The home for
excess compute.
The models you want. At the prices you should pay.
Find capacity, track prices, and route through one API.
THE OPEN MARKET FOR INTELLIGENCE
Find compatible models and migrate your code.
Model pricing
PAST 24 HOURS1M input + 1M output tokens · USD
Connecting to model catalogs and market prices…
Models in demand.
Source: market activity · current reported counters, labeled 24h upstream. A rolling window has not been confirmed. Top 0 models shown; the share bar and totals include all 0.
The biggest savings.
Current discounts from direct list prices.
1M input + 1M output tokens. Discounts use observed market prices and matching direct references; stale quotes are excluded.
Discover more. Spend less.
Models with current discounts will appear here when fresh prices are available.
See how much you save.
Compare market discounts against direct list prices. Higher means more savings.
Higher is better. 99% off means paying 1% of direct list price. Each discount uses the direct price recorded at that time; negative values mean above-list pricing. Recorded observations only; gaps stay visible. In + out = 1M input + 1M output tokens.
Biggest discounts
Market prices against direct list prices.
Waiting for qualified market observations.
Intelligence per dollar
GPQA Diamond score ÷ in + out price.
Waiting for qualified market observations.
Models in demand
Market-reported request activity.*
Waiting for qualified market observations.
Intelligence leaders
Published GPQA Diamond observations.
Waiting for qualified market observations.
A new base URL.
A better price.
Keep your OpenAI-compatible client. Choose an exact model ID, connect a key, and let GPU Router find the eligible route.
Read the quickstart →// Your next request
const completion = await client.chat.completions.create({
model: "openai/gpt-6-astra",
messages: [{ role: "user",
content: "Build something great." }]
});* The market feed labels activity as 24h; the rolling window has not been confirmed. Other venues do not expose comparable public model-wide usage, so totals are not combined. Benchmark observations: Sep 6, 2026; external endpoints, not marketplace quality guarantees.