By use case · Firecrawl pricing

Firecrawl pricing plans: credits, API cost and cost per 1,000 pages

The short answer

Firecrawl sells monthly credits. There is a free tier of 1,000 credits a month, then Hobby at $16 a month for 5,000 credits, Standard at $83 for 100,000, Growth at $333 for 500,000 and Scale at $599 for 1,000,000 on annual billing, or $19, $99, $399 and $749 billed monthly. One credit buys one plain page from scrape, crawl or map, which puts Standard at $0.83 per 1,000 pages. Three rules decide what you actually pay: asking for structured JSON adds 4 credits a page, so typed output costs five times the headline rate; a page that comes back as a 403 or 404 still costs a credit; and top-up credits cost up to three times the in-plan rate. All figures were read from the Firecrawl pricing page and billing documentation on 10 September 2026.

Clean markdown & JSON · JavaScript rendered · robots.txt respected

Last updated September 2026

Live Extraction

Endpoint · POST /v1/extract

POST

try:

Hit Extract to turn this page into clean, LLM-ready data.

robots.txt respected · public data only

Markdown · JSON · structured fields, from one API call. Crawling, rendering and extracting ...

Firecrawl publishes its pricing plainly, and every surcharge is documented, which is more than several vendors in this category manage. The hard part is not finding the numbers. It is converting credits into pages, because the exchange rate changes with what you ask for.

The plain case is 1 credit a page for scrape, crawl and map. Then the options stack on top. The JSON format that runs LLM extraction adds 4 credits a page. PDF parsing adds 1 credit per PDF page, a prompt injection check adds 4, and zero data retention adds 1, so a typed page with zero data retention is 6 credits. Search costs 2 credits per 10 results and browser Interact costs 2 credits a minute, or 7 once a prompt is involved. None of that is hidden. It is simply easy to budget for the 1 and pay for the 5.

We sell a crawl API, so read the last section with the skepticism that deserves. Firecrawl is the right purchase for plenty of teams: it has a free tier and we do not, its core is open source and can be self-hosted, and it runs search and browser sessions we do not offer at all.

If you are pricing the open-source route instead, our breakdown of what self-hosted Firecrawl really costs covers the servers and the AGPL question. Agent builders metering tool calls should read Firecrawl MCP pricing per tool call, and if you have already decided to switch, Firecrawl alternatives compared on cost and output puts the other options side by side.

CRAWL RENDER JS EXTRACT MARKDOWN JSON

Any URL in LLM-ready data out

robots.txt respected public data only

Why it works

Three things the Firecrawl pricing page does not spell out

Typed JSON is five credits

The 1 credit headline covers markdown or HTML. Add the JSON format for LLM extraction and the same page costs 5, so Standard moves from $0.83 to $4.15 per 1,000 pages. Add zero data retention on top and it is 6.

Error pages are billable

The billing documentation charges 1 credit whenever Firecrawl returns a document, and a page that responds with a 403 or 404 still comes back as one. Only a request that returns no document at all is free, so a stale URL list bills at full rate.

Top-ups cost up to 3x

Pay-as-you-go adds credits in $5 increments: 1,000 on Hobby, 2,000 on Standard, 2,500 on Growth and 5,000 on Scale. That is $5.00, $2.50, $2.00 and $1.00 per 1,000, against in-plan rates of $3.20, $0.83, $0.67 and $0.60.

What it handles

Any URL in, clean structured data out

Point ClawEngine at a public page and it crawls, renders the JavaScript and extracts clean markdown or typed JSON in one call. Define a schema for structured fields, and respect robots.txt and Terms of Service by default.

Every published Firecrawl rate, verified 10 September 2026
Monthly and annual prices for every tier, with cost per 1,000 pages
The credit surcharges for JSON, PDF parsing, prompt injection checks and zero data retention
Top-up rates by plan, and which plan rolls credits over
Rate limits and concurrency on every tier
Where Firecrawl is the right purchase and a flat per-page API is not

POST /v1/extract extraction result

200 · JSON

{
  "url": "https://example.com/products/atlas",
  "title": "Atlas Field Notebook",
  "markdown": "# Atlas Field Notebook\n\nDurable...",
  "data": {
    "name": "Atlas Field Notebook",
    "price": 24.00,
    "currency": "USD",
    "rating": 4.7
  },
  "links": [ "/products", "/cart" ],
  "metadata": { "rendered": true }
}

JS rendered · boilerplate stripped ✓ robots.txt respected

Head to head

Firecrawl pricing, annual against monthly, with a flat per-page crawl API for scale

Every Firecrawl figure below was read from its pricing page and billing documentation on 10 September 2026, never from a review aggregator. We put ourselves in the third column and we lose several rows outright.

