MiMo-V2.6-Flash repriced across 2 hosts: Relace output up 814%, DeepInfra through OpenRouter cache read down 4%
Published 28 September 2026
Price move, per 1M tokens
- Relace · input↑ 71%$0.070 → $0.120
- Relace · output↑ 814%$0.14 → $1.28
- Relace · cache read↑ 471%$0.007 → $0.040
- DeepInfra through OpenRouter · inputunchanged$0.14 → $0.14
- DeepInfra through OpenRouter · outputunchanged$0.28 → $0.28
- DeepInfra through OpenRouter · cache read↓ 4%$0.0028 → $0.0027
| host | rate | was | now | change |
|---|---|---|---|---|
| Relace | input | $0.070 | $0.120 | ↑ 71% |
| Relace | output | $0.14 | $1.28 | ↑ 814% |
| Relace | cache read | $0.007 | $0.040 | ↑ 471% |
| DeepInfra through OpenRouter | input | $0.14 | $0.14 | — |
| DeepInfra through OpenRouter | output | $0.28 | $0.28 | — |
| DeepInfra through OpenRouter | cache read | $0.0028 | $0.0027 | ↓ 4% |
Relace output: ↑ 814%DeepInfra through OpenRouter cache read: ↓ 4%
If you buy
On Relace, output-heavy work now costs far more per call, so re-check your spend if you generate long replies there, while cache-heavy prompts on DeepInfra shift only slightly.
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 28 September 2026.
read the original at openrouter.ai ↗