Yelu AI API is an OpenAI-compatible gateway. Keep your existing OpenAI SDK and request shape, change the base URL, and access models from multiple providers through one API.
One API for production AI
Yelu normalizes authentication, routing, streaming, usage data, and errors across supported model providers. Model availability is tied to your account and can be discovered at runtime withGET /v1/models.
Make your first request
Send a chat request in a few minutes with curl, JavaScript, or Python.
Use the OpenAI SDK
Point the official SDK at
https://api.yelu.ai/v1 and keep its typed API.Explore the API
Review endpoints, fields, responses, errors, and runnable request examples.
Build robust integrations
Apply timeouts, retries, observability, model discovery, and safe key handling.
Coding agents
Use Claude Code
Configure Anthropic Messages routing on macOS, Windows, or WSL 2.
Use Codex CLI
Connect Codex to Yelu’s Responses API with a custom model provider.
Core capabilities
Text
Chat Completions and the Responses API with conversation context and reasoning controls.
Multimodal
Vision input, image generation, audio transcription, and multimodal responses.
Agentic
Function calling, tool choice, structured JSON, streaming, and multi-step workflows.
Base URL
All OpenAI-compatible endpoints use this base URL:First request
Set your key once, then send a request. Replace the example model with an ID returned byGET /v1/models if it is not enabled for your account.
Where to go next
1
Create and protect a key
Follow Authentication and load the key from an environment variable or secret manager.
2
Discover models
Call List models instead of hard-coding a provider catalog.
3
Choose an API
Start new agentic workflows with Responses, or use Chat Completions for broad OpenAI compatibility.
4
Prepare for production
Read Rate limits, Errors, and Best practices.