Private AI

Nano GPT logo
NanoGPT
Nano GPT logo
NanoGPT
Nano GPT logo
NanoGPT
Search
 
 
 
 
All conversations

Create

Chat
Studio

Explore

Models
Pricing
AI Apps
Blog

Library

Gallery
Workspace
Usage & billing
API
Suggestions and bugs
Use cases

|

Terms

|

Privacy

|

Refunds
Usage & billing
Teams
Referrals
Presets
Settings
FAQPress & mediaBrand assetsBenchmarksNano RPCEarn crypto
  1. All models overview
  2. Text
  3. Xiaomi

MiMo V2.6 Flash

MiMo V2.6 Flash is Xiaomi's native omnimodal 309B-parameter mixture-of-experts model, activating 15B parameters per token. It balances intelligence, efficiency, and cost for coding, general agents, visual tasks, and cybersecurity, with text, image, video, and audio understanding and a 1M-token context window.

  • Reasoning
  • Vision
  • Audio Input
  • Video Input
  • Tool Calling
  • Structured Output

Added Sep 21, 2026

Model weights

Pricing

Auto routing · per 1M tokens
Input
$0.14
Output
$0.28
Cache read
$0.0028
Compare provider prices

Specifications

Context window
1M
Max output
131.1K
Parameters
309B / 15B
Total / active

Benchmarks

Sourced from LMArena.

Arena Score

1447.5

Overall Rank

#92 / 426

Votes

28,828

Confidence Interval

1442.6 - 1452.5

Category Scores

Coding

#66 / 421

6,583 votes

1510.0

Math

#67 / 408

1,403 votes

1463.2

Longer Query

#86 / 404

11,854 votes

1457.4

Creative Writing

#124 / 424

6,147 votes

1393.6

Instruction Following

#95 / 426

9,450 votes

1434.8

Hard Prompts

#90 / 426

17,828 votes

1472.3

Additional Categories
22

Industry Mathematical

#54 / 405

1,555 votes

1478.8

Chinese

#55 / 399

2,222 votes

1506.3

Hard Prompts English

#61 / 424

6,334 votes

1489.0

Expert

#64 / 374

2,545 votes

1490.3

Industry Software And It Services

#66 / 426

10,365 votes

1499.1

English

#71 / 426

10,006 votes

1468.0

Korean

#77 / 289

434 votes

1407.6

Industry Business And Management And Financial Operations

#78 / 419

4,916 votes

1453.5

French

#79 / 305

1,099 votes

1472.4

Spanish

#81 / 307

1,104 votes

1450.7

German

#89 / 321

450 votes

1443.7

Exclude Ties

#94 / 426

21,614 votes

1447.5

Industry Life And Physical And Social Science

#96 / 424

4,452 votes

1462.3

Non English

#102 / 426

18,812 votes

1428.5

Polish

#103 / 243

439 votes

1429.3

Industry Medicine And Healthcare

#105 / 394

1,835 votes

1457.6

Industry Writing And Literature And Language

#105 / 425

8,058 votes

1415.7

Multi Turn

#105 / 424

4,285 votes

1446.3

Industry Entertainment And Sports And Media

#106 / 424

7,092 votes

1406.7

Japanese

#113 / 288

492 votes

1377.8

Industry Legal And Government

#115 / 397

2,257 votes

1441.8

Russian

#126 / 390

4,708 votes

1421.3

Published 2026-11-19 · Matched as MiMo-V2.6-Flash · CC BY 4.0

LMArena Dataset

Providers

Choose or restrict providers with the API. Provider-selection prices include the selection markup. Provider selection guide · Pricing API (JSON, USD per 1K tokens)

Auto
Auto (ZDR)
$0.14$0.28$0.0028N/AN/A
Auto
Auto (Anonymized)
$0.14$0.28$0.0028N/AN/A
Pareto Inference
Pareto Inference
UNK
$0.14$0.28$0.0028N/AN/A
DeepInfra
DeepInfra
FP8
US
$0.147$0.294$0.0029N/AN/A
Inworld
Inworld
US
$0.147$0.294$0.0032N/AN/A
Xiaomi
Xiaomi
FP8
CN
$0.147$0.294$0.0029N/AN/A
Uomi
Uomi
BF16
GLB
$0.176$0.353N/AN/AN/A
Venice
Venice
FP8
US
$0.184$0.367$0.0039N/AN/A
Heabsy
Heabsy
NVFP4
GLB
$0.50$1.50$0.20N/AN/A
Privacy:ZDR, prompts not retainedNo training on prompts
Batch API
ProviderInputOutputCached input
Auto
Autoxiaomi/mimo-v2.6-flash
$0.14/M$0.28/M$0.0028/M

Batch rows for this model use normal routing and cost the same as standard API requests. Set provider in a row to choose a provider.

Related text models

Compare MiMo V2.6 Flash with similar models from the same provider or model family.

MiMo V2.6 Flash Uncensored Thinking

xiaomi/mimo-v2.6-flash-uncensored:thinking

MiMo V2.6 Flash Uncensored with maximum thinking enabled. Supports a 1M-token context window and tool calling.

MiMo V2.6 Flash Abliterated

xiaomi/mimo-v2.6-flash-abliterated

A MiMo V2.6 Flash finetune with refusal-direction ablation, image input, a 1M-token context window, separate reasoning output, and tool calling.

MiMo V2.6 Flash Uncensored

xiaomi/mimo-v2.6-flash-uncensored

A lower-refusal MiMo V2.6 Flash finetune with a 1M-token context window, separate reasoning output, and tool calling. Supports image input and adjustable thinking effort.

MiMo V2.6 Pro

xiaomi/mimo-v2.6-pro

MiMo V2.6 Pro is Xiaomi's flagship native omnimodal model, built with 1.02T total parameters and 42B active parameters per token. It is designed for demanding coding, long-horizon agent workflows, visual tasks, research, and cybersecurity, with text, image, video, and audio understanding and a 1M-token context window.

MiMo V2.6 Pro UltraSpeed

xiaomi/mimo-v2.6-pro-ultraspeed

MiMo V2.6 Pro UltraSpeed is the latency-optimized serving mode for Xiaomi's flagship MiMo V2.6 Pro checkpoint. It preserves Pro-level quality while delivering up to 20x faster output for real-time coding, interactive agents, and other latency-sensitive workflows, with native text, image, video, and audio understanding and a 1M-token context window.

MiMo V2.5 Pro Thinking (Deprecated)

xiaomi/mimo-v2.5-pro:thinking

Deprecated: this is an older version. Please switch to MiMo V2.6 Pro (xiaomi/mimo-v2.6-pro), Xiaomi's current Pro model, which thinks by default. MiMo V2.5 Pro Thinking is MiMo V2.5 Pro with thinking enabled for coding, long-context reasoning, and agentic orchestration.