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...
With CoreAI, you can start chatting with AionLabs: Aion-RP 1.0 (8B) instantly — no separate subscription needed. CoreAI lets you chat with AionLabs: Aion-RP 1.0 (8B) alongside 300+ other AI models from Aion-labs and other providers like OpenAI, Anthropic, Google, Meta, and more.
AionLabs: Aion-RP 1.0 (8B) holds the #387 spot for context size out of 413 chat models in the CoreAI catalog — 33K tokens, roughly 24,576 words or 49 pages of text in a single conversation. On price, it is the #109 cheapest of 198 standard-tier models by input cost. It joined the catalog on 2025-02-04.
Every model in this table is available on CoreAI — open the web app and run the same prompt through AionLabs: Aion-RP 1.0 (8B) and AionLabs: Aion-2.0 side by side to judge with your own eyes.
A typical question (about 1,000 tokens in, 500 out) runs $0.00160 on AionLabs: Aion-RP 1.0 (8B)'s raw per-token rates; a heavy session with a 50K-token document costs about $0.048. On CoreAI you don't juggle these numbers — one subscription covers AionLabs: Aion-RP 1.0 (8B) and 300+ other models under a plan usage limit, with no API keys. See plans.
AionLabs: Aion-RP 1.0 (8B) handles 33K tokens of context — roughly 24,576 words, or about 49 pages of text in one conversation.
AionLabs: Aion-RP 1.0 (8B)'s underlying rates are $0.8 per 1M input tokens and $1.6 per 1M output tokens. On CoreAI it is included in one subscription alongside 300+ models, so there is no per-token billing to manage.
No — AionLabs: Aion-RP 1.0 (8B) is text-only. If you need image understanding, its standard-tier peers with vision are listed in the comparison table above.
No — AionLabs: Aion-RP 1.0 (8B) answers directly without an extended reasoning phase, which usually means faster responses.
Open the CoreAI web app or the iOS/Android app, pick AionLabs: Aion-RP 1.0 (8B) in the model selector, and chat — no API key, no per-token billing. One subscription covers AionLabs: Aion-RP 1.0 (8B) and 300+ other models.
The closest alternatives on CoreAI are AionLabs: Aion-2.0, Qwen2.5 Coder 32B Instruct, IBM: Granite 4.0 Micro — similar tier and capability. The fastest way to choose is running one prompt through them side by side in CoreAI's Compare view.
Chat with AionLabs: Aion-RP 1.0 (8B) and 300+ other AI models — all in one app.