AI Rate Card

GPT-4.1 mini vs GPT-4.1 nano: API price and specs

GPT-4.1 nano is 75% cheaper than GPT-4.1 mini on input price.

GPT-4.1 nano is 75% cheaper than GPT-4.1 mini on output price.

GPT-4.1 nano is 75% cheaper than GPT-4.1 mini on a 1M-in / 200k-out workload.

FieldGPT-4.1 miniGPT-4.1 nano
Lowest input, per 1M$0.20 +300%$0.05
Median input, per 1M$0.40 +300%$0.10
Lowest output, per 1M$0.80 +300%$0.20
Median output, per 1M$1.60 +300%$0.40
Lowest unit price——
Cost of 1M in + 200k out$0.36 +300%$0.09
Context1M1M
Max output33K +96.5%943K
Providers2321 +8.7%
RegionsEU, GLOBAL, USEU, GLOBAL, US
Acceptsapplication/pdf, file, image, image/gif, image/jpeg, image/png, image/webp, pdf, textfile, image, image/gif, image/jpeg, image/png, image/webp, pdf, text
Returnstexttext
TypeText modelsText models
Free optionnono
Cheapest provideropenrouteropenrouter

Your own workload: how many tokens the model gets (input) and gives back (output) - for example, in a month. The "Cost" row of the table above is recalculated for these numbers, for each model.

Computed from current offers each time the page opens; the best value of a row is bold, the percent is how far behind the best.

Providers selling both

302ai, abacus, aihubmix, azure, cometapi, cortecs, edenai, fastrouter, helicone, impossibl, jiekou, kilo, nearai, openai, openrouter, orcarouter, poe, requesty, trustedrouter, vercel, zenmux

Frequently asked questions

Which is cheaper, GPT-4.1 mini or GPT-4.1 nano?

GPT-4.1 nano is 75% cheaper than GPT-4.1 mini on input price. GPT-4.1 nano is 75% cheaper than GPT-4.1 mini on output price. GPT-4.1 nano is 75% cheaper than GPT-4.1 mini on a 1M-in / 200k-out workload.

Which has the larger context, GPT-4.1 mini or GPT-4.1 nano?

GPT-4.1 mini: 1M tokens; GPT-4.1 nano: 1M tokens.

Where can I use both GPT-4.1 mini and GPT-4.1 nano?

302ai, abacus, aihubmix, azure, cometapi, cortecs, edenai, fastrouter, helicone, impossibl, jiekou, kilo, nearai, openai, openrouter, orcarouter, poe, requesty, trustedrouter, vercel, zenmux