GPT-4o API Pricing

GPT-4o by OpenAI costs $2.50 per million input tokens and $10.00 per million output tokens.

Price verified from OpenAI's pricing page.

Rates and limits

Input / 1M
$2.50
Output / 1M
$10.00
Cached input / 1M
$1.25
Batch discount
50% off
Context window
128K tokens
Max output
16K tokens
Knowledge cutoff
October 2024
Released
May 2024

What GPT-4o costs per month

Token volume split 3:1 between input and output, with no prompt caching.

Tokens per monthInput / outputStandardBatch API
1M750K / 250K$4.38$2.19
10M7.5M / 2.5M$43.75$21.88
100M75M / 25M$437.50$218.75
Estimate your own workload with GPT-4o

Where to run GPT-4o

Prices above are OpenAI's direct rates. Cloud platforms can charge differently; the cloud platform view compares them.

Benchmarks reported by OpenAI

MMLU
88.7%
HumanEval
90.2%
GPQA
53.6%
AIME
13.4%
SWE-bench Verified
38.8%
MMMU
69.1%
HellaSwag
95.5%

GPT-4o pricing FAQ

How much does GPT-4o cost per million tokens?

GPT-4o costs $2.50 per million input tokens and $10.00 per million output tokens, as listed on OpenAI's pricing page on September 30, 2026.

How much does GPT-4o cost for 10 million tokens a month?

About $43.75 a month, assuming 7.5 million input and 2.5 million output tokens with no prompt caching, or $21.88 through the batch API.

What is the context window of GPT-4o?

GPT-4o accepts up to 128,000 tokens of context and returns up to 16,384 output tokens per request.

Does GPT-4o support prompt caching?

Yes. Cached input tokens cost $1.25 per million, 50% less than the standard input rate.

Is there a batch discount for GPT-4o?

Yes. Requests sent through the batch API cost 50% less: $1.25 per million input tokens and $5.00 per million output tokens.

Where can I use the GPT-4o API?

GPT-4o is available through OpenAI API, Azure OpenAI Service, Azure AI Foundry, and OpenRouter.

Compare with other models

Prices shown as input / output per million tokens. All model prices · Side-by-side comparison