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

# Add a model backend

> Wire a new model backend into Mill — pick the interface, register, document.

Most new models need **no code** — a HuggingFace, vLLM, or LiteLLM model is just a config file (see the [Models reference](/docs/reference/models)). Write a backend only when the inference engine or model interface is genuinely new. The repo ships a **[Claude Code](https://claude.com/claude-code) skill** that walks you through it.

<Note>
  The skill lives in the repo at `.claude/skills/adding-a-model/`. In Claude Code, type `/adding-a-model`; you can also read it as plain Markdown.
</Note>

<Card title="adding-a-model skill" icon="cpu-chip" href="https://github.com/haideraltahan/Mill/blob/main/.claude/skills/adding-a-model/SKILL.md">
  Pick the right capability interface, register it, and document it.
</Card>

## The process

1. **Pick the capability interface** — `GenerativeModel` (LLMs/VLMs), `ZeroShotClassifier` (CLIP-style), or `SupervisedClassifier` (timm). It decides which `task_type`s the backend can serve.
2. **Implement and register** — subclass the interface, implement only the batch hooks, and register it with `@register_model` and a cache-safe `model_name`. Declare honest `capabilities` so the evaluator rejects unsupported (model, task) pairs.
3. **Make it loadable** — add a per-family config under `mill/models/configs/`, and gate optional dependencies with a clear `ImportError` plus a `pyproject.toml` extra.
4. **Validate and document** — sanity-check on a benchmark its interface supports, then add a backend section to the [Models reference](/docs/reference/models).