Favicon for xiaomi

Xiaomi: MiMo-V2.5

xiaomi/mimo-v2.5

Model weights

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 tasks. Its 1M context window supports complete documents, extended conversations, and complex task contexts in a single pass, making it ideal for integration with agent frameworks where strong reasoning, rich perception, and cost efficiency all matter.

Modalities
In / out price
$0.40 / $2per 1M
Context
1.0M
Released
Apr 22, 2026

Providers

This model is hosted by one provider. OpenRouter forwards every request without routing.

Pricing

The average price customers actually pay for this model, next to the prices providers post. Caching and discounts mean the price actually paid is often well below the listed one.

Weighted average

Input
$0.1743/M tokens
Output
$2/M tokens
Price history
No effective price data for this selection

Performance

Throughput is how fast the model writes (tokens per second — higher is better). Latency is total round-trip time (lower is better). TTFT is time-to-first-token — how long before you see anything appear (lower is better).

Throughput
52tok/s

P50, best across providers

Latency
1.11s

P50, best provider

AutoExacto benchmarks
GPQA DiamondTAU-BenchStreamLake86.6%--Venice83.0%--GMICloud82.6%--auto-routing83.5%79.3%Novita82.2%78.0%
+1 more providers

Uptime

Uptime is the percentage of the past 3 days that at least one provider was responding to requests. Availability is the percentage of time that inference was successfully served. OpenRouter continuously monitors and uses the next-best provider when one returns an error.

Uptime (3d)The model was reachable. Request routed to a provider.
100.00%
Availability (3d)The model returned inference from any provider. Errors and empty responses count against it.
99.24%

Availability over the last 3 days

Last 72 hours
Availability 99.24%
3 Days Ago2 Days AgoYesterdayNow

Availability over the last 24 hours

OpenRouter Availability
98.95%

When an error occurs in an upstream provider, we can recover by routing to another healthy provider, if your request filters allow it. You can access per-provider uptime data programmatically through the Endpoints API. Learn more about our load balancing and provider routing options.

Benchmarks

Scores on standardized evaluations and this model’s own outputs on shared benchmark prompts. Higher percentages are better — and each rank shows where this model lands among the models evaluated on that source.

Benchmark score summary for Xiaomi: MiMo-V2.5 (Artificial Analysis, Design Arena and Vals AI)
SourceBenchmarkScore
Artificial AnalysisMiMo-V2.5 Coding Index56.8
Artificial AnalysisMiMo-V2.5 Agentic Index15.8
Artificial AnalysisMiMo-V2.5 GPQA Diamond84.9%
Artificial AnalysisMiMo-V2.5 HLE27.2%
Artificial AnalysisMiMo-V2.5 IFBench67.1%
Artificial AnalysisMiMo-V2.5 τ²-Bench Telecom90.6%
Artificial AnalysisMiMo-V2.5 AA-LCR73.0%
Artificial AnalysisMiMo-V2.5 τ-Bench Banking8.7%
Artificial AnalysisMiMo-V2.5 GDPval-AA25.3%
Artificial AnalysisMiMo-V2.5 CritPt3.7%
Artificial AnalysisMiMo-V2.5 SciCode43.9%
Artificial AnalysisMiMo-V2.5 Terminal-Bench Hard41.7%
Artificial AnalysisMiMo-V2.5 Terminal-Bench 4.00.0%
Artificial AnalysisMiMo-V2.5 Terminal-Bench 2.163.7%
Design ArenaMiMo-V2.5 Models Arena 3D Elo1197
Design ArenaMiMo-V2.5 Models Arena Asciiart Elo1139
Design ArenaMiMo-V2.5 Models Arena Code Categories Elo1252
Design ArenaMiMo-V2.5 Models Arena Data Visualization Elo1249
Design ArenaMiMo-V2.5 Models Arena Game Development Elo1242
Design ArenaMiMo-V2.5 Models Arena SVG Elo1175
Design ArenaMiMo-V2.5 Models Arena UI Component Elo1249
Design ArenaMiMo-V2.5 Models Arena Website Elo1260
Vals AIMiMo V2.5 Code Migration14.2%
Vals AIMiMo V2.5 CorpFin v259.9%
Vals AIMiMo V2.5 EMB55.1%
Vals AIMiMo V2.5 Finance Agent (v2)36.7%
Vals AIMiMo V2.5 GPQA Diamond81.6%
Vals AIMiMo V2.5 Harvey's Legal Agent Benchmark v11.7%
Vals AIMiMo V2.5 LiveCodeBench81.5%
Vals AIMiMo V2.5 LegalBench78.9%
Vals AIMiMo V2.5 Legal Research Bench9.1%
Vals AIMiMo V2.5 MedCode31.9%
Vals AIMiMo V2.5 MedScribe72.2%
Vals AIMiMo V2.5 MMLU Pro82.9%
Vals AIMiMo V2.5 MMMU Pro80.0%
Vals AIMiMo V2.5 MortgageTax59.3%
Vals AIMiMo V2.5 ProofBench v1.116.0%
Vals AIMiMo V2.5 SAGE v143.3%
Vals AIMiMo V2.5 SWE-bench71.0%
Vals AIMiMo V2.5 Tax Agent Bench7.8%
Vals AIMiMo V2.5 TaxEval v271.8%
Vals AIMiMo V2.5 Terminal-Bench 2.160.7%
Vals AIMiMo V2.5 Vals Index39.9%
Vals AIMiMo V2.5 Vals Multimodal Index52.8%
Vals AIMiMo V2.5 Vibe Code Bench v1.142.2%

Apps

Public apps that send the most traffic to this model. Good signal for what real production workloads look like — and a hint at which use cases this model is best suited for.

1.
Favicon for https://www.isekai.world/
ISEKAI ZERO
32.2Btokens
2.
Favicon for https://openrouter.ai/images/apps/cline.png
Cline
18.7Btokens
3.
Favicon for https://nousresearch.com
Hermes Agent
17.7Btokens
4.
Favicon for https://github.com/thedotmack/claude-mem
claude-mem
16.1Btokens
5.
Favicon for https://www.hellominds.ai/
Hello Minds, powered by Ethoswarm
new
10.8Btokens
Rest of OpenRouter
434M
Top 5 Apps
314M

Activity

Token volume and request traffic to this model over time.

API

Drop-in code to call this model. OpenRouter's API is OpenAI-compatible — most SDKs work by just swapping the base URL. The only thing that changes between models is the model slug below.

Not currently available through EU in-region routing. In-region routing docs

Frequently asked questions

Explore more models