ColinBuilds.com · Current official OpenAI API pricing
GPT-4.1
- Input / 1M
- $2.00
- Output / 1M
- $8.00
- OpenAI-published context window
- 1,047,576 tokens
GPT-4.1 / gpt-4.1; OpenAI pricing row lists standard pricing at $2 input, $0.50 cached input, and $8 output per 1M tokens · as of July 9, 2026
Compare models
Same per-1M input/output rates as above. Enter your monthly token volumes to compare bills.
GPT-4.1
- Input: 1M × $2.00 = $2.00
- Output: 1M × $8.00 = $8.00
- Total
- $10.00
GPT-4o
- Input: 1M × $2.50 = $2.50
- Output: 1M × $10.00 = $10.00
- Total
- $12.50
Difference
$2.50
GPT-4o costs $2.50 more than GPT-4.1.
Popular comparisons
30 total featuring GPT-4.1.
GPT-4.1 is OpenAI’s current non-reasoning GPT-4.1 API model for instruction-following, tool calling, and long-context text or image-input work.
What this model is
OpenAI’s model page lists GPT-4.1 as the smartest non-reasoning model and identifies the model alias as gpt-4.1. The same page lists the snapshot gpt-4.1-2025-04-14.
GPT-4.1 should not be confused with GPT-4o. OpenAI’s pricing page lists separate rows for gpt-4.1, gpt-4o, and gpt-4o-2024-05-13, with different prices.
Pricing notes
The calculator on this page uses OpenAI’s official standard pricing row for gpt-4.1: $2.00 per 1M input tokens and $8.00 per 1M output tokens.
OpenAI’s pricing row also lists cached input at $0.50 per 1M tokens for gpt-4.1. The top-level calculator fields here use the standard input and output rates, not the cached-input, Batch, Flex, or Priority rates.
Benchmarks and specs
OpenAI’s model page lists GPT-4.1 with a 1,047,576-token context window, a 32,768-token maximum output, and a June 01, 2024 knowledge cutoff. It lists text and image as inputs and text as output.
No benchmark score is shown until an exact benchmark source and model identity are matched to GPT-4.1.
Best fit
GPT-4.1 is best for API tasks that need strong instruction following, reliable tool calling, broad domain knowledge, image input, and a very large context window without using a reasoning model.
For complex tasks where OpenAI recommends a newer reasoning or flagship route, compare GPT-4.1 against the current GPT-5 family rather than treating it as the default top model.