Nothing matches that. Try a protocol, a capability or an endpoint path.
Every company whose models you can call through ChinaAPI, with the families it groups them in and the models in each family. A model maker is the company that builds the model. Which request formats a model accepts, and what the gateway does with each field, is stated per model.
gpt-5.5 is what you send as model. Exact IDs and prices are on the Models page.
glm-5 glm-5-turbo glm-5.1 glm-5.2 glm-5.3 glm-5.3-flash glm-5v-turbo glm-asr-2512 glm-image glm-ttscogview-4cogvideox-3agnes-image-2.0-flash agnes-image-2.1-flash agnes-image-2.5-flashagnes-video-2.5 agnes-video-2.5-flash agnes-video-v2.0agnes-2.5-flash agnes-2.5-pro agnes-2.5-pro-betaqwen-audio-3.0-asr-flash qwen-audio-3.0-realtime-flash qwen-audio-3.0-realtime-plus qwen-audio-3.0-tts-flash qwen-audio-3.0-tts-plus qwen-image-3.0 qwen-image-3.0-pro qwen3-asr-flash qwen3-tts-flash qwen3.5-livetranslate-flash-realtime qwen3.5-ocr qwen3.5-omni-flash qwen3.5-omni-flash-realtime qwen3.5-omni-plus qwen3.5-omni-plus-realtime qwen3.6-27b qwen3.6-35b-a3b qwen3.6-flash qwen3.6-plus qwen3.7-flash qwen3.7-max qwen3.7-plus qwen3.8-2.4t-a95b qwen3.8-27b qwen3.8-flash qwen3.8-maxwan2.7-i2v wan2.7-image wan2.7-image-pro wan2.7-r2v wan2.7-t2v wan2.7-videoedit wan3.0-videohappyhorse-1.1-i2v happyhorse-1.1-r2v happyhorse-1.1-t2vfun-asr-flash-2026-06-15claude-fable-5 claude-fable-5-1 claude-haiku-4-5 claude-opus-4-5 claude-opus-4-6 claude-opus-4-7 claude-opus-4-8 claude-opus-5 claude-sonnet-4-5 claude-sonnet-4-6 claude-sonnet-5doubao-seedance-2-0-260128 doubao-seedance-2-0-fast-260128 doubao-seedance-2-0-mini-260615 doubao-seedance-2-5-260628doubao-seedream-4-5-251128 doubao-seedream-5-0-260128 doubao-seedream-5-0-pro-260628doubao-seed-2-1-pro-260628 doubao-seed-2-1-turbo-260628 doubao-seed-character-260628 doubao-seed-evolvingdeepseek-v4-flash deepseek-v4-flash-legacy deepseek-v4-flash-vision-exp deepseek-v4-progemini-2.5-flash gemini-2.5-flash-image gemini-2.5-pro gemini-3-pro-image gemini-3.1-flash-image gemini-3.1-flash-lite gemini-3.1-flash-lite-image gemini-3.5-flash gemini-3.6-flash gemini-3.7-flash gemini-3.8-flashkling-3.0-turbo kling-v3 kling-v3-omniLongCat-2.0MiniMax-M2 MiniMax-M2.1 MiniMax-M2.1-highspeed MiniMax-M2.5 MiniMax-M2.5-highspeed MiniMax-M2.7 MiniMax-M2.7-highspeed MiniMax-M3MiniMax-H3 MiniMax-Hailuo MiniMax-Hailuo-02 MiniMax-Hailuo-2.3 MiniMax-Hailuo-2.3-Fastspeech-2.8-hd speech-2.8-turbominimax-music-v3.0image-01kimi-k2.5 kimi-k2.6 kimi-k2.7-code kimi-k2.7-code-highspeed kimi-k3gpt-image-2 gpt-image-2.5-flare gpt-image-2.5-sunburstgpt-5.2 gpt-5.4 gpt-5.4-mini gpt-5.5 gpt-5.6-luna gpt-5.6-sol gpt-5.6-terra gpt-6-astrastep-2x-large step-image-edit-2step-asr step-asr-1.1 step-tts-2 step-tts-ministep-1o-audio step-audio-2 step-audio-r1.5 stepaudio-2-asr-pro stepaudio-2.5-asr stepaudio-2.5-chat stepaudio-2.5-ttsstep-1o-turbo-vision step-3.5-flash step-3.5-flash-2603 step-3.7-flashhy-mt2-lite hy-mt2-plus hy-mt2-prohy3 hy4-previewvidu-video-q3 vidu-video-q3-pro vidu-video-q3-turbomimo-v2.5 mimo-v2.5-asr mimo-v2.5-pro mimo-v2.5-tts mimo-v2.5-tts-voiceclone mimo-v2.5-tts-voicedesignA capability profile states, field by field, what the gateway does with a request to one model. Zhipu AI is the first maker with a page of its own. For the others, this directory shows what the catalog lists, and a model without a profile reads Not audited: its parameter support is not guessed. Every published profile is on Model parameters & capabilities.