MiMo-V2.6-Flash
by Xiaomi · xiaomi/mimo-v2.6-flash
MiMo-V2.6-Flash is an open-source foundation model developed by Xiaomi. Built on a Mixture-of-Experts architecture with 309B total parameters and 15B activated per token, it employs a hybrid attention mechanism for...
- Input / 1M tokens
- $0.14
- Output / 1M tokens
- $0.28
- Context
- 1.05M
Specs
| Input price | $0.14 / 1M tokens |
|---|---|
| Output price | $0.28 / 1M tokens |
| Cached input | $0.0028 / 1M tokens |
| Context window | 1.05M tokens |
| Max output | 131K tokens |
| Reads | text, image, video, audio |
| Writes | text |
| Tool calling | Yes |
| Reasoning | Yes |
| Listed | Sep 21, 2026 |
List prices in USD, updated Oct 30, 2026. Providers may charge differently.
Providers
10 providers serve this model, as of Oct 30, 2026, 18:12 UTC.
| Provider | Quantization | Context | Max output | Input / 1M | Output / 1M | Cache read / 1M | Uptime (30 min) | Latency (median) | Throughput (median) | Supports | Status |
|---|---|---|---|---|---|---|---|---|---|---|---|
| Relace | mxfp4 | 1.05M | 131K | $0.087 | $0.187 | $0.003 | 100% | 935 ms | 93 tok/s | Normal | |
| GMICloud | bf16 | 1.05M | 945K | $0.119 | $0.238 | $0.00255 | 100% | 4.44 s | 24 tok/s | Normal | |
| Darkbloom | fp4 | 1.05M | 131K | $0.10 | $0.28 | $0.05 | — | 3.47 s | 36 tok/s | Normal | |
| Io Net | fp8 | 1.05M | 131K | $0.10 | $0.28 | $0.003 | 100% | 1.59 s | 75 tok/s | Normal | |
| Makora | fp8 | 1.05M | 131K | $0.11 | $0.28 | $0.002 | 100% | 755 ms | 79 tok/s | Normal | |
| Cohere | — | 1.05M | 384K | $0.14 | $0.28 | $0.003 | 100% | 877 ms | 110 tok/s | Normal | |
| DeepInfra | fp8 | 1.05M | 944K | $0.14 | $0.28 | $0.0028 | 100% | 1.71 s | 56 tok/s | Normal | |
| Novita | fp8 | 1.05M | 131K | $0.14 | $0.28 | $0.0028 | 100% | 5.81 s | 26 tok/s | Normal | |
| Xiaomi | fp8 | 1.05M | 131K | $0.14 | $0.28 | $0.0028 | 100% | 3.31 s | 30 tok/s | Normal | |
| Venice | fp8 | 1M | 131K | $0.175 | $0.35 | $0.00375 | 100% | 1.60 s | 47 tok/s | Code -2 |
"Cheapest" is the lowest input plus output price; "Fastest" the highest median throughput. Columns empty for every provider are not shown.
Usage
#17
by tokens, Oct 29, 2026
426B
tokens that day · 7 days −55%
Data as of 2026-10-30T18:12:03.879Z.All rankings
Related models
- Xiaomi
MiMo-V2.6-Pro
- Input
- $0.435
- Output
- $0.87
- Context
- 1.05M
- Xiaomi
MiMo-V2.6-Pro-UltraSpeed
- Input
- $4.35
- Output
- $8.70
- Context
- 1.05M
- Xiaomi
MiMo-V2.5-Pro
- Input
- $0.48
- Output
- $1.80
- Context
- 1.05M
- Xiaomi
MiMo-V2.5
- Input
- $0.40
- Output
- $2.00
- Context
- 1.05M
- Qwen
Qwen3.5-35B-A3B
- Input
- $0.14
- Output
- $1.00
- Context
- 262K
- Tencent
Hunyuan A13B Instruct
- Input
- $0.14
- Output
- $0.57
- Context
- 131K