LLM Reference

Xiaomi MiMo-V2.5-Pro

Released
2026-04-22
Last refreshed
2026-05-26
Status
Researched 12d ago
ProprietaryCommercial use with conditionsCodingRAGAgentsLong contextClassificationJSON / Tool useCodingAgentLong Context

Xiaomi MiMo-V2.5-Pro is worth evaluating for coding, rag, and agents when its provider route and context window match the workload.

Use it for

  • Teams evaluating coding, rag, and agents
  • Workloads that can use a 1.05m context window
  • Buyers comparing 3 tracked provider routes

Do not use it for

  • Vision or document-understanding workloads
Specifications
Family
MiMo
Released
2026-04-22
Context
1.05m
Parameters
1T
Architecture
Mixture of Experts
Specialization
code
Openness
Proprietary
License
ProprietaryCommercial use with conditions
Training
pretrained
Created by

Consumer electronics and AI research.

Beijing, China
Founded 2010
Website
Pricing
Output / 1M
$0.870
Input / 1M
$0.435

Cheapest of 3 routes · OpenRouter

About

Xiaomi's April 22, 2026 public-beta flagship in the MiMo-V2.5 series. The official Xiaomi MiMo page describes MiMo-V2.5-Pro as its most capable model to date, focused on general agentic capability, complex software engineering, long-horizon tasks, and ultra-long-context instruction following. OpenRouter lists it as text-to-text with 1,048,576 token context, 131,072 max completion tokens, reasoning controls, tool use, and response_format support. Xiaomi says the V2.5 series will be open-sourced soon, but no public weights/license were verified at research time.

Xiaomi MiMo-V2.5-Pro is a proprietary model in the MiMo family. The structured metadata tracks a 1.05m-token context window, function calling, tool use, and structured outputs. This page tracks provider routes through OpenRouter, Xiaomi, and Novita AI, with the cheapest tracked route listed at $0.435 input and $0.87 output per 1M tokens. Headline tracked benchmarks include Massive Multitask Language Understanding 89.4, MMLU PRO 68.5, and Google-Proof Q&A 66.7.

Top use-case fit: coding, agents, and build tasks

Coding

Q/$ C

1 relevant benchmark in the decision map.

RAG

Included by capability and metadata signals in the decision map.

Agents

Q/$ A

1 relevant benchmark in the decision map.

Provider price ladder

Compare all 3

Compare API pricing across 3 providers for input and output tokens, batch, and cached reads when available.

ProviderInput / 1MOutput / 1MCacheRoute
OpenRouter$0.435$0.870-
Serverless
Xiaomi$0.435$0.870read $0.0036
Serverless
Novita AI$2.00$6.00read $0.400
Serverless

Capabilities

Function CallingTool UseStructured Outputs

Benchmark peer barsfor Coding

Benchmark scores(4)

Scores are benchmark-specific and are direction-aware: the same numeric gap can mean very different outcomes across suites. Use the leaderboard context and this model's provider route to decide whether the winning margin is meaningful for your workload.
BenchmarkScoreVersionSource
Massive Multitask Language Understanding89.4https://huggingface.co/XiaomiMiMo/MiMo-V2.5-Pro
MMLU PRO68.5https://huggingface.co/XiaomiMiMo/MiMo-V2.5-Pro
Google-Proof Q&A66.7diamondhttps://huggingface.co/XiaomiMiMo/MiMo-V2.5-Pro
SWE-bench Verified78.9SWE-Bench Verified (Resolved)https://huggingface.co/XiaomiMiMo/MiMo-V2.5-Pro

Migration checks

No linked migration route is available for this model yet.

