PORTIQ
Start building
CLEAR INPUTS. INFORMED DECISIONS.

Pay for what you use.
Plan for what you build.

Model your costs before you commit. Understand the inputs behind a token-based workload, from a single request to a month of conversations.

Usage-based

Plan around the input and output tokens your workload consumes.

Model-specific

Choose the model that fits your task and check its applicable rates.

Understandable

Separate request volume, token length, and rates in your estimates.

Model rates. Clear estimates.View current input, output, and cache rates. Review actual charges in your workspace.
WORKLOAD COST CALCULATORCurrent PORTIQ rates

Put a number on your idea.

Choose a model. Estimate fresh input, cache usage and output separately.

Input
Unavailable
Output
Unavailable
Cache read
Unavailable

Cache reads and writes are subsets of total input, never additional input. Estimates use current rates; actual requests freeze their rates at start. Text tokens only.

USD / 1M tokens · Current model ratesPricing is unavailable. This model cannot be called.
ESTIMATED MONTHLY COST—

Choose a priced model and valid quantities. Cache reads + writes must not exceed total input.

Input
—
Output
—
Cache read
—
Cache write
—
Cost per request
—
Σ (category tokens × PORTIQ rate)
× request count
How to budget for tokens →
LIVE MODEL PRICING

One rate card. Every token accounted for.

Current model rates for input, output, and cache usage. All prices are shown in USD per million tokens.

Loading current rates…

Pricing, explained.

READY WHEN YOU ARE

Make your next connection.

Your models. Your workspace. One clear path forward.

Start building