Xiaomi: MiMo-V2.5, Other — route, pricing & source
MiMo-V2.5 is a native omnimodal model by Xiaomi. It delivers Pro-level agentic performance at roughly half the inference cost, while surpassing MiMo-V2-Omni in multimodal perception across image and video understanding...
OpenRoutermediumLast checked: Jun 2, 2026
Input
$0.1400 / 1M
/ 1M tokens
Output
$0.2800 / 1M
/ 1M tokens
Cached input
Not available
Not available
Cache write
Not available
Not available
Context and limits
Context window
1.0M
Max output
131,072
Input modalities
text, audio, image, video
Output modalities
text
Weight access
Closed
Availability
Unknown
Capability flags
VisionToolsJSONReasoningAudioLong context
From source metadata + verification fields — confirm provider docs before production.
Benchmarks
- LMArena Text Arenaoverall · official_benchmark_api1,434Independent
Rank: 62 | Votes: 15979 | 95% CI: 1428.2-1439.5 | Published: 2026-05-27 | Model license label in dataset: MIT
- LMArena WebDev Arenaoverall · official_benchmark_api1,440Independent
Rank: 23 | Votes: 3741 | 95% CI: 1429.7-1450.1 | Published: 2026-05-25 | Model license label in dataset: MIT
- LMArena Vision Arenaoverall · official_benchmark_api1,231Independent
Rank: 36 | Votes: 6912 | 95% CI: 1221.7-1239.4 | Published: 2026-05-18 | Model license label in dataset: MIT
Access and license
Official API
No
Open weights
No
Self-hostable
No
License
Open sourceMITCode/weights ship under an open license (often MIT / Apache‑2.0). MIT is a short permissive license: use/modify/redistribute freely with a copyright notice—always read the upstream project text.
Example costs
Scenario: 1K input + 300 output tokens / request
10,000 requests
$2.24
100,000 requests
$22.40
1,000,000 requests
$224.00
Cheaper alternatives
Lower-cost models for the same scenario
Source
Source
OpenRouter Models API
Confidence
medium
Route
OpenRouter
Last checked
Jun 2, 2026
Source notes
- Includes Hugging Face benchmark data only when the dataset is public, ungated, allowlisted, and matched by reviewed aliases.
