Perplexity Answer Reader
Pricing
from $8.50 / 1,000 answer returneds
Perplexity Answer Reader
Ask Perplexity your questions on your own Perplexity API key. One row per answer with the full text, every source and which ones are cited, the searches it ran, and an optional brand check. You pay Perplexity directly and this actor per answer.
Pricing
from $8.50 / 1,000 answer returneds
Rating
0.0
(0)
Developer
Mamba Labs
Maintained by CommunityActor stats
0
Bookmarked
2
Total users
1
Monthly active users
an hour ago
Last modified
Categories
Features
Share
Give your questions and your own Perplexity API key. The actor asks each question through Perplexity's Agent API with web search on and returns one row per answer: the answer text, every source Perplexity found and which of them the answer cites, the cited domains in order, and the searches Perplexity ran. Name a brand and each row also says whether the answer names it, cites its domain, and at what position. You pay Perplexity directly for each call, and you pay this actor per completed answer.
Features
- Works on your own Perplexity API key. The key is sent only to
api.perplexity.ai, and it is never stored, logged, or written to a row. - One row per answer with the answer text, every source (URL, title, domain, date), which sources are cited, the cited domains in order, and the searches Perplexity ran.
- Brand check: give
brandas a name, a domain, orName|domain.com, and optionalcompetitors. Each row says whether the answer names the brand, whether a cited source is on its domain, the citation rank, and the mention rank against your competitors. - Samples: ask each prompt up to 5 times, because Perplexity's answers change between calls.
- Search controls: Perplexity effort level (
fast,low,medium,high) or a named Agent API model, domain allow or deny list, recency window, and searcher country. - Token counts and the cost Perplexity reports for each call, so you can match rows to your Perplexity bill.
- Refused, failed, and unfinished answers are free, and the run never sends a prompt it could not charge.
How the data is read
The actor calls Perplexity's official Agent API, POST https://api.perplexity.ai/v1/agent, with your key, from the Apify platform. It uses no proxy, no browser, no login, and no other developer's actor, and it does not read the perplexity.ai website. Perplexity ended support for the older Sonar Chat Completions API on 2026-09-27, so this actor uses the Agent API. With an effort level, Perplexity picks the model and search settings for that level; with a named model, the actor turns Perplexity's web_search tool on for it.
Your use of the answers falls under your own agreement with Perplexity. Perplexity's API terms (last updated 2026-01-23) let a customer receive output and display it within the customer's own applications.
Input
| Field | Type | Default | What it does |
|---|---|---|---|
prompts | array | The questions to ask Perplexity, one per line. Each is sent as written. As text, one prompt per line; a comma does not split a prompt. | |
api_key | string | Your own Perplexity API key, from console.perplexity.ai. It is sent only to api.perplexity.ai and is never stored, logged, or written to a row. With no key, the run checks up to 3 prompts for free and asks nothing. | |
effort | string | fast | Perplexity's Agent API effort level: fast (default; quick answers with numbered citations), low, medium, or high. Higher levels search more and cost more on your Perplexity bill. Ignored when you name a model. |
model | string | Optional. An Agent API model ID, for example perplexity/sonar or openai/gpt-5.6-sol. When set, the actor asks that model with Perplexity's web search tool on instead of using an effort level. | |
brand | string | Optional. A brand name, a domain, or both as Name/domain.com. Each row then says whether the answer names the brand and cites its domain, and at what position. | |
competitors | array | Optional. Competitor names or Name/domain.com, one per line. Used for the brand mention rank and the competitors named column. | |
samples_per_prompt | string | 1 | How many times to ask each prompt, 1 to 5 (default 1). Answers change between calls, so more samples give a steadier read. Each sample is one Perplexity call and one charged answer. |
search_domain_filter | array | Optional. Domains for Perplexity's web search to use, or to skip with a leading minus, for example -pinterest.com. Up to 20. | |
search_recency_filter | string | Optional. Limit web search results to the last hour, day, week, month, or year. | |
country | string | Optional. Two letter country code, for example US or DE. Perplexity uses it as the searcher's location. | |
concurrency | string | 3 | How many prompts to ask at the same time, 1 to 10 (default 3). Lower it if your Perplexity account hits its rate limit. |
max_charge_usd | string | Optional. The run stops before a charge that would pass this amount. Summary rows are always returned. It does not cap your Perplexity bill. |
Output
| Field | Type | What it holds |
|---|---|---|
row_type | string | One of: answer, run_summary. run_summary is the one free row written when the input is refused. |
prompt | string | The question as you gave it, sent to Perplexity unchanged. |
sample | integer | Which repeat of this prompt the row is, from 1. Set samples_per_prompt to ask the same prompt more than once. |
effort | string | The Agent API effort level used, or null when you named a model. |
model | string | The model Perplexity reports it answered with. |
answer_text | string | The answer text as Perplexity returned it, with its inline citation markers such as [1] or [web:1]. |
sources | array | Every search result Perplexity returned for this answer: id, url, title, domain, date, last_updated, and cited (true when the answer text points to it). |
