///PRICING_MODELS
Scale without limits
Flexible infrastructure for teams of all sizes. Start small, scale indefinitely.
Monthly
Yearly
20% off
FEATURES
Starter
$8
/mo
Pro
$40
/mo
Business
Custom
Model
Llama 3
GPT-4o
Opus / Sonnet
Tokens
8k
128k
1M+
Rate Limit
50 req/min
5,000 req/min
Custom
No Retention
History
7 Days
90 Days
Custom
Residency
US Only
US / EU
Global
SSO
Deploy
VPC
Dedicated GPU
H100 Cluster
Uptime
Best efforts
99.9%
Custom
///SUPPORT
Frequently Asked Questions
Common operational inquiries regarding architecture, security protocols, and deployment strategies.
Do you train on my data?
What is the API latency?
Can I deploy on-premise?
How is data encrypted?
Do you support custom fine-tuning?
What happens if I hit the rate limit?
///SUPPORT
Frequently Asked Questions
Common operational inquiries regarding architecture, security protocols, and deployment strategies.
Do you train on my data?
What is the API latency?
Can I deploy on-premise?
How is data encrypted?
Do you support custom fine-tuning?
What happens if I hit the rate limit?
///SUPPORT
Frequently Asked Questions
Common operational inquiries regarding architecture, security protocols, and deployment strategies.