by 01.AI

Yi-Lightning.

text open weights 16K ctx
Cheapest input
$0.14/M
on 01.AI Platform
Cheapest output
$0.14/M
on 01.AI Platform
Hosted equiv.
~$0.05/hr
@ 100 tok/s on 01.AI Platform

01.AI's fastest production model. Tops the LMSYS Arena Chinese leaderboard.

Where to use it

Cheapest hosted endpoints.

Provider Access $/M in $/M out
01.AI Platform api direct $0.14 $0.14 Launch ↗
01.AI Platform api direct $0.14 $0.14 Launch ↗
Sources

Official references.

FAQ

Frequently asked.

How do I run Yi-Lightning?
Yi-Lightning 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 Yi-Lightning?
Yi-Lightning is available via 01.AI Platform. Each access option lists its own pricing (per million tokens or hourly hosting).
How much does it cost to run Yi-Lightning?
API pricing starts at $0.14/M input tokens and $0.14/M output tokens. Self-hosting cost depends on the GPU you rent — see the Run It Yourself tab.
Is Yi-Lightning open-source or proprietary?
Yi-Lightning is open-weight under the proprietary license. You can download and self-host it.