Your1M.comOne model, many channels and offers — measured on your usage, in one comparable scale
30% cache hit, regular work hours — a good comparison baseline.
Fresh 50% · Cached 30% · Response 20%What is this? How do I read it?
One model, many channels and offers — most of them look like a good deal. Your1M uses your Usage Pattern as a single ruler, converting different pricing rules onto one measure — the effective cost per Your1M — so they become genuinely comparable.
What is being compared
The actual price and capacity of the same model across channels and offers. Every offer × model row is computed under your own Usage Pattern, rather than copied from a vendor price list.
How to read the results
- Your1M: the effective cost per 1,000,000 Input + Final Response tokens under your Usage Pattern (order price ÷ maximum usable capacity).
- Capacity: how many Your1M you can obtain if you spend this offer on this one model only — not necessarily the vendor's nominal allowance.
- Offers that cannot be converted are labelled "not comparable" rather than forced into a number; eligibility-restricted offers show their qualification and a "—".
Thinking does not increase the Your1M denominator, but any Thinking cost charged by the provider is included in the calculation.
Loading comparison data…