Xiaomi: MiMo-V2.6-Flash
xiaomi/mimo-v2.6-flash
MiMo-V2.6-Flash (Xiaomi) is a low-cost open-weight model priced near the bottom of the board, at $0.14/$0.28 per million input/output tokens, served by 6 independent hosts. For the money it delivers #75 of 269 on the TryAii Score — among the best score-per-dollar in its class. Its best result is agentic / tool use (#6 on OSWorld-Verified).
Prompt $/1M
$0.140
Completion $/1M
$0.280
Context
1,050,000 tok
Best provider
43 tok/s · Cohere
Specs
- Model id
- xiaomi/mimo-v2.6-flash
- Display name
- Xiaomi: MiMo-V2.6-Flash
- Modality
- text+image+audio+video->text
- Tokenizer
- Other
- Instruct type
- —
- Context length
- 1,050,000
- Max completion
- 131,072
- Prompt $/1M
- $0.140
- Completion $/1M
- $0.280
- Free tier
- no
Capabilities
- Function callingno
- JSON modeno
- System promptno
- Visionno
- Moderatedno
Benchmark scores
Each axis is one benchmark, normalized to the best model in the field.
No benchmark data for this model.
Speed by provider
| Provider | tok/s |
|---|---|
| Coherefastest | 43 |
| Makora | 42 |
| GMICloud | 30 |
| Xiaomi | 30 |
| DeepInfra | 30 |
| Venice | 29 |
| Darkbloom | 19 |