PLAN 01
Starter
For individual developers and early projects
$49 / month
- Starter Model API allowance
- Single-user API key management
- Basic request logs
- Standard concurrency
- Online support
PRICING
Clear, Flexible Infrastructure Plans
Choose a plan based on product stage, request concurrency, model mix, and GPU requirements.
MOST POPULAR
Most PopularProfessional
For AI product teams
$149 / month
- Higher concurrency
- Multi-model routing
- Team member management
- Usage reports
- Priority GPU scheduling
- Integration support
PLAN 03
Enterprise
For high-volume APIs and GPU workloads
Custom pricing
- Dedicated access and service targets
- Private or hybrid cloud options
- Team permissions and consolidated billing
- Allowlist and security policies
- Dedicated technical support
Exact allowances and model or GPU pricing depend on available resources and business requirements. Online payment is not enabled on this site.
How Billing Works
Model usage may be billed by input and output tokens, request volume, or committed allowance. GPU resources may be billed by configuration and runtime. Final pricing reflects availability, region, concurrency, and the required support scope.