GPT-5 nano API pricing

OpenAI charges $0.05 per million input tokens and $0.4 per million output tokens for GPT-5 nano (gpt-5-nano), and $0.005 per million cached input tokens. A typical request of 1,000 input and 500 output tokens costs $0.00025, or $0.000125 through the batch API.

Prices updated November 14, 2026
Input / 1M tokens
$0.05
Output / 1M tokens
$0.4
Cached input / 1M tokens
$0.005
Typical request
$0.00025
Calculate the cost of your prompt →

GPT-5 nano price per million tokens

Token typeStandardBatch API
Input$0.05$0.025
Cached input$0.005$0.0025
Output$0.4$0.2

API model id: gpt-5-nano. GPT-5 nano supports a 272K-token context window, up to 128K output tokens, image input, tool calling and reasoning.

What GPT-5 nano costs per request

Request1 request1,000 requests1M requests
Short chat message (300 in, 200 out)$0.000095$0.095$95.00
Typical request (1K in, 500 out)$0.00025$0.25$250.00
Long document summary (20K in, 1K out)$0.0014$1.40$1,400.00
Coding agent step (50K in, 2K out)$0.0033$3.30$3,300.00

At standard rates. A token is about 4 characters of English text, so 1,000 tokens is roughly 750 words.

How GPT-5 nano compares

GPT-5 nano price history

GPT-5 nano has cost $0.05 per million input tokens and $0.4 per million output tokens since apicost.app started tracking prices on October 22, 2026.

Every LLM API price increase, cut, new and retired model, dated: LLM API price changes.

Models with a similar price

ModelProviderInput / 1MCached input / 1MOutput / 1MTypical request
Ministral 3 8B 2512Mistral$0.15$0.015$0.15$0.000225
Ministral 8B 2512Mistral$0.15$0.015$0.15$0.000225
Mistral SmallMistral$0.1$0.01$0.3$0.00025
DeepSeek CoderDeepSeek$0.14$0.014$0.28$0.00028
Gemini 2.5 Flash LiteGoogle Gemini$0.1$0.01$0.4$0.0003
Ministral 3 14B 2512Mistral$0.2$0.02$0.2$0.0003
Ministral 14B 2512Mistral$0.2$0.02$0.2$0.0003
GPT-6 LunaOpenAI$0.1$0.01$0.5$0.00035

Other OpenAI models

Every OpenAI model side by side, with batch, caching and long-context prices: OpenAI API pricing. Ways to pay less: batch API, prompt caching, the cheapest models.

Questions and answers

How much does the GPT-5 nano API cost?

OpenAI charges $0.05 per million input tokens and $0.4 per million output tokens for GPT-5 nano (gpt-5-nano), and $0.005 per million cached input tokens. A typical request of 1,000 input and 500 output tokens costs $0.00025, or $0.000125 through the batch API.

Has the GPT-5 nano API price changed?

No. GPT-5 nano has cost $0.05 per million input tokens and $0.4 per million output tokens since apicost.app started tracking prices on October 22, 2026.

Is there a cheaper way to use GPT-5 nano?

Yes. The OpenAI batch API runs requests within 24 hours for $0.025 per million input tokens and $0.2 per million output tokens. Prompt caching lowers the price of repeated input to $0.005 per million tokens.

What is the context window of GPT-5 nano?

GPT-5 nano accepts up to 272,000 input tokens, roughly 204,000 words of English, and writes up to 128,000 output tokens per response. Filling the whole context window once costs $0.0136 in input tokens.

Is GPT-5 nano cheaper than Claude Haiku 5.5?

Yes. Claude Haiku 5.5 from Anthropic costs $0.1 input and $0.5 output per million tokens, so a typical request is $0.00035: 1.4× the price of GPT-5 nano.

Source: OpenAI pricing, via the LiteLLM price list.