# Wafer ## Docs - [Metrics API](https://docs.wafer.ai/dedicated-endpoints/metrics-api.md): Query endpoint-level performance metrics for a Wafer dedicated deployment. - [Dedicated Endpoints](https://docs.wafer.ai/dedicated-endpoints/overview.md): Overview of endpoint-scoped auth, metrics, and request debugging for Wafer dedicated deployments. - [Request Inspection](https://docs.wafer.ai/dedicated-endpoints/request-inspection.md): Inspect recent requests, filter errors, and look up individual request IDs for a Wafer dedicated endpoint. - [Tokenized Completions and Constrained Decoding](https://docs.wafer.ai/dedicated-endpoints/tokenized-completions.md): Use token-ID prompts and EBNF grammar constraints on Wafer dedicated endpoints. - [Error Reference](https://docs.wafer.ai/errors.md): Every error code returned by the Wafer API, what causes it, and what to do about it. - [Serverless](https://docs.wafer.ai/serverless.md): Pay-as-you-go access to Wafer models through OpenAI-compatible and Anthropic-compatible APIs. - [API Reference](https://docs.wafer.ai/serverless/api-reference.md): Direct curl requests, endpoints, headers, and request parameters for Wafer Serverless. - [Serverless Metrics API](https://docs.wafer.ai/serverless/metrics-api.md): Query per-account Serverless performance metrics for pass.wafer.ai. - [Agent Setup](https://docs.wafer.ai/serverless/setup.md): Fast open-source LLMs for Claude Code, Codex, Conductor, OpenClaw, Hermes Agent, Cline, Roo Code, Kilo Code, OpenHands, and other coding agent harnesses. - [Tokenized Completions and Constrained Decoding](https://docs.wafer.ai/serverless/tokenized-completions.md): Use token-ID prompts and EBNF grammar constraints with Wafer Serverless. - [Serverless Usage API](https://docs.wafer.ai/serverless/usage-api.md): Query your own Serverless token usage and estimated cost. - [Zero Data Retention](https://docs.wafer.ai/serverless/zero-data-retention.md): Require ZDR on individual Wafer Serverless requests. ## OpenAPI Specs - [openapi](https://docs.wafer.ai/api-reference/openapi.json)