Our model Iris sees the page in a real browser and returns accurate markdown, tables and icons intact, plus the hidden JSON. Click any line to check where it came from.
Your agent sees what ordinary markdown APIs miss.Ordinary converters keep clutter, drop the table, and never see what only rendered in the browser.Iris sees the rendered page and returns three things: markdown with tables and icons intact, the hidden JSON, and an appendix with everything else.Nothing lost, nothing in the way.
State Extraction
Hidden frontend state delivered as clean JSON
Noise Pruning
Nav, footer, ads, banners gone before you pay for them
Visual Icons
CSS/SVG icons become text your LLM reads
Your agent sees what ordinary markdown APIs miss.Ordinary converters keep clutter, drop the table, and never see what only rendered in the browser.Iris sees the rendered page and returns three things: markdown with tables and icons intact, the hidden JSON, and an appendix with everything else.Nothing lost, nothing in the way.
website.html
Iris
Spatial MD
Loaded By Default
---
type: article
title: Cozy..
status: ok
---
# Cozy Cabin
4.92
| Wifi | Fast |
| x Pool | - |
{} State JSON
Loaded By Default
{
"price": 120,
"currency": "USD",
"rating": 4.92,
"reviews": 128,
"avail": […],
"wifi": true,
"pool": false
}
Appendix
On Demand
Site chrome your agent might need later:
- Global navigation
- Footer links
- Recommendations
- Page controls
- Never the main content
website.html
Iris
Spatial MD
Loaded By Default
---
type: article
title: Cozy..
status: ok
---
# Cozy Cabin
4.92
| Wifi | Fast |
| x Pool | - |
{} State JSON
Loaded By Default
{
"price": 120,
"currency": "USD",
"rating": 4.92,
"reviews": 128,
"avail": […],
"wifi": true,
"pool": false
}
Appendix
On Demand
Site chrome your agent might need later:
- Global navigation
- Footer links
- Recommendations
- Page controls
- Never the main content
Click any line. See the exact spot on the page.
Every line links back to where it came from, so you can verify what your agent saw.
It works out of the box without any configuration—JavaScript rendering, residential proxies, and bot protection are handled automatically for every request.
We already read the whole page so your agent doesn't have to.
Even with accurate markdown, a 10k token page makes your agent slower, more expensive, and more likely to lose focus. Pass a query to Iris and get back only the facts your agent needs.
Paste one prompt into your coding agent. Expand will configure every supported harness detected on this machine, then verify the setup with an exact citation.
Search a page you already fetched for the exact passages you need — ranked, cited snippets, no re-fetch. Billed at $0.001 — $1 per 1,000, independently of Fetch.
99% token reduction99% accuracy
$10 free credits
Concurrency
2
Storage
7 days
Proxies
Support
Email support only
SSO
—
Pay as you go
Popular
Pricing that scales with you.
No monthly commitments.
$2 / 1,000
99% token reduction99% accuracy
$1 / 1,000
Enterprise
Web-scale with white-glove support at enterprise security.
Contact sales
99% token reduction99% accuracy
Contact sales
Free
Try the platform at no cost.
Free credits to explore core features.
Pay as you go
Popular
Pricing that scales with you.
No monthly commitments.
Enterprise
Web-scale with white-glove support at enterprise security.
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
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.
Concurrency
Storage
30 days
Proxies
Support
Standard support
SSO
—
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.
Concurrency
200+
Storage
30+ days
Proxies
Support
High priority support: opt-in Slack channels and live chats
SSO
$10 free credits
$2 / 1,000
Contact sales
99% token reduction99% accuracy
$10 free credits
$1 / 1,000
Contact sales
Concurrency
2
200+
Storage
7 days
30 days
30+ days
Proxies
Support
Email support only
Standard support
High priority support: opt-in Slack channels and live chats
SSO
—
—
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, up to 100 browsers:
Nr. of browsers
40
Price per month
$40
Perfect for short or long bursts. Cancel anytime — you keep the extra concurrency through the end of the billing month (prorated monthly).
Hacker News
Figma pricing
Our World in Data
looks.
