xiaomi/mimo-v2.6-flash

模型发布 OpenRouter 模型 原文语言:中文

OpenRouter 于 2026-09-22 收录该模型(收录时间不等于模型正式发布日期);上下文:1,050,000 tokens;输入价:$0.1400/百万 tokens;输出价:$0.2800/百万 tokens;定位(来源描述):MiMo-V2.6-Flash is an open-source foundation model developed by Xiaomi.

全文

Xiaomi: MiMo-V2.6-Flash

xiaomi/mimo-v2.6-flash

Model weights

Compare

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 mechanism for greater computational efficiency. The model features a 1M-token context window and native multimodal capabilities. Optimized for agentic workflows, it delivers strong performance across coding, visual, general, and research scenarios, excelling at complex, long-horizon tasks with robust generalization across a diverse range of agent harnesses.

Modalities

In / out price

$0.10 / $0.28per 1M

Context

1.1M

Released

Sep 21, 2026

Compare

Providers

Different companies host the same model. OpenRouter routes your request to one of them based on the routing mode you pick: Balanced (price + speed), Nitro (fastest), or Floor (cheapest).

Latency / throughput

$0.180$0.360$0.004500.91s115 tok/s

100.00%

$0.140$0.280$0.002801.94s48 tok/s

97.27%

$0.140$0.280$0.002803.48s29 tok/s

100.00%

$0.140$0.280$0.003001.10s90 tok/s

99.86%

$0.165$0.330$0.004000.34s81 tok/s

99.14%

20% off

$0.14$0.112$0.28$0.224$0.003$0.002403.15s27 tok/s

99.73%

$0.175$0.350$0.003754.28s47 tok/s

91.59%

$0.100$0.280$0.002804.31s19 tok/s

99.16%

ProviderInput / Output /M

Input $0.18 / Output $0.36

115 tok/s100.00% uptime

Input $0.14 / Output $0.28

48 tok/s97.27% uptime

Input $0.14 / Output $0.28

29 tok/s100.00% uptime

Input $0.14 / Output $0.28

90 tok/s99.86% uptime

Input $0.165 / Output $0.33

81 tok/s99.14% uptime

Input $0.112 / Output $0.224

20% off

27 tok/s99.73% uptime

Input $0.175 / Output $0.35

47 tok/s91.59% uptime

Input $0.10 / Output $0.28

19 tok/s99.16% uptime

Pricing

The average price customers actually pay for this model, next to the prices providers post. Caching and discounts mean the price actually paid is often well below the listed one.

Weighted average

Input

$0.01463/M tokens

Output

$0.283/M tokens

MiMo-V2.6-Flash — Price history

Price history

No effective price data for this selection

$0.00875$0.35097.1%1.2%

$0.01180$0.22491.4%0.9%

$0.01255$0.28092.9%88.3%

$0.01917$0.27988.1%2.9%

$0.03832$0.27974.2%3.8%

$0.04447$0.32874.8%0.0%

$0.04677$0.35975.9%2.8%

$0.09716$0.2792.8%0.0%

ProviderInput / Output /M

Token share

Effective in $0.00875 / Effective out $0.350

Token share

1.2%

Effective in $0.01180 / Effective out $0.224

Token share

0.9%

Effective in $0.01255 / Effective out $0.280

Token share

88.3%

Effective in $0.01917 / Effective out $0.279

Token share

2.9%

Effective in $0.03832 / Effective out $0.279

Token share

3.8%

Effective in $0.04447 / Effective out $0.328

Token share

0.0%

Effective in $0.04677 / Effective out $0.359

Token share

2.8%

Effective in $0.09716 / Effective out $0.279

Token share

0.0%

Performance

Throughput is how fast the model writes (tokens per second — higher is better). Latency is total round-trip time (lower is better). TTFT is time-to-first-token — how long before you see anything appear (lower is better).

Throughput

115tok/s

P50, best across providers

Latency

0.34s

P50, best provider

Latency / throughput

AutoExacto benchmarks

GPQA DiamondTAU-BenchVenice85.8%--Novita78.3%78.2%Xiaomi78.4%76.2%GMICloud78.5%75.9%Io Net76.2%76.3%

+7 more providers

Uptime

Uptime is the percentage of the past 3 days that at least one provider was responding to requests. Availability is the percentage of time that inference was successfully served. OpenRouter continuously monitors and uses the next-best provider when one returns an error.

Uptime (3d)The model was reachable. Request routed to a provider.

100.00%

Availability (3d)The model returned inference from any provider. Errors and empty responses count against it.

99.71%

Availability over the last 3 days

Last 72 hours

Availability 99.71%

3 Days Ago2 Days AgoYesterdayNow

Availability over the last 24 hours

OpenRouter Availability

99.86%

Without Routing

97.07%

When an error occurs in an upstream provider, we can recover by routing to another healthy provider, if your request filters allow it. You can access per-provider uptime data programmatically through the Endpoints API. Learn more about our load balancing and provider routing options.

Benchmarks

Scores on standardized evaluations and this model’s own outputs on shared benchmark prompts. Higher percentages are better — and each rank shows where this model lands among the models evaluated on that source.

