GPT-4.1
OpenAIProprietaryNon-reasoningVerifiedReleased Apr 14, 2025Input: image, text, file
Overall score
37.6
Rank 151 of 222 · 21.7–53.5
Context window
1M
1,000,000 tokens
Price per 1M tokens
$2.00 in · $8.00 out
✓ Verified on OpenAI's pricing page
Blended price
$3.50
3:1 input:output tokens
Output speed
—
Not measured yet
Category scores
Scores per capability area with the model's rank among ranked models in that category.
- 1Reasoning71.9
- 2Multilingual#1461.5
- 3Knowledge55.5
- 4Multimodal54.7
- 5Instruction following#9250.3
- 6Coding34.8
- 7Math27.0
Benchmark results (8)
As reported in system cards, papers and public evaluations. Position compares this model with every other model reporting the same benchmark.
Knowledge
| GPQA | 66.3 | #83 of 117 |
| MMLU | 90.2 | #5 of 28 |
Agentic & tool use
| Gert Labs | 25.65 | #52 of 52 |
Coding
| SWE-bench Verified | 54.6 | #79 of 98 |
Multimodal
| Design Arena Website | 1040 | #83 of 91 |
Multilingual
| MMLU-ProX | 72.7 | #13 of 16 |
Instruction following
| IFEval | 87.4 | #28 of 53 |
Math
| FrontierMath v2 (Tiers 1-3) | 5.965 | #63 of 64 |
Pricing by source
USD per 1M tokens.
| Source | Input | Output | Cached in |
|---|---|---|---|
| ✓ Official (OpenAI) checked Oct 17, 2026 · gpt-4.1 | $2.00 | $8.00 | $0.50 |
| BenchLM list price | $2.00 | $8.00 | $0.50 |
| OpenRouter openai/gpt-4.1 | $2.00 | $8.00 | $0.50 |
Standard tier, prompts under 272K tokens.
OpenAI's GPT-4.1 model page lists $2.00 input / $8.00 output per million tokens.
Arena ratings
Human-preference ratings from LMArena. Best-rated variant shown.
| Vision(2025-04-14) | 1210 | #88 · 41K votes |
Speed
Measured by us through OpenRouter (median of trials).
Not measured yet.
Related models
Same family
- GPT-4.1 mini29.2
- GPT-4.1 nano24.5
Similar score
- LFM2.5-24B-A2B37.7 · $0.33
- GPT-5 nano37.3 · $0.14
- GPT-OSS 120B37.3 · $0.26
- Claude 4 Sonnet38.1 · $6.00
- o138.3 · $26.25