Chat, completion, and instruction-tuned models that output text.
Models can support multiple endpoints. We group them by model and list every supported API route.
qwen/qwen-3-5-397b-a17b-2026-02-16minimax/minimax-m2-5-2026-02-12z-ai/glm-5-2026-02-11moonshot-ai/kimi-k2-5-2026-01-27qwen/qwen-3-max-thinking-2026-01-26z-ai/glm-4-7-flash-2026-01-19minimax/minimax-m2-1-2025-12-23z-ai/glm-4-7-2025-12-22xiaomi/mimo-v2-flash-2025-12-16z-ai/glm-4-6v-2025-12-08deepseek/deepseek-v3-2-2025-12-01moonshot-ai/kimi-k2-thinking-2025-11-06minimax/minimax-m2-2025-10-27z-ai/glm-4-6-2025-09-30deepseek/deepseek-v3-2-exp-2025-09-29deepseek/deepseek-v3-1-terminus-2025-09-22moonshot-ai/kimi-k2-2025-09-05deepseek/deepseek-v3-1-2025-08-21z-ai/glm-4-5v-2025-08-11openai/gpt-oss-120b-2025-08-05openai/gpt-oss-20b-2025-08-05z-ai/glm-4-5-2025-07-28z-ai/glm-4-5-air-2025-07-28moonshot-ai/kimi-k2-2025-07-11minimax/minimax-m1-80k-2025-06-16deepseek/deepseek-r1-2025-05-28meta/llama-4-maverick-2025-04-05meta/llama-4-scout-2025-04-05deepseek/deepseek-v3-2025-03-25google/gemma-3-27b-2025-03-12meta/llama-3-3-70b-instruct-2024-12-06meta/llama-3-1-8b-instruct-2024-07-23mistral/mistral-nemo-12b-2024-07-18meta/llama-3-70b-instruct-2024-04-18meta/llama-3-8b-instruct-2024-04-18deepseek/deepseek-ocr-2baidu/ernie-4-5-21b-a3bbaidu/ernie-4-5-21b-a3b-thinkingbaidu/ernie-4-5-300b-a47bbaidu/ernie-4-5-vl-28b-a3bbaidu/ernie-4-5-vl-424b-a47bqwen/qwen-2-5-72bqwen/qwen-2-5-7bqwen/qwen-2-5-vl-72b-instructqwen/qwen-3-235b-a22bqwen/qwen-3-235b-a22b-thinking-2507qwen/qwen-3-30b-a3bqwen/qwen-3-32bqwen/qwen-3-4bqwen/qwen-3-coder-30b-a3b-instructqwen/qwen-3-coder-480b-a35b-instructqwen/qwen-3-coder-nextqwen/qwen-3-next-80b-a3b-instructqwen/qwen-3-next-80b-a3b-thinkingqwen/qwen-3-omni-30b-a3b-instructqwen/qwen-3-omni-30b-a3b-thinkingqwen/qwen-3-vl-235b-a22b-instructqwen/qwen-3-vl-235b-a22b-thinkingqwen/qwen-3-vl-30b-a3b-instructqwen/qwen-3-vl-30b-a3b-thinkingqwen/qwen-3-vl-8b-instructChat, completion, and instruction-tuned models that output text.
Models can support multiple endpoints. We group them by model and list every supported API route.
qwen/qwen-3-5-397b-a17b-2026-02-16minimax/minimax-m2-5-2026-02-12z-ai/glm-5-2026-02-11moonshot-ai/kimi-k2-5-2026-01-27qwen/qwen-3-max-thinking-2026-01-26z-ai/glm-4-7-flash-2026-01-19minimax/minimax-m2-1-2025-12-23z-ai/glm-4-7-2025-12-22xiaomi/mimo-v2-flash-2025-12-16z-ai/glm-4-6v-2025-12-08deepseek/deepseek-v3-2-2025-12-01moonshot-ai/kimi-k2-thinking-2025-11-06minimax/minimax-m2-2025-10-27z-ai/glm-4-6-2025-09-30deepseek/deepseek-v3-2-exp-2025-09-29deepseek/deepseek-v3-1-terminus-2025-09-22moonshot-ai/kimi-k2-2025-09-05deepseek/deepseek-v3-1-2025-08-21z-ai/glm-4-5v-2025-08-11openai/gpt-oss-120b-2025-08-05openai/gpt-oss-20b-2025-08-05z-ai/glm-4-5-2025-07-28z-ai/glm-4-5-air-2025-07-28moonshot-ai/kimi-k2-2025-07-11minimax/minimax-m1-80k-2025-06-16deepseek/deepseek-r1-2025-05-28meta/llama-4-maverick-2025-04-05meta/llama-4-scout-2025-04-05deepseek/deepseek-v3-2025-03-25google/gemma-3-27b-2025-03-12meta/llama-3-3-70b-instruct-2024-12-06meta/llama-3-1-8b-instruct-2024-07-23mistral/mistral-nemo-12b-2024-07-18meta/llama-3-70b-instruct-2024-04-18meta/llama-3-8b-instruct-2024-04-18deepseek/deepseek-ocr-2baidu/ernie-4-5-21b-a3bbaidu/ernie-4-5-21b-a3b-thinkingbaidu/ernie-4-5-300b-a47bbaidu/ernie-4-5-vl-28b-a3bbaidu/ernie-4-5-vl-424b-a47bqwen/qwen-2-5-72bqwen/qwen-2-5-7bqwen/qwen-2-5-vl-72b-instructqwen/qwen-3-235b-a22bqwen/qwen-3-235b-a22b-thinking-2507qwen/qwen-3-30b-a3bqwen/qwen-3-32bqwen/qwen-3-4bqwen/qwen-3-coder-30b-a3b-instructqwen/qwen-3-coder-480b-a35b-instructqwen/qwen-3-coder-nextqwen/qwen-3-next-80b-a3b-instructqwen/qwen-3-next-80b-a3b-thinkingqwen/qwen-3-omni-30b-a3b-instructqwen/qwen-3-omni-30b-a3b-thinkingqwen/qwen-3-vl-235b-a22b-instructqwen/qwen-3-vl-235b-a22b-thinkingqwen/qwen-3-vl-30b-a3b-instructqwen/qwen-3-vl-30b-a3b-thinkingqwen/qwen-3-vl-8b-instruct