> ## 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.

# Build with Fireworks AI

> Fast inference and fine-tuning for open source models

Fireworks AI is the fastest platform for building with open source AI models. Get production-ready inference and fine-tuning with best-in-class speed, cost and quality.

## Get started in minutes

<CardGroup cols="3">
  <Card title="Start fast with Serverless" href="/getting-started/quickstart" icon="bolt">
    Use popular models instantly with pay-per-token pricing. Perfect for quality vibe testing and prototyping.
  </Card>

  <Card title="Deploy models & autoscale on dedicated GPUs" href="/getting-started/ondemand-quickstart" icon="server">
    Deploy with high performance on dedicated GPUs with fast autoscaling and minimal cold starts. Optimize deployments for speed and throughput.
  </Card>

  <Card title="Fine-tune models for best quality" href="/fine-tuning/finetuning-intro" icon="sliders">
    Boost model quality with supervised and reinforcement fine-tuning of models up to 1T+ parameters. Start training in minutes, deploy immediately.
  </Card>
</CardGroup>

<Tip>
  Not sure where to start? First, pick the right model for your use case with our [**model selection guide**](/guides/recommended-models). Then choose [**Serverless**](/getting-started/quickstart) to prototype quickly, move to [**Deployments**](/getting-started/ondemand-quickstart) to optimize and run production workloads, or use [**Fine-tuning**](/fine-tuning/finetuning-intro) to improve quality.

  New to AI or Fireworks? Look up any term in the [**Glossary**](/getting-started/glossary).

  Need help optimizing deployments, fine-tuning models, or setting up production infrastructure? [Talk to our team](https://fireworks.ai/company/contact-us) - we'll help you get the best performance and reliability.
</Tip>

## What you can build

<CardGroup cols="3">
  <Card title="100+ Supported Models" href="https://fireworks.ai/models" icon="books">
    Text, vision, audio, image, and embeddings
  </Card>

  <Card title="Migrate from OpenAI" href="/tools-sdks/openai-compatibility" icon="arrow-right-arrow-left">
    Drop-in replacement for inference and fine-tuning — same API, same SFT data format
  </Card>

  <Card title="Function Calling" href="/guides/function-calling" icon="function">
    Connect models to tools and APIs
  </Card>

  <Card title="Structured Outputs" href="/structured-responses/structured-response-formatting" icon="brackets-curly">
    Reliable JSON responses for agentic workflows
  </Card>

  <Card title="Vision Models" href="/guides/querying-vision-language-models" icon="eye">
    Analyze images and documents
  </Card>

  <Card title="Embeddings & Reranking" href="/guides/querying-embeddings-models" icon="vector">
    Use embeddings & reranking in search & context retrieval
  </Card>

  <Card title="Batch Inference" href="/guides/batch-inference" icon="vector">
    Run async inference jobs at scale, faster and cheaper
  </Card>
</CardGroup>

## Resources & help

<CardGroup cols="3">
  <Card title="Which model should I use?" href="/guides/recommended-models" icon="compass">
    Find the best model for your use case
  </Card>

  <Card title="Cookbook" href="https://github.com/fw-ai/cookbook" icon="book-open">
    Code examples and tutorials
  </Card>

  <Card title="API Reference" href="/api-reference/introduction" icon="code">
    Complete API documentation
  </Card>

  <Card title="Discord Community" href="https://discord.gg/fireworks-ai" icon="discord">
    Ask questions and get help from developers
  </Card>

  <Card title="Security & Compliance" href="https://trust.fireworks.ai/" icon="shield-check">
    SOC 2, HIPAA, and audit reports
  </Card>

  <Card title="System Status" href="https://status.fireworks.ai/" icon="signal">
    Check service uptime
  </Card>

  <Card title="Talk to Sales" href="https://fireworks.ai/company/contact-us" icon="building">
    Talk to our team
  </Card>
</CardGroup>