Kimi K2.6 vs Mistral Small 4
Price, context window & benchmark comparison
VS
Compare different models
Verdict: Mistral Small 4 is 6.5× cheaper than Kimi K2.6 on a typical 3:1 input/output mix. Kimi K2.6 scores higher on the Artificial Analysis Intelligence Index (27 vs 11.3).
| Kimi K2.6 | Mistral Small 4 | |
|---|---|---|
| Input price / 1M | $0.95 | $0.15 |
| Output price / 1M | $4.00 | $0.60 |
| Blended price (3:1) | $1.71 | $0.26 |
| Cached input / 1M | $0.16 | $0.015 |
| Context window | 262K | 262K |
| Max output | 236K | 210K |
| Intelligence index | 27 | 11.3 |
| Coding index | 61.8 | 26.6 |
| Providers | 22 | 3 |
| Best provider uptime (30m) | 100.0% | 100.0% |
| Vision input | Yes | Yes |
| Reasoning | Yes | Yes |
| Tool calling | Yes | Yes |
| Released | 2026-04-20 | 2026-03-16 |
| Retirement | — | — |
Cost calculator
FAQ
Which is cheaper, Kimi K2.6 or Mistral Small 4?
Mistral Small 4 is 6.5× cheaper than Kimi K2.6 on a typical 3:1 input/output mix.
Kimi K2.6 vs Mistral Small 4: which has a bigger context window?
Kimi K2.6: 262,144 tokens. Mistral Small 4: 262,144 tokens.
How much would 1 million requests cost?
At 2,000 input + 500 output tokens per request: Kimi K2.6 ≈ $3,900, Mistral Small 4 ≈ $600.00.
More comparisons
Kimi K2.6 vs GLM 5.3 PrimeKimi K2.6 vs Qwen3.8 Max PrimeKimi K2.6 vs Command A+Kimi K2.6 vs GPT-6 Luna ProKimi K2.6 vs GPT-6 LunaKimi K2.6 vs GPT-6 Sol ProKimi K2.6 vs GPT-6 SolKimi K2.6 vs Claude Opus 5.5Kimi K2.6 vs MiMo-V2.6-Pro-UltraSpeedKimi K2.6 vs MiMo-V2.6-FlashKimi K2.6 vs Grok 4.7Kimi K2.6 vs Qwen3.8 Omni FlashKimi K2.6 vs GLM 5.3 FlashXKimi K2.6 vs DeepSeek V4.1 FlashKimi K2.6 vs GPT-6 AstraKimi K2.6 vs GPT-6 Astra ProMistral 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 5.5