token.app › Compare › GPT-4.1 Nano vs Claude Sonnet 5
GPT-4.1 Nano vs Claude Sonnet 5
Claude Sonnet 5 leads on 2 of 2 shared benchmarks. GPT-4.1 Nano is 23× 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 | Claude Sonnet 5 | |
|---|---|---|
| Provider | OpenAI | Anthropic |
| Input $/1M | $0.100 | $2.00 |
| Output $/1M | $0.400 | $10.00 |
| Blended $/1M | $0.175 | $4.00 |
| Context window | 1.0M | 1M |
| Max output | 33K | 128K |
| Released | Apr 2025 | Jun 2026 |
| Licence | Proprietary | Proprietary |
| GPQA Diamond | 48.9% | 90.5% |
| OTIS Mock AIME | 28.9% | 94.7% |
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…
- Costs less per token — $0.175 vs $4.00 blended
- Larger context window (1.0M)
Choose Claude Sonnet 5 if…
- Higher GPQA Diamond (90.5% vs 48.9%)
- Higher OTIS Mock AIME (94.7% vs 28.9%)
- Newer model (released Jun 2026)
FAQ
Which is better, GPT-4.1 Nano or Claude Sonnet 5?
Across the 2 benchmarks both models have independently-run scores for, GPT-4.1 Nano leads on 0 and Claude Sonnet 5 leads on 2. Benchmarks are one input — price and context window are on this page too.
Is GPT-4.1 Nano cheaper than Claude Sonnet 5?
GPT-4.1 Nano is cheaper: $0.175 versus $4.00 per million tokens blended at 3:1 input:output. Input alone: $0.100 vs $2.00. Output alone: $0.400 vs $10.00.
What context windows do GPT-4.1 Nano and Claude Sonnet 5 have?
GPT-4.1 Nano: 1,047,576 tokens. Claude Sonnet 5: 1,000,000 tokens.
Who makes GPT-4.1 Nano and Claude Sonnet 5?
GPT-4.1 Nano is made by OpenAI. Claude Sonnet 5 is made by Anthropic.