Host Relace cut MiMo-V2.6-Flash input and cache-read pricing by 50%
Published 30 September 2026
Price move, per 1M tokens
- Relace · input↓ 50%$0.080 → $0.040
- Relace · outputunchanged$1.28 → $1.28
- Relace · cache read↓ 50%$0.080 → $0.040
| host | rate | was | now | change |
|---|---|---|---|---|
| Relace | input | $0.080 | $0.040 | ↓ 50% |
| Relace | output | $1.28 | $1.28 | — |
| Relace | cache read | $0.080 | $0.040 | ↓ 50% |
input and cache read: ↓ 50%
If you buy
This cut makes the model easier to run on long prompts and repeated context, so re-check your cache-hit assumptions and whether your workload now fits a lighter budget.
The model
MiMo-V2.6-Flashopen the model →
Proprietary1049K context9 hosts
intelligence46th of 168 writing72nd of 168 coding17th of 168
MiMo-V2.6-Flash is a hosted-only model from Xiaomi, so using it means choosing a host rather than running it yourself. Its measured results are uneven: it places 17th of 168 on Arena Coding as of 25 Sep 2026, but 72nd of 168 on Arena Creative Writing on the same date.
Source
Read on openrouter.ai · we published this on 30 September 2026.
read the original at openrouter.ai ↗