Swipe to compare all columns →

What you are comparing	Firecrawl, billed yearly	Firecrawl, billed monthly	ClawEngine
What the meter counts	Credits: 1 per plain page, more for options	The same credits at the same rates	Pages. One page of plan allowance per page
Entry price	$16 a month on Hobby, after a free tier of 1,000 credits a month	$19 a month on Hobby	$39 a month on Hobby. No free plan
Published tiers	Hobby $16 for 5,000, Standard $83 for 100,000, Growth $333 for 500,000, Scale $599 for 1,000,000, Enterprise by quote	Hobby $19, Standard $99, Growth $399, Scale $749, with the same credits	Hobby $39, Startup $99, Scale $399, Enterprise custom
Cost per 1,000 plain pages	$3.20 Hobby, $0.83 Standard, $0.67 Growth, $0.60 Scale	$3.80 Hobby, $0.99 Standard, $0.80 Growth, $0.75 Scale	$0.78 Hobby, $0.40 Startup, $0.27 Scale
Cost per 1,000 pages as typed JSON	$16.00 Hobby, $4.15 Standard, $3.33 Growth, $3.00 Scale	$19.00 Hobby, $4.95 Standard, $4.00 Growth, $3.75 Scale	The same as plain pages. Schema extraction is included
Other surcharges	PDF parsing 1 credit per PDF page, prompt injection check 4, zero data retention 1	The same surcharges	None published
Top-up credits	$5 buys 1,000 on Hobby, 2,000 on Standard, 2,500 on Growth, 5,000 on Scale	The same $5 increments	Usage-based overage
Unused credits	Reset monthly, except Scale, which carries them for one month	Reset monthly on Hobby, Standard and Growth	Monthly page allowance
What counts as billable	Any returned document, including 403 and 404 pages. No document, no charge	The same rule	Pages successfully returned to you
Concurrency	2 Free, 5 Hobby, 25 Standard, 50 Growth, 100 Scale	The same ladder	Concurrency scales with tier
Scrape rate limit per minute	10 Free, 100 Hobby, 500 Standard, 5,000 Growth, 10,000 Scale	The same ladder	Scales with tier
Search and browser sessions	Search 2 credits per 10 results, Interact 2 to 7 credits a browser minute	The same rates	Not offered. We do not run search or drive browser sessions
Self-hosting	Open-source core you can run yourself	Open-source core you can run yourself	Not offered
Best for	Teams that can commit for a year and mostly want plain markdown	Teams still sizing the workload, or with seasonal volume	Pipelines that need typed JSON from ordinary public pages at one flat rate per page

Why ClawEngine

One API that crawls, renders and extracts

Not a raw HTML dump, not a headless browser fleet to run, and not a brittle parser to maintain. One call crawls a public page, renders its JavaScript and returns clean markdown or typed JSON, built for RAG pipelines and AI agents.

LLM-ready output

Clean markdown or typed JSON with the boilerplate stripped, so the data drops straight into a vector store, a prompt or an agent without a cleanup step.

JavaScript rendered

Each page loads in a real browser environment before extraction, so single-page apps and client-rendered content come back complete, not as an empty shell.

Compliance-first

ClawEngine works on public, permitted data only. It respects robots.txt and site Terms of Service and honors crawl-delay, so responsible scraping is the default.

Code examples

Typed JSON without a surcharge per page

If most of your pages need to come back as typed fields rather than markdown, the extraction step is where credit pricing multiplies. Send a URL and a schema and ClawEngine renders the page and returns typed JSON as a single page of allowance.

curl Extract fields against a schema (POST /v1/extract)

curl https://api.clawengine.ai/v1/extract \
  -H "Authorization: Bearer $CLAWENGINE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "url": "https://example.com/pricing",
    "format": "json",
    "schema": {
      "plan": "string",
      "monthly_usd": "number",
      "included_credits": "number"
    }
  }'

# One page of plan allowance per page, markdown or typed JSON.
# No format surcharge, no top-up rate, no credit for a 404.

Firecrawl pricing: the questions buyers ask

How much does Firecrawl cost?

