AionLabs: Aion-RP 1.0 (8B)
Aion-RP 1.0 (8B) is a text-only model from AionLabs built around roleplay use cases. It accepts text input and can return up to 32,768 tokens within a 32,768-token context window. It does not support tool calls, reasoning modes, or structured output, so workflows that depend on function calling or schema-constrained responses will need a different option. On price, it sits at $0.80 per million input tokens and $1.60 per million output tokens, which is a modest rate for a specialized model. The practical catch is that there is no independent benchmark coverage to anchor expectations, making performance claims unverified at this point. Buyers who want a dedicated roleplay-focused model and are comfortable running their own evaluations may find it worth testing, but anyone requiring proven general capability scores before committing should wait for third-party coverage to emerge.
- Model ID
- aion-labs/aion-rp-llama-3.1-8b
- Vendor
- aion-labs
- Released
- February 2025
- Tokenizer
- Other
- Input Modalities
- text
- Output Modalities
- text
- Max Output
- 32,768 tokens
- Tool Calling
- not supported
- Structured Output
- not supported
- Reasoning Mode
- not supported
- Vision
- text only
- Audio
- no
- Moderated
- no
What it costs in practice
Computed from the current $0.80/M input and $1.60/M output rates. Run your own numbers →
| Job | Tokens | Cost |
|---|---|---|
| Summarize a 50-page report | 30k in / 1.5k out | $0.03 |
| Classify 1,000 customer emails | 500k in / 50k out | $0.48 |
| A month of a busy support chatbot | 5M in / 2M out | $7.20 |
Similar models
Quick answers
- How much does AionLabs: Aion-RP 1.0 (8B) cost?
- $0.80 per million input tokens and $1.60 per million output tokens.
- What is AionLabs: Aion-RP 1.0 (8B)'s context window?
- 32,768 tokens, roughly 49 pages of text in a single request.
- Can AionLabs: Aion-RP 1.0 (8B) process images?
- No, it is text-only on the input side.