fineprint what AI companies quietly changed · RSS

2026-06-14 15:56 UTC · perplexity/api-pricing · live page

2 line(s) added, 1 removed.

Summary by fallback. It may be wrong; the diff below is what actually changed. Raw: 7f65686463-perplexity-api-pricing.diff · commit 7f65686463

diff --git a/snapshots/perplexity/api-pricing.md b/snapshots/perplexity/api-pricing.mdindex b00791c..58f77a1 100644--- a/snapshots/perplexity/api-pricing.md+++ b/snapshots/perplexity/api-pricing.md@@ -25,6 +25,7 @@ When using tools with the Agent API: | `people_search` | $0.005 per invocation | Looks up professionals, employees, and people. $5 per 1,000 tool invocations | | `finance_search` | $0.005 per invocation | Retrieves financial data and market information. $5 per 1,000 tool invocations |+| `sandbox` | $0.03 per session | Isolated container for executing code during an Agent API request. A session covers up to 20 minutes of active use for billing purposes — this is the billing window, not a runtime cap. SDK search queries made from inside the sandbox are billed at $0.005 per request (same as `web_search`). | -Tool costs are separate from model token costs. Each tool invocation is billed individually — if a model makes 3 `web_search` calls and 2 `people_search` calls during a request, you pay model tokens + (3 × $0.005) + (2 × $0.005) for tools.+Most tool costs are per invocation. `sandbox` is billed per container session — a 20-minute billing window per container, not a runtime cap — plus per SDK search query made from inside it. Tool costs are separate from model token costs.  ## Search API Pricing

← Perplexity timeline