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...
| Provider | In $/M | Out $/M | Context | Uptime |
|---|---|---|---|---|
| AionLabs | $0.800 | $1.60 | 33K | — |
Aion-RP 1.0 (8B) costs $0.800 per million input tokens and $1.60 per million output tokens via OpenRouter, making it 194th cheapest of 298 paid models.
Aion-RP 1.0 (8B) generates around 15 tokens per second with 880ms time-to-first-token (p50), the 278th fastest tracked model.
Aion-RP 1.0 (8B) supports a 33K-token context window and can output up to 33K tokens. It accepts text input.