Mistral Large 4 vs GPT-6.1 Sol
Mistral Large 4 is 1.9× cheaper for typical traffic ; GPT-6.1 Sol scores higher on the Artificial Analysis intelligence index (51.8 vs 38.4).
Prices checked Oct 21, 2026
| Mistral Large 4 | GPT-6.1 Sol | |
|---|---|---|
| Developer | Mistral AI | OpenAI |
| Input / 1M tokens | $1.36 | $2.00 |
| Output / 1M tokens | $4.18 | $10.00 |
| Cached input / 1M | $0.14 | $0.10 |
| Context window | 1.05M | 1.05M |
| Max output | 262K | 128K |
| Intelligence index | 38.4 | 51.8 |
| Image input | Yes | Yes |
| Tool calling | Yes | Yes |
| Reasoning mode | Yes | Yes |
| Open weights | No | No |
Monthly cost for common workloads
| Workload | Mistral Large 4 | GPT-6.1 Sol |
|---|---|---|
| Customer chatbot 1,000 conversations a day, 8 turns each | $577 | $1,150 |
| Document Q&A (RAG) 500 questions a day over retrieved documents | $143 | $238 |
| Coding / tool-using agent 200 tasks a day, long tool-heavy contexts | $261 | $447 |
| Content generation 30 long articles a day | $13.08 | $27.90 |
| Classification / extraction 100,000 short items a day | $1,412 | $2,250 |
Estimates include cached-input discounts where a model offers them. Try your own numbers in the cost calculator.
Which one to choose
- Lowest cost: Mistral Large 4 — 1.9× cheaper on a 3:1 input/output mix.
- Longer documents: GPT-6.1 Sol reads up to 1.05M tokens at once.