Benchmark score summary for Xiaomi: MiMo-V2.6-Flash (Artificial Analysis and Vals AI)

SourceBenchmarkScore

Artificial AnalysisMiMo-V2.6-Flash Intelligence Index26.7

Artificial AnalysisMiMo-V2.6-Flash HLE35.1%

Artificial AnalysisMiMo-V2.6-Flash AA-LCR74.3%

Artificial AnalysisMiMo-V2.6-Flash GDPval-AA55.7%

Artificial AnalysisMiMo-V2.6-Flash CritPt12.0%

Artificial AnalysisMiMo-V2.6-Flash SciCode51.3%

Artificial AnalysisMiMo-V2.6-Flash Terminal-Bench 4.022.7%

Artificial AnalysisMiMo-V2.6-Flash AA-Omniscience Accuracy27.2%

Artificial AnalysisMiMo-V2.6-Flash AA-Omniscience Non-Hallucination Rate47.8%

Vals AIMiMo V2.6 Flash Access to Justice Benchmark70.7%

Vals AIMiMo V2.6 Flash BioMysteryBench69.3%

Vals AIMiMo V2.6 Flash Code Migration v1.139.6%

Vals AIMiMo V2.6 Flash CyberBench v1.175.4%

Vals AIMiMo V2.6 Flash EMB v1.168.9%

Vals AIMiMo V2.6 Flash Finance Agent v2.163.3%

Vals AIMiMo V2.6 Flash Vals Finance Index57.1%

Vals AIMiMo V2.6 Flash HLAB-Vals-1.113.3%

Vals AIMiMo V2.6 Flash IOI47.7%

Vals AIMiMo V2.6 Flash Vals Legal Index69.0%

Vals AIMiMo V2.6 Flash Legal Research Bench38.0%

Vals AIMiMo V2.6 Flash MedCode41.1%

Vals AIMiMo V2.6 Flash MedScribe85.3%

Vals AIMiMo V2.6 Flash MysteryMechanism21.6%

Vals AIMiMo V2.6 Flash ProgramBench0.5%

Vals AIMiMo V2.6 Flash ProofBench v1.163.0%

Vals AIMiMo V2.6 Flash Public Benefits Bench v1.167.6%

Vals AIMiMo V2.6 Flash SAGE83.3%

Vals AIMiMo V2.6 Flash Vals Science Index31.7%

Vals AIMiMo V2.6 Flash SRE Bench4.2%

Vals AIMiMo V2.6 Flash Tax Agent Bench28.5%

Vals AIMiMo V2.6 Flash Terminal-Bench 4.024.2%

Vals AIMiMo V2.6 Flash Terminal-Bench-Science4.3%

Vals AIMiMo V2.6 Flash Vals Index54.8%

Vals AIMiMo V2.6 Flash Vibe Code Bench 1-100 v1.124.5%

Vals AIMiMo V2.6 Flash Vibe Code Bench v1.179.0%

Apps

Public apps that send the most traffic to this model. Good signal for what real production workloads look like — and a hint at which use cases this model is best suited for.

1.

Freebuff

Powerful coding models, funded by ads

1.27Ttokens

2.

Cline

Cline is an open-source AI coding agent that lives inside your IDE, autonomously exploring your codebase, editing files, running terminal commands, and using browser automation.

776Btokens

3.

Hello Minds, powered by Ethoswarm

new

709Btokens

4.

Hermes Agent

Hermes Agent is an open-source, self-improving AI agent by Nous Research that runs persistently with memory across sessions, and builds reusable skills from experience. It comes with 40+ built-in tools, including web search, browser automation, and vision, plus scheduled automations and subagents.

424Btokens

5.

ISEKAI ZERO

AI adventures. Travel with your favorite characters

370Btokens

Rest of OpenRouter

22.8B

Top 5 Apps

1.72B

Activity

Token volume and request traffic to this model over time.

API

Drop-in code to call this model. OpenRouter's API is OpenAI-compatible — most SDKs work by just swapping the base URL. The only thing that changes between models is the model slug below.

Not currently available through EU in-region routing. In-region routing docs

Documentation

Guides, cookbooks, blog posts, and tools for building with Xiaomi: MiMo-V2.6-Flash on OpenRouter.

How to Benchmark LLMsBlog post

Frequently asked questions

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 mechanism for greater computational efficiency. The model features a 1M-token context window and native multimodal capabilities.

The MiMo-V2.6-Flash documentation on OpenRouter includes the How to Benchmark LLMs blog post. The quickstart covers API keys and your first request, and the API reference lists every parameter.

MiMo-V2.6-Flash costs $0.10/M input tokens and $0.28/M output tokens, with separate rates for Cache Read at $0.0028/M tokens.

MiMo-V2.6-Flash has a 1,050,000 token context window. It supports up to 131,072 completion tokens.

Yes. MiMo-V2.6-Flash accepts tools and tool_choice for function calling. It also supports structured outputs via a JSON schema in response_format.

MiMo-V2.6-Flash accepts text, images, video, and audio as input and returns text.

MiMo-V2.6-Flash is served by 8 providers on OpenRouter: Darkbloom, GMICloud, Cohere, DeepInfra, Xiaomi, Tenstorrent, Venice, and Makora. Requests are routed to the best available provider, with automatic failover to the others, and you can pin or exclude providers with provider routing.

MiMo-V2.6-Flash was released on September 21, 2026.

正文以来源语言显示。

参考来源

← 返回每日简报