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

# Fireworks

> Fireworks AI model provider configuration and integration guide

If you are a coding agent, prefer the Braintrust [`bt` CLI](/docs/reference/cli/quickstart) for repeatable, scriptable work: running evals, instrumenting code, querying logs, syncing data, managing functions, and configuring coding agents. Use the MCP server for reasoning over Braintrust data in conversation, and for capabilities the CLI doesn't cover, such as monitor views, alerts, and authoring evaluators, preprocessors, and facets.

Fireworks AI provides fast inference for open-source language models including Llama, Mixtral, Code Llama, and other state-of-the-art models. Braintrust integrates seamlessly with Fireworks through direct API access, wrapper functions for automatic tracing, and proxy support.

## Setup

To use Fireworks models, configure your Fireworks API key in Braintrust.

1. Get a Fireworks API key from [Fireworks AI Console](https://fireworks.ai/account/api-keys)
2. Add the Fireworks API key as an [organization or project AI provider](/docs/admin/ai-providers).
3. Set the Fireworks API key and your Braintrust API key as environment variables

```bash title=".env" theme={"theme":{"light":"github-light","dark":"github-dark-dimmed"}}
FIREWORKS_API_KEY=<your-fireworks-api-key>
BRAINTRUST_API_KEY=<your-braintrust-api-key>

# For organizations on the EU data plane, use https://api-eu.braintrust.dev
# For self-hosted deployments, use your data plane URL
# BRAINTRUST_API_URL=<your-braintrust-api-url-here>
```

<Note>
  API keys are stored as one-way cryptographic hashes, never in plaintext.
</Note>

## Use Fireworks with Braintrust gateway

The [Braintrust gateway](/docs/deploy/gateway) allows you to access Fireworks models through a unified interface. Use any [supported provider's SDK](/docs/integrations/ai-providers) to call Fireworks models.

Install the `braintrust` and `openai` packages.

<CodeGroup>
  ```bash Typescript theme={"theme":{"light":"github-light","dark":"github-dark-dimmed"}}
  # pnpm
  pnpm add braintrust openai
  # npm
  npm install braintrust openai
  ```

  ```bash Python theme={"theme":{"light":"github-light","dark":"github-dark-dimmed"}}
  pip install braintrust openai
  ```
</CodeGroup>

Then, initialize the client and make a request to a Fireworks model via the Braintrust gateway.

<CodeGroup dropdown>
  ```typescript theme={"theme":{"light":"github-light","dark":"github-dark-dimmed"}}
  import { OpenAI } from "openai";

  const client = new OpenAI({
    baseURL: "https://gateway.braintrust.dev/v1",
    apiKey: process.env.BRAINTRUST_API_KEY,
  });

  const response = await client.chat.completions.create({
    model: "fireworks/llama-3.1-70b-instruct",
    messages: [{ role: "user", content: "Hello, world!" }],
  });
  ```

  ```python theme={"theme":{"light":"github-light","dark":"github-dark-dimmed"}}
  import os

  from openai import OpenAI

  client = OpenAI(
      base_url="https://gateway.braintrust.dev/v1",
      api_key=os.environ["BRAINTRUST_API_KEY"],
  )

  response = client.chat.completions.create(
      model="fireworks/llama-3.1-70b-instruct",
      messages=[{"role": "user", "content": "Hello, world!"}],
  )
  ```
</CodeGroup>

## Trace logs with Fireworks

Trace your Fireworks LLM calls for observability and monitoring.

When using the Braintrust gateway, API calls are automatically logged to the specified project.

<CodeGroup dropdown>
  ```typescript theme={"theme":{"light":"github-light","dark":"github-dark-dimmed"}}
  import { OpenAI } from "openai";
  import { initLogger } from "braintrust";

  initLogger({
    projectName: "My Project",
    apiKey: process.env.BRAINTRUST_API_KEY,
  });

  const client = new OpenAI({
    baseURL: "https://gateway.braintrust.dev/v1",
    apiKey: process.env.BRAINTRUST_API_KEY,
  });

  // All API calls are automatically logged
  const result = await client.chat.completions.create({
    model: "fireworks/llama-3.1-70b-instruct",
    messages: [{ role: "user", content: "What is machine learning?" }],
  });
  ```

  ```python theme={"theme":{"light":"github-light","dark":"github-dark-dimmed"}}
  import os

  from braintrust import init_logger
  from openai import OpenAI

  init_logger(project="My Project")

  client = OpenAI(
      base_url="https://gateway.braintrust.dev/v1",
      api_key=os.environ["BRAINTRUST_API_KEY"],
  )

  # All API calls are automatically logged
  result = client.chat.completions.create(
      model="fireworks/llama-3.1-70b-instruct",
      messages=[{"role": "user", "content": "What is machine learning?"}],
  )
  ```
</CodeGroup>

<Tip>
  The Braintrust gateway is not required. For more control, learn how to [customize traces](/docs/instrument/advanced-tracing).
</Tip>

## Evaluate with Fireworks

Evaluations distill the non-deterministic outputs of Fireworks models into an effective feedback loop that enables you to ship more reliable, higher quality products. Braintrust `Eval` is a simple function composed of a dataset of user inputs, a task, and a set of scorers. To learn more about evaluations, see the [Experiments](/docs/evaluate/run-evaluations) guide.

<CodeGroup dropdown>
  ```typescript theme={"theme":{"light":"github-light","dark":"github-dark-dimmed"}}
  import { Eval } from "braintrust";
  import { OpenAI } from "openai";

  const client = new OpenAI({
    baseURL: "https://gateway.braintrust.dev/v1",
    apiKey: process.env.BRAINTRUST_API_KEY,
  });

  Eval("Fireworks Evaluation", {
    data: () => [
      { input: "What is 2+2?", expected: "4" },
      { input: "What is the capital of France?", expected: "Paris" },
    ],
    task: async (input) => {
      const response = await client.chat.completions.create({
        model: "fireworks/llama-3.1-70b-instruct",
        messages: [{ role: "user", content: input }],
      });
      return response.choices[0].message.content;
    },
    scores: [
      {
        name: "accuracy",
        scorer: (args) => (args.output === args.expected ? 1 : 0),
      },
    ],
  });
  ```

  ```python theme={"theme":{"light":"github-light","dark":"github-dark-dimmed"}}
  import os

  from braintrust import Eval
  from openai import OpenAI

  client = OpenAI(
      base_url="https://gateway.braintrust.dev/v1",
      api_key=os.environ["BRAINTRUST_API_KEY"],
  )


  def task(input):
      response = client.chat.completions.create(
          model="fireworks/llama-3.1-70b-instruct",
          messages=[{"role": "user", "content": input}],
      )
      return response.choices[0].message.content


  def accuracy_scorer(output, expected, **kwargs):
      return 1 if output == expected else 0


  Eval(
      "Fireworks Evaluation",
      data=[
          {"input": "What is 2+2?", "expected": "4"},
          {"input": "What is the capital of France?", "expected": "Paris"},
      ],
      task=task,
      scores=[accuracy_scorer],
  )
  ```
</CodeGroup>

<Tip>
  To learn more about tool use, multimodal support, attachments, and masking sensitive data with Fireworks, visit the [customize traces](/docs/instrument/advanced-tracing) guide.
</Tip>