airmux inference endpoint, use a workspace inference key, and choose a model ID from the gateway catalog. OpenAI-compatible SDKs use /inf/v1; the Anthropic SDK uses /inf. airmux routes each request to the selected provider.
Set these values for the examples:
- OpenAI Python
- Anthropic Python
- OpenAI JavaScript
- Vercel AI SDK
- LangChain Python
client.models.list(). Results reflect the models visible to the key’s workspace policies and configured credential scopes. See the model discovery reference.
Inference keys begin with sk-inf-. The Messages reference, Chat Completions reference, and Responses reference describe supported request fields.