6 plans · USD pricing
Pay for what you use
From shared model access to dedicated GPU compute. Every plan includes all 270+ models with automatic routing and failover.
Shared Model API
Shared access to all 270+ models
$9/mo
- All 270+ (shared)
- 30 req/min
- 1,200/mo requests
- Community support
API Starter
Dedicated API keys, all models
$19/mo
- All 270+
- 50 req/min
- 2,500/mo requests
- Community support
Most popular
API Pro
Priority routing + fine-tuning
$49/mo
- All 270+ (priority)
- 100 req/min
- 6,000/mo requests
- Custom fine-tuning
- Email support
Dedicated AI Agent
Personal AI agent instance
$89/mo
- All 270+ (dedicated)
- 100 req/min
- 10,000/mo requests
- Dedicated instance
- GPU: Shared GPU
- Custom fine-tuning
- Priority support
API Team
Team collaboration + SSO
$149/mo
- All 270+ (priority)
- 300 req/min
- 20,000/mo requests
- Custom fine-tuning
- SSO & SAML
- Dedicated support
GPU Workbench
Dedicated GPU compute (A100/H100)
$299/mo
- All 270+ + custom
- Unlimited
- Unlimited requests
- Dedicated instance
- GPU: A100 / H100
- Custom fine-tuning
- SSO & SAML
- White-glove support
Full feature comparison
| Feature | Shared Model API $9/mo | API Starter $19/mo | API Pro $49/mo | Dedicated AI Agent $89/mo | API Team $149/mo | GPU Workbench $299/mo |
|---|---|---|---|---|---|---|
| Models | All 270+ (shared) | All 270+ | All 270+ (priority) | All 270+ (dedicated) | All 270+ (priority) | All 270+ + custom |
| Rate limit | 30 req/min | 50 req/min | 100 req/min | 100 req/min | 300 req/min | Unlimited |
| Monthly quota | 1,200/mo | 2,500/mo | 6,000/mo | 10,000/mo | 20,000/mo | Unlimited |
| Dedicated | ||||||
| Shared pool | ||||||
| GPU access | Shared GPU | A100 / H100 | ||||
| SSO / SAML | ||||||
| Fine-tuning | ||||||
| Support | Community | Community | Priority | Dedicated | White-glove |