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

# Fire Pass Setup

> Kimi K2.6 Turbo for personal agentic coding — Fire Pass (Early Access), $49 / month

Fire Pass (Early Access) is a monthly pass that gives you access to **Kimi K2.6 Turbo** for use in personal agentic coding harnesses like [Claude Code](/ecosystem/integrations/claude-code), [OpenCode](https://opencode.ai), Cline, Kilo Code, OpenClaw, and [LangChain Deep Agents](https://docs.langchain.com/oss/python/deepagents/models) — with no per-token charges for that model. Kimi K2.6 Turbo is a private preview of a faster Kimi K2.6 serverless API.

<Note>
  **Fire Pass (Early Access)** is an experimental product. Features, availability, and
  pricing are subject to change.
</Note>

## What's Included

With an active Fire Pass you get:

* **Kimi K2.6 Turbo** requests with zero per-token costs (a powerful reasoning model with a 256k context window, optimized for complex coding tasks)
* A NEW dedicated Fire Pass key that only works for Kimi 2.6 Turbo. Use your normal Fireworks key for all other models.
* Full compatibility with OpenAI- and Anthropic-compatible agentic coding tools

<Warning>
  Only **Kimi K2.6 Turbo** is covered by Fire Pass. Usage of regular Kimi K2.6,
  or any other model on Fireworks, will continue to incur standard per-token
  charges.
</Warning>

## Pricing

|                    |                                             |
| ------------------ | ------------------------------------------- |
| **Cost**           | \$49 per month                              |
| **Payment Method** | Billed directly to your credit card on file |
| **Auto-renew**     | Auto-renew is default on                    |

## Getting Started

<Steps>
  <Step title="Create an account">
    If you haven't already, sign up for a [Fireworks
    account](https://app.fireworks.ai).
  </Step>

  <Step title="Purchase your pass">
    Go to the [**Billing** page](https://app.fireworks.ai/account/billing),
    review the Fire Pass details, and complete your purchase. Your pass
    activates immediately and is valid for one month at \$49 per month.
  </Step>

  <Step title="Get a Fire Pass API key">
    Create a new dedicated Fire Pass API key and use it with any of the
    supported agentic harnesses below. Requests to Kimi K2.6 Turbo will no
    longer incur per-token charges while your pass is active.
  </Step>
</Steps>

## Using your Fire Pass

Fire Pass is designed for use with personal agentic coding harnesses. Below are setup guides for each supported tool.

### General Configuration

If your tool supports custom API endpoints, you can configure it manually using these details:

* **Model ID**: `accounts/fireworks/routers/kimi-k2p6-turbo`
* **API Key**: Generate a new Fire Pass API key (generated at [app.fireworks.ai/api-keys](https://app.fireworks.ai/api-keys))
* **Base URL (OpenAI-compatible)**: `https://api.fireworks.ai/inference/v1`
* **Base URL (Anthropic-compatible)**: `https://api.fireworks.ai/inference` (some tools may expect `/v1/messages` appended)

<AccordionGroup>
  <Accordion title="OpenClaw">
    1. **Configure Kimi K2.6 as the default model** — run the setup script with your Fireworks API key from the [**API Keys** page](https://app.fireworks.ai/api-keys). Replace `YOUR_FIREWORKS_API_KEY` with your key:

    ```bash theme={null}
    curl -fsSL https://storage.googleapis.com/fireworks-public/openclaw/setup-fireworks.sh | bash -s -- YOUR_FIREWORKS_API_KEY
    ```

    This creates `~/.openclaw/openclaw.json` with your Fireworks credentials.

    <Warning>
      Do not share your API key or commit it to version control. Use the
      placeholder above only as a pattern — substitute your real key locally.
    </Warning>

    2. **Install OpenClaw**

    <Tabs>
      <Tab title="macOS / Linux">
        ```bash theme={null}
        curl -fsSL https://openclaw.ai/install.sh | bash
        ```
      </Tab>

      <Tab title="Windows (PowerShell)">
        ```powershell theme={null}
        iwr -useb https://openclaw.ai/install.ps1 | iex
        ```
      </Tab>
    </Tabs>

    3. **Run the onboarding wizard** — in a terminal:

    ```bash theme={null}
    openclaw onboard --install-daemon
    ```

    Choose **Quickstart** mode, skip model and authentication (already configured), and accept the remaining defaults.

    4. **Open the chat UI** — run:

    ```bash theme={null}
    openclaw dashboard
    ```

    The UI opens at [http://127.0.0.1:18789](http://127.0.0.1:18789). Send a message to confirm **Kimi K2.6** is responding.

