Models / Xiaomi / MiMo-V2.6-Pro-UltraSpeed

Xiaomi · mimo

MiMo-V2.6-Pro-UltraSpeed

MiMo pro model for strong multimodal reasoning and agent execution

$4.35 in · $8.70 out

per 1M tokens · first-party price. Reference price from Xiaomi, the lab's own listing.

Provider input prices run from $4.35 to $5.08 per 1M tokens. Output prices run from $8.70 to $10.15.

Context
1,048,576
Max output
131,072
Cache read
$0.036
Cache write
—
Reasoning
Yes
Tool calls
Yes
Structured output
Unknown
Vision
Yes
Open weights
Yes
License
—
Released
Sep 21, 2026
Updated in source
Sep 21, 2026
Knowledge
—
Providers
9

Hugging Face weights

What this model costs per month

Prices are USD per 1M tokens. A month is 30 days. Cache hits use the cache-read rate when the model has one; otherwise the cache field is ignored.

monthly = requests/day × 30 × (input tokens × (1 − cache hit) × input price + input tokens × cache hit × cache-read price + output tokens × output price) ÷ 1,000,000

Providers

Base rates from Models.dev. One row per provider.
ProviderInputOutputCache readCache writeStatus
EmpirioLabs AI$4.35$8.70$4.35——
Kilo Gateway$4.35$8.70$0.036——
NanoGPT$4.35$8.70$0.036$0—
OpenRouter$4.35$8.70$0.036——
Tempr Gateway$4.35$8.70$0.036——
Vercel AI Gateway$4.35$8.70$0.036——
Xiaomireference$4.35$8.70$0.036——
AIHubMix$4.80$9.60$0.038——
above.dev$5.08$10.15$0.042——