Skip to content
Model Season every model has a season

MiMo-V2.5

xiaomi/mimo-v2.5-20260422
XiaomiChinaOpen weights

The 5th most-used model on the router over the last 7 days, with 4.2% of tokens. Weekly share peaked at 18.0% in the week of Jul 20, 2026, with 83T tokens processed since May 4, 2026.

Launch
Apr 22, 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
4.2%
5th of 61 · Sep 4, 2026 to Sep 10, 2026
Peak weekly share
18.0%
week of Jul 20, 2026
Cumulative tokens
83T
since the week of May 4, 2026
Weeks in the top 10
15
of 18 weeks with volume

Weekly token share

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

0%5%10%15%20%25%Jun '26JulAugpeak 18.0% on Jul 20, 2026
See the numbers
WeekShare
Aug 31, 20262.037%
Aug 24, 20268.086%
Aug 17, 202610.644%
Aug 10, 20265.033%
Aug 3, 20267.811%
Jul 27, 202611.102%
Jul 20, 202618.027%
Jul 13, 202614.846%
Jul 6, 202611.302%
Jun 29, 20269.377%
Jun 22, 20269.593%
Jun 15, 20268.449%
Jun 8, 20268.048%
Jun 1, 20266.057%
May 25, 20264.598%
May 18, 20260.326%
May 11, 20260.049%
May 4, 20260.039%

Debuted in the week of May 4, 2026 and peaked at 18.0% 11 weeks later. The latest full week came in at 2.0%, 11% of peak.

What this model is used for new

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

Plus 5 more tasks with a smaller share.

Ranks among the leaders in 17 of the 29 classified tasks. Its largest share is in memory extraction, 12.0% of the task's tokens; in the heaviest task where it appears, workflow execution (24.6% of classified volume), it holds 3.3%.

Snapshot of the rolling 7-day window through Sep 10, 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
GMICloud$0.119$0.2381Mfp8no
DeepInfra$0.133$0.266256kfp8yes
Xiaomi$0.14$0.281Mfp8no
StreamLake$0.168$0.3361Mnot reportedno
Novita$0.168$0.3361Mfp8yes

5 endpoints across 5 providers, with input from $0.119 to $0.168 per 1M tokens. 2 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

Intelligence
22.3
46th of 82
Coding
56.8
39th of 111
Agents
17.4
48th of 86

GPQA Diamond 76.3%

$0.0099 per task, 1353 tasks. 82nd of 131 evaluated. Median of evaluated models: 80.2%, $0.024 per task.

τ-bench verified, airline 70.9%

$0.0081 per task, 400 tasks. 59th of 122 evaluated. Median of evaluated models: 70.7%, $0.056 per task.

Artificial Analysis indexes, exposed by the catalog; benchmarks run by the source and archived on Sep 11, 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 LunaOpenAIOpenAI11.5%$0.451M37.56
Gemini 3.8 FlashGoogleGoogle2.1%$1.501M41.20
Muse Spark 1.3 ContributorMetaMeta1.5%$0.1251M0
Claude Opus 5AnthropicAnthropic1.4%$10.001M50.71
GPT-5.6 SolOpenAIOpenAI1.4%$4.001M47.10
Open weights
Hy4 previewTencentTencent15.5%$1.251M1
DeepSeek V4 Flash 0731DeepSeekDeepSeek10.0%$0.0941.31M34.55
GLM 5.3 FlashZ.ai (GLM)Z.ai (GLM)10.0%$0.2371.31M41.92
MiMo-V2.5this pageXiaomiXiaomi4.2%$0.1751M22.315
DeepSeek V4 Flash 0423DeepSeekDeepSeek3.9%$0.1111M24.819

Share over the last 7 days (Sep 4, 2026 to Sep 10, 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.