Skip to main content
The platform serves a large catalog through a single endpoint, from open-weight models to proprietary ones like GPT and Claude.

Browse the catalog

Explore every available model by provider.

List from the API

Fetch the live catalog from GET /v1/models with pricing, context windows, and capabilities.

​
Model ids

Each model has a provider/model id, such as openai/gpt-5 or qwen/qwen3-30b-a3b-instruct-2507. Pass it as the model field in a request. The same model may be offered under more than one id.

​
Confidential and standard models

Some models run confidentially: inside a TEE, on a provider whose enclave the gateway verifies before forwarding your prompt. Others are standard models from a third-party provider that is not attested. Both are served through the attested gateway, but only a confidential model extends that protection to the model itself. A model’s is_tee flag marks which kind it is, and the receipt proves how a given response was served. See Confidential models.

​
Choosing a model

Models differ in context length, accepted inputs, price, and supported parameters. The GET /v1/models response carries these details for each model, so you can match a model to what your application needs before you call.