Xiaomi (MiMo)

MiMo-V2.6-Flash

Generally availableOpen weights1M contextReasoning

Summary

MiMo-V2.6-Flash is an open-weight language model from Xiaomi (MiMo), released on 22 Sept 2026. It accepts text, images, audio and video and generates text, with a 1M-token context window and up to 131K output tokens per response. As of 18 Nov 2026, the lowest listed API price is $0.14 per million input tokens and $0.28 per million output tokens (Xiaomi MiMo API), across 5 providers we track.

MiMo Flash model for multimodal coding agents and long-context automation

Last verified 18 Nov 2026. Every figure on this page links to its source.

Specifications

DeveloperXiaomi (MiMo)
Release date22 Sept 2026 [models.dev]
StatusGenerally available [models.dev]
WeightsOpen weights [models.dev]
Context window1M (1,048,576 tokens) [models.dev]
Max output131K tokens [models.dev]
InputText, images, audio and video [models.dev]
OutputText [models.dev]
Reasoning modeYes [models.dev]
Tool callingYes [models.dev]
Structured outputYes [models.dev]
Hugging FaceXiaomiMiMo/MiMo-V2.6-Flash-RL

MiMo-V2.6-Flash API pricing by provider

USD per million tokens. Sorted by input price.

ProviderInputOutputCached inputContextSource
Xiaomi MiMo API
mimo-v2.6-flash
$0.14$0.28$0.00281Mmodels.dev, 18 Nov 2026
DeepInfra
XiaomiMiMo/MiMo-V2.6-Flash
$0.14$0.28$0.00281Mmodels.dev, 18 Nov 2026
Novita AI
xiaomimimo/mimo-v2.6-flash
$0.14$0.28$0.00281Mmodels.dev, 18 Nov 2026
OpenRouter
xiaomi/mimo-v2.6-flash
$0.14$0.28$0.00281MOpenRouter, 18 Nov 2026
Vercel AI Gateway
xiaomi/mimo-v2.6-flash
$0.14$0.28$0.00281Mmodels.dev, 18 Nov 2026

Frequently asked questions

What is the context window of MiMo-V2.6-Flash?

MiMo-V2.6-Flash has a context window of 1,048,576 tokens (1M) and can generate up to 131,072 tokens in a single response, according to models.dev.

How much does the MiMo-V2.6-Flash API cost?

Through Xiaomi MiMo API, MiMo-V2.6-Flash costs $0.14 per million input tokens and $0.28 per million output tokens. Prices last verified 18 Nov 2026.

Is MiMo-V2.6-Flash open source?

MiMo-V2.6-Flash is an open-weight model: its weights are published on Hugging Face as XiaomiMiMo/MiMo-V2.6-Flash-RL. Check the license terms before commercial use.

When was MiMo-V2.6-Flash released?

Xiaomi (MiMo) released MiMo-V2.6-Flash on 22 Sept 2026, according to models.dev.

Which providers offer MiMo-V2.6-Flash?

We track MiMo-V2.6-Flash on 5 providers: Xiaomi MiMo API, DeepInfra, Novita AI, OpenRouter, Vercel AI Gateway.

Similar models from other labs

Comparable on output type, weights, release date, price and context window. Prices are the lowest listed, USD per million tokens.

ModelLabReleasedContextInput $/1MOutput $/1MWeights
ricursiveAI/Ripple-65B-PreviewRicursiveai4 Nov 20261M$0.10$0.30Open
MiniMax-M3.1-FlashMiniMax19 Oct 20261M$0.07$0.30Open
GPT-6 Luna ProOpenAI22 Sept 20261.1M$0.10$0.50–
DeepSeek V4.1 Flash 1017DeepSeek17 Oct 20261M$0.04$0.50Open
Muse Spark 1.3 ContributorMeta2 Sept 20261M$0.10$0.20–
Muse Spark 1.2 ContributorMeta21 Aug 20261M$0.10$0.20–

Change history

  • Structured output changed from none to yes
  • Now listed on Novita AI
  • Vercel AI Gateway price changed: input $0.04 → $0.14, output $1.28 → $0.28 per 1M tokens

Sources