Provisioned Throughput

Provisioned Throughput allows enterprise customers to purchase dedicated input and output token capacity for specific models. Buy units with a minimum 30-day commitment for predictable, high-performance API access.

• Predictable latency — Faster, more consistent response times compared to pay-as-you-go, even during peak usage
• Uncapped scale — Your purchased capacity adds directly to your rate limits; overages use standard pay-as-you-go rates
• High reliability — 99.9% uptime SLA with enterprise-grade availability guarantees

Each unit costs $10.00 per day and provides a fixed amount of tokens per minute (TPM):

Input Units  = Required Input TPM  ÷ TPM per Unit (Input)
Output Units = Required Output TPM ÷ TPM per Unit (Output)
Daily Cost   = (Input Units + Output Units) × $10

Example: You need 100,000 input TPM and 50,000 output TPM with grok-4-1-fast-reasoning:

• Input units: 100,000 ÷ 31,500 = 4 units
• Output units: 50,000 ÷ 12,500 = 4 units
• Daily cost: 8 × $10 = $80/day ($2,400 for 30 days)

1. Contact support@x.ai with your expected TPM and preferred models
2. Receive a custom quote based on your requirements
3. Sign the order form and your capacity will be activated

Once activated, your provisioned capacity is automatically applied to all API requests from your team.

You can control provisioned throughput behavior with these headers:

Requests exceeding your allocation fall back to standard rate limits at pay-as-you-go pricing.

Yes. You can add units at any time. Contact support to modify your allocation.

30 days per unit.