    For more about OpenClaw, see [openclaw.ai](https://openclaw.ai).
  </Accordion>

  <Accordion title="OpenCode">
    OpenCode has a built-in provider connection flow that makes setup quick:

    1. Type `/connect` in OpenCode and search for **fireworks.ai**
    2. Paste your Fireworks API key (from [app.fireworks.ai/api-keys](https://app.fireworks.ai/api-keys)) and press Enter
    3. Type `/models` and select **Kimi K2.6 Turbo**

    That's it — you're ready to start coding with your Fire Pass.
  </Accordion>

  <Accordion title="Cline">
    To configure Cline with your Fire Pass:

    1. Install the Cline extension in VS Code from [cline.bot](https://cline.bot) or the VS Code marketplace
    2. Open VS Code settings and search for "Cline" or use the Cline panel
    3. Configure the following settings:

    **API Configuration:**

    * **API Provider**: OpenAI Compatible
    * **Base URL**: `https://api.fireworks.ai/inference/v1`
    * **OpenAI Compatible API Key**: Your Fireworks API key (from [app.fireworks.ai/api-keys](https://app.fireworks.ai/api-keys))
    * **Model ID**: `accounts/fireworks/routers/kimi-k2p6-turbo`

    **Model Configuration:**

    * **Supports Images**: Enabled (checked)
    * **Context Window Size**: 256000
    * **Max Output Tokens**: 256000
    * **Input Price / 1M tokens**: 0 (Fire Pass covers all costs)
    * **Output Price / 1M tokens**: 0 (Fire Pass covers all costs)
    * **Temperature**: 1

    4. Save your settings and start using Cline — your Fire Pass will automatically apply to requests to the turbo router
  </Accordion>

  <Accordion title="Claude Code">
    To configure Claude Code with your Fire Pass, create a `.claude/settings.json` file in your home directory (`~/.claude/settings.json`) or project directory (`.claude/settings.json`):

    ```json theme={null}
    {
        "$schema": "https://json.schemastore.org/claude-code-settings.json",
        "apiKeyHelper": "bash -c 'echo YOUR_FIREWORKS_API_KEY'",
        "env": {
            "ANTHROPIC_BASE_URL": "https://api.fireworks.ai/inference",
            "ANTHROPIC_MODEL": "accounts/fireworks/routers/kimi-k2p6-turbo",
            "ANTHROPIC_SMALL_FAST_MODEL": "accounts/fireworks/routers/kimi-k2p6-turbo",
            "ANTHROPIC_DEFAULT_SONNET_MODEL": "accounts/fireworks/routers/kimi-k2p6-turbo",
            "ANTHROPIC_DEFAULT_HAIKU_MODEL": "accounts/fireworks/routers/kimi-k2p6-turbo",
            "ANTHROPIC_DEFAULT_OPUS_MODEL": "accounts/fireworks/routers/kimi-k2p6-turbo"
        },
        "model": "accounts/fireworks/routers/kimi-k2p6-turbo"
    }
    ```

    Replace `YOUR_FIREWORKS_API_KEY` with your Fireworks API key from [app.fireworks.ai/api-keys](https://app.fireworks.ai/api-keys).

    <Tip>
      Setting all model override flags (`ANTHROPIC_SMALL_FAST_MODEL`, `ANTHROPIC_DEFAULT_SONNET_MODEL`, etc.) ensures Claude Code's subagents (Explore, Web Search, etc.) use your Fire Pass model instead of defaulting to Anthropic's Claude.
    </Tip>

    <Warning>
      Do not share your API key or commit `settings.json` to version control. Use the placeholder above only as a pattern — substitute your real key locally.
    </Warning>

    After saving the file, launch Claude Code:

    ```bash theme={null}
    claude
    ```

    Claude Code will automatically detect the configuration and route all requests through your Fire Pass.

