| Claude Haiku 4.5 | MiMo-V2.6-Flash | |
|---|---|---|
| Input, per 1M tokens | $1.00 | $0.14 |
| Output, per 1M tokens | $5.00 | $0.28 |
| Context window | 200K | 1.05M |
| Classification or routing (600 tokens in, 10 out), per 1,000 | $0.65 | $0.0868 |
| Chat reply (2,000 in, 400 out), per 1,000 | $4.00 | $0.392 |
| Retrieval-augmented answer (8,000 in, 500 out), per 1,000 | $10.50 | $1.26 |
| Confidence signal | no | no |
| Tool calling | yes | yes |
| BANKING77, correct of 400 | 301 | 326 |
Which one should carry your traffic?
If MiMo-V2.6-Flash answers your requests as well as Claude Haiku 4.5, moving that traffic saves 90% 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.
Claude Haiku 4.5 profile · MiMo-V2.6-Flash profile · Measure it on your traffic