Skip to content
  • Models
  • Rankings
  • Ori
Sign Up
Sign Up
OpenRouterOpenRouter
© 2026 OpenRouter, Inc

Product

  • Chat
  • Rankings
  • Benchmarks
  • Apps
  • Discover
  • Models
  • Collections
  • Providers
  • Pricing
  • Business
  • Enterprise
  • Labs

Company

  • About
  • Blog
  • Careers
    Hiring
  • Privacy
  • Terms of Service
  • Trust Center
  • Support
  • Works With OR
  • Data
  • Brand

Developer

  • Documentation
  • API Reference
  • Developer Platform
  • Status

Connect

  • Discord
  • GitHub
  • LinkedIn
  • X
  • YouTube
Favicon for xiaomi

Xiaomi: MiMo-V2.5

xiaomi/mimo-v2.5

Model weights
Compare

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

15% off

$0.119 / $0.238per 1M

Context

1.1M

Released

Apr 22, 2026

Compare
ProvidersPricingPerformanceUptimeBenchmarksAppsActivityFAQExplore

Providers

Different companies host the same model. OpenRouter routes your request to one of them based on the routing mode you pick — Balanced (price + speed), Nitro (fastest), or Exacto (highest tool-calling accuracy).

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.

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).

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.

Benchmarks

Scores on standardized evaluations. Higher percentages are better — and rank percentile shows where this model lands among all models on OpenRouter.

Benchmark score summary for Xiaomi: MiMo-V2.5 (Artificial Analysis and Design Arena)
SourceBenchmarkScore
Artificial AnalysisMiMo-V2.5 Intelligence Index22.3
Artificial AnalysisMiMo-V2.5 Coding Index56.8
Artificial AnalysisMiMo-V2.5 Agentic Index17.4
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 GDPval-AA29.0%
Artificial AnalysisMiMo-V2.5 CritPt3.7%
Artificial AnalysisMiMo-V2.5 SciCode43.9%
Artificial AnalysisMiMo-V2.5 Terminal-Bench Hard41.7%
Artificial AnalysisMiMo-V2.5 AA-Omniscience Accuracy16.8%
Artificial AnalysisMiMo-V2.5 AA-Omniscience Non-Hallucination Rate68.1%
Design ArenaMiMo-V2.5 Models Arena 3D Elo1241
Design ArenaMiMo-V2.5 Models Arena Asciiart Elo1162
Design ArenaMiMo-V2.5 Models Arena Code Categories Elo1275
Design ArenaMiMo-V2.5 Models Arena Data Visualization Elo1267
Design ArenaMiMo-V2.5 Models Arena Game Development Elo1269
Design ArenaMiMo-V2.5 Models Arena SVG Elo1201
Design ArenaMiMo-V2.5 Models Arena UI Component Elo1273
Design ArenaMiMo-V2.5 Models Arena Website Elo1279

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.

Activity

Token volume and request traffic to this model over time.

Quick Start

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.

Explore more models

AI Models with Vision: Multimodal LLMs for Image UnderstandingCollectionAI Model RankingsRanking
$0.14$0.28$0.00284.06s31 tps
96.75%
$0.168$0.336$0.003361.37s19 tps
91.67%
$0.168$0.336$0.00342.77s38 tps
95.69%
15% off
$0.14$0.119$0.28$0.238$0.003$0.002553.50s20 tps
69.37%
5% off
$0.14$0.133$0.28$0.266$0.0028$0.002662.45s7 tps
98.59%
$0.40$2.00$0.082.95s7 tps
95.32%

Throughput

38tok/s

P50, best across providers

Latency

1.37s

P50, best provider

AutoExacto Benchmarks
GPQA DiamondTAU-Benchvgi_benchStreamLake82.3%----Venice84.4%74.7%--NovitaAI82.2%72.6%--auto-routing76.2%70.7%--GMICloud68.4%71.6%--
+3 more providers
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.

