Baseten Provider Setup for Inkling and Model APIs

Baseten Model APIs give hosted, OpenAI-compatible access to frontier models. The official external plugin uses authenticated discovery, so OpenClaw follows the full model set enabled for your Baseten account. Its offline fallback includes every Model API available when this OpenClaw release was built.

Install plugin

openclaw plugins install @openclaw/baseten-provider
openclaw gateway restart

Getting started

Create a Baseten account and API key

Baseten's Basic plan charges no monthly platform fee; Model API calls are priced per use. Create a key in Baseten API key settings and check current rates on the pricing page.

Run onboarding

openclaw onboard --auth-choice baseten-api-key

openclaw onboard --non-interactive \
  --auth-choice baseten-api-key \
  --baseten-api-key "$BASETEN_API_KEY"

export BASETEN_API_KEY=...

Verify the live catalog

openclaw models list --provider baseten

With valid auth, the plugin requests GET /v1/models and lists every model returned for the account. Without auth, it stays offline and uses the bundled fallback.

Inkling

Thinking Machines Lab's Inkling is the default model. In OpenClaw it supports text and image input, tool calling, structured tool schemas, configurable reasoning effort, a 1.048M-token context window, and up to 32k output tokens:

{
  agents: {
    defaults: {
      model: { primary: "baseten/thinkingmachines/inkling" },
    },
  },
}

Use /model baseten/thinkingmachines/inkling to switch an existing chat.

Bundled fallback catalog

The authenticated live catalog is authoritative. These rows keep setup and model selection useful before discovery succeeds:

All bundled models support tool calling and reasoning. OpenClaw maps its thinking levels to models with native reasoning_effort. Baseten's opt-in GLM, Kimi, and Nemotron models default to thinking off; most expose a binary off/on control, while GLM 5.2 exposes off, high, and max. OpenClaw sends these choices through Baseten's chat_template_args.enable_thinking control and, for GLM 5.2, the validated top-level reasoning_effort parameter.

Note

Baseten can add, remove, or change Model APIs independently of OpenClaw releases. The plugin refreshes model ids, context limits, output limits, and input, cached-input, and output pricing from the authenticated API while retaining model-specific OpenClaw transport policy.

Manual config

Most setups only need the API key. To pin the provider explicitly:

{
  env: { BASETEN_API_KEY: "..." },
  agents: {
    defaults: {
      model: { primary: "baseten/thinkingmachines/inkling" },
    },
  },
  models: {
    mode: "merge",
    providers: {
      baseten: {
        baseUrl: "https://inference.baseten.co/v1",
        apiKey: "${BASETEN_API_KEY}",
        api: "openai-completions",
        models: [
          {
            id: "thinkingmachines/inkling",
            name: "Inkling",
            reasoning: true,
            input: ["text", "image"],
            contextWindow: 1048000,
            maxTokens: 32000,
          },
        ],
      },
    },
  },
}

Note

If the Gateway runs as a daemon (launchd, systemd, Docker), make sure BASETEN_API_KEY is available to that process. A key exported only in an interactive shell is not visible to an already-running managed service.

Related

• Model providers, Choosing providers, model refs, and failover behavior.

• Thinking modes, Select OpenClaw reasoning effort levels.

• Models CLI, List, inspect, and select discovered models.

• Models FAQ, Auth profiles and model-selection troubleshooting.