# TinyFish API Review

Source: [TinyFish API Review](<https://www.sota2.com/benchmarks/tinyfish-api-review>)

Collection index: [llms.txt](<https://www.sota2.com/benchmarks/llms.txt>)

Data updated: 2026-11-18

TinyMonitor correctly judged the controlled page edits while its schedule ran continuously. After REST Pause/Resume, two fresh instances on ordinary one- and two-minute schedules made no scheduled source requests during more than ten minutes of observation. Their continuously active controls completed every check in the same post-Resume slots. This November 18 replication used one account and a synthetic pricing page. [Extended Monitor audit](/benchmarks/tinyfish-monitor-audit-2026-11-18.json)

In our November 15 website study, TinyFetch returned readable text for 190 of 192 pages and matched 279 of 343 expected details. TinyAgent handled JavaScript pagination and a table that refreshed after a click. TinyBrowser extracted the same pagination fields with a Playwright script we wrote.

[Download the original test data](/benchmarks/tinyfish-api-review-evidence-2026-11-17.json) · [Real-company study and scoring](/benchmarks/tinyfish-company-study-results-2026-11-18.json) · [Sourced comparison CSV](/benchmarks/tinyfish-company-study-table-2026-11-18.csv) · [TinyFish documentation](https://docs.tinyfish.ai/)

## Results at a glance

| Product | Observed result | Usage recorded for the tested runs |
| --- | --- | --- |
| TinySearch | Found a usable official product landing and pricing source within five returned links for all 12 named companies. First link passed for 3/12 product and 5/12 pricing queries. | $0 in AgentRouter receipts |
| TinyFetch | Returned 190/192 readable pages and matched 279/343 details for supplied URLs. | $0 in the November 15 study |
| TinyAgent | Returned all four bookstore fields and matched the reference outputs on two dynamic pages. | $0.144 pending for the bookstore; $0.08 and $0.128 shown for the two Playground runs |
| TinyBrowser | Retrieved all four bookstore fields after a retry and all five JavaScript pagination fields on a separate run. | About $0.002 pending across the two bookstore sessions; $0.006 shown for the pagination session |
| TinyMonitor | Correctly judged two edits. In the November 18 audit, matched active controls completed 10/10 and 5/5 checks while REST-resumed instances completed 0/10 and 0/5. | $0.015 pending for an initial baseline and two manual checks |
| TinyResearch | Answered four verifiable questions. Its 734-word report exceeded the 500-word limit. | $2.00 pending for one Deep run |
| TinySet | Returned 12 rows, covering 6/12 requested companies. Passed 26/72 field checks; 2/12 requested rows passed all six. | $1.20 pending for this 12-row run; earlier workflow pilot $0.30 pending |

Search and TinySet include the November 18 real-company study. Other recorded amounts cover the original runs and exclude the November 18 Monitor replication. TinySet Wallet showed 12 rows at $0.10 per row, totaling $1.20 pending. These are usage records, not a total invoice for the review. TinyFish publishes rates per Agent step, Browser minute, Monitor check, Research run and TinySet row. [TinyFish pricing](https://www.tinyfish.ai/pricing)

## TinyMonitor scheduled checks after Pause and Resume

In the first controlled run, TinyMonitor correctly ignored an announcement edit and marked the Pro price increase from $20 to $25 relevant. Four scheduled callbacks, including two unchanged checks, arrived 2.9–8.2 seconds into their respective minute slots. This tested change judgment and delivery while the monitor stayed active. [Original change events](/benchmarks/tinyfish-api-review-evidence-2026-11-17.json)

On November 18 we created four fresh Page Monitors under the same account, using ordinary recurring cron expressions `* * * * *` and `*/2 * * * *`. For each cadence one stayed active and one received status-only REST updates to pause and resume. The observation window ran from 10:48 to 11:03 a.m. Pacific. We paused at 10:50:20, resumed at 10:52:20, and waited until after 11:03 before making manual calls. Every expected minute was observed in full. [Plan, request bodies and timestamps](/benchmarks/tinyfish-monitor-audit-2026-11-18.json) · [Official lifecycle contract](https://docs.tinyfish.ai/tinymonitor/api-reference)

| Cadence | Resumed instance before Pause | Always-active control in matching post-Resume slots | Resumed instance in those same slots |
| --- | --- | --- | --- |
| Every minute | 3/3 checks | 10/10 checks | 0/10 checks |
| Every two minutes | 2/2 checks | 5/5 checks | 0/5 checks |

