MiMo-V2.5
XiaomiReleased Apr 22, 2026
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...
- Context window
- 1.0M tokens
- Input
- text, audio, image, video
- Output
- text
- Tokenizer
- Other
- Released
- Apr 22, 2026
- Reasoning
- optional
Pricing
Per 1M tokens. The provider price and our flat 3% fee are separate columns — what you pay is their sum.
| Per 1M tokens | Provider | + 3% fee | You pay |
|---|---|---|---|
| Input | $0.105 | $0.0031 | $0.108 |
| Output | $0.280 | $0.0084 | $0.288 |
Benchmarks
Design Arena
| Category | Elo | Win rate | Rank |
|---|---|---|---|
| 3Dmodels | 1299 | 54.3% | #18 |
| ASCII artmodels | 1195 | 48.3% | #25 |
| Codemodels | 1303 | 55% | #14 |
| Data vizmodels | 1280 | 53.8% | #16 |
| Game devmodels | 1299 | 55.8% | #16 |
| SVGmodels | 1219 | 52.3% | #21 |
| UI componentsmodels | 1312 | 56.1% | #12 |
| Websitesmodels | 1303 | 55.2% | #12 |
Head-to-head preference voting. How we filter and rank
Supported parameters
- frequency_penalty
- include_reasoning
- logit_bias
- logprobs
- max_tokens
- min_p
- presence_penalty
- reasoning
- repetition_penalty
- response_format
- seed
- stop
- structured_outputs
- temperature
- tool_choice
- tools
- top_k
- top_logprobs
- top_p
Call it
OpenAI-compatible: point your SDK at api.openkey.ai/v1 and use model xiaomi/mimo-v2.5.
curl https://api.openkey.ai/v1/chat/completions \
-H "Authorization: Bearer $OPENKEY_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "xiaomi/mimo-v2.5",
"messages": [{"role": "user", "content": "Hello"}]
}'import os
from openai import OpenAI
client = OpenAI(
base_url="https://api.openkey.ai/v1",
api_key=os.environ["OPENKEY_API_KEY"],
)
completion = client.chat.completions.create(
model="xiaomi/mimo-v2.5",
messages=[{"role": "user", "content": "Hello"}],
)
print(completion.choices[0].message.content)import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://api.openkey.ai/v1",
apiKey: process.env.OPENKEY_API_KEY,
});
const completion = await client.chat.completions.create({
model: "xiaomi/mimo-v2.5",
messages: [{ role: "user", content: "Hello" }],
});
console.log(completion.choices[0].message.content);Questions
- How much does MiMo-V2.5 cost via API?
- Through OpenKey, MiMo-V2.5 costs $0.108 per 1M input tokens and $0.288 per 1M output tokens. That is the provider price ($0.105 / $0.280) plus a flat 3% fee — nothing else.
- What is MiMo-V2.5's context window?
- MiMo-V2.5 accepts up to 1.0M tokens of context.
- Is MiMo-V2.5 OpenAI-compatible?
- Yes. Send requests to OpenKey's /v1/chat/completions endpoint with model "xiaomi/mimo-v2.5" using any OpenAI SDK — only the base URL and API key change.
- What inputs does MiMo-V2.5 support?
- MiMo-V2.5 accepts text, audio, image, video input and produces text output.