MiMo V2.6 Pro UltraSpeed

xiaomi/mimo-v2.6-pro-ultraspeed

low-latency serving tier of MiMo V2.6 Pro.

cmd --model xiaomi/mimo-v2.6-pro-ultraspeed
Intelligence index
not yet scored
Output speed
not yet scored
Input
$4.35 /M
Output
$8.70 /M
Cache read
$0.04 /M
Agent-loop cost
$1.33 /M in
Context window
1.05M tokens
Released
Modalities

vs. the lineup

MiMo V2.6 Pro UltraSpeed beside its stablemates and nearest rivals. The ◆ marks the best value in each column across every row shown.

pin a rival:
ModelIntelligenceCodingSpeedInput $/MOutput $/MBlended $/MContext
Muse Spark 1.348.275.8418.4$1.25$4.25$21.05M
MiMo V2.5 Pro26.460.243.4$0.43$0.87$0.541M
MiMo V2.522.356.846.2$0.14$0.28$0.181M
MiMo V2.6 Pro UltraSpeed$4.35$8.70$5.441.05M
MiMo V2.6 Pro$0.43$0.87$0.541.05M
MiMo V2.6 Flash$0.14$0.28$0.181.05M
DeepSeek V4 Pro (latest)pinned36.368.865.3$0.66$1.98$0.991M
DeepSeek V4 Flash (latest)pinned3569.1236.4$0.15$0.60$0.261M

usage calculator

How far a month of credits goes on MiMo V2.6 Pro UltraSpeed.

MiMo V2.6 Pro UltraSpeed runs on GOAT and up — from $10/mo.
Input tokensfresh prompt
800
Output tokensmodel reply
180
Cache read tokensre-read context
50K
cost / request $0.0068 · in $4.35 · out $8.70 · cache $0.04 per M
fresh input 51%output 23%cache reads 26%
Requests / 30 days
1.5K
$10 credits ÷ $0.0068 per request
~292 quick fixes~58 bug fixes~10 feature PRs

what real work costs

Real coding tasks priced end to end on MiMo V2.6 Pro UltraSpeed, from a quick lookup to a full-repo agent run.

One agent task
$0.31
180K in at 75% cache hit, 12K out
What you pay
$1.59 /M
all-in across every token that task touched
Sticker input
$4.35 /M
cache reads bill at $0.04 /M instead
TaskTokens in · outMiMo V2.6 Pro UltraSpeedMuse Spark 1.3Claude Haiku 4.5
Quick lookup / one-liner8K · 1K$0.01$0.0063$0.0065
Review a 500-line PR60K · 4K$0.11$0.05$0.04
Fix a bug (agent loop)180K · 12K$0.31$0.13$0.12
Refactor a module320K · 20K$0.57$0.23$0.21
Full-repo agent run900K · 45K$1.28$0.54$0.49

frequently asked

How much does MiMo V2.6 Pro UltraSpeed cost?
$4.35/M input and $8.70/M output, cache reads $0.04/M. In an agent loop most input is cache-read, so the effective input rate is about $1.33/M.
Which plan do I need?
Available on GOAT and above.
How do I switch to it?
Run cmd --model xiaomi/mimo-v2.6-pro-ultraspeed, or type /model in a session and pick it. You can switch mid-session without losing context.

Ship code that matches your taste

Command Code is the AI coding agent that continuously learns your taste. Start for $1.

Benchmarks from Artificial Analysis (v4.3)commandcode.ai/models/mimo-v2-6-pro-ultraspeed