Skip to content
Model Season every model has a seasonRadar

MiMo-V2.6-Flash

xiaomi/mimo-v2.6-flash-20260921
XiaomiChinaOpen weights

The 28th most-used model on the router over the last 7 days, with 0.53% of tokens.

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
Share, last 7 days
0.53%
28th of 65 · Sep 17, 2026 to Sep 23, 2026
Peak weekly share
no full week with volume
Cumulative tokens
no full week with volume
Weeks in the top 10
0
of 0 weeks with volume

Weekly token share

Share of the router's weekly volume, since the first week with volume

No full week with volume yet. The last-7-days share above comes from the daily window.

What this model is used for new

Tasks where the model ranks among the leaders, and its share of each

This model is not among the leaders in any of the 29 tasks classified in the Sep 23, 2026 snapshot. That does not mean it goes unused: the source lists only the largest models in each task.

Snapshot of the rolling 7-day window through Sep 23, 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

ProviderInputOutputContextQuantizationZero retention
DeepInfra$0.14$0.281Mfp8yes
Xiaomi$0.14$0.281Mfp8no

2 endpoints across 2 providers. 1 offers 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

Intelligence
no index
not published
Coding
no index
not published
Agents
no index
not published

GPQA Diamond 75.0%

$0.0068 per task, 150 tasks. 97th of 144 evaluated. Median of evaluated models: 81.8%, $0.025 per task.

τ-bench verified, airline 76.6%

$0.0069 per task, 47 tasks. 17th of 130 evaluated. Median of evaluated models: 70.5%, $0.053 per task.

Artificial Analysis indexes, exposed by the catalog; benchmarks run by the source and archived on Sep 24, 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

ModelLab7-day shareBlended priceContextIntelligenceWeeks in top 10
Proprietary
GPT-5.6 LunaOpenAIOpenAI6.4%$0.451M37.38
Gemini 3.8 FlashGoogleGoogle1.6%$1.501M40.91
Muse Spark 1.3 ContributorMetaMeta1.6%$0.1251M0
GPT-5.6 SolOpenAIOpenAI1.4%$4.001M47.00
GPT-6 AstraOpenAIOpenAI1.3%$20.001M52.70
Open weights
GLM 5.3 FlashZ.ai (GLM)Z.ai (GLM)14.0%$0.2371.31M41.84
DeepSeek V4.1 FlashDeepSeekDeepSeek13.6%$0.211M39.52
Hy4 previewTencentTencent9.6%$1.251M3
DeepSeek V4 Flash 0731DeepSeekDeepSeek7.0%$0.1021.31M34.37
MiMo-V2.5XiaomiXiaomi4.2%$0.1751M17
MiMo-V2.6-Flashthis pageXiaomiXiaomi0.53%$0.1751M0

Share over the last 7 days (Sep 17, 2026 to Sep 23, 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.

What this page doesn't say. Share here is a slice of one router's traffic, where the deciding factor is usually price per token. It is not market, revenue or user share, and it does not tell you which model fits your workload.