> ## Documentation Index
> Fetch the complete documentation index at: https://docs.toolken.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# OpenClaw

> Point OpenClaw at Toolken by adding one custom provider. Every call from every agent is tracked automatically.

**Add Toolken as a custom provider in your OpenClaw config and every agent request is attributed, costed, and visible in the dashboard -- no code changes to your agents.**

<Steps>
  <Step title="Get your two keys">
    You need two keys:

    | Key          | Where to get it                                     | Looks like    |
    | ------------ | --------------------------------------------------- | ------------- |
    | Toolken key  | Dashboard, under API Keys                           | `tk_live_...` |
    | Provider key | Your OpenAI account (or whichever provider you use) | `sk-...`      |

    Toolken forwards your provider key untouched and never stores it.
  </Step>

  <Step title="Add the Toolken provider to your OpenClaw config">
    Open (or create) `~/.openclaw/openclaw.json` and add a `toolken` entry under `models.providers`:

    ```json5 theme={null}
    {
      models: {
        providers: {
          toolken: {
            baseUrl: "https://gateway.toolken.ai/v1",
            api: "openai-completions",
            apiKey: "${OPENAI_API_KEY}", // your provider key (BYOK); sent as Authorization, forwarded untouched
            headers: {
              "X-Toolken-Key": "${TOOLKEN_KEY}",
              "X-Toolken-Metadata-Agent": "research-agent"
            },
            models: [{ id: "gpt-4o-mini", name: "GPT-4o mini" }]
          }
        }
      }
    }
    ```

    <Tip>Values support `${ENV_VAR}` substitution. Keep both keys in environment variables, not in the file itself.</Tip>
  </Step>

  <Step title="Use the Toolken provider in OpenClaw">
    Select the `toolken` provider and the `gpt-4o-mini` model (or whichever model you listed) when running your agent. OpenClaw routes the request through the gateway, attaching `X-Toolken-Key` and `X-Toolken-Metadata-Agent` automatically.
  </Step>

  <Step title="Confirm the request in your dashboard">
    Within seconds the request appears in the Toolken dashboard, tagged with the `agent` dimension set to `research-agent`. Cost, token usage, and latency are all captured.
  </Step>
</Steps>

<Accordion title="Attribute multiple agents separately">
  `X-Toolken-Metadata-Agent` is set at the provider level, not per request. To break spend down by agent, define one Toolken provider entry per agent and give each a distinct `X-Toolken-Metadata-Agent` value:

  ```json5 theme={null}
  {
    models: {
      providers: {
        toolken-research: {
          baseUrl: "https://gateway.toolken.ai/v1",
          api: "openai-completions",
          apiKey: "${OPENAI_API_KEY}",
          headers: {
            "X-Toolken-Key": "${TOOLKEN_KEY}",
            "X-Toolken-Metadata-Agent": "research-agent"
          },
          models: [{ id: "gpt-4o-mini", name: "GPT-4o mini (research)" }]
        },
        toolken-summarizer: {
          baseUrl: "https://gateway.toolken.ai/v1",
          api: "openai-completions",
          apiKey: "${OPENAI_API_KEY}",
          headers: {
            "X-Toolken-Key": "${TOOLKEN_KEY}",
            "X-Toolken-Metadata-Agent": "summarizer-agent"
          },
          models: [{ id: "gpt-4o-mini", name: "GPT-4o mini (summarizer)" }]
        }
      }
    }
  }
  ```

  Each agent picks its own provider entry. The dashboard shows cost, tokens, and latency broken down by agent name.
</Accordion>

<Note>For the full list of OpenClaw provider config fields -- including fallback models and timeout settings -- see the [OpenClaw provider config reference](https://docs.openclaw.ai/gateway/config-tools).</Note>

## Next

<CardGroup cols={2}>
  <Card title="Custom Properties" icon="tag" href="/features/observability/custom-properties">Tag requests with feature, customer, and metadata headers to slice every metric.</Card>
  <Card title="Providers & Routing" icon="route" href="/features/providers-routing/overview">One gateway URL, 13 providers, your own keys.</Card>
</CardGroup>