Source-fetch and webhook counts agreed in each cell. Both Resume calls returned HTTP 200, and a separate GET confirmed both instances active with no reported error. The fixture logged no post-Resume source requests from either instance before the manual calls. Dashboard All checks stayed at six and four baseline-plus-pre-pause entries. Two subsequent manual calls returned HTTP 201 and read the current $31 price, adding one history entry each. [Independent source log, webhook receipts and Dashboard checks](/benchmarks/tinyfish-monitor-audit-2026-11-18.json)

The November 17 comparison had shown the same gap through Dashboard and REST Resume, at both cadences, using calendar-restricted cron expressions. Its 0/12 figure counted four instances’ first three expected execution times. In the two-minute cases, we made the manual call about 45 seconds into the third due minute. That limited the original observation of that slot. The November 18 repeat used unrestricted recurring schedules and a longer untouched window to address that limitation. [Original comparison](/benchmarks/tinyfish-monitor-api-cadence-2026-11-17.json) · [Independent recount and replication](/benchmarks/tinyfish-monitor-audit-2026-11-18.json)

These runs support a reproducible gap in scheduled execution after Resume for this account and tested configuration. The 0/12 figure was a scoped interruption test. It cannot serve as an overall Monitor success rate. We have not established the internal cause or measured prevalence across accounts. All four new test instances were paused after the audit. [Full audit evidence](/benchmarks/tinyfish-monitor-audit-2026-11-18.json)

## TinySearch found official pages for 12 real companies

The task was to find two pages a buyer could use for each company: a landing page explaining the named product, and an official pricing or rate source. We supplied company names, product hints and root domains. TinySearch received search words, without target URL paths or expected prices. It returned ten webpage links for each of 24 Web queries. This tests page finding when the company is already known. [Frozen sample, exact queries and scoring rules](/benchmarks/tinyfish-company-study-manifest-2026-11-18.json)

All 12 product queries and all 12 pricing queries had a usable official source within the first five returned links. The first link itself passed for 3/12 product queries and 5/12 pricing queries. Position means the link's place in the API's returned list: position 1 is its first link. Each accepted page was checked for company identity, redirects and relevant content. The supplied root domain made this an easier task than discovering an unknown company. [All 24 lists and page adjudications](/benchmarks/tinyfish-company-study-results-2026-11-18.json)

| Company | Product landing found at | Pricing information found at |
| --- | --- | --- |
| Linear | [Position 4](https://linear.app/plan) | [Position 4](https://linear.app/pricing) |
| Notion | [Position 4](https://notion.com/en-gb/product) | [Position 1](https://notion.com/pricing) |
| Loom | [Position 1](https://loom.com/products/android-screen-recorder) | [Position 1](https://loom.com/pricing) |
| Figma | [Position 3](https://figma.com/professional) | [Position 2](https://figma.com/pricing) |
| Firecrawl | [Position 3](https://firecrawl.dev/scrape) | [Position 3](https://firecrawl.dev/pricing) |
| Resend | [Position 1](https://resend.com/products/transactional-emails) | [Position 2](https://resend.com/pricing) |
| Browserbase | [Position 2](https://browserbase.com/computer-use) | [Position 1](https://docs.browserbase.com/account/billing/plans) |
| Exa | [Position 2](https://exa.ai/products/search) | [Position 1](https://exa.ai/docs/admin/pricing) |
| Tiptap | [Position 4](https://tiptap.dev/product/editor) | [Position 4](https://tiptap.dev/pricing) |
| Retool | [Position 4](https://retool.com/) | [Position 1](https://retool.com/pricing) |
| ElevenLabs | [Position 5](https://elevenlabs.io) | [Position 2](https://elevenlabs.io/pricing) |
| Glean | [Position 1](https://glean.com/product/assistant) | [Position 5](https://docs.glean.com/glean-core-suite-pricing) |

