Hyperouter API

Version v1 · Updated September 24, 2026

Hyperouter exposes one OpenAI-compatible HTTP API in front of many model providers. You send a request naming a model; Hyperouter picks the provider (the venue) that serves it best, forwards the request, and bills your balance at that venue’s list price.

Quickstart

1. Request an API key. Keys start with hr-.
2. Store it in an environment variable, e.g. HYPEROUTER_API_KEY.
3. Point any OpenAI SDK at the base URL above and pick a model.

curl https://hyperouter.app/api/v1/chat/completions \
  -H "Authorization: Bearer $HYPEROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "anthropic/claude-sonnet-5",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://hyperouter.app/api/v1",
  apiKey: process.env.HYPEROUTER_API_KEY,
});

const res = await client.chat.completions.create({
  model: "anthropic/claude-sonnet-5",
  messages: [{ role: "user", content: "Hello" }],
});
console.log(res.choices[0].message.content);

import os
from openai import OpenAI

client = OpenAI(
    base_url="https://hyperouter.app/api/v1",
    api_key=os.environ["HYPEROUTER_API_KEY"],
)

res = client.chat.completions.create(
    model="anthropic/claude-sonnet-5",
    messages=[{"role": "user", "content": "Hello"}],
)
print(res.choices[0].message.content)

Authentication

Send your key as a bearer token on every request:

Authorization: Bearer hr-...

Keys carry full access to your balance. Keep them server-side, never in browser or mobile code. To rotate or revoke a key, email account@hyperouter.app; a revoked key stops working immediately.

Chat completions

Accepts the OpenAI Chat Completions request body. Hyperouter adds the models and provider fields for routing.

Request body

Response

Identical to OpenAI’s, plus provider (the venue that filled the request) and usage.cost in USD.

{
  "id": "gen-01J8Z6Q4X2",
  "object": "chat.completion",
  "model": "anthropic/claude-sonnet-5",
  "provider": "anthropic",
  "choices": [{
    "index": 0,
    "message": { "role": "assistant", "content": "Hello! How can I help?" },
    "finish_reason": "stop"
  }],
  "usage": {
    "prompt_tokens": 9,
    "completion_tokens": 8,
    "total_tokens": 17,
    "cost": 0.000147
  }
}

Streaming

With "stream": true the response is a stream of server-sent events in the OpenAI chunk format, ending with data: [DONE]. The last chunk before [DONE] carries usage and provider.

Fallback happens only before the first token is sent. If a venue fails mid-stream, the stream ends with an error event and you are billed only for tokens already delivered.

Routing

By default Hyperouter sends each request to the healthy venue with the lowest price for that model, breaking ties by latency. A venue is considered unhealthy after elevated error rates or timeouts in the last few minutes and is skipped until it recovers.

Override the default with the provider object:

{
  "model": "deepseek/deepseek-v3.2",
  "provider": {
    "sort": "throughput",
    "data_collection": "deny",
    "max_price": { "prompt": 0.5, "completion": 1 }
  },
  "messages": [{ "role": "user", "content": "Hello" }]
}

Models

Lists every model you can call, with live prices per token in USD and the venues serving it. No authentication required.

{
  "data": [{
    "id": "anthropic/claude-sonnet-5",
    "name": "Claude Sonnet 5",
    "context_length": 200000,
    "pricing": { "prompt": "0.000003", "completion": "0.000015" },
    "venues": ["anthropic", "bedrock", "vertex"],
    "modalities": ["text", "image"]
  }]
}

Errors

Errors use standard HTTP status codes and an OpenAI-style body: {"error": {"code": 402, "message": "..."}}.

Billing & limits

• Requests are paid from a prepaid USD balance. Token prices match each venue’s list price; there is no markup.
• Top-ups by card carry a 3.0% fee; USDC and USDT top-ups carry 2.5%. Accounts above $50K per month can move to invoicing.
• Only successful requests are billed. Fallback attempts that fail cost nothing.
• Every response includes usage.cost, so you can reconcile spend per request.
• Rate limits scale with your balance and history. Current limits are returned in X-RateLimit-Limit, X-RateLimit-Remaining and X-RateLimit-Reset headers.

Support

Keys, billing and API questions: account@hyperouter.app. Chat product: chat@hyperouter.app. Please include the id from the response when reporting a specific request.