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

# Build with FriendliAI

> Build with FriendliAI for fast, affordable, and reliable AI inference. Start with Model APIs, then deploy any model on dedicated GPUs with Dedicated Endpoints.

export const PricingCard = ({product}) => <Card title="Pricing" icon="tag" href={product === "model-apis" ? "https://friendli.ai/pricing?product=model-apis" : product === "dedicated-endpoints" ? "https://friendli.ai/pricing?product=dedicated-endpoints" : "https://friendli.ai/pricing"}>
    {product === "model-apis" ? "Pay per usage." : product === "dedicated-endpoints" ? "Reserve dedicated GPUs." : "Pay per usage or reserve dedicated GPUs."}
  </Card>;

export const ModelsCard = ({product}) => <Card title="Models" icon="brain" href={product === "model-apis" ? "https://friendli.ai/models?products=SERVERLESS" : product === "dedicated-endpoints" ? "https://friendli.ai/models?products=DEDICATED" : "https://friendli.ai/models"}>
    {product === "model-apis" ? "Browse a curated set of popular, open-weight models that are ready for you today." : product === "dedicated-endpoints" ? "Browse over 580,000 models and deploy your choice on dedicated GPUs." : "Browse over 580,000 models."}
  </Card>;

FriendliAI's inference is powered by the Friendli Engine, optimized for speed and cost. In a few steps, you get access to a popular set of open-weight models that are comparable to the frontier models you're used to. When you're ready for more, you can deploy any model, including your own, on dedicated GPUs.

## Start Your Journey

Create an API key, choose a model, and send your first request with [Friendli Model APIs](/guides/model-apis/introduction). FriendliAI's [OpenAI-compatible Chat Completions API](/openapi/model-apis/chat-completions) works with most coding agents and SDKs. You can also try the [Anthropic-compatible Messages API](/openapi/model-apis/messages) <Badge color="blue">Beta</Badge>.

<Card title="Model APIs" icon="cloud" href="/guides/introduction/get-started" cta="Get Started">
  Start with a curated set of models available at usage-based pricing.
</Card>

## Run Any Model on Dedicated GPUs

If you want to run any model, including your own, you're ready for [Friendli Dedicated Endpoints](/guides/dedicated-endpoints/introduction). With Dedicated Endpoints, you can browse over 580,000 models and deploy your choice on dedicated GPUs.

<Card title="Dedicated Endpoints" icon="server" href="/guides/dedicated-endpoints/quickstart" cta="Get Started">
  Deploy any model on dedicated GPUs reserved for you.
</Card>

## Resources

<CardGroup cols={2}>
  <Card title="Reference" icon="book" href="/openapi/introduction">
    Learn more about the API and its operations and parameters.
  </Card>

  <Card title="Examples" icon="code" href="/guides/tutorials">
    See what you can do with real-world use cases.
  </Card>
</CardGroup>

<CardGroup cols={3}>
  <ModelsCard />

  <PricingCard />

  <Card title="Blog" icon="newspaper" href="https://friendli.ai/blog">
    Read the latest posts from FriendliAI.
  </Card>
</CardGroup>