Aion-RP 1.0 (8B)

Open weight

AionLabs · Released February 2025 · Knowledge cutoff December 2023

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...

Facts and pricing

Provider
AionLabs
Context window
33K tokens
Input price
8.8 credits / 1M tokens ($0.80 raw)
Output price
17.6 credits / 1M tokens ($1.60 raw)
Vision (image input)
No
Tool calling
No
Extended reasoning
No

Credits are what Zeplik bills: 1 credit = $0.10, computed from the raw provider rate with a 1.10x margin. Raw prices shown per 1M tokens.

Try Aion-RP 1.0 (8B) now

Ask Aion-RP 1.0 (8B) anything. Your prompt opens in the Zeplik app with this model selected.

Aion-RP 1.0 (8B)

What Aion-RP 1.0 (8B) is best for

AionLabs family

ModelContextInput cr/MOutput cr/MReleased
Aion-3.0-Mini131K7.715.4July 2026
Aion-3.0131K33.066.0July 2026
Aion-2.0131K8.817.6February 2026
Aion-RP 1.0 (8B)33K8.817.6February 2025

Frequently asked questions

What is Aion-RP 1.0 (8B)?
Aion-RP 1.0 (8B) is an AI model by AionLabs. 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...
How much does Aion-RP 1.0 (8B) cost on Zeplik?
Input tokens cost 8.8 credits per million and output tokens 17.6 credits per million (1 credit = $0.10; the raw provider rates are $0.80 and $1.60 per million). New accounts start with free credits.
How long can a conversation with Aion-RP 1.0 (8B) be?
Aion-RP 1.0 (8B) has a 33K-token context window (32,768 tokens), which covers the conversation plus any documents you attach.
Does Aion-RP 1.0 (8B) support images and tools?
Aion-RP 1.0 (8B) is text-only and does not support tool calling.

Related models

Aion-3.0-MiniFast and light

Aion-3.0 Mini is a multi-model roleplaying and storytelling system from AionLabs, built on the DeepSeek family of models. It uses a collaborative generation process in which multiple specialized models each...

131K ctx15.4 cr/M outJuly 2026
Aion-3.0Frontier

Aion-3.0 is a multi-model roleplaying and storytelling system from AionLabs, built on the GLM family of models. It uses a collaborative generation process in which multiple specialized models each contribute...

131K ctx66.0 cr/M outJuly 2026
Aion-2.0General purpose

Aion-2.0 is a variant of DeepSeek V3.2 optimized for immersive roleplaying and storytelling. It is particularly strong at introducing tension, crises, and conflict into stories, making narratives feel more engaging....

131K ctx17.6 cr/M outFebruary 2026
GPT-5.6 Luna ProFrontier

GPT-5.6 Luna Pro is the same underlying model as [GPT-5.6 Luna](https://openrouter.ai/openai/gpt-5.6-luna), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. Learn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode

1.1M ctx66.0 cr/M outJuly 2026
GPT-5.6 LunaFrontier

GPT-5.6 Luna is a fast, cost-efficient model in OpenAI's GPT-5.6 series. It is suited for high-volume, latency-sensitive tasks such as chat, classification, and lightweight agentic workflows, providing capable reasoning for...

1.1M ctx66.0 cr/M outJuly 2026
GPT-5.6 Terra ProFrontier

GPT-5.6 Terra Pro is the same underlying model as [GPT-5.6 Terra](https://openrouter.ai/openai/gpt-5.6-terra), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. Learn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode

1.1M ctx165 cr/M outJuly 2026
Aion-RP 1.0 (8B) - AionLabs AI Model | Zeplik Chat