Simple pricing, pay as you go
Starter
$
SAAS
Scale
$
PRIVATE INSTANCE
Enterprise
$
SELF-HOSTED
Configuration
Rate limit
Up to 6000 requests per min
Unlimited
Unlimited
Token limit
up to 2M tokens per min
Unlimited
Unlimited
Mix-models
Up to 3 Routing & Reasoning mix-models
Unlimited
Unlimited
Max memory
10 Go storage
100 Go included and custom storage
Unlimited
Instances
Shared instances
Access to custom RAM, CPU, and GPU instances
On-prem + priority access to GPUs including H100
Seats
1
4
Unlimited
SLA
99,9%
99,9%
Support
Email support
Priority support via private Slack channel
Premium support 24/7
Instances
Shared instances
Access to custom RAM, CPU, and GPU instances
On-prem + priority access to GPUs including H100
Fine-tuning and RL
Private instance
Reinforment learning
Technical support
Hosting
Deployment on any infrastructure GCP, AWS, Azure
Advanced MoAI customization
Import & export Data
Data preparation