source_count | integer | Search results Perplexity returned for this answer. |
cited_urls | array | Source URLs the answer text points to with a citation marker, in order of first citation. |
cited_domains | array | Domains of the cited URLs, in order of first citation, without repeats. |
search_queries | array | The web searches Perplexity ran to write this answer. |
brand | string | The brand name or domain you asked to check, as read. |
brand_named | boolean | True when the answer text names the brand or its domain. |
brand_cited | boolean | True when a cited source is on the brand's domain, or on a subdomain of it. |
brand_citation_rank | integer | Position of the first cited source on the brand's domain among the cited URLs, from 1. Null when not cited. |
brand_mention_rank | integer | 1 when the brand is the first of the brand and its listed competitors to be named in the answer, 2 when one competitor is named before it, and so on. Null when the brand is not named. |
competitors_named | array | Competitors from your list that the answer names, in order of first mention. |
input_tokens | integer | Input tokens Perplexity counted for this answer. |
output_tokens | integer | Output tokens Perplexity counted for this answer. |
search_calls | integer | Web search tool calls Perplexity ran for this answer. |
perplexity_cost_usd | number | The cost Perplexity reports for this call at its list price. It is billed to your Perplexity account, not by this actor. |
response_id | string | Perplexity's ID for this response. |
row_status | string | ok, or why this row carries no data: no_results, no_change, partial, blocked, or error. |
error_reason | string | Why the row is not ok. A refused input reads input_invalid: followed by what to fix. |
billable_events_json | string | What this row was billed as, for example {"answer-row":1}. {} means free. |
scraped_at | string | When the row was written, UTC. |
sources is a list of objects: id, url, title, domain, date, last_updated, and cited. A source is cited when the answer text carries its marker, such as [3] at the fast effort level or [web:3] at low and above.
Pricing
Pay per event. Summary rows and a refused input are free. Your Perplexity account is billed separately by Perplexity for every call, at its own rates (tokens plus a fee per web search); the perplexity_cost_usd column shows the cost Perplexity reports.
| Event | Free plan | Bronze | Silver | Gold |
|---|---|---|---|---|
answer-row, one completed answer with its sources | $0.01 | $0.0095 | $0.009 | $0.0085 |
apify-actor-start, once per run (one per GB of memory; the default 128 MB is one) | $0.002 | $0.002 | $0.002 | $0.002 |
Per 1,000 rows of answer-row: $10.00 on the free plan, $8.50 on Gold.
Free plan cap: 1.50 USD of evaluation a month, about 150 rows. Any paid Apify plan removes the cap, and it resets on the 1st. The run stops before a charge that passes your maximum charge per run in Apify or your max_charge_usd input.
Mamba Labs pays the platform costs of your run, Apify proxy traffic included.
Usage examples
Brand visibility. Put 20 buyer questions in prompts, set brand to YourBrand|yourbrand.com and competitors to your 3 main rivals, and set samples_per_prompt to 3. Count the rows where brand_cited is true.
Source research. Ask one question 5 times and read cited_domains to see which sites Perplexity relies on for that topic.
Clay. Number and on or off inputs are text fields, which is what Clay sends. A list input takes a JSON list, so put the column inside a one item list. Store your Perplexity key in the Clay input as api_key.
MCP. The Mamba Labs MCP server @mambalabsdev/mcp-perplexity-answer-reader exposes this actor to Claude and other MCP clients.
Error handling
| Case | What you get |
|---|---|
| Missing or unreadable input | One free row, row_type run_summary, error_reason starting input_invalid: with what to fix. The run ends successfully and charges nothing but the run start |
| No API key | Up to 3 free rows with error_reason starting no_key:. Nothing is sent to Perplexity |
| Perplexity refuses the key, or the account has no credit | A free row with key_refused: or quota:, and the run stops |
| Perplexity refuses the model, effort, or filter settings | A free row with request_refused:, and the run stops, because every prompt would fail the same way |
| Rate limit or a Perplexity server error | Up to 3 tries per prompt, honoring Retry-After; then a free row with rate_limited: or perplexity_error: |
| An answer that did not finish, or no answer text | A free row with row_status partial or no_results, and the text if any |
max_charge_usd or the Apify charge limit is reached | The run stops before sending the next prompt to Perplexity, and one free row with not_sent: names the first prompt not sent |
| The run is close to its timeout | The actor stops starting new work 90 seconds before the timeout and delivers what it has |
Limitations
- Tested on Perplexity's documented response shapes and on the live refused key path. Answer rows were not seen live before release, because no Mamba Labs key is used in this actor; the first buyer's key is the live test.
- The answer is what the Agent API returns. It can differ from what a person sees on the perplexity.ai website or app.
- Citation markers are matched to sources by their number. If one answer returns two search results with the same number, the row says so in
error_reason. - Each prompt is one Perplexity call with no conversation history. Higher effort levels search more and take longer; one call may take up to 4 minutes before it ends as a free
timeoutrow. - Your Perplexity rate limit and credit balance apply. Lower
concurrencyif your account hits its rate limit.
Mamba Labs actor suite
Built by Mamba Labs.