One model for every input
Text, images, video and audio go into the same model and the same prompt. There is no separate vision or speech service to wire up.
Xiaomi
Disrupted· 80.0% uptime, 7 daysMiMo V2.6 Pro API
The Xiaomi MiMo V2.6 Pro API: 1M context, omnimodal input, open weights
Price per 1M tokens59%off
- Input
- $0.18
$0.435 - Output
- $0.36
$0.87 - Cached input
- $0.001494
Model ID
mimo-v2.6-prochat.py
from openai import OpenAIclient = OpenAI( base_url="https://api.zurelay.com/v1", api_key="YOUR_ZURELAY_KEY",)stream = client.chat.completions.create( model="mimo-v2.6-pro", messages=[{"role": "user", "content": "Explain quicksort in two sentences."}], stream=True,)for chunk in stream: if chunk.choices: print(chunk.choices[0].delta.content or "", end="")Base URL https://api.zurelay.com/v1. Works with any OpenAI SDK.
- Context window
- 1M tokens
- Max output
- 128K tokens
- Input
- Text, Image, Video, Audio
- Output
- Text
- Released
- Sep 22, 2026
- Uptime, 7 days
- 80.0%
Pricing
MiMo V2.6 Pro API pricing. A fraction of the list price.
Pay as you go from prepaid credit, with no subscription and no minimum. Requests that fail are never billed.
| Rate | zurelay | Xiaomi list | You save |
|---|---|---|---|
Input per 1M tokens | $0.18 | 59%off | |
Output per 1M tokens | $0.36 | 59%off | |
Cached input per 1M tokens | $0.001494 | — | — |
One rate at every prompt length, up to the full 1M context window. Streaming, tool calls and structured outputs cost nothing extra.
Savings calculator
Move the sliders to your monthly usage.
Input tokens per month50M
Output tokens per month10M
zurelay
$12.60
Xiaomi list price
$30.45
You save every month$17.85
$214.20 a year
Overview
What is MiMo V2.6 Pro?
MiMo V2.6 Pro is Xiaomi's open-weight flagship, a 1.02-trillion-parameter model that reads text, images, audio and video and holds 1M tokens of context. The MiMo V2.6 Pro API on zurelay suits teams building agents, coding tools and multimodal apps who want Xiaomi's strongest model at 59% below its list price.
MiMo V2.6 Pro is the flagship of Xiaomi's MiMo-V2.6 series, released on September 22, 2026. Through the MiMo V2.6 Pro API you send text, images, video and audio in one request and get text back, with a 1M-token context window and up to 128K output tokens. Xiaomi built it for complex projects, long-horizon tasks, cybersecurity and research.
It is a sparse mixture-of-experts model with 1.02 trillion total parameters and 42 billion active per token. The vision and audio encoders are part of the model, not separate services, so one model handles every input type. A built-in speculative decoding drafter speeds up generation. The weights are open under the MIT license.
Xiaomi trained V2.6 with one mixed reinforcement learning run across coding, general agents, visual tasks and cybersecurity, rather than a separate run per domain. On its model card Xiaomi reports 89.9 on Terminal Bench 2.1, 71.9 on DeepSWE v1.1 and 82.0 on OSWorld-Verified. Xiaomi also cites a score of 46.32 on the Artificial Analysis Intelligence Index and calls it the strongest open-source model at release.
The model supports tool calling, structured output and a thinking mode you can turn on or off per request. On zurelay you reach it with the OpenAI SDK at https://api.zurelay.com/v1 using the model ID mimo-v2.6-pro. You pay $0.18 per 1M input tokens and $0.36 per 1M output tokens, against Xiaomi's list price of $0.435 and $0.87.
Strengths
Where MiMo V2.6 Pro shines. And what teams build with it.
Built for agents
Xiaomi reports 89.9 on Terminal Bench 2.1 and 82.0 on OSWorld-Verified, which cover terminal work and computer use.