    For more details on Claude Code configuration, see the [Claude Code integration guide](/ecosystem/integrations/claude-code).
  </Accordion>

  <Accordion title="Kilo Code">
    To configure Kilo Code with your Fire Pass:

    1. Install the Kilo Code extension in VS Code from the [VS Code marketplace](https://marketplace.visualstudio.com/items?itemName=kilocode.Kilo-Code) or [kilocode.ai](https://kilocode.ai)
    2. Open Kilo Code and select **Bring my own Key** on the "How would you like to get started?" screen
    3. Configure the following settings:

    **API Configuration:**

    * **API Provider**: OpenAI Compatible
    * **Base URL**: `https://api.fireworks.ai/inference/v1`
    * **API Key**: Your Fireworks API key (from [app.fireworks.ai/api-keys](https://app.fireworks.ai/api-keys))
    * **Model**: `accounts/fireworks/routers/kimi-k2p6-turbo`
      * Type or paste the router ID and select "Use custom" when it appears

    **Model Configuration:**

    * **Context Window Size**: 256000 (256K tokens)
    * **Supports images**: Enabled (checked)
    * **Input Price**: 0 (Fire Pass covers all costs)
    * **Output Price**: 0 (Fire Pass covers all costs)

    4. Save your settings and start using Kilo Code — your Fire Pass will automatically apply to requests to the turbo router
  </Accordion>

  <Accordion title="LangChain Deep Agent">
    Set `FIREWORKS_API_KEY` to your API key from [app.fireworks.ai/api-keys](https://app.fireworks.ai/api-keys). Install [LangChain Deep Agents](https://docs.langchain.com/oss/python/deepagents/models) with the Fireworks integration, then pass the turbo router as `fireworks:accounts/fireworks/routers/kimi-k2p6-turbo`:

    ```bash theme={null}
    pip install deepagents langchain-fireworks
    ```

    ```python theme={null}
    from deepagents import create_deep_agent

    agent = create_deep_agent(
        model="fireworks:accounts/fireworks/routers/kimi-k2p6-turbo",
        system_prompt="You are a helpful coding assistant.",
    )
    result = agent.invoke(
        {"messages": [{"role": "user", "content": "Hello"}]},
    )
    ```

    See the LangChain docs for [models](https://docs.langchain.com/oss/python/deepagents/models) and [customization](https://docs.langchain.com/oss/python/deepagents/customization).
  </Accordion>
</AccordionGroup>

## Terms of Use

Fire Pass is intended for **personal agentic coding use only**. By purchasing Fire Pass you agree to the following:

* **Allowed**: Personal development, experimentation, and coding with agentic harnesses (Claude Code, OpenCode, Cline, Kilo Code, OpenClaw, LangChain Deep Agents, and similar tools)
* **Prohibited**: Production workloads, team or shared usage, and any use that violates the [Fireworks Terms of Service](https://fireworks.ai/terms-of-service)

<Warning>
  Violations of these terms may result in pass revocation without refund.
</Warning>

## FAQ

<AccordionGroup>
  <Accordion title="Can I use Fire Pass with any model?">
    No. Fire Pass covers **Kimi K2.6 Turbo** only. All other models,
    including regular Kimi K2.6, are billed at standard per-token rates.
  </Accordion>

  <Accordion title="What happens when my pass expires?">
    When your pass expires, Kimi K2.6 Turbo requests will be billed at standard
    per-token rates. If you have auto-renew enabled and a pass is available, it
    will renew automatically.
  </Accordion>

  <Accordion title="Is auto-renewal guaranteed?">
    No. Auto-renewal is best-effort and your renewal may not go through.
  </Accordion>

  <Accordion title="Can I share my pass with my team?">
    No. Fire Pass is for personal use only. Team or shared usage is
    prohibited under the Terms of Service.
  </Accordion>

  <Accordion title="Do I need an invite code?">
    Fire Pass is currently by invite only.
  </Accordion>

  <Accordion title="Do I need to use a special model ID?">
    Yes. You must use the specific router ID for the turbo model:
    `accounts/fireworks/routers/kimi-k2p6-turbo`. The Fireworks billing system
    will automatically detect your active Fire Pass and zero out the cost
    for requests to this endpoint.
  </Accordion>

  <Accordion title="How will this appear on my billing dashboard?">
    Your usage of Kimi K2.6 Turbo will still be logged in your dashboard so you
    can track your request volume, but the associated cost will show as \$0.00
    while your pass is active. You can also view your pass's active status and
    expiration date directly on the [**Billing**
    page](https://app.fireworks.ai/account/billing).
  </Accordion>

  <Accordion title="How do I cancel auto-renew?">
    You can turn off auto-renewal at any time from the Fire Pass page in your
    Fireworks dashboard. Your pass will remain active until the end of the
    current billing month.
  </Accordion>

  <Accordion title="Can I use other models with my agentic harness?">
    Yes. You can use any Fireworks model with your agentic harness. However,
    only **Kimi K2.6 Turbo** requests are covered by Fire Pass. Usage
    of other models will be billed to your account at standard per-token rates.
  </Accordion>
</AccordionGroup>