AionLabs: Aion-3.0

Text input Text output
Author's Description

Aion-3.0 is a multi-model roleplaying and storytelling system from AionLabs, built on the GLM family of models. It uses a collaborative generation process in which multiple specialized models each contribute...

Key Specifications
Cost
$$$$$
Context
131K
Released
Jul 07, 2026
Speed
Ability
Reliability
Supported Parameters

This model supports the following parameters:

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

This model supports the following features:

Response Format Tools Reasoning
Performance Summary

AionLabs: Aion-3.0, a multi-model roleplaying and storytelling system, demonstrates a strong overall performance profile, particularly in accuracy and reliability, despite its premium pricing and moderate speed. The model exhibits exceptional reliability, achieving a perfect 100% success rate across all 8 benchmarks, indicating consistent and dependable operation. In terms of accuracy, Aion-3.0 excels in several critical areas. It achieves perfect accuracy in both Hallucinations (Baseline) and General Knowledge (Baseline), indicating a robust ability to acknowledge uncertainty and a comprehensive understanding of factual information. It also performs exceptionally well in Coding (96.0% accuracy, 93rd percentile), Reasoning (98.0% accuracy, 85th percentile), Ethics (100.0% accuracy), and Mathematics (96.0% accuracy, 91st percentile), positioning it among the top performers in these demanding categories. A notable weakness appears in Instruction Following (Baseline), where its 67.7% accuracy places it in the 64th percentile, suggesting room for improvement in handling complex, multi-step directives. Email Classification also shows moderate performance at 96.0% accuracy (27th percentile). While Aion-3.0's speed performance is moderate, ranking in the 22nd percentile, its premium pricing (10th percentile) suggests a focus on quality and accuracy over cost-efficiency. Its perfect accuracy in Hallucinations, General Knowledge, and Ethics, often achieved at competitive costs within its accuracy tier, highlights its value proposition in these specific domains.

Model Pricing

Current Pricing

Feature Price (per 1M tokens)
Prompt $3
Completion $6
Input Cache Read $0.75

Price History

Available Endpoints
Provider Endpoint Name Context Length Pricing (Input) Pricing (Output)
AionLabs
AionLabs | aion-labs/aion-3.0-20260707 131K $3 / 1M tokens $6 / 1M tokens
Benchmark Results
Benchmark Category Reasoning Strategy Free Executions Accuracy Cost Duration
Other Models by aion-labs