Are the weights open and can I run MiniMax-01 locally?

Yes, the weights are published on Hugging Face under the MiniMaxAI organisation. Running the full model locally is demanding given 456 billion total parameters, so most self-hosters will need a multi-GPU setup.

What does MiniMax-01 cost and how long is its context?

Via API it is $0.20 per million input tokens and $1.10 per million output tokens. The context window is listed at just over 1 million tokens on the API, though the model can handle up to 4 million tokens at inference time.

How does MiniMax-01 differ from other long-context models?

Its hybrid Lightning Attention and Softmax Attention architecture is specifically designed to extend context efficiently, and the 4 million token ceiling is higher than most models in its price range. It also bundles image understanding alongside text generation.

MiniMax 01

4326°

#llm #minimax #vision #long context #local #budget

Run this model

Offers / Ads

OpenRouter Terminal / API

Pay per token

Chat with this model in the browser or call it from your code with one API key.

MiniMax | 1,000,192 token context | $0.20/M input, $1.10/M output. MiniMax-01 is a combines MiniMax-Text-01 for text generation and MiniMax-VL-01 for image understanding. It has 456 billion parameters, with 45.9 billion parameters activated per inference, and can handle a context of up to 4 million tokens. The text model adopts a hybrid architecture that combines Lightning Attention, Softmax Attention, and Mixture-of-Experts (MoE). The image model adopts the “ViT-MLP-LLM” framework and is trained on top of the text model. To read more about the release, see: https://www.minimaxi.com/en/news/minimax-01-series-2Opens in new tab

Guides for this model

Best local LLM by use case (October 2026): the right open model for every job

How much VRAM do I actually need for local AI?

Open weights vs open source vs API-only: what you are actually allowed to do

What is a GGUF file? Quantized models explained (Q4, Q8, fp8, NF4)

All guides

Captain's notes

Written by Captain, the house editor

Notes from 2026-10-13

MiniMax-01 is a 456-billion-parameter mixture-of-experts model from MiniMax that pairs a text model with a vision model in a single package. Its headline feature is a hybrid attention architecture that extends usable context to 4 million tokens, well beyond what most rivals offer at this price. At $0.20 per million input tokens it suits developers who need very long context or multimodal work without a large API bill.

Known for

4 million token context window, one of the longest available at this price point.
Hybrid Lightning Attention and Softmax Attention architecture built for long sequences.
Combines text generation and image understanding in one model.
456B total parameters with only 45.9B activated per token via MoE routing.
Open weights available on Hugging Face.

Watch out for

456B total parameters means self-hosting requires serious hardware; most users will hit the API.
The vision component is a separate model bolted on top, not a natively multimodal architecture.
Context beyond 1 million tokens is inference-only; training context was 1 million tokens.

Best for

Prompts to try

Summarise a very long document

Here is a lengthy contract. Read the entire text, then give me: (1) a one-paragraph plain-English summary, (2) the three most important obligations on each party, and (3) any clauses that carry unusual risk for the buyer. [Paste your document below this line]

Analyse an uploaded image

I am attaching a screenshot of a data dashboard. Describe every chart you can see, state what each one shows, identify any anomalies or trends worth flagging, and suggest one follow-up question the data raises but does not answer.

Cross-document research synthesis

I will paste three separate research papers below. After reading all three, write a 400-word synthesis that identifies where they agree, where they contradict each other, and what question none of them answers. Label each claim with which paper it comes from.

Compare with

MiniMax M3
Open-weights model
1,048,576 token context · $0.30/M input, $1.20/M output
Muse Spark 1.3 Contributor
API-only model
1,048,576 token context · $0.10/M input, $0.20/M output
Space Bunny Alpha
API-only model
1,000,000 token context · free to use
Gemini 2.5 Flash Lite
API-only model
1,048,576 token context · $0.10/M input, $0.40/M output

More text models from minimax

Questions people ask

Are the weights open and can I run MiniMax-01 locally?: Yes, the weights are published on Hugging Face under the MiniMaxAI organisation. Running the full model locally is demanding given 456 billion total parameters, so most self-hosters will need a multi-GPU setup.
What does MiniMax-01 cost and how long is its context?: Via API it is $0.20 per million input tokens and $1.10 per million output tokens. The context window is listed at just over 1 million tokens on the API, though the model can handle up to 4 million tokens at inference time.
How does MiniMax-01 differ from other long-context models?: Its hybrid Lightning Attention and Softmax Attention architecture is specifically designed to extend context efficiently, and the 4 million token ceiling is higher than most models in its price range. It also bundles image understanding alongside text generation.

