Comparison · prices as of 2026-07-04 · re-verified 2026-08-18

GPT-5 mini vs GPT-5 nano

On price alone, GPT-5 nano (OpenAI) runs about 80% cheaper than GPT-5 mini for a typical chat workload (2K input + 500 output tokens, 1,000 requests/day). Whether that's the right trade depends on the capability gap — the breakdown below shows where each one wins.

Price per million tokens

Spec GPT-5 mini GPT-5 nano
Input / MTok $0.25 $0.05
Output / MTok $2 $0.40
Context window 400K 400K
Max output 128K 128K
Class workhorse fast / lightweight

Estimated monthly cost by workload

Same models, three realistic usage levels. The gap between them scales with volume, so the right pick can change as you grow.

Workload GPT-5 mini GPT-5 nano Cheaper
Light — chatbot 0.5K in / 0.2K out · 200 req/day $3.15 $0.63 GPT-5 nano
Typical — assistant 2K in / 0.5K out · 1K req/day $45.00 $9.00 GPT-5 nano
Heavy — RAG / agent 8K in / 2K out · 5K req/day $900 $180 GPT-5 nano

Which should you pick?

Frequently asked questions

Is GPT-5 mini or GPT-5 nano cheaper?

GPT-5 nano is cheaper — roughly 80% less per month on a typical assistant workload (2K input + 500 output tokens, 1,000 requests/day).

What do GPT-5 mini and GPT-5 nano cost per million tokens?

GPT-5 mini is $0.25 per million input tokens and $2 per million output. GPT-5 nano is $0.05 input and $0.40 output. Prices are first-party API list rates as of 2026-07-04.

Which has the larger context window, GPT-5 mini or GPT-5 nano?

Both handle up to 400K tokens of context.

When should I choose GPT-5 mini over GPT-5 nano?

Choose GPT-5 mini when you need the extra capability of its workhorse class; drop to GPT-5 nano when speed and cost matter more than peak quality.

Related comparisons

Sources: OpenAI pricing · OpenAI pricing. Run your own numbers in the cost calculator.