MiniMax M2 her
4468°
Run this model
Offers / Ads
MiniMax | 65,536 token context | $0.30/M input, $1.20/M output. MiniMax M2-her is a dialogue-first large language model built for immersive roleplay, character-driven chat, and expressive multi-turn conversations. Designed to stay consistent in tone and personality, it supports rich message roles (user_system, group, sample_message_user, sample_message_ai) and can learn from example dialogue to better match the style and pacing of your scenario, making it a strong choice for storytelling, companions, and conversational experiences where natural flow and vivid interaction matter most.
Guides for this model
Open weights vs open source vs API-only: what you are actually allowed to do
The 10 cheapest ChatGPT alternatives in 2026: free local models, free tiers and flat-rate plans
Captain's notes
Notes from 2026-10-13
MiniMax M2-her is a closed-weights dialogue model from MiniMax, built specifically for roleplay, character chat, and multi-turn conversational experiences. Its standout feature is a rich message-role system that lets you feed example dialogue so the model learns your character's voice and pacing. If you are building a companion app, an interactive story, or any scenario where consistent personality matters more than raw reasoning, this is the model to reach for.
Known for
- Stays consistent in tone and personality across long multi-turn conversations.
- Supports rich message roles including sample dialogue to shape character voice.
- Built for immersive roleplay and companion-style chat, not general-purpose tasks.
- Expressive, natural conversational flow suited to storytelling scenarios.
Watch out for
- API-only, no open weights — you cannot run this locally or self-host it.
- Optimised for dialogue; expect weaker performance on coding, reasoning, or data tasks.
- Context window is 65,536 tokens, which rules out very long document work.
Prompts to try
Build a character from scratch
You are playing a world-weary detective in 1940s Los Angeles. Your name is Ray Calloway. You speak in clipped, sardonic sentences and never trust anyone on first meeting. I will play a client who has just walked into your office. Stay in character throughout. Begin the scene.
Match a writing style
Here are two lines of dialogue from a character I am writing: 'Oh, I am sure it will be fine. It always is, until it isn't.' and 'You worry too much. Or perhaps not enough.' Continue a conversation between this character and an anxious friend who has just received bad news. Keep the same dry, detached tone.
Run a group scene
Three characters are arguing around a campfire: Mira, a pragmatic soldier; Theo, an idealistic young scholar; and Sable, a mercenary who only cares about payment. The argument is about whether to warn a nearby village of an approaching army or press on with their own mission. Write the exchange, keeping each voice distinct.
Compare with
- L3.1 70B Euryale v2.2Open-weights model131,072 token context · $0.85/M input, $0.85/M output
- Magnum v4 72BOpen-weights model32,768 token context · $2.50/M input, $5.00/M output
- Cydonia 24B V4.1Open-weights model131,072 token context · $0.30/M input, $0.50/M output
- Llama 3 8B LunarisOpen-weights model8,192 token context · $0.04/M input, $0.05/M output
More text models from minimax
Questions people ask
- Can I run MiniMax M2-her locally?
- No. MiniMax has not released open weights for this model, so it is API access only.
- What does it cost and how long is the context?
- Pricing is $0.30 per million input tokens and $1.20 per million output tokens, with a context window of 65,536 tokens.
- How is M2-her different from a general-purpose chat model?
- It is purpose-built for roleplay and character-driven dialogue, with support for sample message roles that let you teach it a character's voice — something most general models do not offer natively.
Captain's verdictA narrow but genuinely useful tool if dialogue consistency and character voice are your actual problem — not a general-purpose workhorse.
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.
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.
MiniMax M2 her 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.
Browse by Model Family
Text / LLM Models
434
Anima Models
528
Chroma Models
19
Fibo Models
2
Flux Models
1,496
Flux 2 / Klein Models
1,239
Flux 3 Models
3
Moss Models
3
Iris Models
1
MiniMax H3 Models
364
Hunyuan Models
204
Ideogram Models
20
Krea2 Models
717
Qwen Models
20
Qwen2 Models
47
Ltx2 Models
153