Pricing
Only pay for what you need
Free
Try the platform at no cost.
10,000 free credits ($10) to explore everything below.
Everything below is billed in credits: 1,000 credits cost $1, and a successful Fetch is one credit. Buy them as you go; they do not expire. Failed, blocked, and empty requests cost nothing.
10,000 free
One credit per successful Fetch, or $1 per 1,000. Asking for Highlights alongside a Fetch adds one credit. A fetch that fails costs nothing.
1 credit
Search a page you already fetched for the exact passages you need. You get ranked, cited snippets without a re-fetch. One credit per request, or $1 per 1,000, independently of Fetch.
99% token reduction99% accuracy
1 credit
PDFs convert to Markdown at one credit a page, or $1 per 1,000, on top of the Fetch. Scanned pages add five credits each, below. Office files, ebooks, and data files convert locally and cost nothing extra.
PDF, office, ebook, data
1 credit / page
A page with no usable text layer is read by a vision model, which adds five credits ($0.005) on top of the page, so a scanned page costs six credits. Every image is one such page. A 40-page PDF with 15 scanned pages costs 116 credits: 1 for the Fetch, 40 for the pages, and 75 for the scans.
vision model
+5 credits / page
A YouTube URL returns the transcript with timestamps, chapters, and a frame for every moment, for five credits ($0.005) a video on top of the Fetch, whatever its length. A video with no captions is transcribed instead and adds ten credits a minute.
YouTube
5 credits / video
Audio files transcribe to Markdown at ten credits ($0.010) a minute, rounded up, with a one-minute minimum.
MP3, WAV, M4A, FLAC
10 credits / minute
Give Crawl a URL and get back the pages it finds on that site, each one a full Fetch. One credit per page it keeps, the same as a Fetch, or $1 per 1,000. Pages it opens only to follow their links cost nothing.
1 credit / page
Send a question and get back the most relevant pages on the web, ranked, each with its URL, title, and an excerpt. 1.5 credits per search, or $1.50 per 1,000. A search that fails or finds nothing costs nothing.
1.5 credits
Iris uses small models to keep only the high-signal fields and elements, so your agent gets the useful data without the full page JSON flooding its context.
Main content is split from secondary regions like nav, footers, and related links. Your agent reads the main document first and pulls the appendix in only when needed.
Fetch gets past common bot checks and CAPTCHAs on its own, so many pages that block automated access still render. Fully managed, with nothing to configure.
Layout-aware Markdown that preserves tables, grids, pricing pages, and icons instead of flattening them into loose paragraphs, so the structure your agent needs survives extraction.
Concurrency
2
Storage
7 days
Support
Email support only
SSO
—
Pay as you go
PopularPrepaid credits, $1 per 1,000.
Pay only for what you need. No monthly commitments.
Everything below is billed in credits: 1,000 credits cost $1, and a successful Fetch is one credit. Buy them as you go; they do not expire. Failed, blocked, and empty requests cost nothing.
$1 / 1,000
One credit per successful Fetch, or $1 per 1,000. Asking for Highlights alongside a Fetch adds one credit. A fetch that fails costs nothing.
$1 / 1,000
Search a page you already fetched for the exact passages you need. You get ranked, cited snippets without a re-fetch. One credit per request, or $1 per 1,000, independently of Fetch.
99% token reduction99% accuracy
$1 / 1,000
PDFs convert to Markdown at one credit a page, or $1 per 1,000, on top of the Fetch. Scanned pages add five credits each, below. Office files, ebooks, and data files convert locally and cost nothing extra.
PDF, office, ebook, data
$1 / 1,000 pages
A page with no usable text layer is read by a vision model, which adds five credits ($0.005) on top of the page, so a scanned page costs six credits. Every image is one such page. A 40-page PDF with 15 scanned pages costs 116 credits: 1 for the Fetch, 40 for the pages, and 75 for the scans.
vision model
+$5 / 1,000 pages
A YouTube URL returns the transcript with timestamps, chapters, and a frame for every moment, for five credits ($0.005) a video on top of the Fetch, whatever its length. A video with no captions is transcribed instead and adds ten credits a minute.
YouTube
$5 / 1,000 videos
Audio files transcribe to Markdown at ten credits ($0.010) a minute, rounded up, with a one-minute minimum.
MP3, WAV, M4A, FLAC
$0.010 / minute
Give Crawl a URL and get back the pages it finds on that site, each one a full Fetch. One credit per page it keeps, the same as a Fetch, or $1 per 1,000. Pages it opens only to follow their links cost nothing.
$1 / 1,000 pages
Send a question and get back the most relevant pages on the web, ranked, each with its URL, title, and an excerpt. 1.5 credits per search, or $1.50 per 1,000. A search that fails or finds nothing costs nothing.
