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-3.0

aion-labs/aion-3.0
TextInput: textToolsReasoning131KAdded Jul 7, 2026

Try AionLabs: Aion-3.0 now

Runs on your balance at the prices above. New accounts start with free usage.

One API. Every model.

5 of 5 free messages left today. A free account adds free usage and an API key.Create free accountSign in

Session cost $0.00

AionLabs: Aion-3.0 at a glance

  • Input price is 567% higher than the median of 434 Text models.
  • Context window of 131,072 tokens, enough for long documents and multi-turn conversations.
  • Supports tool (function) calling for agents and integrations.
  • Supports reasoning effort control.
  • A typical request (1,000 input / 500 output tokens) costs about $0.02.

About AionLabs: Aion-3.0

AionLabs: Aion-3.0 is a text model from AionLabs. It is a multi-model roleplaying and storytelling system built on the GLM family of models, and it uses a collaborative generation process in which multiple specialized models each contribute to the output. That design means the model is not a single monolithic network but a coordinated set of components, which is worth keeping in mind when you think about how it behaves in production.

The model works with text input and produces text output. It has a context window of 131072 tokens, which is large enough to hold long conversations, extended narrative passages or sizeable reference documents alongside your instructions. The maximum output is 32768 tokens, so responses can be long when you need them to be, though you can of course cap them yourself per request.

Because Aion-3.0 is built for roleplaying and storytelling, the obvious uses follow from that: character driven chat, interactive fiction, long form narrative drafting, world building with persistent context, and conversational agents that need to stay in persona across many turns. The collaborative generation approach is aimed at story and dialogue quality rather than at narrow classification or extraction tasks, so treat it as a general purpose text generator with a strong leaning toward creative and conversational work.

You call it through api14's OpenAI-compatible API using the model id "aion-labs/aion-3.0", so existing OpenAI SDKs and clients work with only the base URL and key changed. The supported request parameters are include_reasoning, max_tokens, reasoning, response_format, temperature, tool_choice, tools and top_p. That combination covers sampling control, output length, structured output via response_format, and function calling via tools with tool_choice, plus explicit switches for reasoning behaviour.

If your task is purely deterministic extraction, classification or strict format conversion with no conversational element, a smaller general purpose model may be simpler and cheaper to operate. Aion-3.0 is at its most useful when the job involves sustained dialogue, character consistency or narrative generation over long inputs.

How to call the AionLabs: Aion-3.0 API

  1. Create an API key in your dashboard.
  2. Install the official openai SDK for your language.
  3. Set baseURL to https://api14.com/api/v1 and model to "aion-labs/aion-3.0".
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-3.0",
  "messages": [
    {
      "role": "user",
      "content": "Explain vector databases in two sentences."
    }
  ]
});
console.log(result.choices[0].message.content);

Supported parameters

include_reasoningmax_tokensreasoningresponse_formattemperaturetool_choicetoolstop_p

Specifications

Context length
131,072
Max output
32,768
Input
text
Output
text

Requests on api14 · last 7 days

10-1710-1810-1910-2010-2110-2210-23

AionLabs: Aion-3.0: frequently asked questions

How much does the AionLabs: Aion-3.0 API cost?
AionLabs: Aion-3.0 costs Input $10.50 / 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-3.0?
AionLabs: Aion-3.0 reads up to 131,072 tokens per request: prompt, history and documents together. It writes up to 32,768 output tokens per response.
What can AionLabs: Aion-3.0 do?
AionLabs: Aion-3.0 accepts text and returns text. It supports tool calling, reasoning effort control.
How do I call AionLabs: Aion-3.0 from my code?
Point any OpenAI SDK at https://api14.com/api/v1 and set the model to "aion-labs/aion-3.0". No other code changes. Copy a ready example from the code panel on this page.
What are alternatives to AionLabs: Aion-3.0?
Comparable Text models at a similar price: AionLabs: Aion 3.5, Mistral: Mistral Medium 3.5, Anthropic: Claude Sonnet 4.6 (batch). Each runs through the same API key, so switching is one string.

AionLabs: Aion-3.0 community

New topic

This community has no topics yet. Open the first one about AionLabs: Aion-3.0.