Models / Xiaomi / MiMo-V2.5

Xiaomi · mimo

MiMo-V2.5

Open MiMo model for multimodal coding agents and long-context automation

$0.14 in · $0.28 out

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

Provider input prices run from $0.14 to $0.70 per 1M tokens. Output prices run from $0.28 to $2.00.

Context
1,048,576
Max output
131,072
Cache read
$0.003
Cache write
—
Reasoning
Yes
Tool calls
Yes
Structured output
Unknown
Vision
Yes
Open weights
Yes
License
—
Released
Apr 22, 2026
Updated in source
Apr 22, 2026
Knowledge
2024-12
Providers
27

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. Where a provider lists the model more than once, the row is the listing whose id is closest to the canonical model id.
ProviderInputOutputCache readCache writeStatus
ClinePass$0.14$0.28$0.003——
Deep Infra$0.14$0.28$0.003—deprecated
Impossibl$0.14$0.28$0.003——
Kilo Gateway$0.14$0.28$0.003——
LLMTR$0.14$0.28———
NanoGPT$0.14$0.28$0.003$0—
OpenRouter$0.14$0.28$0.003——
Pioneer$0.14$0.28$0.003$0.14—
Requesty$0.14$0.28$0.003——
Vercel AI Gateway$0.14$0.28$0.003——
Xiaomireference$0.14$0.28$0.003——
AIHubMix$0.16$0.31$0.003——
CrossModel$0.16$0.32$0.004$0.16—
DevPass$0.17$0.34$0.003——
LLM Gateway$0.17$0.34$0.003——
Novita AI$0.17$0.34$0.003——
AI/ML API$0.19$0.39$0.004——
Ambient$0.40$2.00$0.08$0—
Hugging Face$0.40$2.00———
Venice AI$0.40$2.00$0.08——
ZenMux$0.40$2.00$0.08——
EmpirioLabs AI$0.70$1.40$0.014——
InferX$0$0———
Kenari$0$0———
Xiaomi Token Plan$0$0$0——
Xiaomi Token Plan$0$0$0——
Xiaomi Token Plan$0$0$0——