RentGPU RentGPU
Find a GPU →
by Aion Labs

AionLabs: Aion-3.0.

text open weights 131K ctx
Cheapest input
$3.0/M
on OpenRouter
Cheapest output
$6.0/M
on OpenRouter
Hosted equiv.
~$2.16/hr
@ 100 tok/s on OpenRouter

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...

Where to use it

Cheapest hosted endpoints.

Provider Access $/M in $/M out
OpenRouter api aggregator $3.0 $6.0 Launch ↗
FAQ

Frequently asked.

How do I run AionLabs: Aion-3.0?
AionLabs: Aion-3.0 is open-weight, so you can self-host on rented GPUs. See the Run It Yourself tab for GPU configurations + cost estimates, or use one of the hosted inference providers listed on this page.
Where can I access AionLabs: Aion-3.0?
AionLabs: Aion-3.0 is available via OpenRouter. Each access option lists its own pricing (per million tokens or hourly hosting).
How much does it cost to run AionLabs: Aion-3.0?
API pricing starts at $3.0/M input tokens and $6.0/M output tokens. Self-hosting cost depends on the GPU you rent — see the Run It Yourself tab.
Is AionLabs: Aion-3.0 open-source or proprietary?
AionLabs: Aion-3.0 is open-weight under the license. You can download and self-host it.