All OpenAI models

GPT-4.1

OpenAI · released April 2025

GPT-4.1 is a OpenAI model with a 1.05M token context window — about 1,500 pages of text. It reads Images, Text, and Files and replies in Text.

$2.30

input / 1M tokens

$9.20

output / 1M tokens

1.05M

context — about 1,500 pages

1.9¢

a client proposal

Pricing

Input
$2.30 per million tokens
Output
$9.20 per million tokens
Cached input
$0.575 per million tokens
Web search
1.1¢ per search

Billed from your Alyph wallet. Prices can change when the provider changes theirs — last checked August 9, 2026.

The numbers

Provider
OpenAI
Released
April 2025 (2025-04-14)
Context window
1.05M tokens — about 1,500 pages
Max output
33K tokens per reply
Input
Images, Text, and Files
Output
Text
Reasoning
Answers directly
Knowledge cutoff
2024-06-30

Cost vs Token Amount

Drag the slider to adjust the split between input and output workload.

80% Input20% Output
free$1.84$3.680 tokens250k500k750k1000k
GPT-4.1

Adjust the ratio slider to change how output tokens influence the final price for equivalent workloads.

What a task costs

2K tokens in · 500 tokens out.

GPT-4.1

OpenAI

0.92¢

for this task

50% input · 50% output

Full pricing →

Your $5 welcome credit covers about 543 of these.

Compare GPT-4.1

Closest in price on a typical task:

GPT-4.1 vs Jamba Large 1.7 →GPT-4.1 vs o3 →GPT-4.1 vs Sonar Deep Research →GPT-4.1 vs Sonar Reasoning Pro →Any other combination →

Questions, answered

How much does GPT-4.1 cost on Alyph?

GPT-4.1 costs $2.30 per million input tokens and $9.20 per million output tokens on Alyph. A typical task — 5K tokens in, 800 out — works out to about 1.9¢. Billed from your Alyph wallet, with hard spending limits. Prices can change when the provider changes theirs; this page was last checked on August 9, 2026.

What is GPT-4.1's context window?

1.05M tokens — about 1,500 pages. Replies can be up to 33K tokens long.

Can GPT-4.1 read images and files?

GPT-4.1 reads Images, Text, and Files. Drop a file onto the canvas and it becomes part of the context — the only limit is the context window.

Does GPT-4.1 show its reasoning?

No — GPT-4.1 answers directly, without a visible thinking pass.

Test GPT-4.1 against Jamba Large 1.7

One prompt, both models at the same time, the better answer wins. Free to start, with $5 of credit.

Sign up free Try the demo