Simple, Transparent Pricing
Pay only for what you use. Top up your account credits for API access to pay exactly for the tokens you consume, or contact us for dedicated GPU compute with transparent pricing.
Serverless Inference
Pay-as-you-go API access to open-source models.
- ✓ No monthly commitments
- ✓ Billed incrementally per token
- ✓ Access to all supported models
On Demand Deployments
Reserved GPU compute for consistent workloads.
- B200 SXM6 180GB$6.75 / hour
- H200 SXM5 141GB$3.34 / hour
- H100 SXM5 80GB$2.97 / hour
- A100 SXM4 80GB$1.71 / hour
- A100 SXM4 40GB$1.21 / hour
Payment Methods & Policies
We partner with Paddle as our Merchant of Record to securely process all payments globally. We accept all major credit cards, PayPal, and more depending on your region.
Prices are listed in USD. Taxes may apply depending on your billing location and will be calculated at checkout by Paddle.
For our refund guidelines, please see our Refund Policy.