Base URL
All API requests are routed through:Quick Example (cURL)
Test your connection with a standard Chat Completions request:Supported Endpoints
Chat Completions
Standard OpenAI-compatible endpoint supporting 200+ frontier LLMs.
Responses API
Stateful multi-turn conversations and built-in server tools.
Anthropic Messages
Native support for Anthropic SDKs and Claude models.
Image Generation & Edits
Create, edit, and inpaint images with Flux, SD 3.5, and Recraft.
Platform Features
Server Tools
Generate images and search the web in chat — just append
@flux-2-turbo or @online to any model.Web Search BYOK
Bring your own Tavily, Exa, or Valyu search key for zero Routeway search charges.
Reasoning Models
Use extended thinking models (DeepSeek R1, OpenAI o-series) for complex problem solving.
Prompt Caching
Automatic and explicit KV caching across Anthropic and OpenAI models for up to 90% cost savings.
Structured Outputs
Force models to return valid JSON matching an exact schema.
Tool Calling
Let models invoke your functions to fetch live data and take actions.
Multimodal Inputs
Send images, PDFs, and documents alongside text in a single request.
Streaming
Receive tokens in real-time as they are generated with SSE.
Presets
Bundle a model, system prompt, and parameters into a reusable preset ID.
Service Tiers
Optimize cost and latency with flex (50% discount) and priority tiers.