Fireworks

Fireworks setup (auth + model selection)

Fireworks exposes open-weight and routed models through an OpenAI-compatible API. OpenClaw includes a bundled Fireworks provider plugin that ships with two pre-cataloged Kimi models and accepts any Fireworks model or router id at runtime.

PropertyValue
Provider idfireworks (alias: fireworks-ai)
Pluginbundled, enabledByDefault: true
Auth env varFIREWORKS_API_KEY
Onboarding flag--auth-choice fireworks-api-key
Direct CLI flag--fireworks-api-key <key>
APIOpenAI-compatible (openai-completions)
Base URLhttps://api.fireworks.ai/inference/v1
Default modelfireworks/accounts/fireworks/routers/kimi-k2p5-turbo
Default aliasKimi K2.5 Turbo

Getting started

openclaw onboard --auth-choice fireworks-api-key
openclaw onboard --non-interactive \
  --auth-choice fireworks-api-key \
  --fireworks-api-key "$FIREWORKS_API_KEY"
export FIREWORKS_API_KEY=fw-...
</CodeGroup>

Onboarding stores the key against the `fireworks` provider in your auth profiles and sets the **Fire Pass** Kimi K2.5 Turbo router as the default model.
```bash openclaw models list --provider fireworks ```
The list should include `Kimi K2.6` and `Kimi K2.5 Turbo (Fire Pass)`. If `FIREWORKS_API_KEY` is unresolved, `openclaw models status --json` reports the missing credential under `auth.unusableProfiles`.

Non-interactive setup

For scripted or CI installs, pass everything on the command line:

openclaw onboard --non-interactive \
  --mode local \
  --auth-choice fireworks-api-key \
  --fireworks-api-key "$FIREWORKS_API_KEY" \
  --skip-health \
  --accept-risk

Built-in catalog

Model refNameInputContextMax outputThinking
fireworks/accounts/fireworks/models/kimi-k2p6Kimi K2.6text + image262,144262,144Forced off
fireworks/accounts/fireworks/routers/kimi-k2p5-turboKimi K2.5 Turbo (Fire Pass)text + image256,000256,000Forced off (default)
OpenClaw pins all Fireworks Kimi models to `thinking: off` because Fireworks rejects Kimi thinking parameters in production. Routing the same model through [Moonshot](/docs/openclaw-docs/providers/moonshot directly preserves Kimi reasoning output. See [thinking modes](/docs/openclaw-docs/tools/thinking for switching between providers.

Custom Fireworks model ids

OpenClaw accepts any Fireworks model or router id at runtime. Use the exact id shown by Fireworks and prefix it with fireworks/. Dynamic resolution clones the Fire Pass template (text + image input, OpenAI-compatible API, default cost zero) and disables thinking automatically when the id matches the Kimi pattern.

{
  agents: {
    defaults: {
      model: {
        primary: "fireworks/accounts/fireworks/models/<your-model-id>",
      },
    },
  },
}
Every Fireworks model ref in OpenClaw starts with `fireworks/` followed by the exact id or router path from the Fireworks platform. For example:
- Router model: `fireworks/accounts/fireworks/routers/kimi-k2p5-turbo`
- Direct model: `fireworks/accounts/fireworks/models/<model-name>`

OpenClaw strips the `fireworks/` prefix when constructing the API request and sends the remaining path to the Fireworks endpoint as the OpenAI-compatible `model` field.
Fireworks K2.6 returns a 400 if the request carries `reasoning_*` parameters even though Kimi supports thinking through Moonshot's own API. The bundled policy (`extensions/fireworks/thinking-policy.ts`) advertises only the `off` thinking level for Kimi model ids, so manual `/think` switches and provider-policy surfaces stay aligned with the runtime contract.
To use Kimi reasoning end-to-end, configure the [Moonshot provider](/docs/openclaw-docs/providers/moonshot and route the same model through it.
If the Gateway runs as a managed service (launchd, systemd, Docker), the Fireworks key must be visible to that process — not just to your interactive shell.
<Warning>
  A key sitting only in `~/.profile` will not help a launchd or systemd daemon unless that environment is imported there too. Set the key in `~/.openclaw/.env` or via `env.shellEnv` to make it readable from the gateway process.
</Warning>

On macOS, `openclaw gateway install` already wires `~/.openclaw/.env` into the LaunchAgent environment file. Re-run install (or `openclaw doctor --fix`) after rotating the key.
Choosing providers, model refs, and failover behavior. `/think` levels, provider policies, and routing reasoning-capable models. Run Kimi with native thinking output through Moonshot's own API. General troubleshooting and FAQ.