diff --git a/snapshots/perplexity/api-pricing.md b/snapshots/perplexity/api-pricing.md
index 73501ad..6800a67 100644
--- a/snapshots/perplexity/api-pricing.md
+++ b/snapshots/perplexity/api-pricing.md
@@ -5,4 +5,8 @@ This page shows pricing information to help you understand API costs.For billing
 ## Estimate your cost
 
+## Gateway API Pricing
+
+Gateway API usage is billed per token at each model's published rates — there are no per-request fees. Every model has its own input and output rate, with cache reads billed at the model's discounted cache-read rate and reasoning tokens billed at the output rate. You are always billed at the requested model's rates, regardless of how the request is served. See Gateway Models & Pricing for the full per-model rate card, including cache-write rates and long-context pricing.
+
 ## Agent API Pricing
 
@@ -23,9 +27,9 @@ When using tools with the Agent API:
 | Tool | Price | Description |
 |---|---|---|
-| `web_search` | $0.005 per invocation | Performs web searches to retrieve current information |
-| `fetch_url` | $0.0005 per invocation | Fetches and extracts content from specific URLs |
+| `web_search` | $0.0025 per invocation | Performs web searches to retrieve current information |
+| `fetch_url` | $0.00025 per invocation | Fetches and extracts content from specific URLs |
 | `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`). |
+| `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 $0.0025 per request (same as `web_search`). |
 
 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.
@@ -37,5 +41,5 @@ Most tool costs are per invocation. `sandbox` is billed per container session 
 | Search API | $5.00 | Raw web search results with advanced filtering |
 
-No token costs: Search API charges per request only, with no additional token-based pricing.
+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.
 
 ## Sonar API Pricing
@@ -162,67 +166,28 @@ Token Calculation: 1 token ≈ 4 characters in English text. The exact count may
 ## Cost Examples
 
-## Sonar Web Search Example
-
-Sonar • 500 input + 200 output tokens
-
-- Low
-- Medium
-- High
+## Agent API Web Search
 
-| Component | Cost |
-|---|---|
-| Input tokens | $0.0005 |
-| Output tokens | $0.0002 |
-| Request fee | $0.005 |
-| Total | $0.0057 |
+`openai/gpt-5.2` • 500 input + 200 output tokens • 1 web search
 
 | Component | Cost |
 |---|---|
-| Input tokens | $0.0005 |
-| Output tokens | $0.0002 |
-| Request fee | $0.008 |
-| Total | $0.0087 |
+| Input tokens | $0.000875 |
+| Output tokens | $0.0028 |
+| `web_search` | $0.0025 |
+| Total | $0.006175 |
 
-| Component | Cost |
-|---|---|
-| Input tokens | $0.0005 |
-| Output tokens | $0.0002 |
-| Request fee | $0.012 |
-| Total | $0.0127 |
+## Agent API Research Preset
 
-## Deep Research Example
-
-Sonar Deep Research
-
-- Low
-- Medium
-- High
+`low` preset representative run • 2,000 input + 1,000 output tokens • 1 web search + 1 fetch
 
 | Component | Cost |
 |---|---|
-| Input tokens (33) | $0.000066 |
-| Output tokens (7163) | $0.057304 |
-| Citation tokens (20016) | $0.040032 |
-| Reasoning tokens (73997) | $0.221991 |
-| Search queries (18) | $0.09 |
-| Total | $0.409393 |
+| Model input tokens | $0.001 |
+| Model output tokens | $0.003 |
+| `web_search` | $0.0025 |
+| `fetch_url` | $0.00025 |
+| Total | $0.00675 |
 
-| Component | Cost |
-|---|---|
-| Input tokens (7) | $0.00 |
-| Output tokens (3847) | $0.031 |
-| Citation tokens (47293) | $0.095 |
-| Reasoning tokens (308156) | $0.924 |
-| Search queries (28) | $0.14 |
-| Total | $1.190 |
-
-| Component | Cost |
-|---|---|
-| Input tokens (8) | $0.00 |
-| Output tokens (4435) | $0.035 |
-| Citation tokens (58196) | $0.116 |
-| Reasoning tokens (339594) | $1.019 |
-| Search queries (30) | $0.15 |
-| Total | $1.320 |
+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.
 
 ## Purchase Options