GPT-5 nano token cost & pricing

GPT-5 nano is the cheapest model in OpenAI's GPT-5 family at $0.05 per million input and $0.40 per million output tokens. That is low enough that per-request cost stops being a planning concern: a million requests with a 200-token prompt and 50-token answer costs about $30 in total.

GPT-5 nano specifications

What GPT-5 nano costs in practice

Four common workloads, priced at list rates. Monthly figures assume 30 days.

How many requests does $100 buy?

Assuming a 1,000-token prompt and a 500-token response per request.

How GPT-5 nano pricing actually works

The 8x input-to-output ratio persists, so a long generation still costs meaningfully more than a long prompt. Cached input drops to $0.005 per million — effectively free — which makes nano a strong fit for high-volume jobs with a fixed instruction prefix.

When to use GPT-5 nano

Best for classification, routing, entity extraction, keyword tagging, spam filtering and simple yes/no judgments at scale. Do not use it as a general chat model or for anything requiring multi-step reasoning; it will produce plausible-sounding wrong answers on hard inputs.

How to cut your GPT-5 nano bill

At this price the useful optimization is not cost but throughput: batch your requests, avoid retrying aggressively, and spend the saved budget on escalating the genuinely hard 10% to GPT-5 mini or GPT-5.

Other OpenAI models