OpenClawDocs
View as MarkdownView this page as plain textOpen in ChatGPTAsk questions about this pageOpen in ClaudeAsk questions about this page

Providers

Meta

The Meta API uses the OpenAI-compatible Responses API (POST /v1/responses) for the muse-spark-1.1 reasoning model. The provider ships as a bundled OpenClaw plugin.

Property Value
Provider id meta
Plugin bundled provider
Auth env var MODEL_API_KEY
Onboarding flag --auth-choice meta-api-key
Direct CLI flag --meta-api-key <key>
API Responses API (openai-responses)
Base URL https://api.ai.meta.com/v1
Default model meta/muse-spark-1.1
Default reasoning high (reasoning.effort)

Getting started

  • Set the API key

    Onboarding
    openclaw onboard --auth-choice meta-api-key
    Direct flag
    openclaw onboard --non-interactive --accept-risk \--auth-choice meta-api-key \--meta-api-key "$MODEL_API_KEY"
    Env only
    export MODEL_API_KEY=<key>

  • Verify models are available

    bash
    openclaw models list --provider meta

    Lists the static muse-spark-1.1 catalog entry. If MODEL_API_KEY is unresolved, openclaw models status --json reports the missing credential under auth.unusableProfiles.

    • Non-interactive setup

    bash
    openclaw onboard --non-interactive --accept-risk \  --mode local \  --auth-choice meta-api-key \  --meta-api-key "$MODEL_API_KEY"

    Built-in catalog

    Model ref Name Reasoning Context window Max output
    meta/muse-spark-1.1 Muse Spark 1.1 yes 1,048,576 128,000

    Capabilities:

    • Text + image input
    • Tool calling and streaming
    • Reasoning effort: minimal, low, medium, high, xhigh (default: high)
    • Stateless encrypted reasoning replay (store: false, include: ["reasoning.encrypted_content"])

    Manual config

    json5
    {  env: { MODEL_API_KEY: "<key>" },  agents: {    defaults: {      model: { primary: "meta/muse-spark-1.1" },      models: {        "meta/muse-spark-1.1": { alias: "Muse Spark 1.1" },      },    },  },}

    Smoke test

    bash
    export MODEL_API_KEY=<key>export OPENCLAW_LIVE_TEST=1export META_LIVE_TEST=1pnpm test extensions/meta/meta.live.test.ts

    Live tests use deployed muse-spark against POST /v1/responses.

    Model providers

    Choosing providers, model refs, and failover behavior.
    Thinking modes

    Reasoning effort levels for muse-spark-1.1.
    Configuration reference

    Agent defaults and model configuration.
    Was this useful?
    On this page

    On this page