Roar AI
DocsRequest access
All models
Xiaomi · Open weights

MiMo-V2.5

Xiaomi’s open model that reads, looks and listens — text, images, audio and video.

Input$0.182per 1M tokens
Output$0.364per 1M tokens
BillingOne invoice, in LKRwith every other model
Request early accessSee every model’s rate

About MiMo-V2.5

MiMo-V2.5 is one of the few open-weight models that understands audio and video as well as text and images, using encoders Xiaomi built itself. It is a 310-billion-parameter mixture of experts with 15 billion active per token and a million-token context, released under MIT in April 2026.

Xiaomi reports 56.1% on SWE-bench Pro and 65.8% on Terminal-Bench 2, respectable for its cost. Its weak spot is putting those senses to work: on agent tasks that need it to act on images or video, it scores far lower.

Where it’s strong

Analysing recordings, video and images together with text.

Coding agents on a budget.

Media and document analysis.

Where to be careful

Weak at multimodal agent tasks: 23.8% on Xiaomi’s own Claw-Eval Multimodal.

Xiaomi has not said how its reasoning can be controlled.

Its scores are Xiaomi’s own.

Price in rupees

Input$0.182 per 1M tokens
Output$0.364 per 1M tokens
Cached input$0.0036 per 1M tokens

For scale: 1,000 requests of about 3,000 tokens in and 1,000 out cost $0.91 — a long prompt and a page of answer each. Every rate is published and stays the same from one request to the next. See every model.

Specs

Made byXiaomi
ReleasedApril 2026
TypeChat
Context window1M tokens
ReadsText, Images, Audio, Video
Thinks before answeringNot stated by the maker
WeightsOpen (MIT)
Size310B total, 15B active
Model idmimo-v2.5

Using it from Sri Lanka

MiMo-V2.5 is billed in rupees, on the same monthly invoice as every other model your team uses — no foreign card, no separate Xiaomi account, and one key for all of it.

Prompts sent to MiMo-V2.5 are processed outside Sri Lanka. If a workload has to stay in the country, Qwen3.8-27B (Colombo) runs on our own servers in Colombo.

Call it

Use the OpenAI SDK you already have — point it at Roar AI and name the model. Read the docs.

from openai import OpenAI

client = OpenAI(base_url="https://api.roar-ai.com/v1", api_key="roar_live_…")

reply = client.chat.completions.create(
    model="mimo-v2.5",
    messages=[{"role": "user", "content": "Summarise this contract in plain English."}],
)

Questions

How much does MiMo-V2.5 cost in Sri Lanka?

Input is $0.182 per 1M tokens; output is $0.364 per 1M tokens. For scale, 1,000 requests of about 3,000 tokens in and 1,000 out cost $0.91. The rate is published and does not change from one request to the next.

Can I pay for MiMo-V2.5 in Sri Lankan rupees?

Yes. Usage is billed to one monthly invoice in rupees, together with every other model your team uses, and you can also pay by card. There is no separate Xiaomi account to open and no foreign card needed.

Does MiMo-V2.5 keep data in Sri Lanka?

No — prompts sent to MiMo-V2.5 are processed outside Sri Lanka. If your data has to stay in the country, use Qwen3.8-27B (Colombo), which runs on our servers in Colombo.

Is MiMo-V2.5 open source?

Its weights are open under the MIT licence, so you could run it yourself. Through Roar AI you call it like any other model, with no servers to manage.