OpenRouter gateway details

A multi-model routing platform for developers; switch models by changing the base_url with the OpenAI SDK, ideal for teams comparing the quality and price of many models at once.

Best for: For developers who need unified access to major overseas models, model routing, and cost comparison.

Current status

Reachable

Latency reference

820 ms

/models check

/models supported

Last verified

2026-07-01

Status notes

Docs, model catalog, and pricing page are fairly complete; a good candidate for multi-model routing.

Pricing mode

Billed per model and provider; some models offer free routing or free quota.

Price tags

Standard price, Pay-as-you-go

Free quota

Some free models; actual usable quota depends on your console.

Usually you create an API key in the platform console, then replace the SDK's baseURL, model name, and auth details per the docs. Test streaming, function calling, error codes, and rate limits before launch.

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.AI_GATEWAY_API_KEY,
  baseURL: "see the platform docs"
});

const response = await client.chat.completions.create({
  model: "gpt-4.1-mini",
  messages: [{ role: "user", content: "Test one call through an AI gateway." }]
});

• Supported models: OpenAI, Claude, Gemini, DeepSeek, Grok, Qwen, Moonshot, Flux and more.
• Capabilities: OpenAI-compatible, Streaming, Function calling, Image generation, Embeddings, Balance query.
• Documentation completeness: High; editorial stability score 4.5 / 5.

• Verify cross-border access and billing rules yourself; for production, set budgets, rate limits, and log redaction.
• Third-party relay pricing, models, and availability can change, so re-check them periodically.

Is OpenRouter compatible with the OpenAI API?

This entry is marked as supporting the OpenAI-compatible format, but the exact base_url, model names, and parameters still follow the official docs.

Is OpenRouter ready for production?

Run a small-traffic load test, rate-limit test, and error-code test first, and confirm the billing rules; keep a backup provider for important workloads.