Firecrawl

DEVELOPER · DEVELOPER

Scrapes, crawls, and site maps of any URL, run on their own key.

Connect Firecrawl with Fabriq Developer

Your user pastes their Firecrawl 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="firecrawl", 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 Firecrawl in practice

The same scrape costs anything from 1 to 6 credits depending on the options you pass — asking for structured JSON adds 4 credits a page on top of the base 1 — and plan credits do not roll over, so a month’s allowance either gets used or evaporates. Rate limits are per endpoint, so /crawl is five times tighter than /scrape on every plan.

Scopes that draw scrutiny

Allowed formats (per key) An enterprise-only key restriction that pins a key to specific output formats, so a key limited to markdown cannot pull raw HTML or scripts.
Allowed endpoints (per key) The other half of key restrictions: limits a key to specific endpoint groups such as scrape, crawl or extract. Only team admins can view or change either list.

Rate limits

Requests per minute on /scrape, /map and /search: 10 Free, 100 Hobby, 500 Standard, 5,000 Growth, 10,000 Scale.
/crawl is five times tighter on every plan: 2, 20, 100, 1,000 and 2,000 requests per minute. Batch scrape shares the /crawl limit and extract shares the /agent limit.
Concurrent browsers: 2 Free, 5 Hobby, 25 Standard, 50 Growth, 100+ Scale, with 50,000 to 200,000+ queued jobs.
Monthly credits: 1,000 Free, 5,000 Hobby, 100,000 Standard, 500,000 Growth, 1,000,000 Scale.
Credit cost: 1 per page scraped or crawled, 1 per /map call, 2 per 10 search results rounded up, 2–7 per browser minute on /interact.

Worth knowing

Keyless use is free but capped per IP address per day on both requests and credits, so an unauthenticated agent silently shares a quota with everything else on that egress IP.
Plan credits do not roll over by default. Annual Scale keeps unused credits for one month and Enterprise for two; manually purchased credits survive until the subscription is cancelled.
Per-key format and endpoint restrictions are enforced server-side at authentication and return 403, but the feature is enterprise-gated per organization and only team admins can set it.
Scrape add-ons stack: JSON format adds 4 credits a page, and PII redaction, PDF parsing, video transcription and Zero Data Retention each add their own.

Checked against Rate limits (2026-09-29), Billing and credits (2026-09-29), API key restrictions (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.

firecrawl_delete_agent_by_jobidWRITE

Cancel an agent job. DELETE /agent/{jobId}.

api

firecrawl_delete_batch_scrape_by_idWRITE

Cancel a batch scrape job. DELETE /batch/scrape/{id}.

api

firecrawl_delete_crawl_by_idWRITE

Cancel a crawl job. DELETE /crawl/{id}.

api

firecrawl_delete_interact_by_sessionidWRITE

Delete an interact session. DELETE /interact/{sessionId}.

api

firecrawl_delete_monitor_by_monitoridWRITE

Delete a monitor. DELETE /monitor/{monitorId}.

api

firecrawl_delete_scrape_by_jobid_interactWRITE

Stop the interactive browser session associated with a scrape job. DELETE /scrape/{jobId}/interact.

api

firecrawl_get_agentREAD

List agent runs. GET /agent.

api

firecrawl_get_agent_by_jobidREAD

Get the status of an agent job. GET /agent/{jobId}.

api

firecrawl_get_agent_by_jobid_snapshots_by_snapshotidREAD

Get an output snapshot of an agent job. GET /agent/{jobId}/snapshots/{snapshotId}.

api

firecrawl_get_agent_by_jobid_traceREAD

Get the execution trace of an agent job. GET /agent/{jobId}/trace.

api

firecrawl_get_batch_scrape_by_idREAD

Get the status of a batch scrape job. GET /batch/scrape/{id}.

api

firecrawl_get_batch_scrape_by_id_errorsREAD

Get the errors of a batch scrape job. GET /batch/scrape/{id}/errors.

api

firecrawl_get_crawl_activeREAD

Get all active crawls for the authenticated team. GET /crawl/active.

api

firecrawl_get_crawl_by_idREAD

Get the status of a crawl job. GET /crawl/{id}.

api

firecrawl_get_crawl_by_id_errorsREAD

Get the errors of a crawl job. GET /crawl/{id}/errors.

api

firecrawl_get_extract_by_idREAD

Get the status of an extract job. GET /extract/{id}.

api

firecrawl_get_interactREAD

List interact sessions. GET /interact.

api

firecrawl_get_monitorREAD

List monitors. GET /monitor.

