Near-Pro agent scores
Xiaomi's own results put Flash within a few points of Pro on Terminal Bench 2.1, DeepSWE v1.1 and OSWorld-Verified.
Xiaomi
Disrupted· 89.6% uptime, 7 daysMiMo V2.6 Flash API
The MiMo V2.6 Flash API: Xiaomi's low-cost omnimodal model for high-volume work
Price per 1M tokens57%off
- Input
- $0.06
$0.14 - Output
- $0.12
$0.28 - Cached input
- $0.0012
Model ID
mimo-v2.6-flashchat.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-flash", 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
- 89.6%
Pricing
MiMo V2.6 Flash 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 | $0.06 | 57%off | |
Output per 1M tokens | $0.12 | 57%off | |
Cached input per 1M tokens | $0.0012 | — | — |
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
$4.20
Xiaomi list price
$9.80
You save every month$5.60
$67.20 a year
Overview
What is MiMo V2.6 Flash?
MiMo V2.6 Flash is the efficient model in Xiaomi's MiMo-V2.6 series: 15B active parameters, 1M tokens of context, and text, image, audio and video input. The MiMo V2.6 Flash API on zurelay is for teams running high-volume or latency-sensitive workloads who want near-Pro agent results at 57% below Xiaomi's list price.
MiMo V2.6 Flash is the efficient model in Xiaomi's MiMo-V2.6 series, released alongside Pro on September 22, 2026. The MiMo V2.6 Flash API takes text, images, video and audio, returns text, and supports a 1M-token context window with up to 128K output tokens. Xiaomi positions it as the best balance for high-frequency calls and large-scale tasks.
It is a sparse mixture-of-experts model with 309B total parameters and 15B active per token, spread across 48 layers that mix sliding-window and global attention. The small active size keeps it quick and cheap to serve. The weights are open under the MIT license.
Flash was trained the same way as Pro: one mixed reinforcement learning run across coding, general agents, visual tasks and cybersecurity. It stays close to Pro on agent work. Xiaomi reports 87.6 on Terminal Bench 2.1 against Pro's 89.9, 80.8 on OSWorld-Verified against 82.0, and 95.1 on CyberGym, slightly above Pro.
Its list price is about a third of Pro's. On zurelay you call it with any OpenAI SDK using the model ID mimo-v2.6-flash, and pay $0.06 per 1M input tokens and $0.12 per 1M output tokens, against Xiaomi's list price of $0.14 and $0.28.
Strengths
Where MiMo V2.6 Flash shines. And what teams build with it.
Low cost per call
15B active parameters and a list price about a third of Pro's make it practical for high-volume pipelines.
Omnimodal input
Text, images, video and audio fit in one request, the same input range as Pro.
1M-token context
Long documents, repositories and agent traces fit in one prompt, with room for 128K output tokens.
Use cases
High-volume extraction and tagging
Tag, route or pull fields from large streams of text, images or audio at a low cost per call.
Sub-agents
Use Flash for the frequent tool-calling steps in an agent system and keep Pro for planning or final review.
Media processing
Ask questions about audio clips, video and screenshots directly, without a separate transcription or vision step.
Coding helpers
Run code review, test generation and terminal helpers where latency and cost per call matter.
Get started
Call MiMo V2.6 Flash 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-flash
Send chat completions as usual. Streaming, tool calls and usage reporting work as you expect.
mimo-v2.6-flash
Works with the tools you already use
Compare
Similar models. All on the same key.
59%off
MiMo V2.6 Pro
$0.18 / $0.36 per 1M tokens
Pick MiMo V2.6 Pro for the hardest long-horizon tasks, where its higher scores justify about three times the list price.
MiMo V2.6 Pro API88%off
DeepSeek V4.1 Flash
$0.037 / $0.15 per 1M tokens
Pick DeepSeek V4.1 Flash for text and image work when you want up to 384K output tokens per response.
DeepSeek V4.1 Flash API61%off
DeepSeek V4 Flash 0731
$0.022 / $0.06 per 1M tokens
Pick DeepSeek V4 Flash 0731 for text-only agent work on a fixed, dated checkpoint.
DeepSeek V4 Flash 0731 APIFAQ
MiMo V2.6 Flash API questions.
Anything else, write to sales@zurelay.com and an engineer will answer.
How much does the MiMo V2.6 Flash API cost?
On zurelay, MiMo V2.6 Flash costs $0.06 per 1M input tokens and $0.12 per 1M output tokens, with cached input at $0.0012. Xiaomi's list price is $0.14 input and $0.28 output, so you save 57%.
Is there a cheaper Xiaomi MiMo API?
zurelay serves mimo-v2.6-flash at 57% below Xiaomi's list price. You pay as you go for the tokens you use, and credit never expires.
How do I call the MiMo V2.6 Flash API with the OpenAI SDK?
Set the OpenAI SDK's base URL to https://api.zurelay.com/v1, use your zurelay API key and pass model "mimo-v2.6-flash". Tool calls and streaming work the same way they do with OpenAI models.
What is the MiMo V2.6 Flash context window?
MiMo V2.6 Flash has a 1M-token context window and returns up to 128K output tokens per response, the same limits as Pro.
What is MiMo V2.6 Flash best at?
High-frequency and large-scale work: agents that make many calls, extraction and tagging jobs, and media analysis. Xiaomi trained it on coding, general agents, visual tasks and cybersecurity, and it scores close to Pro on Xiaomi's agent benchmarks.
Should I use MiMo V2.6 Flash or MiMo V2.6 Pro?
Both have the same context window, input types and features. Pro has 1.02T total and 42B active parameters and scores a little higher on most of Xiaomi's agent benchmarks. Flash has 309B total and 15B active, costs about a third as much at list price and is the better default for volume.
Is MiMo V2.6 Flash open source?
Yes. Xiaomi released the weights on Hugging Face under the MIT license. You can use the API today and move to self-hosting later on the same model.
Does the MiMo V2.6 Flash 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 Flash model Xiaomi serves?
Yes. Requests go to MiMo V2.6 Flash, never a 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 Pro API$0.18 / $0.36 per 1M tokens−59%
- 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.