# Wafer

- [Serverless](https://docs.wafer.ai/serverless.md): Access Wafer models through OpenAI-compatible and Anthropic-compatible APIs.
- [Models and Capabilities](https://docs.wafer.ai/serverless/models.md): Discover models, context and output limits, per-API capability flags, reasoning efforts, and pricing from the model catalog.
- [Zero Data Retention](https://docs.wafer.ai/serverless/zero-data-retention.md): Require Zero Data Retention (ZDR) for individual Wafer Serverless requests.
- [Chat Completions](https://docs.wafer.ai/serverless/chat-completions.md): The primary Wafer Serverless API: OpenAI-compatible chat completions with streaming, tools, structured outputs, vision, and reasoning.
- [Responses](https://docs.wafer.ai/serverless/responses.md): Stateless OpenAI Responses-compatible API: supported fields, tools, structured outputs, and streaming events.
- [Messages](https://docs.wafer.ai/serverless/messages.md): Anthropic-compatible Messages API: supported fields, tools, vision, token counting, and streaming events.
- [Errors and Rate Limits](https://docs.wafer.ai/serverless/errors.md): Error format, error codes, retry guidance, rate limits, and streaming failures for Wafer Serverless.
- [Usage and Billing](https://docs.wafer.ai/serverless/usage.md): Token usage in every response, the account usage API, prompt caching, reasoning tokens, and how Wafer Serverless bills.