Diffbot

DATA · DATA & ANALYTICS

Structured page extraction and Knowledge Graph search on their own key.

Connect Diffbot with Fabriq Developer

Your user pastes their Diffbot credential on a page Agentic Fabriq hosts, so it never reaches your backend and never becomes one shared key across all of your users. Same call as OAuth, one more argument.

from af_sdk import AgenticFabriq

af = AgenticFabriq()                      # reads AF_APP_ID / AF_APP_SECRET

url = await af.initiate_connection(request, provider="diffbot", method="api_key")
return redirect(url)                      # an AF-hosted page, not yours

async with await af.for_user(request) as session:
    tools = await session.get_tools()     # only what this user granted

Provider names are surfaces, not vendors, and the authoritative list is the capabilities endpoint rather than any page including this one — an unknown name returns 400 with the valid list. Fabriq Developer is free to start and needs no provider paperwork. Start free or read the quickstart.

Connecting Diffbot in practice

Diffbot charges credits at wildly different rates for the same call volume: an Extract page costs 1 credit, a Knowledge Graph entity download costs 25, and a single facet query costs 100 — the price of a hundred page extractions. The free tier is metered per minute (5 calls) while paid tiers are per second (5 and 25), so the unit changes when you upgrade.

Rate limits

All APIs: Free 5 calls per minute, Startup 5 calls per second, Plus 25 calls per second.
Extract API: Free tier capped at 10,000 calls per month.
Natural Language API: Free tier capped at 500 calls per month.
DQL and Enhance: Free tier capped at 400 entities per month.
Crawl and Bulk Extract on Plus: 25 active jobs and 1,000 total jobs.

Worth knowing

Credit costs per call: Extract 1 (2 with a data-center proxy), Natural Language 1 per document of 1 to 10,000 characters, Knowledge Graph entity download 25, facet query 100, Enhance 25, Enhance with refresh 100.
Credits reset monthly on non-enterprise plans and do not carry over, and overage is billed automatically at the plan’s per-credit rate rather than blocked, so a runaway agent spends rather than stops.
Crawl spidering for links costs 0 credits but every successfully crawled page that is extracted costs 1, so the bill tracks pages found rather than the number of API calls made.
The token is a query-string parameter on every request, so it appears in server logs, referrers and any URL captured for debugging.

Checked against Diffbot rate limits (2026-09-29), Diffbot credits (2026-09-29), Diffbot Extract API (2026-09-29)

Acts as the person, not as itself

Each user connects their own account. Every call carries both identities — the agent and the person it is acting for — so the agent can never reach past what that individual can already do.

Credentials never touch the agent

Tokens live in the vault and attach server-side at call time. The agent holds a session, not a secret, and revoking access does not mean rotating a key.

Every call on the record

Who asked, which agent acted, which action ran, and the verdict that let it through — one audit trail across every integration, not one per vendor.

What an agent can do

Each action is granted on its own. An agent allowed to read is not thereby allowed to write, and the scope beside each row is what the acting user must have connected for it to run at all.

diffbot_delete_customWRITE

Delete a Custom API: Delete definitions of existing Custom APIs for a given URL pattern and API on your token. DELETE api.diffbot.com/v3/custom. The body names the api and urlPattern whose rules are deleted.

api

diffbot_get_accountREAD

Get Account Details: Returns account plan, usage, child tokens, and other account details. GET api.diffbot.com/v4/account.

api

diffbot_get_analyzeREAD

Analyze: Automatically classify a page and extract data according to its type. GET api.diffbot.com/v3/analyze.

api

diffbot_get_articleREAD

Article: Automatically extract clean article text and other data from news articles, blog posts and other text-heavy pages. GET api.diffbot.com/v3/article.

api

diffbot_get_bulkWRITE

Manage a Bulk Extract Job: Pause, delete, restart, or view the status of a bulk job. GET api.diffbot.com/v3/bulk. Requires the Diffbot Plus plan or above (Crawl and Bulk Extract are not available on Free or Startup). Without pause/restart/delete it returns job status; delete=1 permanently deletes the job and its data and restart=1 erases processed data.

