List all supported AI models
Bearer authentication header of the form Bearer <token>, where <token> is your auth token.
OK
Unique identifier of the LLM model. Used when referencing the model in API calls or UI selections and is generally a model id from the LLM provider.
Human-readable name shown to end users (e.g., "OpenAI o1 Preview" or "Mistral-large-2411").
Vendor metadata describing who provides the underlying model (e.g., OpenAI, Anthropic, Mistral, Meta, Custom).
OpenAI, Cohere, Mistral, Meta, Custom Indicates where the model is hosted (first-party, BYOK, region, etc.). Right now, we support "EU" and "US" regions. "Custom" is used for models that are hosted on a custom infrastructure.
EU, US, GLOBAL, Custom Maximum number of tokens accepted per request for this model.
Maximum number of tokens the model can generate in a single response.
Signals whether the model can call tools/functions during execution.
True if the model understands image inputs alongside text.
Version of the API/SDK required to access this model.
v1, v2 Indicates whether the model supports canvas-style collaborative generation features.
Optional model family classification. Null when the model does not belong to a specific OpenAI o-series.
o1, o3 Optional flag to hide or disable the model without removing its metadata. Defaults to true.