# Aion RP 1.0 8B

Aion Labs

Aion-RP-Llama-3.1-8B ranks the highest in the character evaluation portion of the RPBench-Auto benchmark, a roleplaying-specific variant of Arena-Hard-Auto, where LLMs evaluate each other's responses. It is a fine-tuned base model rather than an instruct model, designed to produce more natural and varied writing.

## Technical Specifications

### Context Window

32,768 tokens

### Max Output

32,768 tokens

## Pricing

### Token Costs (per 1M tokens)

- Cache Miss Input: $0.80
- Non-Reasoning Output: $1.60

## Snapshots

1

## Legacy

### Made legacy on February 17, 2026

#### Reason

Niche 8B roleplay fine-tune; too small for production use

#### Recommended Replacement

[Qwen3.6 Plus](/content/models/alibaba-qwen3.6-plus/index.html)