# Relayvia

> Relayvia is an AI API gateway: call listed models by their official names in the OpenAI, Anthropic or Gemini format, billed against your account's prepaid credits.

API base URL: https://api.relayvia.dev/v1

## Getting started

- [Overview](https://relayvia.dev/docs.md): What Relayvia serves, every endpoint at a glance and where to start.
- [Quickstart](https://relayvia.dev/docs/quickstart.md): Four steps: get an API key, choose a model, send your first request and see the usage in the console.
- [Authentication](https://relayvia.dev/docs/authentication.md): Which header each API format uses for your key, and whether its base URL includes /v1.
- [Model list](https://relayvia.dev/docs/models.md): Official model names, the models listed now and how to see which ones your key can use.

## API reference

- [Chat Completions](https://relayvia.dev/docs/api/chat-completions.md): The OpenAI Chat Completions format: parameters, differences, examples and errors.
- [Responses](https://relayvia.dev/docs/api/responses.md): The OpenAI Responses format, used by Codex CLI.
- [Messages](https://relayvia.dev/docs/api/messages.md): The Anthropic Messages format, used by Claude Code.
- [Gemini native](https://relayvia.dev/docs/api/gemini.md): generateContent and streamGenerateContent in the native Gemini format.
- [Models](https://relayvia.dev/docs/api/models.md): GET /v1/models: the models your API key can call.
- [Check credits](https://relayvia.dev/docs/api/balance.md): How much your API key can still spend, from /v1/balance or the OpenAI legacy subscription endpoint.
- [Check usage](https://relayvia.dev/docs/api/usage.md): Usage of your key or team member by model and date, from /v1/usage or the OpenAI legacy usage endpoint.

## Guides

- [Error codes](https://relayvia.dev/docs/errors.md): Every error code with its HTTP status, fixed message and what to do; 402 versus 429; the three error formats.
- [Limits and billing](https://relayvia.dev/docs/limits.md): Rate limits, how a request is priced and charged, and the credit limits that return 402.
- [Async tasks](https://relayvia.dev/docs/async-tasks.md) (Coming soon): Submit image and video tasks, then poll for the result or receive a callback.

## Integrations

- [Claude Code](https://relayvia.dev/docs/tools/claude-code.md): Install Claude Code and point it at Relayvia with a settings file or environment variables.
- [Codex CLI](https://relayvia.dev/docs/tools/codex-cli.md): Install Codex CLI and add Relayvia to ~/.codex/config.toml.
- [Gemini CLI](https://relayvia.dev/docs/tools/gemini-cli.md) (Coming soon): Install Gemini CLI and point it at Relayvia.
- [Cursor](https://relayvia.dev/docs/tools/cursor.md): Enter Relayvia's URL and your API key in Cursor's model settings.
- [Cline](https://relayvia.dev/docs/tools/cline.md): Choose OpenAI Compatible in Cline and enter Relayvia's URL and your API key.
- [Cherry Studio](https://relayvia.dev/docs/tools/cherry-studio.md): Add an OpenAI-type model service in Cherry Studio that points at Relayvia.