token.app › Compare › GPT-4.1 Nano vs Phi 4
GPT-4.1 Nano vs Phi 4
GPT-4.1 Nano and Phi 4 split the 2 shared benchmarks evenly. Phi 4 is 2.0× cheaper per token on a blended 3:1 basis. GPT-4.1 Nano accepts the larger context window (1.0M).
Head to head
Blended price uses a 3:1 input:output mix
| GPT-4.1 Nano | Phi 4 | |
|---|---|---|
| Provider | OpenAI | Microsoft |
| Input $/1M | $0.100 | $0.070 |
| Output $/1M | $0.400 | $0.140 |
| Blended $/1M | $0.175 | $0.088 |
| Context window | 1.0M | 16K |
| Max output | 33K | 16K |
| Released | Apr 2025 | Jan 2025 |
| Licence | Proprietary | Open weights |
| GPQA Diamond | 48.9% | 56.1% |
| OTIS Mock AIME | 28.9% | 13.8% |
Benchmark scores independently run and published by Epoch AI, 'AI Benchmarking Hub', used under CC BY 4.0. Only benchmarks with a score for BOTH models are compared.
Choose GPT-4.1 Nano if…
- Higher OTIS Mock AIME (28.9% vs 13.8%)
- Larger context window (1.0M)
- Newer model (released Apr 2025)
Choose Phi 4 if…
- Costs less per token — $0.088 vs $0.175 blended
- Higher GPQA Diamond (56.1% vs 48.9%)
- Open weights — self-hostable
FAQ
Which is better, GPT-4.1 Nano or Phi 4?
Across the 2 benchmarks both models have independently-run scores for, GPT-4.1 Nano leads on 1 and Phi 4 leads on 1. Benchmarks are one input — price and context window are on this page too.
Is GPT-4.1 Nano cheaper than Phi 4?
Phi 4 is cheaper: $0.088 versus $0.175 per million tokens blended at 3:1 input:output. Input alone: $0.100 vs $0.070. Output alone: $0.400 vs $0.140.
What context windows do GPT-4.1 Nano and Phi 4 have?
GPT-4.1 Nano: 1,047,576 tokens. Phi 4: 16,384 tokens.
Who makes GPT-4.1 Nano and Phi 4?
GPT-4.1 Nano is made by OpenAI. Phi 4 is made by Microsoft.