":"AionLabs","contextLength":131072,"outputMax":32768,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=aion-labs%2Faion-3.0-mini&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["aion-3.0-mini"],"tags":["playground:chat","tier:tier_2"]},{"id":"aion-labs/aion-2.0","info":{"releasedAt":"2026-02-23","name":"Aion-2.0","developer":"AionLabs","contextLength":131072,"outputMax":32768,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=aion-labs%2Faion-2.0&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["aion-2.0"],"tags":["playground:chat","tier:tier_2"]},{"id":"aion-labs/aion-3.0","info":{"releasedAt":"2026-07-07","name":"Aion-3.0","developer":"AionLabs","contextLength":131072,"outputMax":32768,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=aion-labs%2Faion-3.0&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["aion-3.0"],"tags":["playground:chat","tier:tier_2"]},{"id":"aion-labs/aion-rp-llama-3.1-8b","info":{"releasedAt":"2025-02-04","name":"Aion-RP 1.0 (8B)","developer":"AionLabs","contextLength":32768,"outputMax":32768,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=aion-labs%2Faion-rp-llama-3.1-8b&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["aion-rp-llama-3.1-8b"],"tags":["playground:chat","tier:tier_2"]},{"id":"allenai/olmo-3-32b-think","info":{"releasedAt":"2025-11-21","name":"Olmo 3 32B Think","developer":"AllenAI","contextLength":65536,"outputMax":65536,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=allenai%2Folmo-3-32b-think&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["olmo-3-32b-think"],"tags":["playground:chat","tier:tier_2"]},{"id":"amazon/nova-2-lite-v1","info":{"releasedAt":"2025-12-02","name":"Nova 2 Lite","developer":"Amazon","contextLength":1000000,"outputMax":65535,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=amazon%2Fnova-2-lite-v1&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["nova-2-lite-v1"],"tags":["playground:chat","tier:tier_2"]},{"id":"amazon/nova-premier-v1","info":{"releasedAt":"2025-10-31","name":"Nova Premier 1.0","developer":"Amazon","contextLength":1000000,"outputMax":32000,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=amazon%2Fnova-premier-v1&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["nova-premier-v1"],"tags":["playground:chat","tier:tier_2"]},{"id":"amazon/nova-lite-v1","info":{"releasedAt":"2024-12-05","name":"Nova Lite 1.0","developer":"Amazon","contextLength":300000,"outputMax":5120,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=amazon%2Fnova-lite-v1&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["nova-lite-v1"],"tags":["playground:chat","tier:tier_2"]},{"id":"amazon/nova-micro-v1","info":{"releasedAt":"2024-12-05","name":"Nova Micro 1.0","developer":"Amazon","contextLength":128000,"outputMax":5120,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=amazon%2Fnova-micro-v1&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["nova-micro-v1"],"tags":["playground:chat","tier:tier_2"]},{"id":"amazon/nova-pro-v1","info":{"releasedAt":"2024-12-05","name":"Nova Pro 1.0","developer":"Amazon","contextLength":300000,"outputMax":5120,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=amazon%2Fnova-pro-v1&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["nova-pro-v1"],"tags":["playground:chat","tier:tier_2"]},{"id":"arcee-ai/trinity-large-thinking","info":{"releasedAt":"2026-04-01","name":"Trinity Large Thinking","developer":"Arcee AI","contextLength":262144,"outputMax":80000,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=arcee-ai%2Ftrinity-large-thinking&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["trinity-large-thinking"],"tags":["playground:chat","tier:tier_2"]},{"id":"arcee-ai/virtuoso-large","info":{"releasedAt":"2025-05-05","name":"Virtuoso Large","developer":"Arcee AI","contextLength":131072,"outputMax":64000,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=arcee-ai%2Fvirtuoso-large&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["virtuoso-large"],"tags":["playground:chat","tier:tier_2"]},{"id":"arcee-ai/coder-large","info":{"releasedAt":"2025-05-05","name":"Coder Large","developer":"Arcee