AionLabs: Aion-1.0

Text input Text output
Author's Description

Aion-1.0 is a multi-model system designed for high performance across various tasks, including reasoning and coding. It is built on DeepSeek-R1, augmented with additional models and techniques such as Tree...

Key Specifications
Cost
$$$$$
Context
131K
Released
Feb 04, 2025
Speed
Ability
Reliability
Supported Parameters

This model supports the following parameters:

Temperature Include Reasoning Reasoning Max Tokens Top P
Features

This model supports the following features:

Reasoning
Performance Summary

AionLabs: Aion-1.0, a multi-model system built on DeepSeek-R1 with augmentations like Tree of Thoughts and Mixture of Experts, demonstrates exceptional performance across various metrics. It consistently ranks among the fastest models and offers highly competitive pricing, achieving an "Infinityth percentile" in both speed and cost across 8 benchmarks. Reliability is outstanding, with a 100% success rate across all benchmarks, indicating minimal technical failures. In terms of specific performance, Aion-1.0 exhibits strong capabilities in Coding (96.0% accuracy, 96th percentile), Reasoning (97.9% accuracy, 87th percentile), and Mathematics (94.0% accuracy, 78th percentile), aligning with its design as a powerful reasoning model. Its Email Classification performance is perfect at 100% accuracy, also noted for being the most accurate at its price point and speed. General Knowledge is robust at 99.5% accuracy. A notable weakness is its Instruction Following, where it scored 0.0% accuracy. Hallucinations are relatively low at 92.0% accuracy, though this places it in the 43rd percentile. Ethics performance is moderate at 91.0% accuracy (21st percentile). Overall, Aion-1.0 is a highly reliable and cost-effective model with significant strengths in complex problem-solving and coding, though its instruction following requires improvement.

Model Pricing

Current Pricing

Feature Price (per 1M tokens)
Prompt $4
Completion $8

Price History

Available Endpoints
Provider Endpoint Name Context Length Pricing (Input) Pricing (Output)
AionLabs
AionLabs | aion-labs/aion-1.0 131K $4 / 1M tokens $8 / 1M tokens
Benchmark Results
Benchmark Category Reasoning Strategy Free Executions Accuracy Cost Duration
Other Models by aion-labs