Aion-RP 1.0 (8B)

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.

ChatAion Labs33k tokens$0.872 / $1.7441 · 1M

aion-labs/aion-rp-llama-3.1-8b

Context
33k tokens
Completion cap
32,768
Tools
No
JSON
No
Released
2025-02-04

Call it from Geek Hub

Same OpenAI SDK. Change the base URL and the model id.

curl https://api.geekhub.mx/v1/chat/completions \
  -H "Authorization: Bearer $GEEKHUB_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "aion-labs/aion-rp-llama-3.1-8b",
    "messages": [{"role": "user", "content": "Hola"}]
  }'
Get an API key

Frequently asked questions

What is Aion-RP 1.0 (8B)?
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. Aion-RP 1.0 (8B) runs on the Geek Hub API (OpenAI-compatible). Model id: aion-labs/aion-rp-llama-3.1-8b.
Is Aion-RP 1.0 (8B) free?
No. Input is $0.872 per 1M tokens and output is $1.7441 per 1M tokens on Geek Hub (markup included).
What is the context length of Aion-RP 1.0 (8B)?
Aion-RP 1.0 (8B) has a 33k tokens context window. It supports up to 32,768 completion tokens.
Does Aion-RP 1.0 (8B) support tool calling and structured outputs?
Aion-RP 1.0 (8B) does not advertise tool calling on this endpoint. Structured outputs are not listed for this endpoint.
When was Aion-RP 1.0 (8B) released?
Aion-RP 1.0 (8B) was released on 2025-02-04.

More models from Aion Labs