Clarified Search API pricing to confirm that costs are per successful request regardless of the number of queries or extracted text tokens.

Summary by gemma-4-12b. It may be wrong; the diff below is what actually changed. Raw: 8222507d25-perplexity-api-pricing.diff · commit 8222507d25

diff --git a/snapshots/perplexity/api-pricing.md b/snapshots/perplexity/api-pricing.mdindex 0e0e676..92a0bc8 100644--- a/snapshots/perplexity/api-pricing.md+++ b/snapshots/perplexity/api-pricing.md@@ -41,9 +41,20 @@ Most tool costs are per invocation. `sandbox` is billed per container session  | API | Price per 1K requests | Description | |---|---|---|-| Search API | $5.00 | Raw web search results with advanced filtering |-| Search API with Fast Search | $1.00 | Lower-latency web search results. Set `search_type: "fast"` |+| Search API | $5.00 | Ranked web results as JSON, with page text extracted into each result's `snippet`. No model, no generated answer, no token billing. Filter by domain, language, and date, and bias results by country. |+| Search API with Fast Search | $1.00 | Lower-latency results in the same response format. Set `search_type: "fast"` |  Billing unit: Search API charges for each successful `POST /search` request, not for each query in the request. A successful request containing an array of up to five queries is one billing unit. Invalid requests, rate-limited requests, and upstream failures are not billed. A successful response is billed even when it returns no results. There are no additional token-based charges. +Search API cost = successful requests ÷ 1,000 × the price per 1K requests. The amount of extracted text (`max_tokens`, `max_tokens_per_page`) does not change the price.++| Request | Billing units | Cost |+|---|---|---|+| One `POST /search` with one query, up to 20 results | 1 | $5.00 ÷ 1,000 = $0.005 |+| One `POST /search` with one query and `search_type: "fast"` | 1 | $1.00 ÷ 1,000 = $0.001 |+| One `POST /search` with a `query` array of five queries | 1 | $0.005 (standard) or $0.001 (Fast Search) |+| 10,000 successful standard requests in a month | 10,000 | 10 × $5.00 = $50.00 |++What a result contains, the request controls, and the limits on queries, results, and extracted text are in the Search API overview.+ ## Embeddings API Pricing @@ -122,7 +133,7 @@ Token Calculation: 1 token ≈ 4 characters in English text. The exact count may | Total | $0.0059 | -## Agent API Research Preset+## Agent API Research Effort Level -`low` preset representative run • `openai/gpt-6-luna` • 2,000 input + 1,000 output tokens • 1 web search + 1 fetch+`low` effort level representative run • `openai/gpt-6-luna` • 2,000 input + 1,000 output tokens • 1 web search + 1 fetch  | Component | Cost |@@ -134,5 +145,5 @@ Token Calculation: 1 token ≈ 4 characters in English text. The exact count may | Total | $0.0022 | -Actual preset costs vary with the selected model, token usage, and tool invocations. When present on a completed response, `usage.cost.total_cost` reports the calculated request cost.+Actual effort level costs vary with the selected model, token usage, and tool invocations. When present on a completed response, `usage.cost.total_cost` reports the calculated request cost.  ## Purchase Options

← Perplexity timeline