Mistral Small 4 vs Qwen3.5 397B A17B
Price, context window & benchmark comparison
VS
Compare different models
Verdict: Mistral Small 4 is 4.9× cheaper than Qwen3.5 397B A17B on a typical 3:1 input/output mix. Qwen3.5 397B A17B scores higher on the Artificial Analysis Intelligence Index (18.4 vs 11.3).
| Mistral Small 4 | Qwen3.5 397B A17B | |
|---|---|---|
| Input price / 1M | $0.15 | $0.55 |
| Output price / 1M | $0.60 | $3.50 |
| Blended price (3:1) | $0.26 | $1.29 |
| Cached input / 1M | $0.015 | $0.23 |
| Context window | 262K | 262K |
| Max output | 210K | 236K |
| Intelligence index | 11.3 | 18.4 |
| Coding index | 26.6 | 48.2 |
| Providers | 3 | — |
| Best provider uptime (30m) | 100.0% | — |
| Vision input | Yes | Yes |
| Reasoning | Yes | Yes |
| Tool calling | Yes | Yes |
| Released | 2026-03-16 | 2026-02-16 |
| Retirement | — | — |
Cost calculator
FAQ
Which is cheaper, Mistral Small 4 or Qwen3.5 397B A17B?
Mistral Small 4 is 4.9× cheaper than Qwen3.5 397B A17B on a typical 3:1 input/output mix.
Mistral Small 4 vs Qwen3.5 397B A17B: which has a bigger context window?
Mistral Small 4: 262,144 tokens. Qwen3.5 397B A17B: 262,144 tokens.
How much would 1 million requests cost?
At 2,000 input + 500 output tokens per request: Mistral Small 4 ≈ $600.00, Qwen3.5 397B A17B ≈ $2,850.
More comparisons
Mistral Small 4 vs GLM 5.3 PrimeMistral Small 4 vs Qwen3.8 Max PrimeMistral Small 4 vs Command A+Mistral Small 4 vs GPT-6 Luna ProMistral Small 4 vs GPT-6 LunaMistral Small 4 vs GPT-6 Sol ProMistral Small 4 vs GPT-6 SolMistral Small 4 vs Claude Opus 5.5Mistral Small 4 vs MiMo-V2.6-Pro-UltraSpeedMistral Small 4 vs MiMo-V2.6-FlashMistral Small 4 vs Grok 4.7Mistral Small 4 vs Qwen3.8 Omni FlashMistral Small 4 vs GLM 5.3 FlashXMistral Small 4 vs DeepSeek V4.1 FlashMistral Small 4 vs GPT-6 AstraMistral Small 4 vs GPT-6 Astra ProQwen3.5 397B A17B vs GLM 5.3 PrimeQwen3.5 397B A17B vs Qwen3.8 Max PrimeQwen3.5 397B A17B vs Command A+Qwen3.5 397B A17B vs GPT-6 Luna ProQwen3.5 397B A17B vs GPT-6 LunaQwen3.5 397B A17B vs GPT-6 Sol ProQwen3.5 397B A17B vs GPT-6 SolQwen3.5 397B A17B vs Claude Opus 5.5