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

# Deploy and operate AI models across your infrastructure.

> Build or connect inference with durable operations, autoscaling, safe releases, and evidence you can inspect.

<div className="ic-hero not-prose">
  <div className="ic-kicker"><span className="ic-status-dot" /> Private-preview inference control plane</div>

  <div className="ic-actions">
    <a className="ic-button ic-button-primary" href="/quickstart">Start the local tour <span aria-hidden="true">→</span></a>
    <a className="ic-button ic-button-secondary" href="https://infercrane.com/#private-preview">Join private preview <span aria-hidden="true">↗</span></a>
  </div>

  <div className="ic-proof">
    <span>Model to endpoint</span>
    <span>Safe releases</span>
    <span>Explainable operations</span>
    <span>No Kubernetes required</span>
  </div>
</div>

```bash Deploy a model theme={"theme":"css-variables"}
infercrane deploy mistralai/Mistral-7B-Instruct-v0.3 \
  --name support-production

# Safe to close: the operation is persisted by the control plane.
infercrane status support-production --watch
```

InferCrane turns a model or immutable OCI workload into one OpenAI-compatible logical endpoint.
Durable operations provision, reconcile, scale, and safely replace workers behind it. Already
running inference? Connect it in observe-only mode without migrating or transferring ownership.

<div className="ic-flow not-prose" aria-label="InferCrane request path">
  <div className="ic-node"><span className="ic-node-label">request</span><strong>OpenAI client</strong></div>
  <span className="ic-flow-arrow" aria-hidden="true">→</span>
  <div className="ic-node ic-node-accent"><span className="ic-node-label">stable identity</span><strong>endpoint</strong></div>
  <span className="ic-flow-arrow" aria-hidden="true">→</span>
  <div className="ic-node"><span className="ic-node-label">atomic policy</span><strong>route snapshot</strong></div>
  <span className="ic-flow-arrow" aria-hidden="true">→</span>
  <div className="ic-node"><span className="ic-node-label"><i className="ic-dot" /> ready</span><strong>runtime binding</strong></div>
</div>

## Choose your starting point

<CardGroup cols={2}>
  <Card title="Deploy a model" icon="server" href="/showcase/build-inference">
    Start from a reviewed model configuration or explicit serving plan. One durable operation owns the lifecycle.
  </Card>

  <Card title="Connect existing inference" icon="plug" href="/showcase/connect-existing">
    Discover vLLM, SGLang, LiteLLM, or another OpenAI-compatible endpoint before transferring ownership.
  </Card>

  <Card title="Prove the loop locally" icon="flask" href="/quickstart">
    Run the complete GPU-free control and request path in under five minutes.
  </Card>
</CardGroup>

## The production operating loop

<Steps>
  <Step title="Deploy and converge">
    Persist the desired model, runtime, infrastructure, and scale policy before provider work begins.
  </Step>

  <Step title="Observe the real request path">
    Correlate endpoint, revision, replica, queueing, TTFT, generation, errors, and cost evidence.
  </Step>

  <Step title="Validate a candidate">
    Compare active and candidate revisions with benchmark, replay, runtime, and optional signed task-quality evidence.
  </Step>

  <Step title="Promote, reject, or explain">
    Apply deterministic Release Guard policy and preserve the decision for audit and recovery.
  </Step>
</Steps>

<Note>
  Provider and runtime capabilities are declared and conformance-tested, but each adapter has an
  independent qualification state. Review [capability status](/project-status) before relying on an
  exact provider, runtime, model, and accelerator combination.
</Note>

<CardGroup cols={3}>
  <Card title="See production patterns" icon="sparkles" href="/showcase/index">
    Follow real-life deployment, adoption, rollout, cost, and composition journeys.
  </Card>

  <Card title="Understand the architecture" icon="diagram-project" href="/architecture/system">
    See the durable control plane, database-free request path, and replaceable adapter boundaries.
  </Card>

  <Card title="Inspect the CLI" icon="terminal" href="/cli">
    Browse current commands, durable operation behavior, and machine-readable output.
  </Card>

  <Card title="Release and upgrade safely" icon="arrow-up-from-bracket" href="/upgrade">
    Qualify client, protocol, runtime, and control-plane changes with explicit restoration paths.
  </Card>
</CardGroup>