MiMo-V2.6-Pro

Xiaomi's flagship MiMo V2.6 reasoning model: a 1.02T sparse MoE activating 42B parameters per token, MIT licensed, aimed at long-horizon agent work, coding, cybersecurity and research.

Params: 1T, 42B active
Context: 1M tokens
Max output: 131K
Released: Sep 2026
License: MIT

Visit Xiaomi MiMo Compare vs other LLMs →

Hosted API price

List price via Xiaomi MiMo · per 1M tokens

USD

Input: $0.435 /1M
Output: $0.87 /1M
Hosted by: 1 provider

Hosted API pricing

How we price

Order

Providers are listed cheapest input rate first, then by output rate, a tie going to the creator's own listing. A provider that lists the model without a published rate sits at the end.

Prices

Base-tier, on-demand rates in USD per 1M tokens, converted at ECB reference rates where a provider publishes in another currency. Cached-input and batch rates show only where a provider publishes them. "Cheapest" marks the one provider with the lowest input and output pair; a tie wears no badge.

Cost

Input rate times the input tokens plus output rate times the output tokens, at the monthly volume set above the table. Cached-input, batch, long-context and reasoning-token billing are not modelled.

Transparency and funding

Affiliates: Affiliate links are marked. We may earn a commission if you click them, but commissions never affect the order.

Every provider serving MiMo-V2.6-Pro, cheapest input first. Set your monthly volume to see what each would bill.

Input M Output M

Every provider serving MiMo-V2.6-Pro, with its price per 1M input and output tokens and what the volume above would cost
Provider	Input /1M	Output /1M	Cached input /1M	Cost at 10M in + 2M out	Link
Xiaomi MiMo Creator	$0.435	$0.87	$0.0036	$6.09	Visit website

Heads up: Base-tier, on-demand rates per 1M tokens; cached, batch and long-context tiers excluded. A provider may serve a shorter context or a quantized build than the creator's release. Verify before provisioning. More on how we price.

Estimated cost to self-host

MiMo-V2.6-Pro needs about 565 GB of GPU memory at 4-bit with 32K context. The cheapest rental that fits is 8× A100 at about $10,080 a month.

That costs the same as roughly 20B tokens a month on Xiaomi MiMo's API. Self-hosting is more expensive below that volume.

Single node ≤ 8

What it costs to self-host MiMo-V2.6-Pro at each precision: the memory it needs, the cheapest rental that holds it, that rental's month and the API volume it pays off at
Precision	Memory	Cheapest fit (32K context)(Full 1M context)	Cost /mo	Break-even vs API
4-bit INT4 / FP4	565 GB595 GB	8× A100	$10,080$12,672	20B tokens /mo25B tokens /mo
8-bit FP8 / INT8	1,023 GB1,054 GB	4× B300	$22,666$37,555	45B tokens /mo74B tokens /mo
16-bit FP16 / BF16	2,044 GB2,106 GB	8× B300 –	$45,331–	89B tokens /mo–

Estimates based on median on-demand rates for Nvidia GPUs. Memory is weights plus KV cache for one request, using FP8 KV cache where supported and FP16/BF16 otherwise. Break-even assumes a 5:1 input-to-output ratio. No guarantee of runtime support, usable performance, or that a matching quantized build exists. Pricing methodology.

Similarly priced models

The models nearest MiMo-V2.6-Pro by blended rate, each at its own cheapest provider.

Models priced nearest MiMo-V2.6-Pro per 1M tokens, each at its cheapest provider
Model	Blended /1M	Input /1M	Output /1M	Context	Cutoff	vs MiMo-V2.6-Pro
DeepSeek V4.1 Flash DeepSeek	$0.45	$0.30	$1.20	1M		−11%
MiniMax-M2.5 MiniMax	$0.45	$0.30	$1.20	205K		−11%
Gemini 3.1 Flash-Lite Google Cloud	$0.4583	$0.25	$1.50	1M	Jan 2025	−10%
Qwen3.6-Flash Alibaba Cloud	$0.4583	$0.25	$1.50	1M		−10%
Qwen3-VL-235B-A22B Instruct Alibaba Cloud	$0.50	$0.30	$1.50	262K		−1%
MiMo-V2.6-Pro This model Xiaomi MiMo	$0.5075	$0.435	$0.87	1M
DeepSeek V4 Pro DeepSeek	$0.5233	$0.45	$0.89	1M		+3%
GPT-5 Mini OpenAI	$0.5417	$0.25	$2.00	400K	May 2024	+7%
DeepSeek V3 Turbo DeepSeek	$0.55	$0.40	$1.30	64K		+8%
Qwen3-VL-30B-A3B Thinking Alibaba Cloud	$0.5667	$0.20	$2.40	262K		+12%
Qwen3-235B-A22B Thinking (2507) Alibaba Cloud	$0.575	$0.23	$2.30	262K		+13%

USD per 1M tokens at each model's cheapest listed provider. Blended is the cost of 10M input plus 2M output tokens, spread over the 12M.

Runpod

Spin Up a GPU in Seconds - No Setup Required

Deploy AI Models Globally in 30+ Regions

Scale from 0 to 1000 GPUs on Demand

PyTorch, Tensorflow & Docker Ready

Learn more

Capabilities

What MiMo-V2.6-Pro accepts and can do, as published by Xiaomi MiMo.

Text Accepts and generates natural-language text.
Image Accepts images as input alongside text.
Audio Accepts audio as input.
Video Accepts video as input.
Reasoning Thinks before it answers, always on or as a switchable mode.
Function calling Connect to external tools, APIs, and systems.
Structured output Return responses in structured formats like JSON.
Web search Search the web for up-to-date information.

Common questions

What is MiMo-V2.6-Pro good for?

Xiaomi built it for complex projects and long-horizon tasks, naming coding, office work, design, research, content creation, cybersecurity and computer operation. Weights are MIT licensed, and at 1.02T parameters self-hosting takes more than one node.

When is MiMo-V2.6-Pro not a good fit?

Cost-sensitive or high-volume use: it sits at the top of Xiaomi's price range, and it answers in text only. Xiaomi publishes no knowledge cutoff for it, and self-hosting takes more than one node.

What is the cheapest way to run MiMo-V2.6-Pro?

Hosted, unless you push serious volume. Xiaomi MiMo charges $0.435 in / $0.87 out per 1M tokens. The cheapest rental that fits is 8x A100 at $10,080 a month, which costs the same as about 20B tokens a month on that API.

Can I self-host MiMo-V2.6-Pro?

Yes. The weights are MIT licensed. At 4-bit it needs about 565 GB of GPU memory, which starts at roughly $10,080 a month on the cheapest rental that fits.