GPT-5 mini API pricing

OpenAI charges $0.25 per million input tokens and $2 per million output tokens for GPT-5 mini (gpt-5-mini), and $0.025 per million cached input tokens. A typical request of 1,000 input and 500 output tokens costs $0.00125, or $0.000625 through the batch API.

Prices updated November 14, 2026
Input / 1M tokens
$0.25
Output / 1M tokens
$2
Cached input / 1M tokens
$0.025
Typical request
$0.00125
Calculate the cost of your prompt →

GPT-5 mini price per million tokens

Token typeStandardBatch API
Input$0.25$0.125
Cached input$0.025$0.0125
Output$2$1

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

What GPT-5 mini costs per request

Request1 request1,000 requests1M requests
Short chat message (300 in, 200 out)$0.000475$0.48$475.00
Typical request (1K in, 500 out)$0.00125$1.25$1,250.00
Long document summary (20K in, 1K out)$0.007$7.00$7,000.00
Coding agent step (50K in, 2K out)$0.0165$16.50$16,500.00

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

How GPT-5 mini compares

GPT-5 mini price history

GPT-5 mini has cost $0.25 per million input tokens and $2 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
DeepSeek V4 1 Flash 1017Mistral$0.3$0.007$1.2$0.0009
Gemini 3.1 Flash LiteGoogle Gemini$0.25$0.025$1.5$0.001
GPT-4.1 miniOpenAI$0.4$0.1$1.6$0.0012
Mistral Large 3Mistral$0.5$0.05$1.5$0.00125
Mistral Large 2512Mistral$0.5$0.05$1.5$0.00125
Gemini 2.5 FlashGoogle Gemini$0.3$0.03$2.5$0.00155
Gemini 3.5 Flash LiteGoogle Gemini$0.3$0.03$2.5$0.00155
DeepSeek R1DeepSeek$0.55$0.14$2.19$0.00164

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 mini API cost?

OpenAI charges $0.25 per million input tokens and $2 per million output tokens for GPT-5 mini (gpt-5-mini), and $0.025 per million cached input tokens. A typical request of 1,000 input and 500 output tokens costs $0.00125, or $0.000625 through the batch API.

Has the GPT-5 mini API price changed?

No. GPT-5 mini has cost $0.25 per million input tokens and $2 per million output tokens since apicost.app started tracking prices on October 22, 2026.

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

Yes. The OpenAI batch API runs requests within 24 hours for $0.125 per million input tokens and $1 per million output tokens. Prompt caching lowers the price of repeated input to $0.025 per million tokens.

What is the context window of GPT-5 mini?

GPT-5 mini 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 $0.068 in input tokens.

Is GPT-5 mini cheaper than Claude Haiku 4.5?

Yes. Claude Haiku 4.5 from Anthropic costs $1 input and $5 output per million tokens, so a typical request is $0.0035: 2.8× the price of GPT-5 mini.

Source: OpenAI pricing, via the LiteLLM price list.