Head to head

gpt-5-mini vs gpt-5-nano: API Pricing Compared

On a typical chat turn of 10K input and 1K output tokens, gpt-5-nano costs $0.00090 against $0.00450 for gpt-5-mini, making it 80% cheaper. Both rates are read daily from the providers' own pricing pages.

Side by side

gpt-5-minigpt-5-nano
ProviderOpenAIOpenAI
Input / 1M tokens$0.25$0.05
Output / 1M tokens$2.00$0.40
Context windowshortshort
Blended cost / chat turn$0.00450$0.00090
Price verified2026-08-062026-08-06

Cost by workload

The headline rate rarely decides the bill. These are the same four workloads priced against both models.

WorkloadTokensgpt-5-minigpt-5-nano
Single short call2K in, 500 out$0.00150$0.00030
Typical chat turn10K in, 1K out$0.00450$0.00090
Long document pass100K in, 2K out$0.029$0.00580
1,000 chat turns10M in, 1M out$4.50$0.900

Which one actually wins

gpt-5-nano is cheaper on both the input and the output rate, so it never costs more no matter how input-heavy or output-heavy the workload is. There is no crossover point to reason about. Price is only one axis, so weigh it against context window, latency, and the quality difference on your own evaluation set before switching.

Common questions

Which is cheaper, gpt-5-mini or gpt-5-nano?

gpt-5-nano is cheaper for a typical chat turn of 10K input and 1K output tokens, at $0.00090 against $0.00450 for gpt-5-mini, a difference of 80%.

How much does gpt-5-mini cost per 1M tokens?

OpenAI charges $0.25 per 1M input tokens and $2.00 per 1M output tokens for gpt-5-mini, verified 2026-08-06.

How much does gpt-5-nano cost per 1M tokens?

OpenAI charges $0.05 per 1M input tokens and $0.40 per 1M output tokens for gpt-5-nano, verified 2026-08-06.

Does gpt-5-nano stay cheaper for every workload?

Yes. gpt-5-nano is cheaper on both the input and the output rate, so it never costs more regardless of how input-heavy or output-heavy the workload is.

Full pricing pages

Maintained by Jordan Hale, TechFastForward. Both prices are read daily from the official provider pages and recorded only when they move. Compare any other pair on the LLM API Pricing Tracker.