Aion Labs: Aion-3.5-Mini
aion-labs/aion-3.5-mini
Try Aion-3.5-Mini for free in your browser, and add it to your app for free with Puter.js AI API.
Try it free Add to your app// npm install @heyputer/puter.js
import { puter } from '@heyputer/puter.js';
puter.ai.chat("Explain quantum computing in simple terms", {
model: "aion-labs/aion-3.5-mini"
}).then(response => {
document.body.innerHTML = response.message.content;
});
<html>
<body>
<script src="https://js.puter.com/v2/"></script>
<script>
puter.ai.chat("Explain quantum computing in simple terms", {
model: "aion-labs/aion-3.5-mini"
}).then(response => {
document.body.innerHTML = response.message.content;
});
</script>
</body>
</html>
Model Card
Aion-3.5-Mini is AionLabs' smaller, lower-cost multi-model roleplaying and storytelling system, released September 23, 2026 alongside the full Aion-3.5. It shifts architecture from its predecessor, Aion-3.0-Mini, which was built on the DeepSeek family; Aion-3.5-Mini moves to the GLM family, the same base already used by full-size Aion-3.5 and Aion-3.0.
It keeps the collaborative generation process behind the Aion line, in which multiple specialized models each contribute to a response, aimed at stronger narrative structure and more compelling tension and conflict, and handles mature or darker themes with notable nuance.
Compared to Aion-3.0-Mini, context doubles to 262,144 tokens with up to 32,768 output tokens, at an unchanged $0.70/$1.40 per million input/output price. Reasoning is always on, with three effort levels (low, high, max), high by default.
AionLabs has not published benchmarks for this release. It suits developers who want Aion-3.5's narrative approach at lower cost.
Context Window 262K
tokens
Max Output 33K
tokens
Input Cost $0.7
per million tokens
Output Cost $1.4
per million tokens
Release Date Sep 23, 2026
Try Aion-3.5-Mini for free
Try Aion-3.5-Mini instantly in your browser.
This playground uses the Puter.js AI API — no API keys or setup required.
More AI Models From Aion Labs
Aion-3.5
Aion-3.5 is AionLabs' latest multi-model roleplaying and storytelling system, released September 23, 2026 as the successor to Aion-3.0. Like its predecessor, it runs a collaborative generation process built on the GLM family of models, in which several specialized models each contribute to a response rather than one model generating the full output, aimed at stronger narrative structure and more compelling tension and conflict. Aion-3.5 doubles Aion-3.0's context window to 262,144 tokens with up to 32,768 tokens of output, at the same per-token price. It supports tool calling with tool_choice, and JSON-formatted responses without JSON-schema enforcement. AionLabs has not published a benchmark table for Aion-3.5, and no independent one exists yet, so its gains over Aion-3.0 beyond context length are unverified. It fits developers building interactive fiction, character-driven chat, or other creative-writing tools who want the narrative depth and mature-theme handling of the Aion line with more room for long conversations.
ChatAion-3.0
Aion-3.0 is a multi-model roleplaying and storytelling system from AionLabs, built on the GLM family of models. Rather than a single model generating the full response, it runs a collaborative generation process in which multiple specialized models each contribute, aimed at producing stronger narrative structure and more compelling tension and conflict. It handles mature and darker themes with notable nuance, continuing the roleplay and narrative focus of AionLabs' earlier Aion models such as Aion-2.0 and Aion-RP. The model supports a 131K-token context window with up to 32K tokens of output. Aion-3.0 is a good fit for developers building interactive fiction, character-driven chat, or other creative-writing tools where narrative depth and thematic nuance matter more than raw speed.
ChatAion-3.0-Mini
Aion-3.0-Mini is a multi-model roleplaying and storytelling system from AionLabs, built on the DeepSeek family of models rather than the GLM base used in the full Aion-3.0. Like its larger sibling, it runs a collaborative generation process in which multiple specialized models each contribute to a response, aimed at producing stronger narrative structure and more compelling tension and conflict. It handles mature and darker themes with notable nuance, continuing the roleplay and narrative focus of AionLabs' earlier Aion models. The model supports a 131K-token context window with up to 32K tokens of output. Pricing is $0.70 per million input tokens and $1.40 per million output tokens, roughly a quarter of Aion-3.0's cost, making it a fit for developers who want the same collaborative-generation approach to character-driven chat and interactive fiction at a lower price point.
Frequently Asked Questions
You can access Aion-3.5-Mini by Aion Labs through Puter.js AI API. Include the library in your web app or Node.js project and start making calls with just a few lines of JavaScript — no backend and no configuration required. You can also use it with Python or cURL via Puter's OpenAI-compatible API.
Aion-3.5-Mini is free to try with a Puter account. Every account includes a free AI allowance, and you can chat with it in the playground on this page. You can upgrade your account anytime for a larger allowance.
Aion-3.5-Mini is free to integrate using the Puter.js AI API. With the User-Pays Model, you can add AI to your app for $0, since users cover their own AI usage through their Puter account.
| Price per 1M tokens | |
|---|---|
| Input | $0.7 |
| Output | $1.4 |
Aion-3.5-Mini was created by Aion Labs and released on Sep 23, 2026.
Aion-3.5-Mini supports a context window of 262K tokens. For reference, that is roughly equivalent to 524 pages of text.
Aion-3.5-Mini can generate up to 33K tokens in a single response.
Yes — the Aion-3.5-Mini API works with any JavaScript framework, Node.js, or plain HTML through Puter.js. Just include the library and start building. See the documentation for more details.
Add Aion-3.5-Mini to your app for free
Developers can integrate Aion-3.5-Mini for free using the Puter.js AI API.
With the User-Pays Model, each user covers their own AI usage instead of the developer.