XiaomiMultimodalReleased 22 April 2026
MiMo-V2.5 pricing, context and benchmark
MiMo-V2.5 is a native omnimodal model by Xiaomi.
1M
Input context
66K
Output context
$0.4
Official input
$2
Official output
n/a
AA index
01 · Model Overview
Everything that matters, in one table
Context, pricing, cache, modalities and tooling, from the model registry and Artificial Analysis.
| Model | MiMo-V2.5 |
| Model ID | xiaomi/mimo-v2.5 |
| Provider | Xiaomi |
| Release date | 22 April 2026 |
| Status | Generally available |
| Input context | 1,000,000 tokens |
| Output context | 65,536 tokens |
| Official input pricing | $0.4 per 1M tokens |
| Official output pricing | $2 per 1M tokens |
| Cache read pricing | Not published |
| Market input pricing | $0.4 per 1M (cheapest route) |
| Market output pricing | $2 per 1M (cheapest route) |
| Input modalities | text · audio · image · video |
| Output modalities | text |
| Reasoning control | Not exposed |
| Tool support | Text generation only |
| Tokenizer | Other |
| Provider routes | 1 endpoint |
| Artificial Analysis index | Not published |
| Speed | Not published |
| Knowledge cutoff | Not publicly stated |
Input and output support
| Modality | Input | Output | Billed at |
|---|---|---|---|
| Text | ✓ yes | ✓ yes | $0.4 in |
| Image | ✓ yes | no | $0.4 in |
| Audio | ✓ yes | no | $0.4 in |
| Video | ✓ yes | no | $0.4 in |
| File (PDF) | no | no | not supported |
02 · Overview
What is MiMo-V2.5?
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...
MiMo-V2.5 carries a 1M token window, uses the Other tokenizer and is served by Xiaomi. On Hoodgen it sits in the Multimodal tier of the model menu next to its siblings, so you can switch mid conversation without losing the thread.
03 · Release
Release and what changed from the previous version
Released22 April 2026
This is the only release of MiMo-V2.5 on OpenRouter, released 22 April 2026. The provider has not published a knowledge cutoff, so treat training data as recent but unconfirmed for very new events.
04 · Capabilities
Features and capabilities
◉
Vision
Screenshots, charts and photographed documents are read at the text token rate.
♪
Audio and video
Calls, meetings and screen recordings can be summarised in one pass.
07 · Use cases
What can you do with MiMo-V2.5?
Document understanding
Screenshots, charts, scanned pages and PDFs read in the prompt.
Mixed media briefs
One thread holding text, images and files together.
Extraction
Schema constrained JSON out of messy inputs.
Research synthesis
Several sources condensed with the figures preserved.
09 · Pricing
MiMo-V2.5 pricing
Official pricing
List price
$0.4 / 1M in
$2 / 1M out
- 1M context
- text, audio, image, video input
Cheapest route
$0.4 / 1M in
$2 / 1M out
- 1 route on OpenRouter
- What Hoodgen routes to first
- Same model, lower bill
Market pricing, every route
| Provider | Tier | Input | Output | Cache read | Uptime 24h |
|---|---|---|---|---|---|
| Venice | standard | $0.4 | $2 | $0.08 | 99.8% |
API pricing and cost calculator
| Rate | Per call | Total | Credits |
|---|---|---|---|
| Cheapest route | $0.0072 | $3.58 | 3401 |
| List price | $0.0110 | $5.50 | 5225 |
10 · Developers
API and developer information
| Model ID | xiaomi/mimo-v2.5 |
| Endpoint | https://openrouter.ai/api/v1/chat/completions |
| Parameters | prompt and max_tokens |
| Streaming | Yes, server sent events |
| Modality string | text+image+audio+video->text |
| Max prompt tokens | 1,000,000 |
| Max completion tokens | 65,536 |
curl https://openrouter.ai/api/v1/chat/completions \
-H "Authorization: Bearer $OPENROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "xiaomi/mimo-v2.5",
"messages": [{ "role": "user", "content": "Summarise this document." }],
"max_tokens": 1024
}'11 · Limitations
Model limitations
| Text only output | It cannot generate images, audio or video. Pair it with an image model on Hoodgen when you need visuals. |
| Output cap | 65,536 tokens per request. Long deliverables have to be chunked. |
| Benchmarks not published | Artificial Analysis does not publish an Intelligence Index for this release, so no benchmark score is claimed here. |
| Knowledge cutoff | The provider does not state a fixed cutoff for every release. Verify very recent events against search. |
12 · Comparison
MiMo-V2.5 vs other Xiaomi models
| Model | Context | Input /1M | Output /1M | AA index | Released |
|---|---|---|---|---|---|
| MiMo-V2.5 | 1M | $0.4 | $2 | n/a | 2026 |
| MiMo-V2.6-Pro-UltraSpeed | 1.05M | $4.35 | $8.7 | n/a | Sep 2026 |
| MiMo-V2.5-Pro | 1.02M | $0.435 | $0.87 | n/a | 2026 |
| MiMo-V2.6-Pro | 1.05M | $0.326 | $0.652 | 30 | Sep 2026 |
| MiMo-V2.6-Flash | 1.05M | $0.1 | $0.28 | 27 | Sep 2026 |
13 · Privacy
Privacy and data policy
- On Hoodgen, prompts and attachments answer that request and stay in your conversation history so you can reopen it. They are not used to train models.
- Requests route through OpenRouter to Xiaomi and are covered by that provider's API terms.
- Do not paste secrets or personal data you would not send to any hosted model.
14 · FAQ
MiMo-V2.5 questions, answered
MiMo-V2.5 is a multimodal model from Xiaomi, released 22 April 2026. MiMo-V2.5 is a native omnimodal model by Xiaomi.
✦
Start chatting with MiMo-V2.5
Free to try on Hoodgen AI, with a live credit estimate before every send. No API key, no setup.