Pricing

Know what you pay before you ship.

Published inference rates, no hidden tiers. Providers see the same economics on every job they accept.

Open Scalattice Cloud
  • Per-token billing
  • No hidden tiers
  • Live dashboard
Laptop showing usage metrics and spend analytics
Published rates and live usage in one place
Per-tokenInput & output billed separately
PublishedRates before you ship
SharedSame economics for both sides
LiveUsage in Scalattice Cloud

Developers

Per-token inference.

Billed per million input and output tokens. Rates vary by model size and region. Compare against your current vendor in Scalattice Cloud.

Small Fast models for chat and tools
Large Reasoning and long context
Regional Pick geography at request time 
# Per-million tokens
qwen-3.6        in $0.18  out $0.72
mistral-large   in $2.10  out $6.30
deepseek-r1     in $0.55  out $2.19
llama-3-70b     in $0.59  out $0.79
Full rate card in Scalattice Cloud
Example models Qwen Mistral DeepSeek Llama

Providers

Earn per job served.

You set availability. We match paying workloads. Payouts tracked live with no fees.

Share

Revenue split

Transparent percentage on every completed inference job.

Payouts

Monthly cycles

Withdraw when you hit the minimum threshold.

Control

Your schedule

Pause capacity anytime from the provider dashboard.

# Provider dashboard: this month
jobs completed    847
tokens served     12.4M
earnings          $284.50
next payout       Jul 1
Live earnings on Scalattice Cloud

Enterprise

Volume and committed use.

Teams running steady production load can talk to us about committed capacity and custom regions.

Committed capacity

Reserve GPU pools for predictable latency and spend.

Custom regions

Deploy to jurisdictions your compliance team requires.

Invoicing

Annual contracts and PO-based billing for finance teams.

Contact the team