AI","contextLength":32768,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=arcee-ai%2Fcoder-large&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["coder-large"],"tags":["playground:chat","tier:tier_2"]},{"id":"bytedance-seed/seed-2.0-lite","info":{"releasedAt":"2026-03-10","name":"Seed-2.0-Lite","developer":"ByteDance","contextLength":262144,"outputMax":131072,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=bytedance-seed%2Fseed-2.0-lite&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["seed-2.0-lite"],"tags":["playground:chat","tier:tier_2"]},{"id":"bytedance-seed/seed-2.0-mini","info":{"releasedAt":"2026-02-26","name":"Seed-2.0-Mini","developer":"ByteDance","contextLength":262144,"outputMax":131072,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=bytedance-seed%2Fseed-2.0-mini&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["seed-2.0-mini"],"tags":["playground:chat","tier:tier_2"]},{"id":"bytedance-seed/seed-1.6-flash","info":{"releasedAt":"2025-12-23","name":"Seed 1.6 Flash","developer":"ByteDance","contextLength":262144,"outputMax":32768,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=bytedance-seed%2Fseed-1.6-flash&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["seed-1.6-flash"],"tags":["playground:chat","tier:tier_2"]},{"id":"bytedance-seed/seed-1.6","info":{"releasedAt":"2025-12-23","name":"Seed 1.6","developer":"ByteDance","contextLength":262144,"outputMax":32768,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=bytedance-seed%2Fseed-1.6&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["seed-1.6"],"tags":["playground:chat","tier:tier_2"]},{"id":"cognitivecomputations/dolphin-mistral-24b-venice-edition","info":{"name":"Venice Uncensored","developer":"Venice","description":"Venice Uncensored (Dolphin Mistral 24B Venice Edition) is an uncensored, instruction-tuned chat model built on Mistral Small 24B by Cognitive Computations in partnership with Venice.ai. It follows system prompts closely and is designed to respond without built-in content refusals.","contextLength":128000,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=cognitivecomputations%2Fdolphin-mistral-24b-venice-edition&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["dolphin-mistral-24b-venice-edition"],"tags":["playground:chat","tier:tier_2"]},{"id":"deepcogito/cogito-v2.1-671b","info":{"releasedAt":"2025-11-13","name":"Cogito v2.1 671B","developer":"Deep Cogito","contextLength":128000,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=deepcogito%2Fcogito-v2.1-671b&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["cogito-v2.1-671b"],"tags":["playground:chat","tier:tier_2"]},{"id":"ibm-granite/granite-4.1-8b","info":{"releasedAt":"2026-04-30","name":"Granite 4.1 8B","developer":"IBM","contextLength":131072,"outputMax":131072,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=ibm-granite%2Fgranite-4.1-8b&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["granite-4.1-8b"],"tags":["playground:chat","tier:tier_2"]},{"id":"ibm-granite/granite-4.0-h-micro","info":{"releasedAt":"2025-10-20","name":"Granite 4.0 Micro","developer":"IBM","contextLength":131000,"outputMax":131000,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=ibm-granite%2Fgranite-4.0-h-micro&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["granite-4.0-h-micro"],"tags":["playground:chat","tier:tier_2"]},{"id":"inception/mercury-2","info":{"releasedAt":"2026-03-04","name":"Mercury 2","developer":"Inception","contextLength":128000,"outputMax":50000,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=inception%2Fmercury-2&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["mercury-2"],"tags":["playground:chat","tier:tier_2"]},{"id":"inclusionai/ring-2.6-1t","info":{"releasedAt":"2026-05-08","name":"Ring-2.6-1T","developer":"inclusionAI","contextLength":262144,"outputMax":65536,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=inclusionai%2Fring-2.6-1t&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["ring-2.6-1t"],"tags":["playground:chat","tier:tier_2"]},{"id":"inclusionai/ling-2.6-1t","info":{"releasedAt":"2026-04-23","name":"Ling-2.6-1T","developer":"inclusionAI","contextLength":262144,"outputMax":32768,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=inclusionai%2Fling-2.6-1t&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["ling-2.6-1t"],"tags":["playground:chat","tier:tier_2"]},{"id":"inclusionai/ling-2.6-flash","info":{"releasedAt":"2026-04-21","name":"Ling-2.6-flash","developer":"inclusionAI","contextLength":262144,"outputMax":32768,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=inclusionai%2Fling-2.6-flash&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["ling-2.6-flash"],"tags":["playground:chat","tier:tier_2"]},{"id":"inflection/inflection-3-pi","info":{"releasedAt":"2024-10-11","name":"3 