Long context
Xiaomi sized the 1M-token window for long repositories, tool traces and multi-session agent runs.
Open weights under MIT
The weights are public, so you can build on the API now and self-host later without switching models.
Use cases
Coding agents
Run repository-scale edits, terminal tasks and test loops with the whole codebase in context.
Computer-use and visual agents
Give agents screenshots and screen recordings so they can operate software and check results visually.
Security research
Xiaomi lists cybersecurity as a target workload and reports 94.0 on CyberGym.
Meeting and media analysis
Summarize or search across audio, video and slides in one request instead of chaining transcription and vision models.
Get started
Call MiMo V2.6 Pro in three steps.
No waitlist and no new SDK. If your code already talks to OpenAI, it already talks to zurelay.
- 1
Create a key
Sign up, add credit and create an API key. Set a monthly budget or a rate limit per key if you like.
- 2
Point your SDK at zurelay
Change the base URL. Everything else in your code stays the same.
https://api.zurelay.com/v1 - 3
Use mimo-v2.6-pro
Send chat completions as usual. Streaming, tool calls and usage reporting work as you expect.
mimo-v2.6-pro
Works with the tools you already use
Compare
Similar models. All on the same key.
57%off
MiMo V2.6 Flash
$0.06 / $0.12 per 1M tokens
Pick MiMo V2.6 Flash for high-volume calls: the same context and inputs, close agent scores, about a third of the list price.
MiMo V2.6 Flash API84%off
DeepSeek V4 Pro 0813
$0.23 / $0.62 per 1M tokens
Pick DeepSeek V4 Pro 0813 when your inputs are text only and you want up to 384K output tokens per response.
DeepSeek V4 Pro 0813 API65%off
Grok 4.7
$0.70 / $2.10 per 1M tokens
Pick Grok 4.7 when you want xAI's model for long coding and knowledge work, with fine control over reasoning effort.
Grok 4.7 APIFAQ
MiMo V2.6 Pro API questions.
Anything else, write to sales@zurelay.com and an engineer will answer.
How much does the MiMo V2.6 Pro API cost?
On zurelay, MiMo V2.6 Pro costs $0.18 per 1M input tokens and $0.36 per 1M output tokens, with cached input at $0.001494. Xiaomi's list price is $0.435 input and $0.87 output, so you save 59%.
Is there a cheaper Xiaomi MiMo API?
zurelay serves mimo-v2.6-pro at 59% below Xiaomi's list price. You pay as you go, and credit never expires. For a lower cost per token, MiMo V2.6 Flash is available on the same API key.
How do I call the MiMo V2.6 Pro API with the OpenAI SDK?
Point the OpenAI SDK at https://api.zurelay.com/v1 with your zurelay API key and set model to "mimo-v2.6-pro". Chat Completions requests, tool definitions and streaming work the way they do with OpenAI models.
What is the MiMo V2.6 Pro context window?
MiMo V2.6 Pro has a 1M-token context window and returns up to 128K output tokens per response.
What is MiMo V2.6 Pro best at?
Xiaomi built it for complex projects, long-horizon agent tasks, coding, cybersecurity and research. It is also a good fit when your inputs mix documents, images, audio and video, because one model reads all of them.
Does MiMo V2.6 Pro accept images, audio and video?
Yes. It takes text, images, video and audio as input and returns text. It does not generate images or speech.
Is MiMo V2.6 Pro open source?
Yes. Xiaomi published the weights on Hugging Face under the MIT license. It is a mixture-of-experts model with 1.02T total parameters and 42B active per token, so self-hosting takes a multi-GPU setup. The API is the quick way to use it.
Does the MiMo V2.6 Pro API support streaming and per-key rate limits?
Streaming works with stream: true, as with the OpenAI API. You can set a requests-per-minute cap and a monthly budget on each zurelay API key.
Is it the same MiMo V2.6 Pro model Xiaomi serves?
