Baseten Model APIs provide hosted, OpenAI-compatible access to frontier models. The official external plugin uses authenticated discovery, so Apus follows the complete model set enabled for your Baseten account. Its offline fallback contains the current curated models listed below.

Install plugin

apus plugins install @openclaw/baseten-provider

Installation applies to a running Gateway automatically; otherwise it takes effect on the next startup. See Apply changes and inspect.

Getting started

Baseten's Basic plan has no monthly platform fee. Model API calls are usage-priced. Create a key in [Baseten API key settings](https://app.baseten.co/settings/api_keys) and check current rates on the [pricing page](https://www.baseten.co/pricing).

apus onboard --auth-choice baseten-api-key

apus onboard --non-interactive --accept-risk --skip-health \
  --auth-choice baseten-api-key \
  --baseten-api-key "$BASETEN_API_KEY"

export BASETEN_API_KEY=...

Onboarding saves the connection settings without copying the generated catalog into your config. Existing model rows, aliases, and an explicit primary model stay unchanged. If you use `models.mode: "replace"`, onboarding also adds the bundled catalog because that mode disables implicit discovery.

```bash
apus models list --provider baseten
```

With usable 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.

{
  agents: {
    defaults: {
      model: { primary: "baseten/deepseek-ai/DeepSeek-V4.1-Flash" },
    },
  },
}

Use /model baseten/deepseek-ai/DeepSeek-V4.1-Flash -s to switch the current session. Its thinking choices are off, low, high, and max, with high as the native default. Apus sends off as reasoning_effort: "none". See Baseten's reasoning controls.

Saved explicit selections such as baseten/thinkingmachines/inkling are not redirected to the new default. If a previously selected model is no longer available, list the current catalog and choose a replacement explicitly. Reconnecting the API key preserves the saved primary model.

Bundled fallback catalog

The authenticated live catalog is authoritative. This curated fallback covers current Model APIs; live discovery can include additional models. Removing a retired row from this fallback does not delete an explicitly authored row from your config:

All bundled models support tool calling and reasoning. Apus maps its thinking levels to models with native reasoning_effort. Its opt-in GLM and Nemotron routes default to thinking off. Nemotron exposes a binary off/on control; the bundled GLM 5.2 definitions expose off, high, and max. These routes use Baseten's chat_template_args.enable_thinking control. GLM's scalar effort and image input depend on discovery advertising those capabilities; sparse live GLM rows currently omit them.

The same thinking controls apply to agent turns and standalone model completions. Current DeepSeek V4 Pro 0813 and explicitly configured older Pro references preserve replayed reasoning metadata while thinking is enabled and remove it for explicit off requests. The current Pro endpoint additionally receives the required thinking envelope when scalar effort is sent.

Manual config

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

{
  env: { vars: { BASETEN_API_KEY: "..." } },
  agents: {
    defaults: {
      model: { primary: "baseten/deepseek-ai/DeepSeek-V4.1-Flash" },
    },
  },
  models: {
    mode: "merge",
    providers: {
      baseten: {
        baseUrl: "https://inference.baseten.co/v1",
        apiKey: "${BASETEN_API_KEY}",
        api: "openai-completions",
        models: [
          {
            id: "deepseek-ai/DeepSeek-V4.1-Flash",
            name: "DeepSeek V4.1 Flash",
            reasoning: true,
            input: ["text", "image"],
            contextWindow: 1048576,
            maxTokens: 262144,
          },
        ],
      },
    },
  },
}

Related

Choosing providers, model refs, and failover behavior.

Select Apus reasoning effort levels.

List, inspect, and select discovered models.

Auth profiles and model-selection troubleshooting.