Home / Directory / Agents & orchestration / AI web search APIs / Firecrawl
Firecrawl
Open-source web data API from San Francisco that searches, crawls, and scrapes sites and returns clean markdown or structured data for AI agents.
Developers building agents, RAG apps, and AI features that need search results and full page content from the live web in LLM-ready formats.
Teams that only need ranked links from a search index, or buyers who need guaranteed access to sites that block automated traffic.
Verdict
Firecrawl is a web data company in San Francisco, California, founded by Caleb Peffer, Eric Ciarla, and Nicolas Silberstein Camara, who built it as internal tooling for their earlier AI search product, Mendable. Developers call its API to search the web, scrape a page, crawl a whole site, or interact with a page, and get back markdown, JSON, or screenshots ready for a language model. It matters because getting clean, current web content into a model is often harder than the model call, and Firecrawl is open source, so teams can inspect or self-host it.
Score Breakdown
How Firecrawl scores in the categories that matter to its buyers.
Pricing
Firecrawl prices in monthly credits. Prices below are per month, billed annually; one search costs about two credits and one page scrape one credit.
| Plan | Price | What stands out |
|---|---|---|
| Free | $0 | 1,000 credits a month, low rate limits |
| Standard | $83 / month | 100,000 credits, about 100,000 pages scraped |
| Growth | $333 / month | 500,000 credits, priority support |
| Scale | $599 / month | 1,000,000 credits, 100 concurrent requests |
| Enterprise | Custom | Zero data retention, SSO, SLA, bulk discounts |
The Field at a Glance
How Firecrawl compares with other AI web search APIs vendors we reviewed, by Overall Score and relative typical engagement cost.
Firecrawl scores 7.9 in AI web search APIs, ahead of Exa (7.7), Linkup (7.5), and Valyu (7.2). Relative cost lands lower for this subcategory.
Use-case matrix
| Use case | Fit | Notes |
|---|---|---|
| Full page content for agents | Strong | Returns markdown and structured JSON. |
| Crawling whole sites | Strong | Crawl and map endpoints cover entire domains. |
| Self-hosting | Strong | The core project is open source on GitHub. |
| Ranked web search | Mixed | Search is offered, though peers like Exa and Linkup focus on the index. |
| Sites with heavy bot protection | Mixed | Results depend on the target site. |
| Simple budgeting | Mixed | Credit costs differ by endpoint. |
Who it’s for
Good fit
- AI agent builders
- RAG pipelines over public websites
- Teams replacing in-house scrapers
Poor fit
- Teams that only need search links
- Scraping sites that forbid it
- Buyers who need a fixed price per query type
Review Excerpts
Below are excerpts from public reviews. Our team scoured public reviews, forums, and chat rooms to get a balanced view of customers' experience with this company. Paid reviews and pay-for-play sites such as Clutch were excluded.
“If you're coding with AI, and haven't discovered @firecrawl yet, prepare to have your mind blown 🤯”
“Started using @firecrawl for a project, I wish I used this sooner.”
Plans are priced in credits that buy roughly half as many searches as page scrapes; the $83 Standard plan's 100,000 credits cover about 50,000 searches or 100,000 pages.
Methodology
This page is an independent evaluation of Firecrawl for buyers comparing options in ai web search apis. AI Industry Reviews accepts no sponsorships, advertising, or pay-for-placement fees. Firecrawl did not pay for this review.
What we scored
The headline number is an Overall Score on a 0-10 scale. Eight criteria sit under it in two groups.
- Buyer outcomes (for ai web search apis)
- Clean LLM-ready output
- Search plus full content
- Open source and self-hosting
- Pricing clarity
- Company & commercial
- Innovation & product leadership
- Project management & communication
- Pricing
- Contract fairness
Pricing measures whether the price looks fair for the value delivered, including packaging and renewal friction that show up in real buying cycles.
Score Composition
| Input | Weight | What it covers |
|---|---|---|
| Reviews | 40% | A proprietary read of what practitioners say about likes, complaints, and day-to-day use, including public review sites, forums, and private chat rooms. Paid reviews and pay-for-play sites such as Clutch are out of scope. |
| Product | 35% | Hands-on look at screens and workflows. |
| Pricing | 15% | Whether the price looks fair for what you get. |
| Docs & training | 10% | Docs, tutorials, and training material. |
How we balanced the evidence
The Overall Score is the simple average of the eight criteria. Recommendation language follows that score and the fit pattern described above.
Scope
Firecrawl is graded here as ai web search apis. Criteria scores can move as more review volume and product checks are added.