xiaomiReleased Sep 21, 2026

Xiaomi: MiMo-V2.6-Pro

MiMo-V2.6-Pro is the flagship foundation model developed by Xiaomi. Built at a scale of over 1T parameters, it is designed to push the ceiling of capability for the most demanding...

Context window1.1M
Max output131.1K
Provider endpoints6
Benchmark results19
Measured performance

Benchmark results

All leaderboards ↗
1,514.66

Effort not specified

Independent result
1,684.34

Effort not specified

Independent result
AutomationBench-AA ↗AA Index 4.3.2 collection
58.62%

Effort not specified

Independent result
SciCode ↗AA Index 4.3.2 collection
60.88%AA · Under review

Effort not specified

Independent result
GDP.pdf ↗AA Index 4.3.2 collection
19.2%

Effort not specified

Independent result
CritPt ↗AA Index 4.3.2 collection
26.57%AA · Under review

Effort not specified

Independent result
AA-Omniscience ↗AA Index 4.3.2 collection
8.38

Effort not specified

Independent result
86.33%

Effort not specified

Independent result
LiveBench Overall ↗2.0 · 2026-10-14 (dataset 2026-09-02)
74.87%

Effort: high · single run · equal mean of 7 suites

Independent result
LiveBench Design ↗2.0 · 2026-10-14 (dataset 2026-09-02)
78.5%

Effort: high · single run

Independent result
LiveBench Research ↗2.0 · 2026-10-14 (dataset 2026-09-02)
76.7%

Effort: high · single run

Independent result
LiveBench Browser Use ↗2.0 · 2026-10-14 (dataset 2026-09-02)
88%

Effort: high · single run

Independent result
LiveBench Coding ↗2.0 · 2026-10-14 (dataset 2026-09-02)
81.5%

Effort: high · single run

Independent result
LiveBench Agentic ↗2.0 · 2026-10-14 (dataset 2026-09-02)
47.5%

Effort: high · single run

Independent result
LiveBench Reasoning ↗2.0 · 2026-10-14 (dataset 2026-09-02)
79.6%

Effort: high · single run

Independent result
Provider measurements

Speed

1 configuration
≈10K input tokens1 requestmedian / 72h

Artificial Analysis · first-party providers · serving endpoint not reported

Xiaomi

MiMo-V2.6-Pro

Reasoning Not reported

Output rate
48.0431 tok/s
Time to first chunk
4.26139 s
Last checked Source ↗
Methodology 2.2.0 & measurement details

First chunk includes request processing and network time, and may include reasoning.

Prompt
long · ≈10,000 input tokens
Parallel requests
1
Minimum answer
1,500 tokens
Aggregation
median over 72 hours
Token counting
o200k_base
Benchmark client
Google Cloud us-central1-a
Serving endpoint
Not reported
Serving region
Not reported
Sample size
Not reported
Window end
Not reported
Access & cost

Prices across providers

6 quotes

Your token mix

USD · listed token rates

DeepInfra · via OpenRouterdeepinfra/fp8 · quantization=fp8
$0.6475
Novita · via OpenRouternovita/fp8 · quantization=fp8
$0.6525
GMICloud · via OpenRoutergmicloud/bf16 · quantization=bf16
$0.6525
Xiaomi · via OpenRouterxiaomi/fp8 · quantization=fp8
$0.6525

OpenRouter

Catalog quote
Input
$0.435
Output
$0.87
Cached input
$0.0036
USD / 1M tokens
1.1M context131.1K max outputPrice source ↗Checked Oct 17, 2026
Endpoint IDxiaomi/mimo-v2.6-pro

novita

via Hugging Face
Input
$0.435
Output
$0.87
USD / 1M tokens
1M contextPrice source ↗Checked Oct 17, 2026
Endpoint IDXiaomiMiMo/MiMo-V2.6-Pro-RL

DeepInfra

via OpenRouter

deepinfra/fp8 · quantization=fp8

Input
$0.43
Output
$0.87
Cached input
$0.0036
USD / 1M tokens
1M context943.7K max outputPrice source ↗Checked Oct 17, 2026
Endpoint IDxiaomi/mimo-v2.6-pro::deepinfra/fp8

Novita

via OpenRouter

novita/fp8 · quantization=fp8

Input
$0.435
Output
$0.87
Cached input
$0.0036
USD / 1M tokens
1M context131.1K max outputPrice source ↗Checked Oct 17, 2026
Endpoint IDxiaomi/mimo-v2.6-pro::novita/fp8

GMICloud

via OpenRouter

gmicloud/bf16 · quantization=bf16

Input
$0.435
Output
$0.87
Cached input
$0.004
USD / 1M tokens
1.1M context945K max outputPrice source ↗Checked Oct 17, 2026
Endpoint IDxiaomi/mimo-v2.6-pro::gmicloud/bf16

Xiaomi

via OpenRouter

xiaomi/fp8 · quantization=fp8

Input
$0.435
Output
$0.87
Cached input
$0.0036
USD / 1M tokens
1M context131.1K max outputPrice source ↗Checked Oct 17, 2026
Endpoint IDxiaomi/mimo-v2.6-pro::xiaomi/fp8

Model specifications

Developer
xiaomi
Modality
Language
Context
1,050,000 tokens
Maximum output
131,072 tokens
Weights
Open weights
Released
Sep 21, 2026
Provider listed
Sep 21, 2026
First discovered
Oct 16, 2026

Exact identities

  • openrouterxiaomi/mimo-v2.6-pro
  • huggingfaceXiaomiMiMo/MiMo-V2.6-Pro-RL
  • artificial-analysis24d8fdfe-6241-424e-b7b7-1b6efb06e4fb
  • livebenchmimo-v2.6-pro

Sources

Updated Oct 17, 2026

More from xiaomi

View all ↗
xiaomiListed 25 days ago

Xiaomi: MiMo-V2.6-Pro-UltraSpeed

MiMo-V2.6-Pro-UltraSpeed is the fast speed edition of Xiaomi's flagship foundation model, MiMo-V2.6-Pro. Built from the same 1T MiMo-V2.6-Pro checkpoint, it matches the original model in quality while…

1M contextImage inputAudio inputNo reported score
No reported score
$4.35in$8.70out/ 1M tokens · USDXiaomi · via OpenRouter · 2 endpointsxiaomi/fp8 · quantization=fp8
xiaomiListed 26 days ago

Xiaomi: MiMo-V2.6-Flash

MiMo-V2.6-Flash is an open-source foundation model developed by Xiaomi. Built on a Mixture-of-Experts architecture with 309B total parameters and 15B activated per token, it employs a hybrid attention…

1.1M contextImage inputAudio inputNo reported score
No reported score
$0.10in$0.28out/ 1M tokens · USDDarkbloom · via OpenRouter · 10 endpointsdarkbloom/fp4 · quantization=fp4
xiaomiListed Apr 22

Xiaomi: MiMo-V2.5-Pro

MiMo-V2.5-Pro is Xiaomi’s flagship model, delivering strong performance in general agentic capabilities, complex software engineering, and long-horizon tasks, with top rankings on benchmarks such as…

1.1M contextTool callingStructured outputNo reported score
No reported score
$0.3045in$0.609out/ 1M tokens · USDGMICloud · via OpenRouter · 9 endpointsgmicloud/bf16 · quantization=bf16
xiaomiListed Apr 22

Xiaomi: MiMo-V2.5

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…

1.1M contextImage inputAudio inputNo reported score
No reported score
$0.14in$0.28out/ 1M tokens · USDdeepinfra · via Hugging Face · 9 endpoints