# Prentis

> One inference API. An OpenAI client and an Anthropic client reach the same models.

- [Introduction](https://docs.compute.prentis.ai/introduction.md): One inference API. An OpenAI client and an Anthropic client reach the same models.
- [Quickstart](https://docs.compute.prentis.ai/quickstart.md): From a fresh account to a working call, in three steps.
- [Models and resource names](https://docs.compute.prentis.ai/models-and-resource-names.md): When to write a bare slug, when to write a full resource name, and what happens when a model retires.
- [Authentication](https://docs.compute.prentis.ai/authentication.md): Bearer keys, the x-api-key alias, and what happens when a key is revoked.
- [Rate limits and quotas](https://docs.compute.prentis.ai/rate-limits-and-quotas.md): What throttles you, which of the three 429s you are looking at, and how to back off.
- [Errors](https://docs.compute.prentis.ai/errors.md): Every error the inference API can return, whether it is safe to retry, and whether it costs you anything.
- [API reference](https://docs.compute.prentis.ai/api-reference/introduction.md): Base URL, authentication, the headers on every response, and what is on this tab.
- [Chat completions](https://docs.compute.prentis.ai/api-reference/chat-completions.md): OpenAI-compatible chat completion. Point any OpenAI SDK at this base URL with a Prentis key and nothing else in your code changes.
- [Completions](https://docs.compute.prentis.ai/api-reference/completions.md): Legacy text completion, for prompts that are not a conversation. Only models that declare the text-completion capability accept it; the rest return MODEL_CAPABILITY_UNSUPPORTED.
- [Messages](https://docs.compute.prentis.ai/api-reference/messages.md): Anthropic-compatible Messages endpoint. Anthropic SDKs and Claude Code work by changing base_url alone, and x-api-key is accepted alongside Authorization: Bearer. Pass a Prentis model name -- there is no claude-* aliasing.
- [List models](https://docs.compute.prentis.ai/api-reference/list-models.md): Every model this account can call, in the shape OpenAI clients expect.
- [Get model](https://docs.compute.prentis.ai/api-reference/get-model.md): One model by id, in the shape OpenAI clients expect.

## OpenAPI Specs

- [prentis.openapi](/openapi/prentis.openapi.yaml)