AionLabs: Aion 3.5 Mini

Text input Text output
Author's Description

Aion 3.5 Mini is a multi-model roleplaying and storytelling system from AionLabs, built on the GLM family of models. It is the smaller, lower-cost sibling of Aion 3.5 and uses...

Key Specifications
Cost
$$$$$
Context
262K
Released
Sep 23, 2026
Speed
Ability
Reliability
Supported Parameters

This model supports the following parameters:

Top P Max Tokens Temperature Tool Choice Response Format Include Reasoning Tools Reasoning
Features

This model supports the following features:

Tools Response Format Reasoning
Performance Summary

AionLabs: Aion 3.5 Mini, a multi-model roleplaying and storytelling system, demonstrates exceptional reliability with a 99% success rate across benchmarks, indicating consistent and usable responses. However, its speed performance tends to be slower, ranking in the 13th percentile, and its pricing is moderate, placing it in the 25th percentile. The model exhibits strong performance in specialized areas such as Coding and Mathematics, achieving 96.0% and 94.0% accuracy respectively, positioning it in the 94th and 72nd percentiles. It also shows commendable reasoning capabilities (96.0% accuracy, 75th percentile) and a low hallucination rate (96.0% accuracy, 53rd percentile). General Knowledge is also a strength at 99.0% accuracy. A notable weakness is its performance in Email Classification, where it scored 91.0% accuracy, placing it in the 13th percentile. Instruction Following also presents a moderate area for improvement at 64.0% accuracy. Overall, Aion 3.5 Mini is a highly reliable model with particular strengths in technical and logical tasks, though its speed and certain classification tasks could be enhanced.

Model Pricing

Current Pricing

Feature Price (per 1M tokens)
Prompt $0.7
Completion $1.4
Input Cache Read $0.18

Price History

Available Endpoints
Provider Endpoint Name Context Length Pricing (Input) Pricing (Output)
AionLabs
AionLabs | aion-labs/aion-3.5-mini-20260923 262K $0.7 / 1M tokens $1.4 / 1M tokens
Benchmark Results
Benchmark Category Reasoning Strategy Free Executions Accuracy Cost Duration
Other Models by aion-labs