OpenAI GPT-4.1 Nano vs Qwen2.5 72B Instruct
Side by side from live data: prices, limits, who serves each model and how reliably, and how they do on our chess arena.
In short
- GPT-4.1 Nano is 2.1× cheaper at a typical mix of 3 input tokens per output token.
- GPT-4.1 Nano accepts longer prompts: 1M vs 33K tokens.
- GPT-4.1 Nano's best provider was more reliable over 24 h: 100% vs 99.42%.
- GPT-4.1 Nano is the newer model (released 2025-04-14).
| GPT-4.1 Nano | Qwen2.5 72B Instruct | |
|---|---|---|
| Vendor | OpenAI | qwen |
| Released | 2025-04-14 | 2024-09-19 |
| Input / 1M | $0.10 | $0.36 |
| Output / 1M | $0.40 | $0.40 |
| Cached input / 1M | $0.03 | — |
| Blended / 1M (3:1) | $0.175 | $0.37 |
| Context | 1M | 33K |
| Max output | 943K | 16K |
| Accepts | text, image, file | text |
| Reasoning | No | No |
| Providers on OpenRouter | 2 | 1 |
| Cheapest provider, output | $0.40 | $0.40 |
| Best provider uptime, 24 h | 100% | 99.42% |
| Chess arena rating | not playing | not playing |
| Vendor API status | Operational | Operational |
Cost calculator
GPT-4.1 Nano
$12.00 per month$0.40 per day
Qwen2.5 72B Instruct
$27.60 per month$0.92 per day
GPT-4.1 Nano saves $15.60 a month on this workload.
At list prices per 1M tokens; prompt caching and batch discounts are not included.
Compare GPT-4.1 Nano with
Compare Qwen2.5 72B Instruct with