GPT-4o API pricing

OpenAI charges $2.5 per million input tokens and $10 per million output tokens for GPT-4o (gpt-4o), and $1.25 per million cached input tokens. A typical request of 1,000 input and 500 output tokens costs $0.0075, or $0.00375 through the batch API.

Prices updated November 14, 2026
Input / 1M tokens
$2.5
Output / 1M tokens
$10
Cached input / 1M tokens
$1.25
Typical request
$0.0075
Calculate the cost of your prompt →

GPT-4o price per million tokens

Token typeStandardBatch API
Input$2.5$1.25
Cached input$1.25–
Output$10$5

API model id: gpt-4o. GPT-4o supports a 128K-token context window, up to 16.4K output tokens, image input and tool calling.

What GPT-4o costs per request

Request1 request1,000 requests1M requests
Short chat message (300 in, 200 out)$0.00275$2.75$2,750.00
Typical request (1K in, 500 out)$0.0075$7.50$7,500.00
Long document summary (20K in, 1K out)$0.06$60.00$60,000.00
Coding agent step (50K in, 2K out)$0.15$145.00$145,000.00

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

How GPT-4o compares

GPT-4o price history

GPT-4o has cost $2.5 per million input tokens and $10 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
GPT-6 SolOpenAI$2$0.2$10$0.007
GPT-6.1 SolOpenAI$2$0.1$10$0.007
Claude Sonnet 5Anthropic$2$0.2$10$0.007
Claude Sonnet 5.5Anthropic$2$0.1$10$0.007
Gemini 4 ArgonGoogle Gemini$2$0.1$10$0.007
Gemini 4 CarbonGoogle Gemini$2$0.1$10$0.007
GPT-5.6 TerraOpenAI$2$0.2$12$0.008
Gemini 3.1 Pro PreviewGoogle Gemini$2$0.2$12$0.008

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-4o API cost?

OpenAI charges $2.5 per million input tokens and $10 per million output tokens for GPT-4o (gpt-4o), and $1.25 per million cached input tokens. A typical request of 1,000 input and 500 output tokens costs $0.0075, or $0.00375 through the batch API.

Has the GPT-4o API price changed?

No. GPT-4o has cost $2.5 per million input tokens and $10 per million output tokens since apicost.app started tracking prices on October 22, 2026.

Is there a cheaper way to use GPT-4o?

Yes. The OpenAI batch API runs requests within 24 hours for $1.25 per million input tokens and $5 per million output tokens. Prompt caching lowers the price of repeated input to $1.25 per million tokens.

What is the context window of GPT-4o?

GPT-4o accepts up to 128,000 input tokens, roughly 96,000 words of English, and writes up to 16,384 output tokens per response. Filling the whole context window once costs $0.32 in input tokens.

Is GPT-4o cheaper than Claude Sonnet 5?

They cost about the same. Claude Sonnet 5 from Anthropic costs $2 input and $10 output per million tokens, so a typical request is $0.007: about the same price as GPT-4o.

Source: OpenAI pricing, via the LiteLLM price list.