InferenceCustom Endpoints

Set Up an Anthropic-Compatible Endpoint

View as Markdown

Use the custom Anthropic-compatible provider to configure a custom base URL and model with COMPATIBLE_ANTHROPIC_API_KEY. The runtime API differs by agent capability.

Run Onboarding

Start the onboard wizard.

$nemoclaw onboard

Select Other Anthropic-compatible endpoint. Enter the endpoint base URL, model ID, and API key when prompted. Use any non-empty placeholder such as dummy when the endpoint does not require authentication.

Understand OpenClaw Validation

OpenClaw uses the native Anthropic Messages frontend for this provider. NemoClaw validates the endpoint with a non-streaming /v1/messages request and then a stream: true request to the same path.

The streaming check requires exactly one message_start, at least one content_block_delta, and one message_stop in a well-formed server-sent event sequence. An endpoint whose non-streaming response works but whose streaming response is malformed fails during onboarding.

Set NEMOCLAW_REASONING=true to skip the streaming check for a reasoning-only model. Agent runs still use streaming, so this setting moves any streaming defect to runtime.

Refer to Onboarding fails with duplicate Anthropic message_start events when the streaming validation fails with duplicate start events.

Run Non-Interactive Onboarding

Set NEMOCLAW_PROVIDER=anthropicCompatible and provide the endpoint URL, model, and credential.

$NEMOCLAW_PROVIDER=anthropicCompatible \
>  NEMOCLAW_ENDPOINT_URL=http://localhost:8080 \
>  NEMOCLAW_MODEL=my-model \
>  COMPATIBLE_ANTHROPIC_API_KEY=dummy \
>  nemoclaw onboard --non-interactive