InferIndex
Language, English, EN
Account

Model comparisons

InferIndex · https://inferindex.dev/en/compare/openai/gpt-4.1-nano/vs/openai/gpt-5-nano

GPT-4.1 Nano vs GPT-5 Nano

GPT-4.1 Nano costs from $0.175 per million tokens and GPT-5 Nano from $0.138 (at a 3:1 input:output mix): the cheapest price for each; prices checked on .

Verdict

At these prices, GPT-4.1 Nano costs 1.3× as much as GPT-5 Nano per million tokens (at a 3:1 input:output mix).

Each model's lowest blended price, per 1M tokens, across every provider we track.

GPT-4.1 Nano vs GPT-5 Nano: API prices
ModelLowest blended price, $ per 1M tokens. Green background: the most favourable value of each column.Input price of the cheapest offer, per 1M tokensOutput price of the cheapest offer, per 1M tokensThe provider's published policy says the text you send is not used to train models. We only show what is published; we can't check it ourselves.For 2,000 input tokens and 500 output tokens per request, 1,000 requests a day, at the cheapest offer for that workload. Change the workload above.OffersProvidersThe maximum amount of text, counted in tokens, the model can take in and write in a single request. Past this limit, the request is refused or cut.Observation
GPT-5 Nano, OpenAIat OpenAI Most expensive offer · $0.151. The highest blended price among comparable offers: one price per provider (its cheapest route), standard tier, current prices only. Priority tiers and prices converted from points are not counted. Green background: the most favourable value of each column., most favourable value of the column $0.05, most favourable value of the column$0.40$0.138, most favourable value of the column$9.00, most favourable value of the columnat OpenAI3218, most favourable value of the column400k Cheapest. Lowest blended price, $ per 1M tokens
GPT-4.1 Nano, OpenAIat Azure via OpenRouter $0.175 $0.10$0.40$0.175$12.00at Azure via OpenRouter21121M

Green background: the most favourable value of each column.

Prices as of Oct 31, 2026, 11:18 AM UTCSame rules as the API's /cheapest route. The monthly estimate uses the cheapest offer for that workload.

Share

Other comparisons