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

# Build with RunInfra

> Plain English to production AI endpoints.

RunInfra is the fastest way to ship open-source AI models as production APIs. Describe the endpoint you need in plain English and RunInfra picks the model, benchmarks real GPUs, applies kernel optimizations, and deploys an OpenAI-compatible HTTP endpoint.

## Get started in minutes

<Columns cols={3}>
  <Card title="Start fast with a chat prompt" icon="sparkles" href="/introduction/quickstart">
    Describe your use case in [the dashboard](https://runinfra.ai/~). The agent builds, optimizes, and deploys in one flow.
  </Card>

  <Card title="Optimize on real GPUs" icon="zap" href="/features/optimization">
    Profile across L4 to B200. Search AWQ, GPTQ, FP8 variants. Apply Forge kernels.
  </Card>

  <Card title="Deploy with one click" icon="cloud" href="/deployments/overview">
    Flex scale-to-zero or Active always-on. Cold starts under 2 seconds.
  </Card>
</Columns>

<Tip>
  Not sure where to start? Pick a model with the [model catalog](/features/models), then choose [Flex](/deployments/overview) to prototype and move to [Active](/deployments/overview) for production traffic. Need help tuning a workload? [Talk to our team](https://runinfra.ai/contact).
</Tip>

## What you can build

<Columns cols={3}>
  <Card title="Voice agents" icon="mic" href="/use-cases/voice-agent">
    Streaming STT, LLM, TTS fused at sub-600ms turn-taking.
  </Card>

  <Card title="AI assistants" icon="sparkles" href="/use-cases/ai-assistant">
    Llama, Hermes, Qwen with tools, streaming, structured output.
  </Card>

  <Card title="Embeddings + rerank" icon="search" href="/use-cases/embeddings">
    BGE encoder + cross-encoder reranker in one round-trip.
  </Card>

  <Card title="RAG search" icon="library" href="/use-cases/rag-search">
    Hybrid retrieval, grounded generation, auditable citations.
  </Card>

  <Card title="Document AI" icon="file-text" href="/use-cases/document-ai">
    Vision-language models parsing PDFs and forms to JSON.
  </Card>

  <Card title="Transcription" icon="audio-lines" href="/use-cases/transcription">
    Whisper with diarization and PII redaction.
  </Card>
</Columns>

## Resources and help

<Columns cols={3}>
  <Card title="Which model should I use?" icon="compass" href="/features/models">
    Pick the right model for your use case.
  </Card>

  <Card title="Example prompts" icon="list-checks" href="/prompting/example-prompts">
    Copy-ready prompts for every pipeline shape.
  </Card>

  <Card title="API reference" icon="code" href="/api-reference/introduction">
    Supported OpenAI-compatible endpoints and fields.
  </Card>

  <Card title="Plans and pricing" icon="credit-card" href="/introduction/plans">
    Compare Core and Enterprise.
  </Card>

  <Card title="Troubleshooting" icon="life-buoy" href="/tips/troubleshooting">
    Fix 4xx, 5xx, cold starts, and deploy failures.
  </Card>

  <Card title="Talk to sales" icon="building" href="https://runinfra.ai/contact">
    Volume pricing, SLAs, and SOC 2 or HIPAA.
  </Card>
</Columns>