# PrimaLabs

> Developer documentation for the PrimaLabs serverless LLM inference platform.

- [Introduction](https://docs.primalabs.ai/inference/introduction.md): Serverless LLM inference on PrimaLabs — OpenAI-compatible, one bearer key, pay per token.
- [Quickstart](https://docs.primalabs.ai/inference/quickstart.md): Make your first PrimaLabs API call in under a minute.
- [Authentication](https://docs.primalabs.ai/inference/authentication.md): How PrimaLabs API keys work and how to create one.
- [Models](https://docs.primalabs.ai/inference/models.md): The model catalog, pricing, and context windows.
- [Rate limits](https://docs.primalabs.ai/inference/rate-limits.md): The three limits in front of every request, and how to handle them.
- [Errors](https://docs.primalabs.ai/inference/errors.md): HTTP status codes the API returns and how to respond to each.
- [Zero data retention](https://docs.primalabs.ai/platform/data-retention.md): What PrimaLabs stores about your requests — and what it never stores.

## OpenAPI Specs

- [openapi](/api-reference/inference/openapi.yaml)