Cheaper Inference

A Keak company

Log in Create account

Inference API gateway

Save 30% on inference

We source excess inference capacity and pass the savings to you.

Start saving View models

How it works

One wallet, one key, multiple models

Create an account, choose a supported model, and let the gateway handle routing, metering, and wallet settlement.

01

Fund your wallet

Add balance once, then keep it topped up manually or with auto-recharge.

02

Select any model

Pass the model name in your OpenAI-compatible request body.

03

Pay for exact usage

Input and output tokens are measured per request, then charged from your balance.

Catalog

Supported models and pricing

Access

Ready to start saving?

Create an account, fund your wallet, and issue your first API key.

Account

Sign in or create an account

Docs

Start sending requests

Base URL

http://127.0.0.1:8000/v1

Authentication

Authorization: Bearer ir_live_YOUR_API_KEY

Chat completions

curl http://127.0.0.1:8000/v1/chat/completions \
  -H "Authorization: Bearer ir_live_YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-opus-4.6",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Models

curl http://127.0.0.1:8000/v1/models \
  -H "Authorization: Bearer ir_live_YOUR_API_KEY"

Billing

Requests are billed from returned input and output token usage. Wallet balance is checked before inference starts.

Available model names

Copy an exact model id into the model field of your request.