Aion Labs

Aion-RP 1.0 (8B)

Generally available33K context

Summary

Aion-RP 1.0 (8B) is a language model from Aion Labs, released on 4 Feb 2025. It accepts text and generates text, with a 33K-token context window and up to 29K output tokens per response.

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...

Last verified 4 Oct 2026. Every figure on this page links to its source.

Specifications

DeveloperAion Labs
Release date4 Feb 2025 [OpenRouter]
StatusGenerally available
Context window33K (32,768 tokens) [OpenRouter]
Max output29K tokens [OpenRouter]
Knowledge cutoff31 Dec 2023 [OpenRouter]
InputText [OpenRouter]
OutputText [OpenRouter]
Reasoning modeNo [OpenRouter]
Tool callingNo [OpenRouter]
Structured outputNo [OpenRouter]

Aion-RP 1.0 (8B) API pricing by provider

USD per million tokens. Sorted by input price.

We do not currently track a paid API listing for this model.

Frequently asked questions

What is the context window of Aion-RP 1.0 (8B)?

Aion-RP 1.0 (8B) has a context window of 32,768 tokens (33K) and can generate up to 29,491 tokens in a single response, according to OpenRouter.

When was Aion-RP 1.0 (8B) released?

Aion Labs released Aion-RP 1.0 (8B) on 4 Feb 2025, according to OpenRouter.

Similar models from other labs

Comparable on output type, weights, release date, price and context window. Prices are the lowest listed, USD per million tokens.

ModelLabReleasedContextInput $/1MOutput $/1MWeights
Mistral Small 3Mistral AI30 Jan 202533K$0.05$0.08Open
SabaMistral AI17 Feb 202533K$0.20$0.60Closed
Skyfall 36B V2Thedrummer10 Mar 202533K$0.55$0.80Open
Magnum v4 72BAnthracite ORG22 Oct 202433K$2.50$5Open
Qwen-VL OCRAlibaba (Qwen)28 Oct 202434K$0.07$0.16Closed
Qwen 3 Embedding 4BAlibaba (Qwen)5 Jun 202533K$0.01–Open

Change history

  • No longer listed on openrouter

Sources