Pi","developer":"Inflection","contextLength":8000,"outputMax":1024,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=inflection%2Finflection-3-pi&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["inflection-3-pi"],"tags":["playground:chat","tier:tier_2"]},{"id":"inflection/inflection-3-productivity","info":{"releasedAt":"2024-10-11","name":"3 Productivity","developer":"Inflection","contextLength":8000,"outputMax":1024,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=inflection%2Finflection-3-productivity&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["inflection-3-productivity"],"tags":["playground:chat","tier:tier_2"]},{"id":"kwaipilot/kat-coder-pro-v2","info":{"releasedAt":"2026-03-27","name":"KAT-Coder-Pro V2","developer":"Kwaipilot","contextLength":256000,"outputMax":80000,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=kwaipilot%2Fkat-coder-pro-v2&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["kat-coder-pro-v2"],"tags":["playground:chat","tier:tier_2"]},{"id":"kwaipilot/kat-coder-pro-v2.5","info":{"name":"KAT-Coder-Pro V2.5","developer":"Kwaipilot","contextLength":256000,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=kwaipilot%2Fkat-coder-pro-v2.5&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["kat-coder-pro-v2.5"],"tags":["playground:chat","tier:tier_2"]},{"id":"kwaipilot/kat-coder-air-v2.5","info":{"name":"KAT-Coder-Air V2.5","developer":"Kwaipilot","contextLength":256000,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=kwaipilot%2Fkat-coder-air-v2.5&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["kat-coder-air-v2.5"],"tags":["playground:chat","tier:tier_2"]},{"id":"mancer/weaver","info":{"releasedAt":"2023-08-02","name":"Weaver (alpha)","developer":"Mancer","contextLength":8000,"outputMax":2000,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=mancer%2Fweaver&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["weaver"],"tags":["playground:chat","tier:tier_2"]},{"id":"moonshotai/kimi-latest","info":{"releasedAt":"2026-04-27","name":"Kimi Latest","developer":"Moonshot","contextLength":262144,"outputMax":262144,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=moonshotai%2Fkimi-latest&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["kimi-latest"],"tags":["playground:chat","tier:tier_2"]},{"id":"moonshotai/kimi-k2-thinking","info":{"releasedAt":"2025-11-06","name":"Kimi K2 Thinking","developer":"Moonshot","contextLength":262144,"outputMax":100352,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=moonshotai%2Fkimi-k2-thinking&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["kimi-k2-thinking"],"tags":["playground:chat","tier:tier_2"]},{"id":"moonshotai/kimi-k2-0905","info":{"releasedAt":"2025-09-04","name":"Kimi K2 0905","developer":"Moonshot","contextLength":262144,"outputMax":100352,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=moonshotai%2Fkimi-k2-0905&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["kimi-k2-0905"],"tags":["playground:chat","tier:tier_2"]},{"id":"moonshotai/kimi-k2","info":{"releasedAt":"2025-07-11","name":"Kimi K2 0711","developer":"Moonshot","contextLength":131072,"outputMax":100352,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=moonshotai%2Fkimi-k2&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["kimi-k2"],"tags":["playground:chat","tier:tier_2"]},{"id":"morph/morph-v3-large","info":{"releasedAt":"2025-07-07","name":"V3 Large","developer":"Morph","contextLength":262144,"outputMax":131072,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=morph%2Fmorph-v3-large&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["morph-v3-large"],"tags":["playground:chat","tier:tier_2"]},{"id":"morph/morph-v3-fast","info":{"releasedAt":"2025-07-07","name":"V3 