# Shadow Inference — Agent Docs

Agent-facing documentation bundle for the Shadow Inference OpenAI-compatible API. Start with the quickstart, then consult the topics below as needed.

- [Quickstart](quickstart.md): Authenticate and make your first request in under a minute.
- [API Reference](api-reference.md): Every `/v1*` endpoint: methods, parameters, request/response shapes.
- [Models](models.md): The model catalog: model_id, tier, and context window for every model.
- [Pricing](pricing.md): Per-model €/M-token rates.
- [Dedicated Endpoints](dedicated.md): Private single-tenant model deployments billed per GPU-card-minute: when to use one, lifecycle, management API, and exactly what bills.
- [Streaming](streaming.md): The server-sent-events (SSE) contract for chat/completions streaming.
- [Tool Use](tool-use.md): Function calling (`tools` / `tool_choice`) with the chat completions API.