Aion-2.0
Aion-2.0 is an AI model developed by AionLabs, based on the DeepSeek V3.2 architecture. It is specifically optimized for immersive storytelling and roleplaying, with a focus on building narrative tension and conflict.
Aion-2.0 specs and pricing
- Provider: AionLabs
- Released: February 23, 2026
- Context window: 131K tokens
- Max output: 33K tokens
- Input: text
- Output: text
- Price: $0.80 input / $1.60 output per 1M tokens
- Reasoning: yes
- Tool calling: yes
What Aion-2.0 is good at
- Writing creative fiction and stories
- Engaging in interactive roleplay scenarios
- Developing complex narrative plots
To-dos to try with Aion-2.0
- Write a short story about a detective discovering a hidden secret in a small town.
- Act as a fantasy character and guide me through a tense negotiation scene.
- Draft a plot outline for a thriller novel that focuses on escalating conflict between two rivals.
FAQ
- What is the primary focus of Aion-2.0? Aion-2.0 is designed to excel at immersive roleplaying and storytelling by emphasizing tension and narrative conflict.
- Who developed Aion-2.0? Aion-2.0 was developed by AionLabs as a variant of the DeepSeek V3.2 model.
- How much does Aion-2.0 cost? Aion-2.0 costs $0.80 per million input tokens and $1.60 per million output tokens through OpenRouter. In todo.is a typical agent step costs about 2.46 credits ($1 = 100 credits).
- What is the context window of Aion-2.0? Aion-2.0 can read up to 131K tokens at once and write up to 33K tokens in one reply.
- Can I use Aion-2.0 without coding? Yes. In todo.is you pick Aion-2.0 as your agent's model and write to-dos in plain words, on the web, the Android app, WhatsApp or Telegram. No API key needed: credits are included, or you can bring your own key.
JavaScript is required to use the todo.is app.