Parallel FindAll pricing
$0.03 to $1 a match, plus a fee per run.
Parallel FindAll costs a fixed fee per run plus a charge per match: $0.25 and $0.03 on base, $2 and $0.15 on core, $10 and $1 on pro. On Parallel's own benchmark, 1,000 correct matches cost $60, $230 and $1,430.
SpecStream is the live web data engine for teams and agents. Deep Search returns every match as a finished row at 5¢, 15¢ or $1, facts included, with no fee per run. The most a run can cost is quoted before it starts.
New accounts get $10 of credit, no card. At 5¢ a row, that is up to 200 rows.
Every FindAll price, and what SpecStream charges for the same list
| SpecStream | Parallel FindAll | |
|---|---|---|
| The unit you pay for | A delivered row: 5¢, 15¢ or $1 by how much the row needs, plus 5¢ for an email and 15¢ for a phone. The same rate on every plan | A fixed cost for each run plus a cost for each match, both set by the generator. Each enrichment is billed per match on top |
| Price per match | 5¢ a row with up to 5 facts, 15¢ with up to 15 facts and one set of related records, $1 with no limit | preview $0.00, base $0.03, core $0.15, pro $1.00 |
| Fee per run | None. A run that finds nothing costs nothing | preview $0.10, base $0.25, core $2.00, pro $10.00. Extending a run adds matches with no second fixed cost |
| 1,000 matches, by the formula | $50 at 5¢ or $150 at 15¢, with the facts in the row | $30.25 on base, $152 on core and $1,010 on pro, before enrichments |
| Cost per 1,000 correct matches (CPM) | A result that fails one of your conditions is not delivered and not billed, so 1,000 delivered rows cost $50 at 5¢, $150 at 15¢ and $1,000 at $1 | On Parallel's benchmark of 40 queries, tested Nov 13 to 17, 2025: 60 on Base at 30.3% recall, 230 on Core at 52.5% and 1,430 on Pro at 61.3%. The page defines the cost as the average cost to find 1,000 correct matches, in USD |
| Facts on each row | Included in the row rate: up to 5 facts at 5¢, up to 15 facts and one set of related records at 15¢, no limit at $1 | Each enrichment is a Task run on every match, at $5 to $2,400 per 1,000 runs by processor, billed on top of the match |
| What failed or empty work costs | Nothing. A row left out, a retry and a run that finds nothing are not charged | The cost formula is the fixed cost plus the matches, so every run pays its $0.10 to $10.00. A cancelled run is charged for the work completed, enrichments included |
| The cost cap before a run | The most the run can cost, quoted before it starts. Nothing runs until you approve it, and there are no automatic overages | A match limit you set. The bill follows the formula: the fixed cost, plus each match, plus each enrichment |
| A list you already have | Import a CSV, Excel file, Google Sheet or Airtable base of up to 20,000 rows. SpecStream fills in or checks each row and matches it to one identity, with any namesakes shown alongside their evidence. Import is free. A row that matches pays its rate, and a row that does not costs 5¢ | A Task run on each row, from $5 per 1,000 runs on lite to $2,400 per 1,000 on ultra8x |
| Reruns and change labels | Hourly to yearly. Each row comes back labeled changed, unchanged or no longer matching. A changed or new row costs half its rate, an unchanged row 1¢ | Extending a run adds new matches at the per-match cost. Monitor is a separate API at $3 (lite) or $10 (base) per 1,000 checks |
| API status and limits | MCP server, REST API, Python and TypeScript SDKs, a CLI and A2A. An agent can buy one request with no account, by card or in USDC | REST endpoints under /v1beta, a public beta whose formats can change with 30 days notice. 300 new runs an hour |
| Free to start | $10 of credit on a new account, no card | $5 free monthly with a card on file, plus up to $80 at signup |
What a FindAll list costs in practice, and on SpecStream
List price per match, CPM per correct match
FindAll's pricing table charges $0.03, $0.15 or $1.00 for each match. Parallel's FindAll product page prints a second set of numbers: 60, 230 and 1,430 CPM for Base, Core and Pro. Its footnote reads CPM as USD per 1,000 requests, and its method says the cost is the average cost to find 1,000 correct matches.
That is 6¢, 23¢ and $1.43 for each correct match on Parallel's own 40 queries, against a list price of 3¢, 15¢ and $1. On the same benchmark Base found 30.3% of the entities, Core 52.5% and Pro 61.3%.
A SpecStream row costs 5¢ with up to 5 facts, and a result that fails one of your conditions is not delivered and not billed. 1,000 delivered rows cost $50.
The fee is paid on every run, and weighs most on short lists
Parallel's guide says to test each query on preview first, at $0.10, and to choose pro when you expect few matches. A pro run that returns 5 matches costs $15, $3 a match. A core run that returns 20 costs $5, 25¢ a match.
SpecStream has no fee for a run. 5 rows at $1 cost $5 and 20 rows at 15¢ cost $3, and a run that finds nothing costs nothing.
Each fact on FindAll is billed again per match
A FindAll match says that a candidate meets your conditions. Each further fact is an enrichment, a Task run on every match at the processor's rate: $10 per 1,000 on base, $25 on core, up to $2,400 on ultra8x. 1,000 matches on core with two core enrichments cost $202.