Yes. Requests go to MiMo V2.6 Pro, never a smaller or substitute model. Responses are sampled, so wording varies between runs, as it does on Xiaomi's own platform. zurelay is independent and not affiliated with Xiaomi.
More models on zurelay
All models- Claude Opus 5.5 API$1.40 / $7.00 per 1M tokens−65%
- GPT-6 Astra API$2.50 / $12.50 per 1M tokens−75%
- Nano Banana Pro APIfrom $0.035 per image−74%
- Nano Banana 2 APIfrom $0.025 per image−63%
- Claude Sonnet 5.5 API$0.80 / $4.00 per 1M tokens−60%
- GPT-6.1 Sol API$0.50 / $2.50 per 1M tokens−75%
- GPT-6 Sol API$0.50 / $2.50 per 1M tokens−75%
- GPT-6 Luna API$0.025 / $0.125 per 1M tokens−75%
- Grok 4.7 API$0.70 / $2.10 per 1M tokens−65%
- MiMo V2.6 Flash API$0.06 / $0.12 per 1M tokens−57%
- DeepSeek V4.1 Flash API$0.037 / $0.15 per 1M tokens−88%
- DeepSeek V4 Flash API$0.045 / $0.18 per 1M tokens−85%
- DeepSeek V4 Flash 0731 API$0.022 / $0.06 per 1M tokens−61%
- DeepSeek V4 Pro 0813 API$0.23 / $0.62 per 1M tokens−84%
- Claude Fable 5.1 API$3.50 / $17.50 per 1M tokens−65%
- Claude Fable 5 API$3.50 / $17.50 per 1M tokens−65%
- Claude Opus 5 API$1.75 / $8.75 per 1M tokens−65%
- Claude Opus 4.8 API$1.75 / $8.75 per 1M tokens−65%
- Claude Opus 4.7 API$1.78 / $8.93 per 1M tokens−64%
- Claude Opus 4.6 API$1.75 / $8.75 per 1M tokens−65%
- Claude Haiku 4.5 API$0.38 / $1.90 per 1M tokens−62%
- GPT-5.6 Sol API$1.14 / $5.70 per 1M tokens−72%
- GPT-5.6 Terra API$0.54 / $3.26 per 1M tokens−73%
- GPT-5.6 Luna API$0.08 / $0.49 per 1M tokens−59%
- Gemini 3.7 Flash API$0.32 / $1.59 per 1M tokens−58%
- Gemini 3.5 Flash-Lite API$0.12 / $1.04 per 1M tokens−58%
- Gemini 3.1 Flash-Lite API$0.10 / $0.59 per 1M tokens−61%
- GLM-5.3 API$0.38 / $1.21 per 1M tokens−73%
- GLM-5.2 API$0.38 / $1.21 per 1M tokens−73%
- Kimi K3 API$1.27 / $6.37 per 1M tokens−58%
- Qwen 3.8 Max API$1.20 / $3.60 per 1M tokens−40%
- Qwen 3.8 Flash API$0.07 / $0.22 per 1M tokens−53%
- Qwen 3.8 Omni Flash API$0.075 / $0.235 per 1M tokens−50%
- HY4 Preview API$0.40 / $1.20 per 1M tokens−52%
- MiniMax M2.7 API$0.13 / $0.51 per 1M tokens−57%
- GPT Image 2.5 Flare API$0.02 per image−62%
- GPT Image 2.5 Sunburst API$0.02 per image−62%
- GPT Image 2 API$0.02 per image−62%
- Seedance 2.5 APIfrom $0.14 per secondVideo
- Seedance 2.0 APIfrom $0.097 per secondVideo
- Seedance 2.0 Fast APIfrom $0.074 per secondVideo
- Seedance 2.0 Mini APIfrom $0.047 per secondVideo
Stop paying list price.
Start saving today.
Create a key in seconds, point the SDK you already use at zurelay, and every request costs up to 85% less from the first token.