Fast","developer":"Morph","contextLength":81920,"outputMax":38000,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=morph%2Fmorph-v3-fast&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["morph-v3-fast"],"tags":["playground:chat","tier:tier_2"]},{"id":"nex-agi/nex-n2-mini","info":{"releasedAt":"2026-06-24","name":"Nex-N2-Mini","developer":"Nex AGI","contextLength":262144,"outputMax":262144,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=nex-agi%2Fnex-n2-mini&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["nex-n2-mini"],"tags":["playground:chat","tier:tier_2"]},{"id":"nex-agi/nex-n2-pro","info":{"releasedAt":"2026-06-08","name":"Nex-N2-Pro","developer":"Nex AGI","contextLength":262144,"outputMax":262144,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=nex-agi%2Fnex-n2-pro&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["nex-n2-pro"],"tags":["playground:chat","tier:tier_2"]},{"id":"perceptron/perceptron-mk1","info":{"releasedAt":"2026-05-12","name":"Mk1","developer":"Perceptron","contextLength":32768,"outputMax":8192,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=perceptron%2Fperceptron-mk1&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["perceptron-mk1"],"tags":["playground:chat","tier:tier_2"]},{"id":"poolside/laguna-xs-2.1","info":{"releasedAt":"2026-07-02","name":"Laguna XS 2.1","developer":"Poolside","contextLength":262144,"outputMax":32768,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=poolside%2Flaguna-xs-2.1&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["laguna-xs-2.1"],"tags":["playground:chat","tier:tier_2"]},{"id":"poolside/laguna-m.1","info":{"releasedAt":"2026-04-28","name":"Laguna M.1","developer":"Poolside","contextLength":262144,"outputMax":32768,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=poolside%2Flaguna-m.1&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["laguna-m.1"],"tags":["playground:chat","tier:tier_2"]},{"id":"rekaai/reka-edge","info":{"releasedAt":"2026-03-20","name":"Reka Edge","developer":"RekaAI","contextLength":16384,"outputMax":16384,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=rekaai%2Freka-edge&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["reka-edge"],"tags":["playground:chat","tier:tier_2"]},{"id":"rekaai/reka-flash-3","info":{"releasedAt":"2025-03-12","name":"Reka Flash 3","developer":"RekaAI","contextLength":65536,"outputMax":65536,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=rekaai%2Freka-flash-3&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["reka-flash-3"],"tags":["playground:chat","tier:tier_2"]},{"id":"relace/relace-search","info":{"releasedAt":"2025-12-08","name":"Search","developer":"Relace","contextLength":256000,"outputMax":128000,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=relace%2Frelace-search&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["relace-search"],"tags":["playground:chat","tier:tier_2"]},{"id":"relace/relace-apply-3","info":{"releasedAt":"2025-09-26","name":"Apply 3","developer":"Relace","contextLength":256000,"outputMax":128000,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=relace%2Frelace-apply-3&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["relace-apply-3"],"tags":["playground:chat","tier:tier_2"]},{"id":"sao10k/l3.1-70b-hanami-x1","info":{"releasedAt":"2025-01-08","name":"Llama 3.1 70B Hanami x1","developer":"Sao10K","contextLength":16000,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=sao10k%2Fl3.1-70b-hanami-x1&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["l3.1-70b-hanami-x1"],"tags":["playground:chat","tier:tier_2"]},{"id":"sao10k/l3.3-euryale-70b","info":{"releasedAt":"2024-12-18","name":"Llama 3.3 Euryale 70B","developer":"Sao10K","contextLength":131072,"outputMax":16384,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=sao10k%2Fl3.3-euryale-70b&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["l3.3-euryale-70b"],"tags":["playground:chat","tier:tier_2"]},{"id":"sao10k/l3.1-euryale-70b","info":{"releasedAt":"2024-08-28","name":"Llama 3.1 Euryale 70B v2.2","developer":"Sao10K","contextLength":131072,"outputMax":16384,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=sao10k%2Fl3.1-euryale-70b&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["l3.1-euryale-70b"],"tags":["playground:chat","tier:tier_2"]},{"id":"sao10k/l3-lunaris-8b","info":{"releasedAt":"2024-08-13","name":"Llama 3 8B