api

diffbot_get_bulk_dataREAD

Retrieve Bulk Extract Job Data: Download the extracted results of a bulk job. GET api.diffbot.com/v3/bulk/data. Requires the Diffbot Plus plan or above (Crawl and Bulk Extract are not available on Free or Startup).

api

diffbot_get_by_apiREAD

Extract with Custom API: Extracts a page using a modified Extract API or a custom ruleset. GET api.diffbot.com/v3/{api}. api is the Custom API name as a single path segment; custom, crawl and bulk are refused (they have their own tools).

api

diffbot_get_crawlWRITE

Manage a Crawl Job: Pause, delete, restart, or view the status of a crawl job. GET api.diffbot.com/v3/crawl. Requires the Diffbot Plus plan or above (Crawl and Bulk Extract are not available on Free or Startup). Without pause/restart/delete it returns job status; delete=1 permanently deletes the job and its data and restart=1 erases processed data.

api

diffbot_get_crawl_dataREAD

Retrieve Crawl Job Data: Download the extracted results of a crawl job. GET api.diffbot.com/v3/crawl/data. Requires the Diffbot Plus plan or above (Crawl and Bulk Extract are not available on Free or Startup).

api

diffbot_get_customREAD

Retrieve Custom APIs: Get all the Custom APIs and their rules currently defined on your token. GET api.diffbot.com/v3/custom.

api

diffbot_get_discussionREAD

Discussion: Automatically structure and extract entire threads of reviews/comments from articles, product pages, and forum threads. GET api.diffbot.com/v3/discussion.

api

diffbot_get_eventREAD

Event: Automatically extracts dates, location and address information, images and event descriptions from event pages. GET api.diffbot.com/v3/event.

api

diffbot_get_imageREAD

Image: Automatically identifies the primary image(s) on any web page and returns comprehensive information and metadata for each image. GET api.diffbot.com/v3/image.

api

diffbot_get_jobREAD

Job: Automatically extracts structured information from job postings. GET api.diffbot.com/v3/job.

api

diffbot_get_kg_v3_dqlREAD

Search with DQL: Search the Knowledge Graph using DQL. GET kg.diffbot.com/kg/v3/dql.

api

diffbot_get_kg_v3_dql_reportREAD

Coverage report by Query: Download coverage report by DQL query. GET kg.diffbot.com/kg/v3/dql/report.

api

diffbot_get_kg_v3_dql_report_by_idREAD

Coverage report by ID: Download coverage report by report ID. GET kg.diffbot.com/kg/v3/dql/report/{id}.

api

diffbot_get_kg_v3_enhanceREAD

Enhance: Enrich a person or organization record with partial data input. GET kg.diffbot.com/kg/v3/enhance. Needs at least one identifier besides `type`: `id`, `name`, `url`, `phone` or `ip`; `location` also counts for an Organization and `email` for a Person. Diffbot refuses the call without one (400 "One of {...} is required.", naming the identifiers for the requested type).

api

diffbot_get_kg_v3_enhance_bulk_by_bulkjobidREAD

Download Results of Bulkjob: Download the result of a completed Enhance Bulkjob. GET kg.diffbot.com/kg/v3/enhance/bulk/{bulkjobId}.

api

diffbot_get_kg_v3_enhance_bulk_by_bulkjobid_by_jobidxREAD

Download Single Result of Bulkjob: Use this API to download the result of a single job within a bulkjob by specifying the index of the job. GET kg.diffbot.com/kg/v3/enhance/bulk/{bulkjobId}/{jobIdx}.

api

diffbot_get_kg_v3_enhance_bulk_by_bulkjobid_deleteWRITE

Delete Bulkjob: Delete bulkjob. GET kg.diffbot.com/kg/v3/enhance/bulk/{bulkjobId}/delete. Permanently deletes the bulkjob.

api

diffbot_get_kg_v3_enhance_bulk_by_bulkjobid_statusREAD

Poll bulkjob status: Poll the status of an Enhance Bulkjob. GET kg.diffbot.com/kg/v3/enhance/bulk/{bulkjobId}/status.

