Author's Description
Aion-2.0 is a variant of DeepSeek V3.2 optimized for immersive roleplaying and storytelling. It is particularly strong at introducing tension, crises, and conflict into stories, making narratives feel more engaging. It also handles mature and darker themes with more nuance and depth.
Key Specifications
Supported Parameters
This model supports the following parameters:
Features
This model supports the following features:
Performance Summary
AionLabs: Aion-2.0, a DeepSeek V3.2 variant optimized for immersive roleplaying and storytelling, demonstrates exceptional reliability with a 100% success rate across all benchmarks, indicating consistent and usable responses. However, its performance is characterized by longer response times, ranking in the 11th percentile for speed, and it is positioned at premium pricing levels, falling into the 17th percentile for cost. Despite its speed and cost profile, Aion-2.0 exhibits remarkable accuracy in several critical areas. It achieved perfect scores in Hallucinations, Reasoning, and Ethics, often being the most accurate model at its price point and speed for these categories. It also shows strong performance in Mathematics (96.0% accuracy, 95th percentile), Coding (93.0% accuracy, 81st percentile), and General Knowledge (99.5% accuracy, 71st percentile). A notable weakness is its Instruction Following capability, where it scored 55.0% accuracy, placing it in the 52nd percentile. Email Classification is strong at 99.0% accuracy. Overall, Aion-2.0 excels in tasks requiring high precision and complex problem-solving, particularly in areas relevant to its specialized storytelling and roleplaying context, while its primary drawbacks are its speed and cost.
Model Pricing
Current Pricing
| Feature | Price (per 1M tokens) |
|---|---|
| Prompt | $0.8 |
| Completion | $1.6 |
Price History
Available Endpoints
| Provider | Endpoint Name | Context Length | Pricing (Input) | Pricing (Output) |
|---|---|---|---|---|
|
AionLabs
|
AionLabs | aion-labs/aion-2.0-20260223 | 131K | $0.8 / 1M tokens | $1.6 / 1M tokens |
Benchmark Results
| Benchmark | Category | Reasoning | Strategy | Free | Executions | Accuracy | Cost | Duration |
|---|
Other Models by aion-labs
|
|
Released | Params | Context |
|
Speed | Ability | Cost |
|---|---|---|---|---|---|---|---|
| AionLabs: Aion-1.0 | Feb 04, 2025 | — | 131K |
Text input
Text output
|
★ | ★★★ | $$$$$ |
| AionLabs: Aion-1.0-Mini | Feb 04, 2025 | ~32B | 131K |
Text input
Text output
|
★★ | ★ | $$$$ |
| AionLabs: Aion-RP 1.0 (8B) | Feb 04, 2025 | 8B | 32K |
Text input
Text output
|
★★ | ★ | $$$ |