For Glean, the pricing query's first result led to `glean.ai`, a different company from the supplied `glean.com`. We rejected it. Glean's own Core Suite pricing documentation appeared at position 5 and described per-user licensing and model-usage charges. We did not verify a numeric starting base-seat price in the inspected references. A same-name company or a page with pricing vocabulary alone did not earn a match. [Returned list and ruling](/benchmarks/tinyfish-company-study-results-2026-11-18.json) · [Official Core Suite pricing documentation](https://docs.glean.com/glean-core-suite-pricing)

A usable official alternative could pass without matching the frozen reference URL character for character. Linear's Plan landing described project management; Figma's Professional landing explained design features and Full seats; Loom's Android screen-recorder landing was valid because we specified no operating system. Retool and ElevenLabs homepages explained the named products. We retained each ruling and the original reference separately. Documentation did not substitute for a product landing; current rate documentation could satisfy the pricing job. Finding these pages did not establish that an extracted price would be right.

The 24 calls completed without retries, with a median provider latency of 1.25 seconds. Each AgentRouter receipt recorded $0. The earlier six-query pilot remains in the original evidence; it is excluded from these 24-query results. [New calls and receipts](/benchmarks/tinyfish-company-study-results-2026-11-18.json) · [Earlier pilot](/benchmarks/tinyfish-api-review-evidence-2026-11-17.json)

## TinyFetch read 190 pages and missed all six expected Tiptap prices

In the November 15 study, we supplied 192 exact URLs and checked page text against 343 details. TinyFetch found 46 of 59 prices and 105 of 127 customer quotes. It matched all nine expected prices on Firecrawl’s pricing page and zero of six on Tiptap’s, even though both responses contained readable text. The median run took 1.64 seconds, with a 9.2-second P95. When a workflow uses extracted prices, verify the amounts and billing units against the source. [TinyFetch task review](https://www.sota2.com/benchmarks/tinyfish-company-data) · [Website benchmark methodology](https://www.sota2.com/benchmarks/company-website-evidence)

## TinyAgent followed a goal and TinyBrowser ran a script

Both tools retrieved the requested title, price, stock line and URL for *It’s Only the Himalayas* from a public bookstore fixture. TinyAgent ran for 54 seconds after we removed the unsupported root-level `additionalProperties` keyword from the output schema. The first TinyBrowser client attempt timed out after 50 seconds. On retry we narrowed the link selector and changed how the client exited on errors. The second attempt returned all four fields in 2.64 seconds, including its CDP connection. The cause of the timeout remains unknown. [Bookstore fixture](https://books.toscrape.com/catalogue/its-only-the-himalayas_981/index.html) · [Run outputs](/benchmarks/tinyfish-api-review-evidence-2026-11-17.json)

For JavaScript pagination, both returned the right page URL, card count, first two authors and visible Previous link. TinyAgent followed a natural-language goal. TinyBrowser ran our Playwright script in 2.33 seconds including its CDP connection. That timing excludes provisioning and script authoring. In another TinyAgent run, it switched an AJAX awards table from 2014 to 2015, waited for the new rows and returned the correct winners with their award and nomination counts. We tested public, read-only workflows. [Pagination fixture](https://quotes.toscrape.com/js/) · [AJAX fixture](https://www.scrapethissite.com/pages/ajax-javascript/) · [Outputs and reference values](/benchmarks/tinyfish-api-review-evidence-2026-11-17.json)

## TinyResearch exceeded the brief and TinySet lost half the company list

We asked TinyResearch Deep for a brief explaining Bing Webmaster Tools’ AI Performance report. Four answers about citation counts, grounding queries, which pages a query cited and traditional search rankings agreed with Microsoft's documentation. The report finished in 2 minutes 19 seconds and ran to approximately 734 words on a 500-word request. [Microsoft's reference](https://www.bing.com/webmasters/help/ai-performance-9f8e7d6c) · [Research run and citation checks](/benchmarks/tinyfish-api-review-evidence-2026-11-17.json)

For TinySet, the job was a buyer-verifiable vendor table: one row for each of the same 12 companies, with product and pricing URLs, entry paid plan, amount, currency, billing basis and a supporting official source. The prompt required regular month-to-month pricing, excluded free tiers and temporary promotions, specified Figma Full seats and Retool builders, and preserved Exa's request unit. Company names and root domains were supplied; answer paths and prices were withheld. This was an independent TinySet run on the same sample. It did not receive TinySearch's returned links. [Exact request and untouched returned rows](/benchmarks/tinyfish-company-study-results-2026-11-18.json)

