AionLabs: Aion-3.0
aion-labs/aion-3.0
ReasoningToolsJSON
Intelligence
—
Design Elo
—
Speed
75
116th fastest
Latency
889ms
first token
Input price
$3.00
269th cheapest
Context
131K
33K max out
How it compares
Faster than62%
of all ranked models
Cheaper than11%
of all ranked models
Overview
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...
Providers & pricing (1)
| Provider | In $/M | Out $/M | Context | Uptime |
|---|---|---|---|---|
| AionLabs | $3.00 | $6.00 | 131K | 100% |
Specifications
Context window131K
Max output33K
Knowledge cutoff—
Input modalitiestext
Output modalitiestext
Prompt caching—
Cache read price$0.750/M
ModeratedNo
Aion-3.0 FAQ
How much does Aion-3.0 cost?
Aion-3.0 costs $3.00 per million input tokens and $6.00 per million output tokens via OpenRouter, making it 269th cheapest of 303 paid models.
How fast is Aion-3.0?
Aion-3.0 generates around 75 tokens per second with 889ms time-to-first-token (p50), the 116th fastest tracked model.
What is Aion-3.0's context window?
Aion-3.0 supports a 131K-token context window and can output up to 33K tokens. It accepts text input.