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

# DEPLOY A MODEL

> Serve a model behind an Oumi inference endpoint

<Steps>
  <Step title="Write a deployment spec">
    Set `MODEL_ID` to the model you want to serve, then paste the block:

    ```bash theme={null}
    MODEL_ID=1

    cat > deployment.json <<EOF
    {
      "displayName": "support-classifier",
      "modelSpec": {
        "type": "custom",
        "modelId": $MODEL_ID,
        "autoscaling": { "minReplicas": 0, "maxReplicas": 1, "scaleDownIdleSeconds": 60 }
      }
    }
    EOF
    ```
  </Step>

  <Step title="Create the deployment">
    ```bash theme={null}
    oumi-cli deployments create --input-json-file deployment.json
    ```

    Returns the deployment ID.
  </Step>

  <Step title="Retrieve deployment info">
    ```bash theme={null}
    oumi-cli deployments endpoint <DEPLOYMENT_ID>
    ```

    Prints the inference URL, the model path, and a runnable curl snippet.
  </Step>
</Steps>

<Columns cols={2}>
  <Card title="Evaluate a model" icon="chart-column" href="/cli/workflows/evaluate-a-model">
    Score the model you deployed.
  </Card>

  <Card title="Deployments reference" icon="list" href="/cli/commands/deployments">
    Every flag on every deployment command, including inference log export.
  </Card>
</Columns>