Aion 3.0
5742°
Run this model
Offers / Ads
AionLabs | 131,072 token context | $3.00/M input, $6.00/M output. Aion-3.0 is a multi-model roleplaying and storytelling system from AionLabs, built on the GLM family of models. It uses a collaborative generation process in which multiple specialized models each contribute to a response, producing stronger narrative structure and more compelling tension and conflict.
Guides for this model
Flat fee vs tokens: why unlimited plans like Graydient.ai are the best value for AI creators in 2026
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
Aion-3.0 is a closed-weights roleplaying and storytelling model from AionLabs, built on the GLM family. Its unusual architecture runs multiple specialized models in parallel, each contributing to a single response, which the maker says produces better narrative structure, tension and conflict than a single model alone. It suits writers and interactive fiction creators who want more than a generic chat assistant.
Known for
- Multi-model collaborative generation designed specifically for narrative work
- Stronger tension and conflict in generated stories, per AionLabs
- Built on the GLM model family with a 131,072-token context window
- Oriented toward roleplay and long-form storytelling rather than general tasks
Watch out for
- API-only, no open weights: you cannot run this locally or inspect the model.
- At $6.00/M output tokens, extended storytelling sessions can add up quickly.
- Specialized for narrative; expect weaker performance on coding, math or data tasks.
Prompts to try
Open a gothic novel
Write the opening scene of a gothic novel set in a decaying coastal manor. Introduce two characters whose motives are immediately at odds. Keep the prose atmospheric but spare. End the scene on an unresolved moment of tension, not a cliffhanger reveal.
Villain with real grievance
Write a scene from the point of view of the antagonist. They have just learned their plan is unraveling. Show their internal reasoning, make their grievance feel legitimate, and let them decide on a course of action that will make things worse for the protagonist.
Escalate a negotiation scene
Two diplomats are negotiating a ceasefire. One is hiding that their own government has already ordered an attack for dawn. Write the conversation: formal on the surface, each line carrying a second meaning. Let the tension build without either character breaking composure.
Compare with
- Aion 3.5API-only model262,144 token context · $3.00/M input, $6.00/M output
- Aion 3.5 MiniAPI-only model262,144 token context · $0.70/M input, $1.40/M output
- Aion-3.0-MiniAPI-only model131,072 token context · $0.70/M input, $1.40/M output
- Aion-2.0API-only model131,072 token context · $0.80/M input, $1.60/M output
More text models from aion-labs
Questions people ask
- Can I run Aion-3.0 locally?
- No. AionLabs has not released open weights, and there is no Hugging Face repository. Access is API-only.
- What does Aion-3.0 cost and how long is its context?
- Pricing is $3.00 per million input tokens and $6.00 per million output tokens, with a 131,072-token context window.
- What makes Aion-3.0 different from a standard chat model for fiction?
- Rather than a single model generating a response, Aion-3.0 routes the task through multiple specialized models that each contribute, which AionLabs says produces better narrative structure and more convincing conflict.
Captain's verdictA purpose-built narrative engine worth the premium if storytelling quality matters to you, but too specialized and too closed for general use.
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.
Aion 3.0 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