+
+
+
+
Fast open inference, flat rate
Flat-rate API access to the fastest open-source models. Built for developers and AI agents.
Loved by
+ more
Featured
Wafer Pass
Pay first, onboard after. Weekly or annually, cancel anytime.
Save 20%WeeklyYearly
Read docsStarter
Solo devs, daily agents
$10/wk$10/wk
$416/yr billed annually- 1,000 requests per 5-hour window
- Access to every model Wafer hosts
Pro
PopularPower users, continuous agents
$25/wk$25/wk
$1040/yr billed annually- 5,000 requests per 5-hour window
- Zero Data Retention (ZDR) included
Backed by
Fifty Years
Y Combinator
Liquid 2
Jeff DeanChief Scientist at Google
Woj ZarembaCo-Founder at OpenAI
Dan FuHead of Kernels at Together
Charlie SonghurstMeta Board of Directors
Arash FerdowsiCo-Founder at Dropbox
Kawal GandhiOffice of the CTO at Google
NVIDIA Inception
Fifty Years
Y Combinator
Liquid 2
Jeff DeanChief Scientist at Google
Woj ZarembaCo-Founder at OpenAI
Dan FuHead of Kernels at Together
Charlie SonghurstMeta Board of Directors
Arash FerdowsiCo-Founder at Dropbox
Kawal GandhiOffice of the CTO at Google
NVIDIA Inception
Fifty Years
Y Combinator
Liquid 2
Jeff DeanChief Scientist at Google
Woj ZarembaCo-Founder at OpenAI
Dan FuHead of Kernels at Together
Charlie SonghurstMeta Board of Directors
Arash FerdowsiCo-Founder at Dropbox
Kawal GandhiOffice of the CTO at Google
NVIDIA Inception
Performance
AI that optimizes AI
Wafer agents autonomously profile, diagnose, and optimize inference across the entire stack. This means we can run the fastest AI on the planet on any AI hardware.
2.8xfaster than base SGLang
ExampleOutput throughput · Qwen3.5-397B · Input/Output: 1600 / 7000
4003002001000
408.4
144.8
WaferBase SGLang
tok/s (higher is better)
Enterprise inference optimization
Get set up with the best performance for any custom model, with inference optimization tailored to your hardware, workloads, and production constraints, in less than 24 hours.