Firecrawl has a free tier of 1,000 credits a month, then Hobby at $16 a month for 5,000 credits, Standard at $83 for 100,000, Growth at $333 for 500,000 and Scale at $599 for 1,000,000 on annual billing. Billed monthly those are $19, $99, $399 and $749. Enterprise is quoted and adds zero data retention and SSO.

How much does Firecrawl cost per page?

A plain page is 1 credit, which is $3.20 per 1,000 on Hobby, $0.83 on Standard, $0.67 on Growth and $0.60 on Scale at annual rates. Billed monthly the same pages cost $3.80, $0.99, $0.80 and $0.75. Ask for typed JSON and each page becomes 5 credits, which multiplies every one of those figures by five.

What does one Firecrawl credit buy?

One credit buys one page from a basic scrape, crawl or map call, or one map call covering a whole site. Search costs 2 credits per 10 results, so the Standard plan is described as 50,000 searches or 100,000 pages. Options add to the page cost: JSON output 4 credits, PDF parsing 1 per PDF page and zero data retention 1.

Do Firecrawl credits expire?

Plan credits reset each billing period on Hobby, Standard and Growth, so unused credits are lost. Scale carries unused credits for one month, which the billing documentation ties to annual billing, and Enterprise carries them for two. Pay-as-you-go credits bought on top of a plan expire if you cancel the subscription.

How much does Firecrawl extract cost?

Structured extraction on a scrape or crawl uses the JSON format, which adds 4 credits a page for a total of 5. On Standard that is $4.15 per 1,000 typed pages at annual rates. The separate autonomous agent is usage-based with 5 free runs a day and no fixed per-run price, so measure it on a real task before you budget.

How much does Firecrawl search cost?

Search costs 2 credits per 10 results, rounded up per batch of ten. A standard search returning ten results is therefore 2 credits, which is why Standard advertises 50,000 searches against 100,000 pages. At the annual Standard rate that works out at about $1.66 per 1,000 searches, before scraping any of the result pages.

Does Firecrawl charge for failed requests?

It depends what failed. If Firecrawl returns no document at all, because nothing responded or every rendering attempt failed, the request costs 0 credits. If the target responds with an error such as a 403 or 404, that page is still returned to you and costs 1 credit, so blocked or dead URLs are billable.

What happens when I run out of Firecrawl credits?

Requests start returning HTTP 402 Payment Required unless pay-as-you-go is enabled. With it enabled, Firecrawl adds a $5 increment of credits each time your balance reaches zero: 1,000 credits on Hobby, 2,000 on Standard, 2,500 on Growth and 5,000 on Scale. Pay-as-you-go is available on paid plans only.

What are the Firecrawl rate limits on each plan?

Scrape, map and search allow 10 requests a minute on Free, 100 on Hobby, 500 on Standard, 5,000 on Growth and 10,000 on Scale. Crawl, agent and interact are lower at 2, 20, 100, 1,000 and 2,000 a minute. Concurrent browser requests run 2, 5, 25, 50 and 100 across the same tiers.

What is the cheapest Firecrawl plan?

The free tier gives 1,000 credits a month with no card. The cheapest paid plan is Hobby at $16 a month billed yearly or $19 monthly for 5,000 credits, but it is also the most expensive per credit at $3.20 per 1,000. Standard costs about four times less per credit, so Hobby only makes sense below a few thousand pages a month.

Good questions

Questions about Firecrawl pricing

No. Every paid tier can be billed monthly, at $19, $99, $399 and $749 for Hobby, Standard, Growth and Scale. Annual billing brings those to $16, $83, $333 and $599 a month, a saving of roughly 16 to 20 percent, and the billing documentation ties the one-month credit rollover on Scale to annual billing.

It is five times the plain rate. The JSON format adds 4 credits to every page, so Standard costs $4.15 per 1,000 typed pages, Growth $3.33 and Scale $3.00 on annual billing. A flat per-page plan that counts a schema-typed page as one page is cheaper once most of your pages need typed output rather than markdown.

Read every web scraping question

Explore more

More ways to turn the web into data with ClawEngine

See every use case See pricing Back to the web scraping API

Stop wrangling raw HTML. Get LLM-ready data.

Point ClawEngine at a public page and one call crawls, renders the JavaScript and extracts clean markdown or typed JSON, ready for your RAG pipeline or AI agent. Public, permitted data only.

See pricing

Crawl · render JS · extract markdown & JSON · robots.txt respected, public data only