LLMPrivate

MiMo-V2.5

Xiaomi's open-weight, omnimodal AI with 1M context and strong agentic capabilities — built for developers who want sovereignty and uncensored, private inference.

Get API key

What is MiMo-V2.5?

MiMo-V2.5 is a 310B-parameter sparse Mixture-of-Experts (MoE) model from Xiaomi, released April 2026. It natively processes text, images, video, and audio within a unified architecture, supports up to 1 million tokens of context, and delivers powerful reasoning and tool-use capabilities for agentic workflows.

Use MiMo-V2.5 privately on Venice

On Venice, MiMo-V2.5 runs with zero retention — your prompts are never stored or profiled. This open, MIT-licensed model can be used privately for uncensored, permissionless development, giving you full sovereignty over your AI workflows without Big Tech surveillance.

Private (zero retention)
No prompt training
TEE · hardware enclave
End-to-end encrypted

What can MiMo-V2.5 do?

Strengths
  • Fully open weights under MIT license — ideal for self-hosting, fine-tuning, and commercial deployment without restrictions.
  • Native omnimodal understandingprocesses text, images, video, and audio in a single unified model.
  • 1 million token context window enables ultra-long document reasoning and complex agentic workflows.
  • Supports tool use, web search, and structured JSON output — optimized for autonomous agents and coding tasks.
  • Cost-efficient at $0.14/$0.28 per million tokens (in/out), with cached input as low as $0.05/M.
Limitations
  • Slightly less intelligent than MiMo-V2.5-Pro and closed frontier models like Claude Opus on agentic benchmarks.
  • Not uncensored — content moderation policies apply per Xiaomi's documentation.
  • No end-to-end encryption or TEE execution on Venice, limiting privacy to zero retention only.

MiMo-V2.5 capabilities

How to use MiMo-V2.5 via API

Venice exposes an OpenAI-compatible API. Swap your base URL and call xiaomi-mimo-v2-5.

curl https://api.venice.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $VENICE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "xiaomi-mimo-v2-5",
    "messages": [{ "role": "user", "content": "Explain quantum tunneling simply." }]
  }'

Specifications

MakerXiaomi
ReleasedApril 22, 2026
ArchitectureSparse Mixture-of-Experts (MoE)
Parameters310B total, ~15B active per token
Open weightsYes — MIT license
Context window1,000K tokens
Max output65.536K tokens
CapabilitiesVision, Function calling, Reasoning, Web search, Code-optimized
Privacy on VenicePrivate — zero retention
Available on Venice sinceJun 2026
LicenseMIT

Pricing

Billed per token on Venice: $0.14 per 1M input tokens and $0.28 per 1M output tokens.

Input / 1M tokens
$0.14
Output / 1M tokens
$0.28
Cached input / 1M
$0.05

New Venice accounts include a free daily allowance and 500 welcome credits — no credit card required.

MiMo-V2.5 vs alternatives

ModelMax outputOpen weightsPrice (in/out per 1M)Strongest at
MiMo-V2.565.536KYes$0.14 in · $0.28 out / 1MOmnimodal agents, open deployment
Claude Opus 565.536KNo$6 in · $30 out / 1MHigh-intelligence agentic tasks
DeepSeek V4 Flash 073165.536KNo$0.17 in · $0.35 out / 1MSpeed and coding
Google Gemma 4 31B Instruct65.536KYes$0.12 in · $0.36 out / 1MEfficient small-scale reasoning

Open, MIT-licensed model with native vision, audio, and video support — ideal for private, sovereign AI.

What is MiMo-V2.5 good for?

  • Building autonomous agents that process multimodal inputs and call external tools.
  • Long-context analysis of legal, financial, or technical documents with image and text.
  • Multimodal RAG pipelines using private, cached data with audio and visual content.
  • Cost-sensitive production deployments where open weights and commercial use are required.
  • Developers seeking full control over AI inference without vendor lock-in.

Prompting tips

  • Use structured JSON output for reliable parsing in agent pipelines.
  • Include image, audio, or video inputs directly — the model natively understands them.
  • Leverage web search and function calling for real-time data and actions.
  • Break complex tasks into steps — the 1M context supports deep reasoning chains.

Version history

MiMo-V2-Pro
2025

Predecessor model

MiMo-V2.5
2026-04

CurrentCurrent — omnimodal, 1M context, MIT-licensed

Frequently asked questions

MiMo-V2.5 is a 310B-parameter sparse MoE model from Xiaomi, released in April 2026. It natively supports text, image, audio, and video understanding, with a 1 million token context window and strong agentic capabilities for autonomous workflows.

MiMo-V2.5 is not free, but it is open-weight and commercially usable under the MIT license. On Venice, you pay per token — $0.14 per million input tokens and $0.28 per million output tokens, with lower rates for cached input.

Yes, MiMo-V2.5 is fully open weights under the MIT license, meaning you can inspect, self-host, fine-tune, and deploy it commercially without restrictions.

Yes, MiMo-V2.5 natively supports image, video, and audio input through dedicated encoders, enabling true multimodal reasoning in a single model.

MiMo-V2.5 supports up to 1 million tokens of context, allowing it to process extremely long documents, transcripts, or complex reasoning chains in a single session.

Yes, MiMo-V2.5 supports tool use, web search, and function calling, making it well-suited for building autonomous agents and interactive applications.

MiMo-V2.5 is open and more affordable, with native multimodal support, while Claude Opus 5 has higher reasoning intelligence but is closed, more expensive, and lacks vision. Choose MiMo-V2.5 for sovereignty and multimodal use, Opus for maximum reasoning power.

Yes, on Venice, MiMo-V2.5 runs with zero retention — your prompts are never stored, profiled, or used for training, ensuring private, uncensored, and permissionless AI use.

Run MiMo-V2.5 privately.

No prompt logging. No data used for training. Free to start — no credit card.

Room