On SpecStream the facts are part of the row: 1,000 rows with up to 15 facts each cost $150. The searches and pages behind a row are not billed.
A hard maximum on every run
A FindAll bill is a formula you work out from the generator, the matches and the enrichments. SpecStream quotes the most the run can cost, good for 30 minutes, and reading and pricing a request cost nothing. Nothing runs until you or your agent approve that amount, the charge never goes past it, and whatever the run does not use goes back to your balance.
The most accurate web search API, on the same key
The SpecStream Search API scores 97.9 F-score on all 1,000 official SimpleQA Verified questions, 978 of them correct, and 64.0 item F1 and 43.4 row F1 on all 200 official WideSearch tasks. Every score and its method are on the benchmarks page.
Other list and entity APIs priced next to FindAll
SpecStream
The live web data engine for teams and agents. Deep Search returns every match as a row at 5¢, 15¢ or $1, facts included, with a source URL and read time on every value and no fee per run. New accounts get $10 of credit, no card.
Parallel Entity Search
The synchronous part of FindAll for people and companies: $5 per 1,000 requests with 100 results, then $0.05 per 1,000 results. Each entity comes back as a name, a url and a description, ranked and not checked against your conditions. A SpecStream row carries the facts you asked for and meets every condition you wrote.
Parallel Task API
One run per input row, at $5 per 1,000 runs on lite to $2,400 on ultra8x, charged for completed runs. You bring the list. SpecStream finds the rows from one request and fills a list of up to 20,000 rows you import.
Exa Agent
List building and enrichment billed per run: $0.012 to $1.00 at a fixed effort, or metered up to a $5 cap on auto, with $0.02 for an email and $0.07 for a phone on top. SpecStream prices the row: 5¢, 15¢ or $1 for each one delivered, under a maximum you approve.
How SpecStream scores
The same numbers as the benchmarks page, from the official tasks and scorers.
How to move a FindAll query to SpecStream
1. Write your FindAll objective and its match conditions as one sentence, and add the facts you want on each row in place of enrichments. Sign up and you get $10 of credit, no card.
2. Or send the request from code. This call spends nothing: the 402 reply shows how SpecStream read the request, the columns and the most it can cost.
curl -i https://api.specstream.ai/v1/agent/lists \
-H "Content-Type: application/json" \
-d '{"request": "Series A and B healthcare AI companies in the US with an FDA-cleared product, with the CEO, the last funding round and the product name", "count": 25}'3. Approve that maximum by card through Stripe's Link agent wallet, or in USDC on Base, Arbitrum or Polygon, and you pay for the rows found. On an account, your agent uses the MCP server at https://api.specstream.ai/mcp and your team uses the workspace, from the same balance. The routes are in the API docs.
Frequently asked questions
Something we didn't answer? Talk to a human
How much does Parallel FindAll cost?
preview, $0.25 and $0.03 on base, $2.00 and $0.15 on core, $10.00 and $1.00 on pro. Enrichments are billed on top as Task runs at $5 to $2,400 per 1,000. Read on Parallel's pricing docs on Nov 12, 2026.What does CPM mean on the FindAll page?
What do 100 matches cost on FindAll?
base, $17 on core and $110 on pro, before enrichments. On SpecStream 100 rows cost $5 with up to 5 facts each or $15 with up to 15 facts each, and the charge never passes the maximum you approved.Does FindAll charge when a run finds nothing?
Are enrichments included in the FindAll match price?
lite, $10 on base, $25 on core. A SpecStream row includes up to 5 facts at 5¢ and up to 15 at 15¢.What is the best Parallel FindAll alternative?
Does SpecStream have an API and an MCP server?
https://api.specstream.ai/mcp over Streamable HTTP, with OAuth or an API key.Sources
SpecStream wrote this page. Each FindAll figure comes from Parallel's own product page, pricing page and docs, read on Nov 12, 2026.
- SpecStream pricingspecstream.ai/pricing, read Nov 12, 2026
- SpecStream for agentsspecstream.ai/agents.md, read Nov 12, 2026
- SpecStream benchmarksspecstream.ai/benchmarks, read Nov 12, 2026
- Parallel FindAll product pageparallel.ai/products/findall, read Nov 12, 2026
- Parallel pricing docsdocs.parallel.ai/getting-started/pricing.md, read Nov 12, 2026
- Parallel FindAll generatorsdocs.parallel.ai/findall-api/core-concepts/findall-generator-pricing.md, read Nov 12, 2026
- Parallel FindAll quickstartdocs.parallel.ai/findall-api/findall-quickstart.md, read Nov 12, 2026
- Parallel Entity Searchdocs.parallel.ai/findall-api/entity-search.md, read Nov 12, 2026
- Parallel rate limitsdocs.parallel.ai/getting-started/rate-limits.md, read Nov 12, 2026
- Parallel plansparallel.ai/pricing, read Nov 12, 2026
- Exa pricingexa.ai/docs/admin/pricing.md, read Nov 12, 2026




