Baseten

Verified Code examples on this page have been automatically tested and verified.

Route agentgateway LLM traffic to models hosted on Baseten.

Configure Baseten as an LLM provider in agentgateway.

Configuration

Review the following example configuration.

# yaml-language-server: $schema=https://agentgateway.dev/schema/config

llm:
  models:
  - name: "*"
    provider: baseten
    params:
      apiKey: "$BASETEN_API_KEY"

Review the following example configuration.

Setting	Description
`name`	The model name to match in incoming requests. When a client sends `"model": "<name>"`, the request is routed to this provider. Use `*` to match any model name.
`provider`	The LLM provider, set to `baseten`.
`params.model`	Optional. If set, this model is used for all requests. If not set, the request must include the model to use.
`params.apiKey`	Your Baseten API key. You can reference environment variables using the `$VAR_NAME` syntax.
`params.baseUrl`	Optional. Overrides the provider base URL. Default: `https://inference.baseten.co/v1`.

Example request

After running agentgateway with the configuration from the previous section, you can send an OpenAI-compatible request to the v1/chat/completions endpoint by replacing <your-baseten-model-id> with your Baseten model or deployment ID:

curl -X POST http://localhost:4000/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{
    "model": "<your-baseten-model-id>",
    "messages": [{"role": "user", "content": "Hello from Baseten!"}]
  }'

Configuration​

Example request​

Configuration

Example request