Cohere Command A vs OpenAI GPT-4.1
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 is 1.3× cheaper at a typical mix of 3 input tokens per output token.
- GPT-4.1 accepts longer prompts: 1M vs 256K tokens.
- GPT-4.1 is the newer model (released 2025-04-14).
| Command A | GPT-4.1 | |
|---|---|---|
| Vendor | Cohere | OpenAI |
| Released | 2025-03-13 | 2025-04-14 |
| Input / 1M | $2.50 | $2.00 |
| Output / 1M | $10.00 | $8.00 |
| Cached input / 1M | — | $0.50 |
| Blended / 1M (3:1) | $4.38 | $3.50 |
| Context | 256K | 1M |
| Max output | 8K | 33K |
| Accepts | text | text, image, file |
| Reasoning | No | No |
| Providers on OpenRouter | 1 | 3 |
| Cheapest provider, output | $10.00 | $8.00 |
| Best provider uptime, 24 h | 100% | 100% |
| Chess arena rating | not playing | not playing |
| Vendor API status | Operational | Operational |
Cost calculator
Command A
$300 per month$10.00 per day
GPT-4.1
$240 per month$8.00 per day
GPT-4.1 saves $60.00 a month on this workload.
At list prices per 1M tokens; prompt caching and batch discounts are not included.
Compare Command A with