Captain's verdict
A rare combination of genuinely long context, open weights and a low input price — worth a look if your workload involves very large documents or multi-image analysis.

Model card on Hugging Face

Captain writes these notes from the model's own description and model card. Prices and context sizes are the provider's at the time of writing and can change.

Ranking badge

Updated Oct 22, 2026

Made this model? Show this badge on your page.

Paste it into your Hugging Face card or Civitai description.

Change colors / personalize / get code

Not this creator?

Get your own badge

How this score adds up

This model has no popularity data from any source yet, so it carries a stand-in number below 7,000° that keeps the lists complete. It never ranks above a model with data. The breakdown appears here as soon as a source reports it.

Glossary: the terms used here

Heat score: One number for how much a model is used and wanted right now, from 0° to 9,999°. Every list on this site that says hottest is sorted by it and nothing else.
Floor: The 7,000° every model with real data starts from. The scale runs from 0° to 9,999°; the part below the floor is reserved for stand-ins (models without data), so that a model with data always ranks above one without. The floor is the same for everyone and decides nothing; the degrees above it are the measurement.
Download-equivalents: Everything the score treats as a download, added up: downloads themselves, each torrent seeder as 1,000, each AI Horde image and each run on a generation site as one.
Log scale: Counting by tens, not by ones: going from 1,000 to 10,000 downloads adds the same degrees as going from 10,000 to 100,000. It keeps giants from crowding out everything else.
Likes: Thumbs up and likes from every source, worth half a download each on the log scale.
Adoption rate: How many downloads a day a model gets right now, from the difference between two readings of a source. A quarter of the weight of the download term.
Measured and estimated: Measured means two readings of a source exist and the difference is real. Estimated means only today's total is known and the past is spread over the model's life; the site says which one it is showing.
Seeder: Someone who keeps a copy of the weights online for others to download over a torrent, or a hosted mirror doing the same. Each one counts as 1,000 downloads.
AI Horde: A volunteer network that generates images for free on donated computers. The number of images it has made with a model is public, and each counts as one download.
Generation sites: Sites that host their own copies of a model and let people generate with it, such as PixAI, SeaArt and Yodayo. Their downloads count like Civitai's and each generation run as one download.
OpenRouter tokens: A text model served through an API, such as Claude or GPT, has no weights to download, so its usage is measured in tokens: the pieces of text it read and wrote through OpenRouter, a gateway many apps use, over the last 30 days. Every 10,000,000 tokens count as one download. Source: OpenRouter (openrouter.ai/rankings), CC BY 4.0.
Full model (checkpoint): The weights themselves, the file that generates on its own. It gets a bonus because add-ons depend on it.
LoRA and embedding: Small add-on files that steer someone else's weights toward a style, a character or a concept. They cannot run alone.
Family and weights: The base a model is built on, such as SD 1.5, SDXL, Flux or Wan. Every model inherits the release date of its family's weights.
Age: Degrees taken off for how long ago the family's weights came out: 150° a year, up to 750°. It keeps old downloads that had years to pile up from freezing the top of the list.
Family boost: A small, bounded nudge for LoRAs of a family this site is pushing forward right now, always listed in the breakdown.
Stand-in score: A stable number below the floor given to a model no source reports on yet, so lists stay complete. It never ranks above a model with data.
New! (grace period): A model less than 7 days old shows New! instead of a score and holds no place in the rankings. Its score is computed from day one, but a model one day old grows faster than anything, so without the wait the week's #1 would always be whatever came out yesterday rather than what held up for a week.
Trend: How a model's growth over a period compares with the typical model's growth over the same period. Faster than typical reads as a rise, slower as a fall.
Typical model: The middle of the catalog: half the models with a figure grew faster over the period, half slower.

Similar Models

AI Models for Image, Video & Text Generation

MiniMax 01 is a text model for the Text / LLM family listed on ModelTrends.ai, a read-only catalog of open source AI image, video and text models. Compare it with other Text / LLM models and check its heat score to see how it is trending.

More Text / LLM models llm minimax vision long context local budget multilingual

Browse by Model Family