Aion-3.0-Mini is a multi-model roleplaying and storytelling system from AionLabs.
It is built on the DeepSeek family of models.
| Developer | AionLabs |
|---|---|
| Model ID | aion-labs/aion-3.0-mini |
| Release Date | July 6, 2026 |
| Context Window | 131,072 tokens (~131K) |
| Max Output Tokens | 32,768 tokens |
| Modalities | Image, Text → Text |
| Capabilities | file input, parallel tool calls, reasoning, streaming, structured (JSON schema) output, tool/function calling, vision, web search |
Model identity
The exact model id is aion-labs/aion-3.0-mini.
System design
It uses a collaborative generation process in which multiple specialized models each contribute to a response.
Narrative focus
The model is described as being tuned for immersive roleplay and storytelling.
Creative emphasis
Descriptions highlight stronger narrative structure, tension, conflict, and nuanced mature themes.
Availability
It is listed through OpenRouter-compatible provider catalogues.
Roleplay chat
Suitable for character-driven conversation experiences.
Interactive fiction
Fits interactive storytelling and narrative generation workflows.
Creative writing support
Useful for generating story structure and dramatic tension in fictional content.
Dialogue systems
Can support responses that rely on multi-part narrative collaboration.
Aion-3.0
A related model in the same family is referenced alongside Aion-3.0-Mini in provider catalogues.
Sources: https://developer.puter.com/ai/aion-labs/aion-3.0-mini/ · https://krater.ai/models/aion-3-0-mini · https://www.vibecoding.cz/llm/aion-labs-aion-3-0-mini/
Measured on the AI/ML API gateway across live traffic. Figures are medians unless stated. Last updated 2026-10-12.
Aion-3.0-Mini is documented as suited to character-driven chat applications, interactive storytelling, and persona-consistent dialogue.
It is also described as a fit for AI chatbots and virtual assistants.
Another documented use case is content writing and copywriting automation.
It is additionally listed for data analysis, summarization, and extraction.
import requests r = requests.post( "https://api.aimlapi.com/v1/chat/completions", headers={"Authorization": "Bearer " + AIMLAPI_KEY}, json={ "model": "aion-labs/aion-3.0-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-3.0-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-3.0-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 |
A documented pricing caveat for Aion-3.0-Mini is that OpenRouter lists a separate cache-read rate of $0.18 per 1M tokens, with cache-write priced at $0 in Pi’s model page.
| Model | Input | Output | Context | Best for |
|---|---|---|---|---|
Aion-3.0-Mini This page | Agentic workflows and structured output | |||
| Reasoning + agents | ||||
| Reasoning + agents |
Aion-3.0-Mini has a 131,072 tokens context window and can return up to 32,768 tokens.
Aion-3.0-Mini takes image, text as input and returns text.
Use aion-labs/aion-3.0-mini as the model id. Requests go to https://api.aimlapi.com/v1/chat/completions.
Aion-3.0-Mini became available on July 7, 2026.
Aion-3.0-Mini is priced at input $0.96278 / 1M tokens, output $1.92556 / 1M tokens, cached input $0.247572 / 1M tokens.
Yes, Aion-3.0-Mini can stream responses as they are generated.
Yes, Aion-3.0-Mini accepts image input alongside text.
Yes, it supports tool use including parallel tool calls.
