xiaomiListed Apr 22, 2026

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 ClawEval, GDPVal, and SWE-bench Pro....

Context window1.1M
Max output131.1K
Provider endpoints9
Benchmark results0
Measured performance

Benchmark results

All leaderboards ↗
—

No published results in this index yet

Scores appear here when an evaluation matches this exact model.

Access & cost

Prices across providers

9 quotes

Your token mix

USD · listed token rates

GMICloud · via OpenRoutergmicloud/bf16 · quantization=bf16
$0.4568
AtlasCloud · via OpenRouteratlas-cloud/fp8 · quantization=fp8
$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-v2.5-pro

novita

via Hugging Face
Input
$0.522
Output
$1.044
USD / 1M tokens
1M contextPrice source ↗Checked Oct 17, 2026
Endpoint IDXiaomiMiMo/MiMo-V2.5-Pro

deepinfra

via Hugging Face
Input
$1.00
Output
$3.00
USD / 1M tokens
1M contextPrice source ↗Checked Oct 17, 2026
Endpoint IDXiaomiMiMo/MiMo-V2.5-Pro

GMICloud

via OpenRouter

gmicloud/bf16 · quantization=bf16

Input
$0.3045
Output
$0.609
Cached input
$0.0028
USD / 1M tokens

Source discount 30%; rates as published

1.1M context945K max outputPrice source ↗Checked Oct 17, 2026
Endpoint IDxiaomi/mimo-v2.5-pro::gmicloud/bf16

AtlasCloud

via OpenRouter

atlas-cloud/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-v2.5-pro::atlas-cloud/fp8

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-v2.5-pro::xiaomi/fp8

DigitalOcean

via OpenRouter

digitalocean

Provider degraded
Input
$0.48
Output
$1.80
Cached input
$0.096
USD / 1M tokens

Endpoint degraded (status -2)

262.1K context235.9K max outputPrice source ↗Checked Oct 17, 2026
Endpoint IDxiaomi/mimo-v2.5-pro::digitalocean

Novita

via OpenRouter

novita

Input
$0.4802
Output
$0.9605
Cached input
$0.003956
USD / 1M tokens

Source discount 8%; rates as published

1M context131.1K max outputPrice source ↗Checked Oct 17, 2026
Endpoint IDxiaomi/mimo-v2.5-pro::novita

StreamLake

via OpenRouter

streamlake

Input
$0.522
Output
$1.044
Cached input
$0.00432
USD / 1M tokens
1M context128K max outputPrice source ↗Checked Oct 17, 2026
Endpoint IDxiaomi/mimo-v2.5-pro::streamlake

Model specifications

Developer
xiaomi
Modality
Language
Context
1,050,000 tokens
Maximum output
131,072 tokens
Weights
Open weights
Provider listed
Apr 22, 2026
First discovered
Oct 16, 2026

Exact identities

  • openrouterxiaomi/mimo-v2.5-pro
  • huggingfaceXiaomiMiMo/MiMo-V2.5-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

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