---
name: pricing-tracker
description: Extract pricing tiers from a vendor's pricing page and normalize them into a consistent shape. Optimized for SaaS, API, cloud, LLM, and CDN pricing pages — all of which share similar structure but ...
---

# pricing-tracker

Extract pricing tiers from a vendor's pricing page and normalize them into a consistent shape. Optimized for SaaS, API, cloud, LLM, and CDN pricing pages — all of which share similar structure but inconsistent naming.

# pricing-trackerby firecrawl
Extract pricing tiers from a vendor's pricing page and normalize them into a consistent shape. Optimized for SaaS, API, cloud, LLM, and CDN pricing pages — all of which share similar structure but inconsistent naming.

`npx skills add https://github.com/firecrawl/firecrawl-agent --skill pricing-tracker`Download ZIPGitHub

## Pricing Tracker

Extract pricing tiers from a vendor's pricing page and normalize them into a consistent shape. Optimized for SaaS, API, cloud, LLM, and CDN pricing pages — all of which share similar structure but inconsistent naming.

## When to use

* User provides a pricing URL: "get pricing from https://openai.com/api/pricing"

* User names a vendor: "what does Vercel cost?", "get Anthropic API pricing"

* User wants to compare prices across vendors (delegate per-vendor extraction to this skill, then aggregate)

* User wants to monitor pricing on a schedule (combine with `exportSkill: true` to generate a standalone workflow)

Do NOT use for e-commerce SKU pricing — use `e-commerce` instead.

## Strategy

*
Find the pricing URL.

* If the user provided one, use it.

* Otherwise search `"<vendor> pricing"` and take the top result from the vendor's own domain.

*
Scrape with `only-main-content`. Pricing pages are heavy on nav and testimonials that waste context.

*
Identify the unit. Every pricing page has one of these shapes — pick the right one:

* Per seat — SaaS (Notion, Linear, Vercel)

* Per request / token / call — API and LLM (OpenAI, Anthropic)

* Per GB / TB — storage, bandwidth, CDN

* Per minute / hour — compute (Modal, Replicate)

* Flat monthly — simple SaaS tiers

* Usage-based with tiers — cloud (AWS, GCP)

*
Extract every tier. Include Free and Enterprise even when their price is `$0` or `"Contact sales"` — users care about those as much as the paid tiers.

*
Flag the gotchas.

* Annual vs monthly pricing (often a 20% discount buried on annual)

* Overage rates past the included quota

* Seat minimums ("Team plan starts at 5 seats")

* Features gated to higher tiers

* "Free tier" that requires a credit card

*
Call `formatOutput` once with the full pricing object.

## Quick start

```
`// Single vendor
await agent.run({
prompt: 'Get OpenAI API pricing for every model',
urls: ['https://openai.com/api/pricing'],
skills: ['pricing-tracker'],
format: 'json',
})
`
```

```
`// Export as cron-friendly workflow for price monitoring
await agent.run({
prompt: 'Track Vercel Pro pricing',
urls: ['https://vercel.com/pricing'],
skills: ['pricing-tracker'],
exportSkill: true,
})
// exportedSkill.workflow → standalone script you can run on a schedule
`
```

## Output schema

```
`{
"vendor": "OpenAI",
"url": "https://openai.com/api/pricing",
"currency": "USD",
"billingPeriod": "monthly",
"unit": "per 1M tokens",
"tiers": [
{
"name": "gpt-4o",
"price": 2.5,
"unit": "per 1M input tokens",
"includedQuota": null,
"features": [],
"limits": {},
"enterpriseOnly": false
}
],
"freeTierAvailable": false,
"enterpriseContactOnly": false,
"notes": "Output tokens priced separately at $10 / 1M. Batch API is 50% off.",
"capturedAt": "2026-04-15",
"sources": ["https://openai.com/api/pricing"]
}
`
```

## Tips

* Numbers are numbers, not strings. Price `2.5`, never `"$2.50"`. Strip currency symbols and commas. Put the currency in `currency` and the unit in `unit`.

* Do not guess. If a tier shows "Contact sales", put `null` in `price` and set `enterpriseContactOnly: true`. Never make up a number.

* Model-tier grids count as tiers. For LLM pricing pages with many models, emit one `tier` entry per model.

* Capture `capturedAt: <date>` in every output. Makes downstream diffing against a previous run trivial.

* Annual vs monthly: if both are shown, capture the monthly rate as the primary price and note the annual discount in `notes`.

* Always include `sources: [...]` — at minimum the scraped pricing URL.

## See also

* competitor-analysis — when pricing is one axis of a broader comparison

* structured-extraction — lower-level helper if your schema diverges from the default

* deep-research — for pricing that requires cross-referencing third-party sources

## More skills from firecrawl
oracleby firecrawlBest practices for using the oracle CLI (prompt + file bundling, engines, sessions, and file attachment patterns).ordercliby firecrawlFoodora-only CLI for checking past orders and active order status (Deliveroo WIP).peekabooby firecrawlCapture and automate macOS UI with the Peekaboo CLI.sagby firecrawlElevenLabs text-to-speech with mac-style say UX.session-logsby firecrawlSearch and analyze your own session logs (older/parent conversations) using jq.sherpa-onnx-ttsby firecrawlLocal text-to-speech via sherpa-onnx (offline, no cloud)sentryby firecrawlsentry — an installable skill for AI agents, published by firecrawl/skills.wordpress-routerby firecrawlUse when the user asks about WordPress codebases (plugins, themes, block themes, Gutenberg blocks, WP core checkouts) and you need to quickly classify the repo…

---

**Source**: https://github.com/firecrawl/firecrawl-agent/tree/HEAD/agent-core/src/skills/definitions/pricing-tracker
**Author**: firecrawl
**Discovered via**: mcpservers.org