Home

    ---
    title: apogee-ai-serving
    description: Tier-aware router (CHEAP/BALANCED/EXPENSIVE), shadow traffic, canaries, batch inference.
    ---

    # apogee-ai-serving

    > Tier-aware router (CHEAP/BALANCED/EXPENSIVE), shadow traffic, canaries, batch inference.

    ## What is in this package

    | Capability | What you get |

| --- | --- | | Tier router | Routes by CHEAP / BALANCED / EXPENSIVE | | Shadow traffic | Mirror live requests to a candidate model without affecting users | | Canary | Gradual rollout with success-metric gating | | Batch | Asynchronous batch inference for offline jobs |

    ## Install

    ```bash
    pip install apogee-ai-serving
    ```

    ## Where it fits

    This package is part of the [Apogee Framework](/framework/) ecosystem. It can be used:

    - **Standalone** — install and use directly via `pip` (or `npm` for `@apogee/ai-ui-react`).
    - **As a plugin** — generated projects detect it and register matching CLI subcommands automatically.

    See the [framework's modules overview](/framework/modules/overview/) for how all 28 packages fit together.

    ## Read next

    - [Installation](getting-started/installation.md)
    - [Quickstart](getting-started/quickstart.md)
    - [Reference](reference/index.md)