01Core reference
Docs
API Documentation
Complete reference for chat completions, streaming, tool calling, JSON schema validation, and rate-limit headers.
Developer ecosystem
Resources & Hub
Everything you need to integrate, route, monitor, and scale with InferencePass. From the first request to a production incident, the useful context stays close.
- REST & OpenAI compatible
- Sub-1.2ms routing
- Zero prompt logging
Platform tooling
Take what you need. Leave with more context.
Useful reference material and live signals, organized around the work developers actually do.
Open docs
02Live telemetry
Status
Live Route Status
Current route availability, operational health checks, historical incident reports, and catalogue versions.
03Open source
SDKs
Official SDKs
TypeScript and Node.js client patterns plus the OpenAPI specification for generated clients.
04Verified routes
Models
Model Catalogue
Review supported models, context limits, token basis calculations, and active upstream verification.
05Developer tool
Playground
Interactive Playground
Run prompts against available models, compare results, inspect usage, and test tools live.
06Controls
Security
Security & Compliance
Explore session controls, browser data policies, and the architectural boundaries behind the service.
One-line integration
Bring your client.
Keep your options.
Point an existing OpenAI client to the gateway and let the route handle provider selection and failover.
quickstart.tsTypeScript
import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://api.inferencepass.com/v1",
apiKey: process.env.INFERENCEPASS_API_KEY,
});
const response = await client.chat.completions.create({
model: "gpt-4o",
messages: [{ role: "user", content: "Explain deterministic routing." }],
});