FLEXIBLE PRICING

Flexible Pricing for Every Enterprise

Transparent pricing with volume discounts and custom enterprise plans

PRICING MODELS

Choose Your Payment Model

Pay-as-you-go

No upfront commitment. Pay only for what you use with per-token pricing.

  • Instant access
  • No minimum spend
  • Scale up or down anytime

Reserved Capacity

Commit to usage volume for discounted rates and guaranteed capacity.

  • 15-30% discount
  • Priority allocation
  • Flexible terms

Enterprise Plan

Custom solutions with dedicated support and SLA guarantees.

  • Volume discounts
  • 24/7 premium support
  • Custom SLA
STANDARD API PRICING

Transparent Token-Based Pricing

deepseek/deepseek-v3.2
Context: 163,840
Input $0.25/M
Output $0.35/M
deepseek/deepseek-r1
Context: 64,000
Input $0.70/M
Output $2.50/M
qwen/qwen3.5-397b-a17b
Context: 262,144
Input $0.39/M
Output $2.34/M
qwen/qwen3-235b-a22b
Context: 131,072
Input $0.455/M
Output $1.82/M
google/gemma-4-31b-it
Context: 262,144
Input $0.14/M
Output $0.40/M
google/gemma-3-27b-it
Context: 131,072
Input $0.08/M
Output $0.16/M
minimax/minimax-m2.5
Context: 196,608
Input $0.15/M
Output $1.00/M
minimax/minimax-m2.7
Context: 204,800
Input $0.30/M
Output $1.20/M

Pricing per million tokens. All prices in USD. Volume discounts available for enterprise customers.

Ready to Get Started?

Talk to our sales team for custom pricing and enterprise solutions