$1.50 / 1,000
Iris uses small models to keep only the high-signal fields and elements, so your agent gets the useful data without the full page JSON flooding its context.
Main content is split from secondary regions like nav, footers, and related links. Your agent reads the main document first and pulls the appendix in only when needed.
Fetch gets past common bot checks and CAPTCHAs on its own, so many pages that block automated access still render. Fully managed, with nothing to configure.
Layout-aware Markdown that preserves tables, grids, pricing pages, and icons instead of flattening them into loose paragraphs, so the structure your agent needs survives extraction.
Concurrency
Burst up to 100 concurrent requests.
Storage
30 days
Support
Standard support
SSO
—
Enterprise
Web-scale with white-glove support at enterprise security.
Everything below is billed in credits: 1,000 credits cost $1, and a successful Fetch is one credit. Buy them as you go; they do not expire. Failed, blocked, and empty requests cost nothing.
Custom allocation
One credit per successful Fetch, or $1 per 1,000. Asking for Highlights alongside a Fetch adds one credit. A fetch that fails costs nothing.
Contact sales
Search a page you already fetched for the exact passages you need. You get ranked, cited snippets without a re-fetch. One credit per request, or $1 per 1,000, independently of Fetch.
99% token reduction99% accuracy
Contact sales
PDFs convert to Markdown at one credit a page, or $1 per 1,000, on top of the Fetch. Scanned pages add five credits each, below. Office files, ebooks, and data files convert locally and cost nothing extra.
PDF, office, ebook, data
Contact sales
A page with no usable text layer is read by a vision model, which adds five credits ($0.005) on top of the page, so a scanned page costs six credits. Every image is one such page. A 40-page PDF with 15 scanned pages costs 116 credits: 1 for the Fetch, 40 for the pages, and 75 for the scans.
vision model
Contact sales
A YouTube URL returns the transcript with timestamps, chapters, and a frame for every moment, for five credits ($0.005) a video on top of the Fetch, whatever its length. A video with no captions is transcribed instead and adds ten credits a minute.
YouTube
Contact sales
Audio files transcribe to Markdown at ten credits ($0.010) a minute, rounded up, with a one-minute minimum.
MP3, WAV, M4A, FLAC
Contact sales
Give Crawl a URL and get back the pages it finds on that site, each one a full Fetch. One credit per page it keeps, the same as a Fetch, or $1 per 1,000. Pages it opens only to follow their links cost nothing.
Contact sales
Send a question and get back the most relevant pages on the web, ranked, each with its URL, title, and an excerpt. 1.5 credits per search, or $1.50 per 1,000. A search that fails or finds nothing costs nothing.
Contact sales
Iris uses small models to keep only the high-signal fields and elements, so your agent gets the useful data without the full page JSON flooding its context.
Main content is split from secondary regions like nav, footers, and related links. Your agent reads the main document first and pulls the appendix in only when needed.
Fetch gets past common bot checks and CAPTCHAs on its own, so many pages that block automated access still render. Fully managed, with nothing to configure.
Layout-aware Markdown that preserves tables, grids, pricing pages, and icons instead of flattening them into loose paragraphs, so the structure your agent needs survives extraction.
Concurrency
200+
Storage
30+ days
Support
High priority support: opt-in Slack channels and live chats
SSO
| Feature | FreeTry the platform at no cost. 10,000 free credits ($10) to explore everything below. | Pay as you goPopularPrepaid credits, $1 per 1,000. Pay only for what you need. No monthly commitments. | EnterpriseWeb-scale with white-glove support at enterprise security. |
|---|---|---|---|
Everything below is billed in credits: 1,000 credits cost $1, and a successful Fetch is one credit. Buy them as you go; they do not expire. Failed, blocked, and empty requests cost nothing. | 10,000 free | $1 / 1,000 | Custom allocation |
One credit per successful Fetch, or $1 per 1,000. Asking for Highlights alongside a Fetch adds one credit. A fetch that fails costs nothing. | 1 credit | $1 / 1,000 | Contact sales |
Search a page you already fetched for the exact passages you need. You get ranked, cited snippets without a re-fetch. One credit per request, or $1 per 1,000, independently of Fetch. 99% token reduction99% accuracy | 1 credit | $1 / 1,000 | Contact sales |
PDFs convert to Markdown at one credit a page, or $1 per 1,000, on top of the Fetch. Scanned pages add five credits each, below. Office files, ebooks, and data files convert locally and cost nothing extra. PDF, office, ebook, data | 1 credit / page | $1 / 1,000 pages | Contact sales |
