Roar AI
Get started
All models
Xiaomi · Open weights

MiMo-V2.5 API in Singapore

Xiaomi’s open model that reads, looks and listens — text, images, audio and video. Priced in Singapore dollars for teams in Singapore, on the same key as every other model.

InputS$0.2366per 1M tokens
OutputS$0.4732per 1M tokens
BillingOne bill, in SGDwith every other model

MiMo-V2.5 API pricing in Singapore

InputS$0.2366 per 1M tokens · $0.182
OutputS$0.4732 per 1M tokens · $0.364
Cached inputS$0.0047 per 1M tokens · $0.0036

In Singapore dollars, the currency your card is charged in, with the published US dollar rate beside each.

For scale: 1,000 requests of about 3,000 tokens in and 1,000 out cost S$1.18 — 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.

Prices are our published US dollar rates converted at S$1.30 to the dollar, our rate for October — the same rate your card is charged.

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.

What is MiMo-V2.5 good for?

  • 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.

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
Processed inGlobal
Model idmimo-v2.5

Using MiMo-V2.5 from Singapore

Roar AI provides access to MiMo-V2.5 through the Roar AI gateway, charged in Singapore dollars on one bill with every other model. Requests from Singapore go through our gateway in Singapore. Developers can use MiMo-V2.5 alongside other supported models without a separate integration for every provider.

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."}],
)

Where is MiMo-V2.5 processed?

Requests to MiMo-V2.5 are processed on international infrastructure, outside Singapore. The model directory says where each model is processed.

Questions

How much does MiMo-V2.5 cost in Singapore?

Input is S$0.2366 per 1M tokens; output is S$0.4732 per 1M tokens. For scale, 1,000 requests of about 3,000 tokens in and 1,000 out cost S$1.18. Prices are our published US dollar rates converted at S$1.30 to the dollar, our rate for October — the same rate your card is charged. The rate is published and does not change from one request to the next.

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.

Try MiMo-V2.5
on one key

Sign up, get a key and call it with the SDK you already use. Pay in your local currency, on one bill.