Mistral vs Qwen: the short answer
Qwen has the cheapest API option (Qwen3 235B A22B Instruct 2507 at $0.00/M input). Full benchmark, pricing, and capability breakdown below.
Benchmarks: Mistral vs Qwen at their best
Each bar is the best score any Mistral or Qwen model achieves on that benchmark. Only benchmarks where both brands have a score are shown.
🧠 Intelligence & Knowledge
💻 Coding
🔢 Math
📝 Instruction Following
Model releases over time
Every Mistral and Qwen model with a known release date, on one timeline — the release cadence of each brand at a glance.
Model Release Timeline
24 releasesHow Mistral and Qwen have trended
The best score each brand's frontier model reaches over time. Higher is better — this is the aggregate "Mistral vs Qwen as brands" view.
Pricing & Models
| Model | Input /M | Output /M | Context | Coding |
|---|---|---|---|---|
| Mistral Large 4 | $0.70 | $2.10 | 1049K | — |
| Mistral Medium 3.5 | $1.50 | $7.50 | 262K | — |
| Mistral Small 2603 | $0.15 | $0.60 | 262K | — |
| Mistral Small Creative | $0.10 | $0.30 | 33K | — |
| Devstral 2 2512 | $0.40 | $0.90 | 262K | — |
| Ministral 3 14B 2512 | $0.20 | $0.20 | 262K | — |
| Ministral 3 8B 2512 | $0.15 | $0.15 | 262K | — |
| Ministral 3 3B 2512 | $0.10 | $0.10 | 131K | — |
| Model | Input /M | Output /M | Context | Coding |
|---|---|---|---|---|
| Qwen3.8 Flash | $0.15 | $0.47 | 1000K | — |
| Qwen3.8 27B | $0.04 | $0.90 | 1000K | — |
| Qwen3.8 2.4T-A95B | $0.90 | $0.90 | 1010K | — |
| Qwen3.8 Max | $2.00 | $6.00 | 1000K | — |
| Qwen3.7 Flash | $0.03 | $0.13 | 1000K | — |
| Qwen3.7 Plus | $0.32 | $1.28 | 1000K | — |
| Qwen3.7 Max | $1.48 | $4.42 | 1000K | — |
| Qwen3.6 Flash | $0.19 | $1.13 | 1000K | — |
Prices are per 1M tokens, lowest available across API providers. Showing the 8 most recent models per brand.