We use cookies. Cookies and browser storage keep you signed in and remember your preferences. With your permission we also measure how the site is used. You can any time. See our cookie policy.
AionLabs: Aion-RP 1.0 (8B)
aion-labs/aion-rp-llama-3.1-8bTry AionLabs: Aion-RP 1.0 (8B) now
Runs on your balance at the prices above. New accounts start with free usage.
One API. Every model.
Session cost $0.00
Settings
Advanced parameters
AionLabs: Aion-RP 1.0 (8B) at a glance
- Input price is 78% higher than the median of 434 Text models.
- Context window of 32,768 tokens, enough for long documents and multi-turn conversations.
- A typical request (1,000 input / 500 output tokens) costs about $0.00560.
About AionLabs: Aion-RP 1.0 (8B)
AionLabs: Aion-RP 1.0 (8B) is a text model from AionLabs, built on Llama 3.1 8B and fine-tuned for roleplay. AionLabs describes it as ranking highest in the character evaluation portion of the RPBench-Auto benchmark, a roleplaying-specific variant of Arena-Hard-Auto in which LLMs evaluate each other's responses. It was released by the provider on 4 February 2025.
The model takes text as input and returns text as output, so it works as a chat or completion model rather than a multimodal one. It has a context window of 32768 tokens and a maximum output of 29491 tokens, which leaves room for long conversations or extended generations within a single request. Its knowledge cutoff is 31 December 2023, so anything after that date is outside what it learned during training.
Because it is tuned for roleplay, the natural fit is character driven chat: interactive fiction, persona based assistants, dialogue for games or simulations, and any application where consistent character voice matters more than general knowledge. The 32768 token context helps when a scene or conversation needs to stay coherent across many turns, and the large output ceiling supports long in character replies. It is a text only model, so tasks that depend on images, audio or other modalities are out of scope.
You call it through api14's OpenAI-compatible API using the model id "aion-labs/aion-rp-llama-3.1-8b". Requests follow the usual chat completions shape, and the supported parameters are max_tokens, temperature and top_p. Use max_tokens to cap reply length, and temperature or top_p to steer how varied the character responses are. Other parameters you may be used to from other providers are not listed as supported here, so keep requests to this set.
Since it is an 8B fine-tune aimed at roleplay, it is not the obvious choice for tasks that lean on broad world knowledge or heavy reasoning, and its December 2023 cutoff means it will not know later events. For those cases a general purpose or larger model may fit better. For character work within its context and output limits, it is a focused option.
How to call the AionLabs: Aion-RP 1.0 (8B) API
- Create an API key in your dashboard.
- Install the official openai SDK for your language.
- Set baseURL to https://api14.com/api/v1 and model to "aion-labs/aion-rp-llama-3.1-8b".
import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://api14.com/api/v1",
apiKey: process.env.API14_API_KEY,
});
const result = await client.chat.completions.create({
"model": "aion-labs/aion-rp-llama-3.1-8b",
"messages": [
{
"role": "user",
"content": "Explain vector databases in two sentences."
}
]
});
console.log(result.choices[0].message.content);
Supported parameters
max_tokenstemperaturetop_pSpecifications
- Context length
- 32,768
- Max output
- 29,491
- Input
- text
- Output
- text
- Knowledge cutoff
- 2023-12-31
Requests on api14 · last 7 days
AionLabs: Aion-RP 1.0 (8B): frequently asked questions
- How much does the AionLabs: Aion-RP 1.0 (8B) API cost?
- AionLabs: Aion-RP 1.0 (8B) costs Input $2.80 / 1M tokens. It is charged from your USD balance only for successful requests; failed requests are free.
- What is the context window of AionLabs: Aion-RP 1.0 (8B)?
- AionLabs: Aion-RP 1.0 (8B) reads up to 32,768 tokens per request: prompt, history and documents together. It writes up to 29,491 output tokens per response.
- What can AionLabs: Aion-RP 1.0 (8B) do?
- AionLabs: Aion-RP 1.0 (8B) accepts text and returns text.
- How do I call AionLabs: Aion-RP 1.0 (8B) from my code?
- Point any OpenAI SDK at https://api14.com/api/v1 and set the model to "aion-labs/aion-rp-llama-3.1-8b". No other code changes. Copy a ready example from the code panel on this page.
- What are alternatives to AionLabs: Aion-RP 1.0 (8B)?
- Comparable Text models at a similar price: AionLabs: Aion-2.0, Z.ai: GLM 4.5V, Mistral: Devstral 2 2512. Each runs through the same API key, so switching is one string.
AionLabs: Aion-RP 1.0 (8B) community
New topicThis community has no topics yet. Open the first one about AionLabs: Aion-RP 1.0 (8B).