Aion 3.5 Mini is described as a multi-model roleplaying and storytelling system from AionLabs, built on the GLM family of models. It is presented as the smaller, lower-cost sibling of Aion 3.5 and uses the same collaborative generation process in which multiple specialized models contribute to a response.
The model is identified as aion-labs/aion-3.5-mini in the available sources.
| Developer | AionLabs |
|---|---|
| Model ID | aion-labs/aion-3.5-mini |
| Release Date | September 23, 2026 |
| Context Window | 262,144 tokens (~262K) |
| Max Output Tokens | 32,768 tokens |
| Modalities | Text → Text |
| Capabilities | file input, parallel tool calls, reasoning, streaming, structured (JSON schema) output, tool/function calling, web search |
Model family
The model is described as being built on the GLM family of models.
System style
It uses a collaborative generation process where multiple specialized models contribute to one response.
Roleplay and storytelling
The model is positioned for roleplaying and storytelling use cases.
Smaller sibling
It is described as the smaller, lower-cost sibling of Aion 3.5.
API identifier
The exact model id shown in the sources is aion-labs/aion-3.5-mini.
Narrative generation
Suitable for generating structured stories and narrative text.
Roleplaying applications
Positioned for roleplaying-style interactions and character-driven outputs.
Mature or darker themes
Sources say it handles mature or darker themes with notable nuance.
Aion 3.5
Described as the larger sibling model in the same AionLabs line.
Aion 3.0 Mini
Named in source material as the predecessor model that Aion 3.5 Mini replaces.
Sources: https://www.aionlabs.ai/docs/api-reference/ · https://www.orcarouter.ai/blog/aion-3-5-mini-release · https://pi.dev/models/openrouter/aion-labs-aion-3-5-mini
Measured on the AI/ML API gateway across live traffic. Figures are medians unless stated. Last updated 2026-10-12.
Interactive fiction and roleplaying games with dynamic, evolving narratives are a stated fit for Aion 3.5 Mini.
Long-form content generation with consistent context is another documented use, with the model described as suitable for producing extended output while maintaining narrative coherence.
AI agents that need tool use, web search, and structured data output are also explicitly listed as a use case.
Private, low-cost automation for classification, routing, or lightweight coding tasks is documented as a further fit for the model.
import requests r = requests.post( "https://api.aimlapi.com/v1/chat/completions", headers={"Authorization": "Bearer " + AIMLAPI_KEY}, json={ "model": "aion-labs/aion-3.5-mini", "messages": [ { "role": "user", "content": "Hello!" } ] }, ) print(r.json())
const r = await fetch("https://api.aimlapi.com/v1/chat/completions", { method: "POST", headers: { Authorization: `Bearer ${process.env.AIMLAPI_KEY}`, "Content-Type": "application/json", }, body: JSON.stringify({ "model": "aion-labs/aion-3.5-mini", "messages": [ { "role": "user", "content": "Hello!" } ] }), }); console.log(await r.json());
curl -X POST https://api.aimlapi.com/v1/chat/completions \ -H "Authorization: Bearer $AIMLAPI_KEY" \ -H "Content-Type: application/json" \ -d '{"model":"aion-labs/aion-3.5-mini","messages":[{"role":"user","content":"Hello!"}]}'
OpenAI-compatible — swap the base URL and it works with your existing SDK.
| Type | Price |
|---|---|
| Input | |
| Output | |
| Cached input |
Aion 3.5 Mini has a documented cache-read rate of $0.18/M tokens, with no cache-write premium listed in the available source.
