modelgrep
A

AionLabs: Aion-2.0

aion-labs/aion-2.0

Reasoning
Use via OpenRouter ↗
Intelligence
Design Elo
Speed
27
244th fastest
Latency
2.0s
first token
Input price
$0.800
192nd cheapest
Context
131K
33K max out

How it compares

Faster than17%
of all ranked models
Cheaper than36%
of all ranked models

Overview

Aion-2.0 is a variant of DeepSeek V3.2 optimized for immersive roleplaying and storytelling. It is particularly strong at introducing tension, crises, and conflict into stories, making narratives feel more engaging....

Providers & pricing (1)

ProviderIn $/MOut $/MUptime
AionLabs$0.800$1.60100%

Specifications

Context window131K
Max output33K
Knowledge cutoff
Input modalitiestext
Output modalitiestext
Prompt caching
Cache read price$0.200/M
ModeratedNo

Aion-2.0 FAQ

How much does Aion-2.0 cost?

Aion-2.0 costs $0.800 per million input tokens and $1.60 per million output tokens via OpenRouter, making it 192nd cheapest of 298 paid models.

How fast is Aion-2.0?

Aion-2.0 generates around 27 tokens per second with 2.0s time-to-first-token (p50), the 244th fastest tracked model.

What is Aion-2.0's context window?

Aion-2.0 supports a 131K-token context window and can output up to 33K tokens. It accepts text input.

Compare head-to-head