AI Rate Card

GPT-4.1 vs GPT-4o (2024-11-20): API price and specs

GPT-4.1 is 60% cheaper than GPT-4o (2024-11-20) on input price.

GPT-4.1 is 60% cheaper than GPT-4o (2024-11-20) on output price.

GPT-4.1 is 60% cheaper than GPT-4o (2024-11-20) on a 1M-in / 200k-out workload.

GPT-4.1 has a 718.4% larger context than GPT-4o (2024-11-20).

FieldGPT-4.1GPT-4o (2024-11-20)
Lowest input, per 1M$1.00$2.50 +150%
Median input, per 1M$2.00$2.50 +25%
Lowest output, per 1M$4.00$10.00 +150%
Median output, per 1M$8.00$10.00 +25%
Lowest unit price——
Cost of 1M in + 200k out$1.80$4.50 +150%
Context1M128K +87.8%
Max output33K16K +50%
Providers248 +66.7%
RegionsEU, GLOBAL, USUS
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 provideropenrouteraihubmix

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

aihubmix, edenai, fastrouter, kilo, openai, openrouter, orcarouter, requesty

Frequently asked questions

Which is cheaper, GPT-4.1 or GPT-4o (2024-11-20)?

GPT-4.1 is 60% cheaper than GPT-4o (2024-11-20) on input price. GPT-4.1 is 60% cheaper than GPT-4o (2024-11-20) on output price. GPT-4.1 is 60% cheaper than GPT-4o (2024-11-20) on a 1M-in / 200k-out workload.

Which has the larger context, GPT-4.1 or GPT-4o (2024-11-20)?

GPT-4.1: 1M tokens; GPT-4o (2024-11-20): 128K tokens.

Where can I use both GPT-4.1 and GPT-4o (2024-11-20)?

aihubmix, edenai, fastrouter, kilo, openai, openrouter, orcarouter, requesty