GPT-4.1 nano
OpenAIProprietaryNon-reasoningProvisionalReleased Apr 14, 2025Input: image, text, file
Overall score
24.5
Rank 207 of 222 · 10.1–38.8
Context window
1M
1,000,000 tokens
Price per 1M tokens
$0.10 in · $0.40 out
Source: BenchLM
Blended price
$0.17
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.
- 1Knowledge40.8
- 2Reasoning38.9
- 3Instruction following#12436.0
- 4Multimodal29.8
Benchmark results (4)
As reported in system cards, papers and public evaluations. Position compares this model with every other model reporting the same benchmark.
Knowledge
| GPQA | 50.3 | #101 of 117 |
| MMLU | 80.1 | #21 of 28 |
Multimodal
| Design Arena Website | 974 | #86 of 91 |
Instruction following
| IFEval | 83.2 | #37 of 53 |
Pricing by source
USD per 1M tokens.
| Source | Input | Output | Cached in |
|---|---|---|---|
| List price (BenchLM) | $0.10 | $0.40 | — |
| OpenRouter openai/gpt-4.1-nano | $0.10 | $0.40 | $0.025 |
OpenAI's GPT-4.1 nano model page lists $0.10 input / $0.40 output per million tokens.
Arena ratings
Human-preference ratings from LMArena. Best-rated variant shown.
| Vision(2025-04-14) | 1063 | #139 · 1.2K votes |
Speed
Measured by us through OpenRouter (median of trials).
Not measured yet.
Related models
Same family
- GPT-4.137.6
- GPT-4.1 mini29.2
Similar score
- Ministral 3 14B24.9 · $0.20
- Phi-425.0 · $0.087
- Nemotron 3.5 Lightning 30B A3B NVFP425.7 · —
- Qwen2.5 Coder 32B Instruct26.6 · $0.74
- GPT-4o mini26.8 · $0.26