The direct API automatically generated a ten-column spec and returned 12 rows. Only six belonged to the requested companies. Loom, Firecrawl, Resend, Browserbase, Tiptap and Glean were missing; Slack, Zoom, Atlassian, Dropbox, Vercel and Stripe appeared instead. We confirmed both the original prompt and the same returned rows in TinyFish's dashboard. There were no duplicate company names and no manual row repairs. [Request, API rows and coverage](/benchmarks/tinyfish-company-study-results-2026-11-18.json)

| Requested company | TinySet's returned claim | Independently checked reference | Field checks passed |
| --- | --- | --- | --- |
| Linear | [Business · $16 · per user per month, billed monthly](https://linear.app/pricing) | [Basic · $12 · per user per month, billed monthly](https://linear.app/pricing) | 3/6 |
| Notion | [Plus · $10 · per month per member](https://notion.com/pricing) | [Plus · $12 · per member or seat per month, billed monthly](https://www.notion.com/pricing) | 3/6 |
| Loom | Missing | [Business · $18 · per user per month, billed monthly](https://www.loom.com/pricing) | 0/6 |
| Figma | [Professional · $16 · per month per Full seat, billed monthly](https://figma.com/pricing) | [Professional · $20 · per Full seat per month, billed monthly](https://www.figma.com/pricing/) | 4/6 |
| Firecrawl | Missing | [Hobby · $19 · per month, billed monthly](https://www.firecrawl.dev/pricing) | 0/6 |
| Resend | Missing | [Pro · $20 · per month, billed monthly; entry transactional email volume](https://resend.com/pricing) | 0/6 |
| Browserbase | Missing | [Developer · $20 · per month, billed monthly](https://www.browserbase.com/pricing) | 0/6 |
| Exa | [Lite Search · $4 · per 1,000 requests, pay-as-you-go, up to 10 results](https://exa.ai/pricing) | [Lite Search · $4 · per 1000 Lite Search requests, pay as you go](https://exa.ai/pricing) | 6/6 |
| Tiptap | Missing | [Start · $49 · per month, billed monthly; hosted platform](https://tiptap.dev/pricing) | 0/6 |
| Retool | [Team · $10 · per month per builder, monthly billing](https://retool.com/pricing) | [Team · $12 · per builder per month, billed monthly](https://retool.com/pricing) | 4/6 |
| ElevenLabs | [Starter · $6 · per month, month-to-month](https://elevenlabs.io/pricing) | [Starter · $6 · per month, regular recurring rate after first-month promotion](https://elevenlabs.io/pricing) | 6/6 |
| Glean | Missing | [No numeric base-seat rate verified; sales enquiry](https://www.glean.com/get-a-demo) | 0/6 |

Six checks applied to every requested row: correct product page, pricing page, plan, amount and currency, billing basis, and source support for the returned price tuple. Missing requested companies earned zero; unrelated replacements earned no credit. The run passed 26/72 checks. Exa and ElevenLabs were the only requested rows passing all six, for 2/12 complete rows. A billing-unit point could pass independently of the amount; the source-support point required the plan, amount and billing conditions to agree together. [Per-field decisions and sourced CSV](/benchmarks/tinyfish-company-study-table-2026-11-18.csv)

Figma and Retool illustrate the pricing failure. TinySet labeled $16 per Full seat and $10 per builder as monthly billing. Those were annual-billing equivalents. Before the run, we switched the official pages to monthly and verified $20 and $12 respectively. Notion returned the $10 annual equivalent instead of $12 monthly and omitted the commitment. Linear returned Business at the $16 annual equivalent, although the task asked for the lowest paid plan, Basic at $12 monthly. Links to official pricing pages did not support those claimed tuples. [Figma pricing](https://www.figma.com/pricing/) · [Retool pricing](https://retool.com/pricing) · [Notion pricing](https://www.notion.com/pricing) · [Linear pricing](https://linear.app/pricing)

