OpenAI · released 2025-04
GPT-4.1
Long-context workhorse still on the menu.
context
1M
output max
32K
input /M
$2.00
output /M
$8.00
modalities
T·I
Verdict
What it's actually good at
Strengths
- +Huge context
- +Reliable tool use
- +Well-documented
Weaknesses
- −Superseded by GPT-5 for most tasks
Our scores
reasoning
8.0
coding
9.0
writing
8.0
speed
7.0
value
8.0
Previous-generation workhorse with a million-token context. Still a strong choice for codebases and document QA.
Pricing
Cost at common volumes
| Monthly volume | Input | Output | Est. monthly |
|---|---|---|---|
| Side project | 1M tok | 0.3M tok | $4.40 |
| Growing app | 50M tok | 15M tok | $220.00 |
| Production | 500M tok | 150M tok | $2200.00 |
| Scale | 5000M tok | 1500M tok | $22000.00 |
Estimates assume uncached input. Prompt caching and batch APIs can cut this by 50–90% for many workloads. Use the calculator →
Head-to-head