Lunaris","developer":"Sao10K","contextLength":8192,"outputMax":16384,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=sao10k%2Fl3-lunaris-8b&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["l3-lunaris-8b"],"tags":["playground:chat","tier:tier_2"]},{"id":"thedrummer/cydonia-24b-v4.1","info":{"releasedAt":"2025-09-27","name":"Cydonia 24B V4.1","developer":"TheDrummer","contextLength":131072,"outputMax":131072,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=thedrummer%2Fcydonia-24b-v4.1&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["cydonia-24b-v4.1"],"tags":["playground:chat","tier:tier_2"]},{"id":"thedrummer/skyfall-36b-v2","info":{"releasedAt":"2025-03-10","name":"Skyfall 36B V2","developer":"TheDrummer","contextLength":32768,"outputMax":32768,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=thedrummer%2Fskyfall-36b-v2&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["skyfall-36b-v2"],"tags":["playground:chat","tier:tier_2"]},{"id":"thedrummer/unslopnemo-12b","info":{"releasedAt":"2024-11-08","name":"UnslopNemo 12B","developer":"TheDrummer","contextLength":32768,"outputMax":32768,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=thedrummer%2Funslopnemo-12b&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["unslopnemo-12b"],"tags":["playground:chat","tier:tier_2"]},{"id":"thedrummer/rocinante-12b","info":{"releasedAt":"2024-09-30","name":"Rocinante 12B","developer":"TheDrummer","contextLength":32768,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=thedrummer%2Frocinante-12b&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["rocinante-12b"],"tags":["playground:chat","tier:tier_2"]},{"id":"undi95/remm-slerp-l2-13b","info":{"releasedAt":"2023-07-22","name":"ReMM SLERP 13B","developer":"Undi95","contextLength":6144,"outputMax":4096,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=undi95%2Fremm-slerp-l2-13b&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["remm-slerp-l2-13b"],"tags":["playground:chat","tier:tier_2"]},{"id":"upstage/solar-pro-3","info":{"releasedAt":"2026-01-27","name":"Solar Pro 3","developer":"Upstage","contextLength":128000,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=upstage%2Fsolar-pro-3&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["solar-pro-3"],"tags":["playground:chat","tier:tier_2"]},{"id":"writer/palmyra-x5","info":{"releasedAt":"2026-01-21","name":"Palmyra X5","developer":"Writer","contextLength":1040000,"outputMax":8192,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=writer%2Fpalmyra-x5&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["palmyra-x5"],"tags":["playground:chat","tier:tier_2"]},{"id":"z-ai/glm-5v-turbo","info":{"releasedAt":"2026-04-01","name":"GLM 5V Turbo","developer":"Zhipu AI","contextLength":202752,"outputMax":131072,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=z-ai%2Fglm-5v-turbo&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["glm-5v-turbo"],"tags":["playground:chat","tier:tier_2"]},{"id":"z-ai/glm-5-turbo","info":{"releasedAt":"2026-03-15","name":"GLM 5 Turbo","developer":"Zhipu AI","contextLength":262144,"outputMax":131072,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=z-ai%2Fglm-5-turbo&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["glm-5-turbo"],"tags":["playground:chat","tier:tier_2"]},{"id":"z-ai/glm-4.7-flash","info":{"releasedAt":"2026-01-19","name":"GLM 4.7 Flash","developer":"Zhipu AI","contextLength":202752,"outputMax":16384,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=z-ai%2Fglm-4.7-flash&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["glm-4.7-flash"],"tags":["playground:chat","tier:tier_2"]},{"id":"z-ai/glm-4.6v","info":{"releasedAt":"2025-12-08","name":"GLM 4.6V","developer":"Zhipu AI","contextLength":131072,"outputMax":32768,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=z-ai%2Fglm-4.6v&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["glm-4.6v"],"tags":["playground:chat","tier:tier_2"]},{"id":"z-ai/glm-4.5v","info":{"releasedAt":"2025-08-11","name":"GLM 4.5V","developer":"Zhipu AI","contextLength":65536,"outputMax":16384,"url":"","docsUrl":"","docsJson":"https://api.aimlapi.com/docs-json?model=z-ai%2Fglm-4.5v&endpoint=openai%2Fchat-completions"},"type":"openai/chat-completions","aliases":["glm-4.5v"],"tags":["playground:chat","tier:tier_2"]}]}