router
Start saving

Save up to 92%
on AI models

Access leading discounted AI models from multiple providers through one
API, without changing your request format.

Start saving Talk to sales
Usage-based walletUsage-based pricingNo monthly commitment
Live

See our live catalog rates

Browse available model capacity, compare market discounts, and inspect current activity across providers.

Provider
All providers
Retention
ZDRStandard prices

Loading 24-hour token activity…

ModelInputOutputDiscount24h activityDetails
$10.00/M$1.98/M$50.00/M$9.90/M80% off—Loading activity
$1.00/M$0.9/M$5.00/M$4.50/M10% off—Loading activity
$5.00/M$0.736/M$25.00/M$3.678/M85% off—Loading activity
$5.00/M$0.736/M$25.00/M$3.678/M85% off—Loading activity
$5.00/M$0.736/M$25.00/M$3.678/M85% off—Loading activity
$5.00/M$0.662/M$25.00/M$3.31/M86% off—Loading activity

Usage based. No separate routing surcharge. Verified list prices cap rates; otherwise, configured prices apply without a claimed discount.
Provider routes are selected automatically. Prices and availability depend on the capabilities your request needs.

OpenAI SDK compatibleModel selected per requestEvery request visible in History

Change two values.
Access every leading provider.

Replace your base URL and API key. Keep your messages, tools, streaming, and response handling exactly where they are.

https://your-router.workers.dev/v1
Read the documentation
base-url.ts

// Live configuration update

- baseURL: "https://api.openai.com/v1"

+ baseURL: "https://your-router.workers.dev/v1"

+ apiKey: process.env.ROUTER_API_KEY

Chat CompletionsResponsesMessages
OpenAIAnthropicGoogleDeepSeekZ.aiQwen

Your data boundaries,
clearly explained.

See what the marketplace records, where caching can occur, and which routes support zero-data-retention controls.

request.log

› POST /v1/chat/completions 200

› model deepseek-v4-flash

› usage tokens & billing

› content [excluded from logs]

Application records

Request logs contain usage and billing metadata. Saved experiments and opt-in response caching have separate controls.

Read the privacy policy
Data controlsby verified route

Zero data retention

Only verified routes qualify for zero-retention workloads.

Review data controls
router──────

Upstream providers

Request content is sent to the eligible providers needed to serve it.

Review subprocessors
Cache control
Prompt caching

Optional caching

Enable account response caching explicitly. Provider cache controls pass through when supported.

Review caching guidance
For capacity sellers

Turn unused inference
capacity into revenue

Tell us where you have available capacity and its approximate dollar value. Our team will review the fit and contact you directly.

  • 1Share available capacity
  • 2We review provider fit
  • 3Discuss supply and settlement

We will only use these details to review and respond to your submission.

Lower the cost of your
next API request

Create an account, fund your wallet, and keep your current request format.

Start saving Talk to sales