Request-Based Pricing

Intentgine uses a simple per-request pricing model. Every API call counts as a fixed number of requests based on the endpoint.

Request Costs

All operations are billed at a flat per-request rate based on your plan tier.

Operation	Cost
Resolve	1 request
Resolve Quick	2 requests
Resolve Respond	2 requests
Classify	1 request
Classify (with extraction)	2 requests
Classify Respond	2 requests, 4 if extraction is enabled
Batch Classify	1 request per unique item (cache hits at half rate)

Classification Extraction Costs

When a classification set has extraction enabled, additional requests may be used:

Scenario	Requests
Standard classification	1
Classification + extraction	2

Example: “Turn on kitchen and turn off bedroom”

• Initial classification: 1 request
• Extraction with sub-classifications: 1 request (all sub-queries classified in single LLM call)
• Total: 2 requests

Benefit: Extraction saves both requests and HTTP round trips compared to manual approach:

• Manual approach: 1 API call + N additional API calls = 1 + N requests + N HTTP calls
• With extraction: 1 API call = 2 requests + 1 HTTP call
• Saves: N-1 requests and N HTTP round trips

See the Classification Extraction Guide for details.

How Billing Works

1. Subscription: You subscribe to a monthly plan that includes a set number of requests (e.g., 15,000 requests/month).
2. Overage Packs: If you exceed your monthly allocation, purchase overage packs (one-time, never expires).
3. Deduction: Requests are deducted from your balance in real-time as you make API calls.
4. Exhaustion: If your balance hits zero, API requests will return 402 Payment Required until you purchase more.

Pricing Tiers

Plan	Price	Requests	Per-Request Rate
Hobbyist	$7.50/mo	5,000	$0.00150
Starter	$22.05/mo	15,000	$0.00147
Business	$71.50/mo	50,000	$0.00143

Higher volume plans get better per-request rates due to improved cache efficiency at scale.