MiMo-V2.6-Flash
The 19th most-used model on the router over the last 7 days, with 1.2% of tokens. Weekly share peaked at 6.7% in the week of Oct 5, 2026, with 48T tokens processed since Sep 21, 2026.
- Launch
- Sep 21, 2026
- Context
- 1M tokens
- Modality
- text, image, audio and video → text
- Reasoning
- yes
- License
- Open weights
- Input
- $0.14 / 1M
- Output
- $0.28 / 1M
Weekly token share
Share of the router's weekly volume, since the first week with volume
See the numbers
| Week | Share |
|---|---|
| Nov 2, 2026 | 1.074% |
| Oct 26, 2026 | 1.558% |
| Oct 19, 2026 | 3.230% |
| Oct 12, 2026 | 6.059% |
| Oct 5, 2026 | 6.667% |
| Sep 28, 2026 | 5.804% |
| Sep 21, 2026 | 3.772% |
Debuted in the week of Sep 21, 2026 and peaked at 6.7% 2 weeks later. The latest full week came in at 1.1%, 16% of peak.
What this model is used for new
Tasks where the model ranks among the leaders, and its share of each
Ranks among the leaders in 5 of the 29 classified tasks. Its largest share is in frontend and UI, 3.2% of the task's tokens; in the heaviest task where it appears, code generation (9.8% of classified volume), it holds 1.5%.
Snapshot of the rolling 7-day window through Nov 9, 2026. Share: the model's tokens in the task over the task's total tokens. Weight: the task's share of classified volume.
Where to run it
Endpoints in the source's catalog, from cheapest to most expensive on input
| Provider | Input | Output | Context | Quantization | Zero retention |
|---|---|---|---|---|---|
| Darkbloom | $0.10 | $0.28 | 1M | fp4 | no |
| GMICloud | $0.112 | $0.224 | 1M | bf16 | no |
| Cohere | $0.14 | $0.28 | 1M | fp8 | yes |
| Makora | $0.14 | $0.28 | 1M | fp8 | yes |
| DeepInfra | $0.14 | $0.28 | 1M | fp8 | yes |
| Xiaomi | $0.14 | $0.28 | 1M | fp8 | no |
| Venice | $0.175 | $0.35 | 1M | fp8 | yes |
7 endpoints across 7 providers, with input from $0.10 to $0.175 per 1M tokens. 4 offer zero data retention.
Prices in US dollars per million tokens, from the latest archived endpoint catalog.
Benchmarks
Artificial Analysis indexes and benchmarks run by the source, with cost per task
GPQA Diamond 73.2%
$0.017 per task, 990 tasks. 101st of 145 evaluated. Median of evaluated models: 82.6%, $0.025 per task.
τ-bench verified, airline 77.9%
$0.015 per task, 250 tasks. 11th of 142 evaluated. Median of evaluated models: 71.6%, $0.063 per task.
Artificial Analysis indexes, exposed by the catalog; benchmarks run by the source and archived on Nov 10, 2026. The gray mark is the median of evaluated models.
Against the week's largest models
The five largest proprietary and five largest open-weights models over the last 7 days
| Model | Lab | 7-day share | Blended price | Context | Intelligence | Weeks in top 10 |
|---|---|---|---|---|---|---|
| Proprietary | ||||||
| GPT-6 LunaOpenAI | OpenAI | 3.4% | $0.20 | 1M | 27.9 | 7 |
| Claude Opus 5.5Anthropic | Anthropic | 3.2% | $8.00 | 1M | 59.1 | 5 |
| GPT-6.1 SolOpenAI | OpenAI | 1.9% | $4.00 | 1M | 54.6 | 0 |
| jev-1.13Typesafe | Typesafe | 1.4% | — | — | — | 0 |
| Muse Spark 1.3 ContributorMeta | Meta | 1.4% | $0.125 | 1M | — | 0 |
| Open weights | ||||||
| DeepSeek V4.1 Flash 1017DeepSeek | DeepSeek | 26.6% | $0.13 | 1M | 28.6 | 3 |
| DeepSeek V4.1 FlashDeepSeek | DeepSeek | 8.4% | $0.525 | 1M | — | 9 |
| Hy4Tencent | Tencent | 7.7% | $0.625 | 1M | 34.6 | 1 |
| GLM 5.3 FlashZ.ai (GLM) | Z.ai (GLM) | 5.8% | $0.05 | 1M | 27.8 | 11 |
| Step 5 PreviewStepFun | StepFun | 3.4% | $1.43 | 1M | 28.5 | 4 |
| MiMo-V2.6-Flashthis pageXiaomi | Xiaomi | 1.2% | $0.175 | 1M | 26.7 | 5 |
Share over the last 7 days (Nov 3, 2026 to Nov 9, 2026). Blended price in US dollars per million tokens, weighted 75% input and 25% output. A dash means the number is not published, not zero.