api

firecrawl_get_monitor_by_monitoridREAD

Get a monitor. GET /monitor/{monitorId}.

api

firecrawl_get_monitor_by_monitorid_checksREAD

List monitor checks. GET /monitor/{monitorId}/checks.

api

firecrawl_get_monitor_by_monitorid_checks_by_checkidREAD

Get a monitor check. GET /monitor/{monitorId}/checks/{checkId}.

api

firecrawl_get_scrape_by_jobidREAD

Get the status of a scrape job. GET /scrape/{jobId}.

api

firecrawl_get_search_developerREAD

Search the developer index. GET /search/developer.

api

firecrawl_get_search_research_papersREAD

Search papers. GET /search/research/papers.

api

firecrawl_get_search_research_papers_by_idREAD

Inspect or read a paper. GET /search/research/papers/{id}.

api

firecrawl_get_search_research_papers_by_id_similarREAD

Find related papers. GET /search/research/papers/{id}/similar.

api

firecrawl_get_team_activityREAD

List recent API activity. GET /team/activity. Lists your team's recent API activity from the last 24 hours. Returns metadata about each job including the job ID, which can be used with the corresponding GET endpoint (e.g. GET /crawl/{id}) to retrieve full results. Supports cursor-based pagination and filtering by endpoint.

api

firecrawl_get_team_credit_usageREAD

Get remaining credits for the authenticated team. GET /team/credit-usage.

api

firecrawl_get_team_credit_usage_historicalREAD

Get historical credit usage for the authenticated team. GET /team/credit-usage/historical.

api

firecrawl_get_team_queue_statusREAD

Metrics about your team's scrape queue. GET /team/queue-status.

api

firecrawl_get_team_threat_protectionREAD

Get the team's threat protection policy. GET /team/threat-protection.

api

firecrawl_get_team_token_usageREAD

Get remaining tokens for the authenticated team (Extract only). GET /team/token-usage.

api

firecrawl_get_team_token_usage_historicalREAD

Get historical token usage for the authenticated team (Extract only). GET /team/token-usage/historical.

api

firecrawl_patch_monitor_by_monitoridWRITE

Update a monitor. PATCH /monitor/{monitorId}.

api

firecrawl_post_agentWRITE

Start an agent task for agentic data extraction. POST /agent.

api

firecrawl_post_batch_scrapeWRITE

Scrape multiple URLs and optionally extract information using an LLM. POST /batch/scrape.

api

firecrawl_post_crawlWRITE

Crawl multiple URLs based on options. POST /crawl.

api

firecrawl_post_crawl_params_previewWRITE

Preview crawl parameters generated from natural language prompt. POST /crawl/params-preview.

api

firecrawl_post_extractWRITE

Extract structured data from pages using LLMs. POST /extract.

api

firecrawl_post_feedbackWRITE

Submit feedback for a v2 job. POST /feedback.

api

firecrawl_post_interactWRITE

Create an interact session. POST /interact.

api

firecrawl_post_interact_by_sessionid_executeWRITE

Execute code in an interact session. POST /interact/{sessionId}/execute.

api

firecrawl_post_mapWRITE

Map multiple URLs based on options. POST /map.

api

firecrawl_post_monitorWRITE

Create a monitor. POST /monitor.

api

firecrawl_post_monitor_by_monitorid_runWRITE

Run a monitor. POST /monitor/{monitorId}/run.

api

firecrawl_post_scrapeWRITE

Scrape a single URL and optionally extract information using an LLM. POST /scrape.

api

firecrawl_post_scrape_by_jobid_interactWRITE

Interact with the browser session associated with a scrape job. POST /scrape/{jobId}/interact.

api

firecrawl_post_searchWRITE

Search and optionally scrape search results. POST /search.

api

firecrawl_post_search_by_jobid_feedbackWRITE

Submit feedback for a search job. POST /search/{jobId}/feedback.

api

firecrawl_post_search_developerWRITE

Search the developer index. POST /search/developer.

api

firecrawl_post_support_askWRITE

Ask the Firecrawl support agent. POST /support/ask. Diagnose Firecrawl job, account, and API usage issues with an AI support agent.

api

firecrawl_post_support_docs_searchWRITE

Search Firecrawl docs with citations. POST /support/docs-search. Answer Firecrawl documentation questions using the public docs corpus.

api

firecrawl_put_team_threat_protectionWRITE

Update the team's threat protection policy. PUT /team/threat-protection. Full-document update. Unspecified fields reset to defaults. Enterprise feature, team admins only.

api

Often connected alongside

Put Firecrawl behind one governed endpoint.

Same permissions, same audit trail, whatever else you connect next.

Start free See pricing