Firecrawl
Firecrawl publishes Free (500 credits) / Hobby / Standard / Growth / Scale / Enterprise tiers with per-credit overage rates and a credit-per-endpoint table (1/scrape, 2/10 search results, 5/agent run). xpay verified the no-card free tier, four self-serve Stripe-checkout paid tiers, and an explicit agent-onboarding skill at /agent-onboarding/SKILL.md that handles signup and key issuance — the closest thing to a machine-readable agent pricing manifest in this batch.
Flexible pricing — Start for free, then scale as you grow.
1 credit/page scrape; auto-recharge credit packs (e.g. $9 / 1k extra on Hobby)
$0
$16
per monthSelf-serve
Self-serve
Contact sales
How Firecrawl scores on the 7 agent-ready dimensions
Public pricing
15 / 15
Usage-based / metered
22 / 25
Self-serve checkout
12 / 15
Public API
15 / 15
Low / no minimum
8 / 10
Unauth automated payment
6 / 10
Bonus (machine-readable pricing)On top of /100 base
0 / 5
Total
78 / 100
Six-step check: can an agent actually buy from Firecrawl?
Discover price
https://www.firecrawl.dev/pricing — six tier cards plus per-endpoint credit tableSelect a plan
Free / Hobby / Standard / Growth / Scale / Enterprise distinguishablePay per task
1 credit per page scrape; explicit overage packsAvoid a sales call
Four paid tiers self-serve via StripeAPI docs without auth
https://docs.firecrawl.dev — publicEstimate cost upfront
Per-endpoint credit cost table on /pricingPros and cons for AI agents
Observational summary written by xpay from the signals captured on 2026-05-03. Not a review of the product — only of its current pricing posture for agent buyers.- Pricing is publicly visible on an indexable page — agents can read tiers without scraping past auth.
- Per-unit billing is published, so an agent can budget for a single task before committing.
- API documentation is reachable without a login — discovery and integration can happen in one session.
- Per-unit rate is concrete enough that an agent can model expected spend before issuing a request.
- A free tier exists, lowering the bar for an agent builder to prototype before committing budget.
- Some tiers are sales-led; the highest-capacity surfaces are not self-serve.
- PPU requires account creation and an issued API key; a fully unauthenticated agent purchase is not yet supported.
- No /.well-known/ai-pricing.json or equivalent machine-readable pricing manifest is published — agents must rely on HTML scraping.
How Firecrawl could lift its score
Firecrawl is the most agent-ready provider in batch A. To reach 100/100: publish a strict /.well-known/ai-pricing.json (the SKILL.md is close but unstructured) and offer a one-shot anonymous PPU endpoint so an agent can pay-and-scrape without account creation.
| pricing_visible | true |
| headline_phrasing | Flexible pricing — Start for free, then scale as you grow. |
| tier_count | 6 |
| lowest_paid_entry_usd | 16 |
| free_tier | true |
| free_tier_terms | 500 credits one-time, no card, no time limit |
| per_unit_price | 1 credit/page scrape; auto-recharge credit packs (e.g. $9 / 1k extra on Hobby) |
| annual_required | false |
| self_serve_paid_tiers | 4 |
| sales_only_tiers | 1 |
| public_api_docs_url | https://docs.firecrawl.dev |
| api_docs_auth_walled | false |
| ai_pricing_json_present | false |
| agents_txt_present | false |
| anonymous_purchase_path | false |
Firecrawl
78
/ 100 (rubric v1.1)Data & Scraping APIs
Flexible pricing — Start for free, then scale as you grow.
6
Yes
500 credits one-time, no card, no time limit
$16/mo
1 credit/page scrape; auto-recharge credit packs (e.g. $9 / 1k extra on Hobby)
4 / 1
Public
No
Not published
2026-05-03