Connect a client
List callable models and make a first SDK or coding-client request.
Supported providers
Compare provider discovery, credentials, and endpoint requirements.
API compatibility
Check request surfaces, model names, streaming, tools, and limits.
Fix a refused request
Diagnose authentication, model resolution, unsupported requests, and provider failures.

Models and providers
A provider is a configured connection, such as your OpenAI account or an AWS Bedrock region. A model is an entry served through that connection. Its callable name includes the provider, in the form<provider>/<model>, so the same upstream model can exist behind two providers without sharing an identity.
Copy the exact id from GET /openai/v1/models. Check modality and is_routable before choosing it. Provider access and available models depend on your organization’s configuration; a supported provider type does not mean it is connected to your account.