Exa preserved Lite Search at $4 per 1,000 requests. ElevenLabs selected the regular $6 Starter rate after its $1 first-month offer. The server reported completion about 48 seconds after dataset creation; the next status poll confirmed ready with all rows readable. Wallet recorded $1.20 pending for 12 rows at $0.10 each. This was one automatically planned run in one account. It establishes observed coverage and price errors for this request; the internal cause and performance with seeded rows or another spec remain untested. The earlier three-domain workflow check remains available as historical evidence. [Real-company run and scoring](/benchmarks/tinyfish-company-study-results-2026-11-18.json) · [Exa pricing](https://exa.ai/pricing) · [ElevenLabs pricing](https://elevenlabs.io/pricing) · [Earlier workflow pilot](/benchmarks/tinyfish-api-review-evidence-2026-11-17.json)

## What we tested

This API pilot covers seven products on November 17–18, with Fetch results reused from November 15. We used AgentRouter for Search and the earlier Fetch study, TinyFish's direct APIs for the other five products, and its dashboard and Playground for follow-up checks. Search and TinySet received the same purposive 12-company sample on November 18. Four subscription cases were Linear, Notion, Loom and Figma; four API cases were Firecrawl, Resend, Browserbase and Exa; four pricing cases were Tiptap's hosted platform, Retool builder seats, ElevenLabs promotions and Glean sales enquiries. These strata were selected for different price-reading conditions, without a claim that every company fits only one category. [Frozen dataset manifest](/benchmarks/tinyfish-company-study-manifest-2026-11-18.json)

We fixed the companies, references, query templates and scoring rules at 19:38:45 UTC before the first new Search run at 19:38:59. Reference prices came from official pages; monthly toggles were checked before testing. Additional official pages could qualify after independent content verification, with their rulings saved separately. Prices represent the November 18 observation, exclude taxes and may change. We checked each requested company's identity, not just output row count. The 72 TinySet checks measure six conditions per requested company, not 72 independent samples. [Inputs, reference provenance, receipts and all decisions](/benchmarks/tinyfish-company-study-results-2026-11-18.json)

The 12 companies form a small, hand-selected workflow study. Search was given the correct domains. TinySet had one automatically planned run. These results do not measure open-ended company discovery, repeated-run reliability, or a combined Search-to-TinySet pipeline. The broader review also did not test a combined Search-to-Fetch workflow, topic monitoring, email delivery, authenticated browser workflows, vault or saved browser profiles, enterprise access, or sustained workloads. The browser tasks were public and read-only; the Monitor replication used a synthetic controlled page under one account. [Original test evidence](/benchmarks/tinyfish-api-review-evidence-2026-11-17.json) · [Monitor audit](/benchmarks/tinyfish-monitor-audit-2026-11-18.json)

## Test data

[Product profile](/products/tinyfish-tinyfetch) · [TinyFish company](/companies/tinyfish) · [TinyFetch Task Review](/benchmarks/tinyfish-company-data)

[Real-company inputs and scoring](/benchmarks/tinyfish-company-study-results-2026-11-18.json) · [Frozen manifest](/benchmarks/tinyfish-company-study-manifest-2026-11-18.json) · [Sourced comparison CSV](/benchmarks/tinyfish-company-study-table-2026-11-18.csv) · [Monitor audit](/benchmarks/tinyfish-monitor-audit-2026-11-18.json) · [Original API outputs](/benchmarks/tinyfish-api-review-evidence-2026-11-17.json)

## Related SOTA2 benchmarks

The TinyFetch task and comparison reuse the website evidence cited above. The other product reviews use their own samples and scoring.

[TinyFish Task Review: Collecting Company Data from Websites](/benchmarks/tinyfish-company-data) — Details of the November 15 TinyFetch extraction test reused in this API review.

[Best Tools for Collecting Company Data from Websites](/benchmarks/company-website-evidence) — Compare TinyFetch with other tools using the same company website dataset and field checks.

[Firecrawl Whole Product Review](/benchmarks/firecrawl-product-review) — A separate feature review of web extraction, browser interaction, company and people lookup, and provider-specific results.

[Context.dev API Feature Review](/benchmarks/context-dev-api) — Another review of webpage extraction and monitoring, with additional G2 review and PDF table tests.

