Home / Models / Aion Labs / Aion-3.0-Mini

Aion-3.0-Mini pricing and routing profile

Aion-3.0-Mini from Aion Labs lists at $0.70 per million input tokens and $1.40 per million output tokens, with a 131,072-token context window. Prices from OpenRouter's catalogue on 2026-09-28.

Input, per 1M tokens$0.70
Output, per 1M tokens$1.40
Cached input, per 1M$0.18
Context window131K
Confidence signalNot exposed

Tool callingReasoning control

Cost per 1,000 requests

Request shapeList cost
Classification or routing (600 tokens in, 10 out)$0.434
Chat reply (2,000 in, 400 out)$1.96
Retrieval-augmented answer (8,000 in, 500 out)$6.30

Before prompt caching. Try your own shape in the cost calculator.

Can Gimbix route to it first?

Not as a first-answer model through OpenRouter: no host returns token log probabilities for Aion-3.0-Mini. It can still be the model Gimbix falls back to when a cheaper model is unsure.

Cheaper models that can answer first

Models priced below Aion-3.0-Mini that expose a confidence signal. Whether they answer your traffic as well is what a Gimbix pilot measures.

ModelInput / output per 1MCheaper on a chat reply
Llama 3.3 Euryale 70B$0.65 / $0.7518%
DeepSeek V4 Flash Vision Exp$0.44 / $1.3228%
MiMo-V2.5-Pro$0.435 / $0.8738%
Qwen3.7 Plus$0.32 / $1.2841%
Muse Glimmer 30B$0.30 / $1.2045%
MiniMax M3$0.30 / $1.2045%

Questions

How much does Aion-3.0-Mini cost?

Aion-3.0-Mini lists at $0.70 per million input tokens and $1.40 per million output tokens on OpenRouter as of 2026-09-28. A typical chat reply of 2,000 input and 400 output tokens costs about $1.96 per 1,000 requests.

What is the context window of Aion-3.0-Mini?

131,072 tokens.

Can a cheaper model replace Aion-3.0-Mini?

Sometimes. Gimbix proves it on your own traffic before routing: the cheaper model must match Aion-3.0-Mini on one half of your requests and make at most three answers worse on the other.