| Mistral Small 4 | MiMo-V2.6-Flash | |
|---|---|---|
| Input, per 1M tokens | $0.15 | $0.14 |
| Output, per 1M tokens | $0.60 | $0.28 |
| Context window | 262K | 1.05M |
| Classification or routing (600 tokens in, 10 out), per 1,000 | $0.096 | $0.0868 |
| Chat reply (2,000 in, 400 out), per 1,000 | $0.54 | $0.392 |
| Retrieval-augmented answer (8,000 in, 500 out), per 1,000 | $1.50 | $1.26 |
| Confidence signal | no | no |
| Tool calling | yes | yes |
| BANKING77, correct of 400 | not measured | 326 |
Which one should carry your traffic?
If MiMo-V2.6-Flash answers your requests as well as Mistral Small 4, moving that traffic saves 27% on chat-shaped requests. Averages cannot tell you whether it does for your requests. MiMo-V2.6-Flash does not expose a confidence signal through OpenRouter, so Gimbix would test it as a full replacement rather than a first answer.
Mistral Small 4 profile · MiMo-V2.6-Flash profile · Measure it on your traffic