Loading
90 days of the enterprise, pro and team plans free, no card needed. See the plans
Aion Labs
aion-labs/aion-rp-llama-3.1-8bCatalogue: Indexed in the reference catalogue; nothing on this deployment answers as this model yet.
Published by the vendor; the platform bills at the target's declared price.
Aion Labs aion-labs/aion-rp-llama-3.1-8b
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...
Aion-RP 1.0 (8B) earns a request on quality for its task at its price; a short, general request would go to Nemotron 3.5 Super VL (free) instead - free per million input tokens against $0.80 here; and the hardest requests, where the quality floor rules it out, to Claude Opus 5.5 (batch). Your rules decide the floor; the trace shows the comparison for every request.
Lower input price and an intelligence index within 5 points (this model has no published index).
Nothing on this deployment answers as this model yet. Connect your own provider under Model providers, or add a target to your catalogue - the router picks it up without retraining.
# targets.yaml - declare a target that runs Aion-RP 1.0 (8B)
targets:
- id: aion-rp-llama-3-1-8b
kind: llm
name: Aion-RP 1.0 (8B)
metadata:
model: aion-labs/aion-rp-llama-3.1-8b # links the target to this catalogue entry
capabilities:
domains: [general]
supports_tools: false
context_window: 32768
cost:
usd_per_1k_tokens: 0.001200Input list price per million tokens; Aion-RP 1.0 (8B) is the 3rd cheapest of 6 listed.
Photo: RDNE Stock project
A higher intelligence index, best first, with the price it comes at.
The catalogue prints input and output prices and what three typical monthly workloads cost on each.