99.65%

Availability over the last 3 days

Last 72 hours
Availability 99.65%
3 Days Ago2 Days AgoYesterdayNow

Availability over the last 24 hours

OpenRouter Availability
99.66%
Without Routing
92.07%

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 customization options.

1.
Favicon for https://freebuff.com/
Freebuff
Powerful coding models, funded by ads
8.18Ttokens
2.
Favicon for https://www.isekai.world/
ISEKAI ZERO
AI adventures. Travel with your favorite characters
257Btokens
3.
Favicon for https://cline.bot/
Cline
Cline is an open-source AI coding agent that lives inside your IDE, autonomously exploring your codebase, editing files, running terminal commands, and using browser automation.
170Btokens
4.
Favicon for https://nousresearch.com
Hermes Agent
Hermes Agent is an open-source, self-improving AI agent by Nous Research that runs persistently with memory across sessions, and builds reusable skills from experience. It comes with 40+ built-in tools, including web search, browser automation, and vision, plus scheduled automations and subagents.
138Btokens
5.
Favicon for https://claude.ai/apple-touch-icon.png
Claude Code
Claude Code is Anthropic's agentic coding tool that reads your entire codebase, plans and executes changes across files, runs tests, and iterates on failures, all from natural language prompts.
99.9Btokens

Frequently asked questions

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.

MiMo-V2.5 costs $0.119/M input tokens and $0.238/M output tokens, with separate rates for Cache Read at $0.00255/M tokens.

MiMo-V2.5 has a 1,050,000 token context window.

Yes. MiMo-V2.5 accepts tools and tool_choice for function calling. It does not support response_format, so JSON output is not enforced.

MiMo-V2.5 accepts text, audio, images and video as input and returns text.

MiMo-V2.5 is served by 6 providers on OpenRouter: GMICloud, DeepInfra, Xiaomi, StreamLake, NovitaAI and Venice. Requests are routed to the best available provider, with automatic failover to the others, and you can pin or exclude providers with provider routing.

MiMo-V2.5 was released on April 22, 2026.

More models from Xiaomi

MiMo-V2.5-Pro

MiMo-V2.5-Pro is Xiaomi’s flagship model, delivering strong performance in general agentic capabilities, complex software engineering, and long-horizon tasks, with top rankings on benchmarks such as ClawEval, GDPVal, and SWE-bench Pro. It can independently and autonomously complete professional tasks that would take human experts days or weeks, involving more than a thousand tool calls. Its context length of up to 1M makes it well suited for integration with a wide range of agent frameworks.

Text1.1M context$0.3045 / $0.609
MiMo-V2-Omni

MiMo-V2-Omni is a frontier omni-modal model that natively processes image, video, and audio inputs within a unified architecture. It combines strong multimodal perception with agentic capability - visual grounding, multi-step planning, tool use, and code execution - making it well-suited for complex real-world tasks that span modalities, 256K context window.

Text262K context
MiMo-V2-Pro

MiMo-V2-Pro is Xiaomi's flagship foundation model, featuring over 1T total parameters and a 1M context length, deeply optimized for agentic scenarios. It is highly adaptable to general agent frameworks like OpenClaw. It ranks among the global top tier in the standard PinchBench and ClawBench benchmarks, with perceived performance approaching that of Opus 4.6. MiMo-V2-Pro is designed to serve as the brain of agent systems, orchestrating complex workflows, driving production engineering tasks, and delivering results reliably.

Text1.0M context
MiMo-V2-Flash

MiMo-V2-Flash is an open-source foundation language model developed by Xiaomi. It is a Mixture-of-Experts model with 309B total parameters and 15B active parameters, adopting hybrid attention architecture. MiMo-V2-Flash supports a hybrid-thinking toggle and a 256K context window, and excels at reasoning, coding, and agent scenarios. On SWE-bench Verified and SWE-bench Multilingual, MiMo-V2-Flash ranks as the top #1 open-source model globally, delivering performance comparable to Claude Sonnet 4.5 while costing only about 3.5% as much.

Users can control the reasoning behaviour with the reasoning enabled boolean. Learn more in our docs.

Text262K context