A page with no usable text layer is read by a vision model, which adds five credits ($0.005) on top of the page, so a scanned page costs six credits. Every image is one such page. A 40-page PDF with 15 scanned pages costs 116 credits: 1 for the Fetch, 40 for the pages, and 75 for the scans. vision model | +5 credits / page | +$5 / 1,000 pages | Contact sales |
A YouTube URL returns the transcript with timestamps, chapters, and a frame for every moment, for five credits ($0.005) a video on top of the Fetch, whatever its length. A video with no captions is transcribed instead and adds ten credits a minute. YouTube | 5 credits / video | $5 / 1,000 videos | Contact sales |
Audio files transcribe to Markdown at ten credits ($0.010) a minute, rounded up, with a one-minute minimum. MP3, WAV, M4A, FLAC | 10 credits / minute | $0.010 / minute | Contact sales |
Give Crawl a URL and get back the pages it finds on that site, each one a full Fetch. One credit per page it keeps, the same as a Fetch, or $1 per 1,000. Pages it opens only to follow their links cost nothing. | 1 credit / page | $1 / 1,000 pages | Contact sales |
Send a question and get back the most relevant pages on the web, ranked, each with its URL, title, and an excerpt. 1.5 credits per search, or $1.50 per 1,000. A search that fails or finds nothing costs nothing. | 1.5 credits | $1.50 / 1,000 | Contact sales |
Iris uses small models to keep only the high-signal fields and elements, so your agent gets the useful data without the full page JSON flooding its context. | |||
Main content is split from secondary regions like nav, footers, and related links. Your agent reads the main document first and pulls the appendix in only when needed. | |||
Fetch gets past common bot checks and CAPTCHAs on its own, so many pages that block automated access still render. Fully managed, with nothing to configure. | |||
Layout-aware Markdown that preserves tables, grids, pricing pages, and icons instead of flattening them into loose paragraphs, so the structure your agent needs survives extraction. | |||
Concurrency | 2 | Burst up to 100 concurrent requests. | 200+ |
Storage | 7 days | 30 days | 30+ days |
Support | Email support only | Standard support | High priority support: opt-in Slack channels and live chats |
SSO | — | — |
Tiers
Expand's concurrency is controlled by tiers.
These tiers are unlocked permanently, for successful spend and time since first successful transaction:
| Tier | Qualification | Concurrency Limit |
|---|---|---|
| 0 | Free Tier | 2 |
| 1 | $10 in successful spend | 5 |
| 2 | $50 in successful spend + 7 full days since first successful transaction | 10 |
| 3 | $200 in successful spend + 14 full days since first successful transaction | 20 |
| 4 | $500 in successful spend + 30 full days since first successful transaction | 50 |
| 5 | $1000 in successful spend + 60 full days since first successful transaction | 100 |
Example: If I have $250 in successful spend:
- Immediately: Tier 1
- After 7 full days since first successful transaction: Tier 2
- After 14 full days since first successful transaction: Tier 3
Provisioned Concurrency
Need instant concurrency without waiting for the tier to upgrade?
Just $1 per browser a month, as many as you need (up to 1,000):
Nr. of browsers
40
Price per month
$40
Perfect for short or long bursts. Billed by card, separately from your credits. Adding browsers mid-month is prorated; lowering the count or cancelling takes effect at the end of the billing month, so you keep what you paid for.
Contact us for more info.
What could fewer tokens save?
Adjust your volume, model, and mix of full pages and Highlights. See how fewer input tokens could change your model bill.
Requests per day
5001K2.5K5K10K25K50K100K
Model
Usage mix
Spatial Markdown + JSON
50%
Highlights
50%
Full-page baseline
37,218 tokens/req
Your blended average
-57%
15,818 tokens/req
Monthly savings
$3,210
Annual savings
$38,520
FAQ
Questions
What does one credit buy?
One successful Fetch costs one credit. A Highlights search costs one credit separately. Using Highlights alongside a new Fetch costs two credits. A thousand credits cost $1.
Do I pay for failed requests?
Requests that return no content, such as failed, blocked or empty ones, cost nothing. An error page the site serves, like a 404, is still a page and costs a credit. Your prepaid credits do not expire.
Is crawling priced differently?
Each rendered page in a crawl costs one credit, the same as Fetch. Document conversion and other add-ons have their own rates in the table above.
Can I get more concurrent browsers?
Concurrency increases with your successful spend and account history. You can also provision browsers for $1 per browser per month, billed separately from credits.
Are the calculator savings guaranteed?
No. The calculator models input-token savings with fixed page sizes per request (37,218 tokens for the baseline, 29,774 for Spatial Markdown + JSON, 1,861 for Highlights), 30 days a month, and uncached model rates last checked September 14, 2026. Your pages, queries, cache use and model pricing will change the result. Expand charges and output tokens are not included.
