Pricing

Know what you pay before you ship.

Published catalog rates, adjusted for demand and capacity. Providers earn a transparent share of each completed job.

Open Scalattice Cloud View models

Per-token billing
Catalog rates published
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

TransparentSame economics for devs and providers

LiveUsage in Scalattice Cloud

Live rates

Rates by model.

Loading live rates…

Developers

Per-token inference.

Billed per million input and output tokens. Rates vary by model and demand. Compare usage in Scalattice Cloud.

Published Rates you can quote before you ship

Per token Input and output billed separately

Demand Rates adjust for capacity

# Per-million tokens (live catalog)
# Loading published rates…

Live rates · open Scalattice Cloud for the full catalog

Catalog families

Qwen

Llama

DeepSeek

Gemma

Mistral

gpt-oss

Go to Scalattice Cloud for the full catalog

Providers

Earn per job served.

You set availability. Scalattice routes paying inference to your hardware. Payouts tracked in the dashboard with no connection fees.

Revenue split

The majority of developer token spend on each completed inference job.

Payouts

On demand

Request a payout any time your available balance is above the minimum threshold.

Control

Per-machine schedule

Set availability windows for each GPU from Scalattice Cloud.

# Provider dashboard (example)
jobs completed    847
tokens served     12.4M
earnings          $284.50
available         $42.50
# request payout any time (min $10)

Example earnings (illustrative)

Enterprise

Volume and committed use.

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