API versions

mimo-v2.5-pro
Show all 52 popular comparisonssorted by 7-day search impressions
Xiaomi MiMo-V2.5-Pro vs Claude 3.7 Sonnet34Xiaomi MiMo-V2.5-Pro vs Llama Guard 2 8B32Xiaomi MiMo-V2.5-Pro vs Qwen3.5-9B30Xiaomi MiMo-V2.5-Pro vs Claude Haiku 4.530Xiaomi MiMo-V2.5-Pro vs Gemma 7B Instruct27Xiaomi MiMo-V2.5-Pro vs GPT-126Xiaomi MiMo-V2.5-Pro vs Mistral Small 322Xiaomi MiMo-V2.5-Pro vs Mistral 7B v0.121Xiaomi MiMo-V2.5-Pro vs GPT-420Xiaomi MiMo-V2.5-Pro vs Gemini 3.1 Pro Preview Custom Tools20Xiaomi MiMo-V2.5-Pro vs Nemotron Mini 4B Instruct19Xiaomi MiMo-V2.5-Pro vs Llama Guard 7B18Xiaomi MiMo-V2.5-Pro vs ShieldGemma 9B17Xiaomi MiMo-V2.5-Pro vs GPT-2 Medium15Xiaomi MiMo-V2.5-Pro vs Claude Instant 1.115Xiaomi MiMo-V2.5-Pro vs Mistral Nemotron13Xiaomi MiMo-V2.5-Pro vs GPT-212Xiaomi MiMo-V2.5-Pro vs Phi-4 Mini Flash Reasoning12Xiaomi MiMo-V2.5-Pro vs Llama 3.3 Nemotron Super 49B v112Xiaomi MiMo-V2.5-Pro vs Mistral Large 3 675B Instruct11Xiaomi MiMo-V2.5-Pro vs Mistral Medium 3 Instruct10Xiaomi MiMo-V2.5-Pro vs Together AI - Llama 3 8B Lite9Xiaomi MiMo-V2.5-Pro vs Sarvam-M Multilingual Hybrid9Xiaomi MiMo-V2.5-Pro vs Dracarys Llama 3.1 70B Instruct7Xiaomi MiMo-V2.5-Pro vs Llama 3.1 Nemotron Nano VL 8B v17Xiaomi MiMo-V2.5-Pro vs Magistral Small 25067Xiaomi MiMo-V2.5-Pro vs Together AI Qwen2-7B-Instruct7Xiaomi MiMo-V2.5-Pro vs Bielik 11B v2.6 Instruct6Xiaomi MiMo-V2.5-Pro vs Nemotron Mini Hindi 4B Instruct6Xiaomi MiMo-V2.5-Pro vs Phi-4 Reasoning Vision 15B5Xiaomi MiMo-V2.5-Pro vs Llama 3 Swallow 70B Instruct5Xiaomi MiMo-V2.5-Pro vs Llama 3.1 NemoGuard 8B Topic Control4Xiaomi MiMo-V2.5-Pro vs Qwen2-7B-Instruct4Xiaomi MiMo-V2.5-Pro vs Together AI Qwen2-72B-Instruct4Xiaomi MiMo-V2.5-Pro vs Llama 3.1 Nemotron Nano 4B v1.14Xiaomi MiMo-V2.5-Pro vs Llama 3.1 Nemotron 70B Reward4Xiaomi MiMo-V2.5-Pro vs Falcon 3 7B Instruct3Xiaomi MiMo-V2.5-Pro vs Llama 3.1 Swallow 8B Instruct3Xiaomi MiMo-V2.5-Pro vs Teuken 7B Instruct3Xiaomi MiMo-V2.5-Pro vs Colosseum 355B Instruct2Xiaomi MiMo-V2.5-Pro vs GPT-4 Turbo Preview2Xiaomi MiMo-V2.5-Pro vs Llama 3.1 NemoGuard 8B Content Safety2Xiaomi MiMo-V2.5-Pro vs Seed-OSS 36B Instruct2Xiaomi MiMo-V2.5-Pro vs Mistral Large 22Xiaomi MiMo-V2.5-Pro vs Sarvam 30B2Xiaomi MiMo-V2.5-Pro vs Aquila 2 34B2Xiaomi MiMo-V2.5-Pro vs Llama 3 Taiwan 70B Instruct1Xiaomi MiMo-V2.5-Pro vs text-davinci1Xiaomi MiMo-V2.5-Pro vs Marin 8B Instruct1Xiaomi MiMo-V2.5-Pro vs Aquila 2 7B1Xiaomi MiMo-V2.5-Pro vs Stockmark 2 100B Instruct1Xiaomi MiMo-V2.5-Pro vs Italia 10B Instruct1