All upstreams operational

One API for every
frontier model

AnyRouters aggregates the official APIs of OpenAI, Anthropic Claude, Google Gemini and AWS Bedrock behind a single OpenAI-compatible endpoint — one key, one bill, automatic failover.

Get Started View Docs

base_url https://api.anyrouters.com/v1

Quickstart

Drop-in. No SDK changes.

Point your existing OpenAI client at our endpoint and route to any model by name. That's the whole migration.

curl https://api.anyrouters.com/v1/chat/completions \
  -H "Authorization: Bearer $ANYROUTERS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-opus-4",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'
from openai import OpenAI

client = OpenAI(
    base_url="https://api.anyrouters.com/v1",
    api_key="sk-anyrouters-...",
)

response = client.chat.completions.create(
    model="claude-opus-4",  # or gpt-5, gemini-2.5-pro, ...
    messages=[{"role": "user", "content": "Hello!"}],
)
import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.anyrouters.com/v1",
  apiKey: "sk-anyrouters-...",
});

const response = await client.chat.completions.create({
  model: "claude-opus-4", // or gpt-5, gemini-2.5-pro, ...
  messages: [{ role: "user", content: "Hello!" }],
});

Models

Every frontier lab, one catalog

Official upstream APIs only — no resold quotas, no gray-market keys. New models land within days of release.

OpenAI

gpt-5 gpt-5-mini o-series

Anthropic

claude-opus-4 claude-sonnet-4 claude-haiku-4

Google

gemini-2.5-pro gemini-2.5-flash

AWS Bedrock

claude on bedrock nova llama

Model names shown for routing reference. All trademarks belong to their respective owners.

Why AnyRouters

Built for production traffic

Unified API

Fully OpenAI-compatible chat completions across every provider. Switch from GPT to Claude to Gemini by changing one string — streaming, tools and vision included.

Pay as you go

Transparent per-token pricing with no subscriptions or minimums. Top up by card via Stripe, track spend per key in real time, export invoices anytime.

Reliable routing

Multiple upstream channels per model with health checks and automatic failover. When one provider degrades, your requests reroute in milliseconds.

Start shipping in minutes

Create a key, top up, and call any model — no sales call required.

Get Started