Skip to main content
APIAny.AI exposes public model IDs. These IDs are stable product contracts for your application. Current public model families include:
  • Image generation models such as Z-Image, Nano Banana, GPT Image, and Seedance image models.
  • Video generation models such as Seedance, Veo, Wan, and Gemini Omni.
  • Chat models such as Gemini, GPT, DeepSeek, and MiniMax.

​
Public model IDs

Use the model ID shown in the dashboard and model pages:

​
Model usage

Use the public model ID in API requests and APIAny.AI returns a standardized response for that model family.

​
Capability metadata

GET /v1/models returns a capability_metadata object for every model, so client code can configure a model without hardcoding assumptions:
  • input and output list the accepted and produced types.
  • features reports stream, tools, vision, jsonMode, and whether the model reasons at all (thinking).
  • reasoning reports the reasoning controls: mode (always-on, optional or none), the accepted efforts, the defaultEffort applied when effort is omitted, and disableWith for models whose reasoning can be turned off.
  • limits reports contextWindow and maxOutputTokens.
Official model IDs are accepted as equivalent IDs for deepseek-flash (= deepseek-v4.1-flash) and deepseek-v4-pro (= deepseek-v4); GET /v1/models marks such entries with alias_of.