MiMo V2.6 Pro
XiaomiKey mimo-v2.6-proAlso reported as xiaomi/mimo-v2.6-pro, cline-pass/mimo-v2.6-pro, mm/mimo-v2.6-pro, xiaomi token plan/mimo-v2.6-pro, mimo/mimo-v2.6-pro, opencode/mimo-v2.6-pro, mm0e-com/auto/mimo-v2.6-pro, cmc/xiaomi/mimo-v2.6-pro, opencode-go/mimo-v2.6-pro
- Rank
- #68
- by active users
- Active users
- 5
- Down 4 from 9 active users in the previous 7 days. vs previous 7 days
- Adoption
- 0.8%
- of 609 accounts
- Tokens
- 119.2M
- cache included
- Est. cost
- $5
- at public list prices
- First seen
- Sep 21, 2026
- in any submission
Nov 6–12, 2026 (UTC)609 accounts100% of tokens from an identified modelData through Nov 12, 2026, 07:50 UTCHow we count
Daily active users
Distinct accounts that used this model on each UTC day.
0 active users on Nov 12, 2026
Show daily values
| Date (UTC) | Active users | Tokens |
|---|---|---|
| Nov 6, 2026 | 2 | 11.9M |
| Nov 7, 2026 | 1 | 722K |
| Nov 8, 2026 | 2 | 1.4M |
| Nov 9, 2026 | 1 | 2.7M |
| Nov 10, 2026 | 2 | 1.4M |
| Nov 11, 2026 | 1 | 101M |
| Nov 12, 2026 | 0 | 0 |
Token mix
How the 119.2M tokens split. Cache reads are usually most of an agent's tokens and are priced far below input.
- Input5.6%
- Output1.6%
- Cache read93%
- Cache write0%
- Reasoning<0.1%
Agents that carry MiMo V2.6 Pro
Each agent's share of this model's tokens, and how many accounts used the model through it.
Claude Code90% of this model's tokens1active users
OpenCode10.0% of this model's tokens2active users
Hermes Agent<0.1% of this model's tokens1active users- cc-mirror/curl<0.1% of this model's tokens1active users
Benchmarks
The best result for MiMo V2.6 Pro in each benchmark Tokscale tracks. Each benchmark has its own unit, run conditions and source, so compare a score only with other models on the same benchmark. Rank is among the models Tokscale matched in that benchmark.
- WebDev ArenaWeb development · LMArena1,625
WebDev Arena: 1,625
- Model
- MiMo V2.6 Pro
- Listed as
- MiMo-V2.6-Pro
- Conditions
- Not reported
- Interval
- 1615–1635
- Unit
- Arena score
- Published
- Oct 19, 2026
- Retrieved
- Oct 21, 2026
Source · LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset on Hugging Face), CC BY 4.0
Rank #20 of 110 matched modelsNo conditions reportedPublished Oct 19, 2026Source: huggingface.co (opens in a new tab) - Agent ArenaAgents · LMArena+0.04
Agent Arena: +0.04
- Model
- MiMo V2.6 Pro
- Listed as
- MiMo-V2.6-Pro
- Conditions
- Arena Agent Mode
- Interval
- 0.03 to 0.05
- Unit
- net improvement
- Published
- Oct 19, 2026
- Retrieved
- Oct 21, 2026
Source · LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset on Hugging Face), CC BY 4.0
Rank #13 of 48 matched modelsArena Agent ModePublished Oct 19, 2026Source: huggingface.co (opens in a new tab)
Pricing
List prices from models.dev in US dollars per 1M tokens, retrieved Nov 12, 2026. Xiaomi is the lab's own API and the reference price for the estimates below.
Price at real agent usageEstimate at list prices
What 1M tokens cost at the reference list price when they split into input, output and cache the way Tokscale users' agents used them. It is not what anyone paid.
- At this model's mix
- $0.04
- Est. per 1M tokens
93% cache reads - At the community mix
- $0.02
- Est. per 1M tokens
96% cache reads - 3:1 input/output blend
- $0.54
- Per 1M tokens at list prices
No cache
Cache reads were 93% of MiMo V2.6 Pro tokens in the last 7 days and 96% of all tokens. The 3:1 blend, (3 × input + output) ÷ 4, is the usual comparison and ignores cache.
Assumptions
- Xiaomi list prices per 1M tokens: input $0.43, output $0.87, cache read $0.004.
- This model's mix is its own input, output, cache and reasoning tokens in the last 7 days.
- The community mix is the tokens of every identified model in the last 7 days.
- This is an estimate at list prices, not what anyone paid.
- Reasoning tokens are priced as output.
- Long-context tiers, batch pricing and discounts are not applied.
- Token mixes come from public Tokscale submissions. Hidden accounts are excluded.
- No cache-write price is listed, so cache writes are priced as input.
List prices by provider
- XiaomiReference
mimo-v2.6-pro$0.43 input per 1M tokens$0.87 output per 1M tokens$0.004 cache read per 1M tokensCache write not listed1.05M tokens of context - OpenRouter
xiaomi/mimo-v2.6-pro$0.43 input per 1M tokens$0.87 output per 1M tokens$0.004 cache read per 1M tokensCache write not listed1.05M tokens of context - Vercel AI Gateway
xiaomi/mimo-v2.6-pro$0.43 input per 1M tokens$0.87 output per 1M tokens$0.004 cache read per 1M tokensCache write not listed1.05M tokens of context - Deep Infra
XiaomiMiMo/MiMo-V2.6-Pro$0.43 input per 1M tokens$0.87 output per 1M tokens$0.004 cache read per 1M tokensCache write not listed1.05M tokens of context
Specs
From models.dev (MIT), retrieved Nov 12, 2026, as the lab or the first listed provider reports them. A dash means models.dev does not list the value.
- Context window
- 1.05M tokens
- Max output
- 131K tokens
- Input
- Text, Image, Audio, Video
- Output
- Text
- Knowledge cutoff
- — not listed
- Release date
- Sep 22, 2026
- Open weights
- Yes
- Reasoning
- Yes
- Tool calling
- Yes
Top public profiles
Public profiles that used MiMo V2.6 Pro most in this period, by tokens. Hidden accounts are never listed.
- 1
Christopher Butler@techsaint107.3Mtokens$5est. cost5active days$5 est. cost · 5 active days
- 2
Clement mondary@mondary11.8Mtokens—est. cost1active daysno price · 1 active days
- 3
Brandon Wie@brandonwie23.6Ktokens<$1est. cost1active days<$1 est. cost · 1 active days
- 4
PROTIK MONDAL@MNDL-276.1Ktokens—est. cost1active daysno price · 1 active days
- 5
如是@MiFaZhan394tokens<$1est. cost1active days<$1 est. cost · 1 active days
More from Xiaomi
Other Xiaomi models in the same period, by active users.
- MiMo V2.6 Flash Free0.5% adoption3active users
- MiMo V2.6 Flash0.3% adoption2active users
- MiMo V2 6 Flash 00.2% adoption1active users
- MiMo V2.50.2% adoption1active users
- MiMo V2 6 Pro 00.2% adoption1active users
Sources and attribution
Each score keeps its own source, unit and run conditions. Tokscale does not combine benchmarks into one score, and a missing score means the model was not evaluated, not that it scored zero.