Loading the SOTA2 catalog…
Wafer
Fastest open source LLMs for enterprise, providing serverless inference and dedicated endpoints for mission-critical AI workloads.
- Founded
- 2025
- Headquarters
- San Francisco
- Company size
- 1–10
- Products tracked
- 2
Products by Wafer
Pricing for Wafer
Usage Based, Enterprise Custom
This is the broad commercial model reported for Wafer. Product-level terms are listed below when available.
- Pricing model
- Usage Based
- Starting price
- Input $1.00 / Output $3.20 / Cache $0.10 per M tokens
- Pricing model
- Enterprise Custom
Trust profile
Security and compliance
No compliance claims have been published for this company.
TLS encryption for data in transit
Encryption at rest for stored logs
Access controls on internal systems
Audit logging
Zero Data Retention (ZDR) for Serverless on ZDR-supported models