GPT-4.1 API Pricing

GPT-4.1 by OpenAI costs $2.00 per million input tokens and $8.00 per million output tokens.

Price verified from OpenAI's pricing page.

Rates and limits

Input / 1M
$2.00
Output / 1M
$8.00
Cached input / 1M
$0.50
Batch discount
50% off
Context window
1.05M tokens
Max output
32K tokens
Knowledge cutoff
October 2024
Released
April 2025

What GPT-4.1 costs per month

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

Tokens per monthInput / outputStandardBatch API
1M750K / 250K$3.50$1.75
10M7.5M / 2.5M$35.00$17.50
100M75M / 25M$350.00$175.00
Estimate your own workload with GPT-4.1

Where to run GPT-4.1

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

Benchmarks reported by OpenAI

MMLU
89%
HumanEval
92%
GPQA
60%
MMMU
75%

GPT-4.1 pricing FAQ

How much does GPT-4.1 cost per million tokens?

GPT-4.1 costs $2.00 per million input tokens and $8.00 per million output tokens, as listed on OpenAI's pricing page on September 30, 2026.

How much does GPT-4.1 cost for 10 million tokens a month?

About $35.00 a month, assuming 7.5 million input and 2.5 million output tokens with no prompt caching, or $17.50 through the batch API.

What is the context window of GPT-4.1?

GPT-4.1 accepts up to 1,047,576 tokens of context and returns up to 32,000 output tokens per request.

Does GPT-4.1 support prompt caching?

Yes. Cached input tokens cost $0.50 per million, 75% less than the standard input rate.

Is there a batch discount for GPT-4.1?

Yes. Requests sent through the batch API cost 50% less: $1.00 per million input tokens and $4.00 per million output tokens.

Where can I use the GPT-4.1 API?

GPT-4.1 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