api

diffbot_get_kg_v3_enhance_bulk_by_bulkjobid_stopWRITE

Stop Bulkjob: Stop an active Enhance Bulkjob. GET kg.diffbot.com/kg/v3/enhance/bulk/{bulkjobId}/stop.

api

diffbot_get_kg_v3_enhance_bulk_report_by_bulkjobid_by_reportidREAD

Download Bulkjob Coverage Report: Download the coverage report of a completed Bulk Enhance job. GET kg.diffbot.com/kg/v3/enhance/bulk/report/{bulkjobId}/{reportId}.

api

diffbot_get_kg_v3_enhance_bulk_statusREAD

List Bulkjobs for Token: Poll the status of all Enhance Bulkjobs for a token. GET kg.diffbot.com/kg/v3/enhance/bulk/status.

api

diffbot_get_kg_v3_enhance_combineREAD

Combine: Enrich a person record and return both person and current employer data. GET kg.diffbot.com/kg/v3/enhance/combine. Needs at least one identifier besides `type`: `name`, `email`, `url`, `phone` or `ip`. Diffbot refuses the call without one (400 "One of {name, email, url, phone, ip} is required.").

api

diffbot_get_listREAD

List: Automatically structures a list of items from news index pages, product listings pages, search engine results pages, and other "list-like" pages. GET api.diffbot.com/v3/list.

api

diffbot_get_productREAD

Product: Automatically extract pricing, product specs, images, and more from an e-commerce product page. GET api.diffbot.com/v3/product.

api

diffbot_get_videoREAD

Video: The Video API automatically extracts detailed video information—including most metadata, thumbnail images, direct video URL and embed code from nearly any video page or video platform on the web. GET api.diffbot.com/v3/video.

api

diffbot_get_web_searchREAD

Run a Web Search: Search Diffbot's Web Index. GET llm.diffbot.com/api/v1/web_search.

api

diffbot_post_bulkWRITE

Create a Bulk Extract Job: Extract a list of URLs asynchronously. POST api.diffbot.com/v3/bulk. Requires the Diffbot Plus plan or above (Crawl and Bulk Extract are not available on Free or Startup). The body is sent form-encoded, as Diffbot requires.

api

diffbot_post_crawlWRITE

Create a Crawl: Create and start a job to spider and extract pages through a site. POST api.diffbot.com/v3/crawl. Requires the Diffbot Plus plan or above (Crawl and Bulk Extract are not available on Free or Startup). The body is sent form-encoded, as Diffbot requires.

api

diffbot_post_customWRITE

Create or Update a Custom API: Create or update the parameters and ruleset of an existing Custom API. POST api.diffbot.com/v3/custom.

api

diffbot_post_kg_v3_dqlREAD

Search with DQL: Search the Knowledge Graph using DQL. POST kg.diffbot.com/kg/v3/dql.

api

diffbot_post_kg_v3_enhanceREAD

Enhance: Enrich a person or organization record with partial data input (POST option). POST kg.diffbot.com/kg/v3/enhance. Needs at least one identifier besides `type` inside `body`: `id`, `name`, `url`, `phone` or `ip`; `location` also counts for an Organization and `email` for a Person. Diffbot refuses the call without one (400 "One of {...} is required.", naming the identifiers for the requested type).

api

diffbot_post_kg_v3_enhance_bulkWRITE

Create a Bulkjob: Enhance multiple records in bulk asynchronously. POST kg.diffbot.com/kg/v3/enhance/bulk.

api

diffbot_post_kg_v3_enhance_bulk_by_bulkjobidREAD

Download Results of Bulkjob: Download the result of a completed Enhance Bulkjob. POST kg.diffbot.com/kg/v3/enhance/bulk/{bulkjobId}.

api

diffbot_post_nl_v1READ

Process Text. POST nl.diffbot.com/v1/.

api

diffbot_post_web_searchREAD

Run a Web Search. POST llm.diffbot.com/api/v1/web_search.