NEW 1,000 free credits on signup · 223 endpoints, one API key, MCP-ready See pricing
NEW · Stream traces to your existing observability stack

Web scraping, crawling & search
for AI agents.

Scrape, crawl, search, and extract the live web — plus domain intelligence and vertical actors — behind one API key, one bill, and one MCP server. Flat 1 credit per call, no multipliers, refund on failure.

No credit card 223 endpoints, one API key MCP server included

POST api.ollagraph.com/v1/scrape/llm-ready
1 credit 200 OK
REQUEST
# curl, Python, TypeScript — same shape, same answer.
curl https://api.ollagraph.com/v1/scrape/llm-ready \
  -H "Authorization: Bearer $OLLAGRAPH_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "url": "https://en.wikipedia.org/wiki/Web_scraping",
    "max_tokens": 512,
    "overlap_tokens": 64
  }'
RESPONSE abridged · ~2,400 tokens · 5 chunks
{
  "status": "success",
  "url": "https://en.wikipedia.org/wiki/Web_scraping",
  "title": "Web scraping - Wikipedia",
  "rendered_with_js": false,
  "rendered_via":    "direct",
  "chunks": [
    {
      "text":        "Web scraping is the process of automatically extracting data from websites…",
      "token_count": 498,
      "byte_start":  0,
      "byte_end":    2196
    },
    { /* chunk 2, 3, 4, 5 */ }
  ]
}
JS-RENDERED WHEN NEEDED
SPA detection auto-retries through a residential rendering pool. Same response shape; rendered_via tells you which path served the page.
CREDIT-METERED, REFUND-ON-FAIL
Most endpoints cost 1 credit; orchestrators cost 3. If the upstream fetch errors, we refund automatically before returning — you only pay for successful calls.
MCP-NATIVE
Every endpoint is also an MCP tool. pipx run ollagraph-mcp and Claude Desktop / Cursor gets all 223 of them at once.
Refund on failed calls Never stores your scraped content Uptime SLA on Team & Business 223 endpoints, one API key Built on open web standards
PLATFORM

One platform.
The whole web stack.

The core web-data primitives — scrape, crawl, search, and extract — behind a single auth, a single bill, and one MCP server. No more duct-taping a scraper, a SERP, a parser, and a headless browser.

Smart crawling

Render-aware crawls that follow links, respect robots, and bypass anti-bot walls cleanly.

Web search

Search the live web across engines, merged and deduped by URL — ranked results from one call, no SERP scraping to maintain.

Structured extraction

Structured extraction with JSON schemas, retries, and verification — typed end-to-end.

Agent observability

Trace every tool call, token, and step. Replay runs. Diff prompts. Find regressions fast.

Browser automation

Stealth Chromium pools that scale to thousands of concurrent sessions in seconds.

AEO audits

Audit how AI crawlers see, cite, and rank your site. Get a remediation checklist instantly.

Markdown conversion

Clean, model-ready markdown for any page. Strips chrome, keeps semantics, preserves citations.

Async jobs

Fire-and-forget jobs with webhooks, idempotency keys, fan-out, and durable retries.

Plus full domain & security intelligence — DNS, SSL/TLS posture, redirect graphs, and threat signals. Explore the intelligence suite →

DEVELOPER EXPERIENCE

One endpoint.
One auth. One billing.

Typed SDKs in TypeScript and Python. A first-class REST API. Idempotent jobs, streaming responses, webhooks, and structured errors. Built the way you wished scraping APIs were built ten years ago.

Typed everywhere
Schemas generate SDK methods, error types, and trace shape.
Streaming-first
SSE & WebSocket for long crawls. Tail logs, results, and progress live.
Local-first DX
CLI, dashboards in the terminal, replay from a trace ID.
POST /v1/crawl
// Crawl a site, extract structured data, observe every step.
import { Ollagraph } from "@ollagraph/sdk";

const og = new Ollagraph({ apiKey: process.env.OG_KEY! });

const job = await og.crawl.start({
  url:       "https://news.ycombinator.com",
  depth:     3,
  renderer:  "chromium-stealth",
  extract: {
    schema: {
      title:   "string",
      url:     "url",
      points:  "int",
      author:  "string",
    },
  },
  observe: { trace: true, redact: ["email"] },
});

for await (const ev of og.stream(job.id)) {
  console.log(ev.phase, ev.url, ev.latencyMs);
}
PRICING

Priced for how agents
actually run.

A flat 1 credit per call — no 5× render or extract multipliers, so a JavaScript-rendered page costs the same as a static one. Pay as you go from $5, get refunded automatically when a fetch fails, and start with 1,000 free credits.

1,000 free credits Pay-as-you-go from $5 Flat 1 credit — no multipliers Refund on failure No content retention
How it compares Ollagraph Firecrawl Typical scraping API
Price per call Flat 1 credit 1–5× by feature Per-request tiers
Pay-as-you-go from $5 Yes No Varies
Refund on failed fetch Yes No No
Free to start 1,000 credits 500 credits Trial
MCP server included Yes Yes No
Search + crawl + extract + intelligence, one key Yes Scrape + crawl Scrape only
No scraped-content retention Yes

On raw static HTML a few providers match our entry rate. Where Ollagraph pulls ahead is real-world, JavaScript-rendered pages — one flat credit, no render multiplier — plus pay-as-you-go, refund-on-failure, and the largest free tier. Firecrawl is a great markdown-first tool; we go further on predictability and breadth.

ENTERPRISE

Built for teams at scale.

Volume pricing, an uptime SLA, SCIM, SAML, and fine-grained RBAC — plus the data-handling guarantee that matters for agent workloads: we never persist scraped content. For teams who need to know exactly where their data goes.

Uptime SLA Volume pricing SCIM & SAML No content retention Audit logs → your SIEM Dedicated support
governance.audit · 2026-05-24 3 events
14:02:17 SCIM
user u_84a1 assigned role "observer" by sso/okta
14:01:08 CMK
workspace acme/prod rotated KMS key · 30d cadence
13:58:42 POLICY
egress to "*.internal.com" blocked · policy:allowlist

Built on open web standards — we honor the Robots Exclusion Protocol (RFC 9309), extract W3C JSON-LD structured data, and follow the Sitemaps and robots.txt conventions the whole web already relies on.

FAQ

Questions, answered.

How does Ollagraph compare to Firecrawl?

Firecrawl is an excellent markdown-first context API. Ollagraph covers the same scrape, crawl, and extract surface, then adds web search, domain intelligence, vertical actors, and agent observability behind one key. On price it bills a flat 1 credit per call with no per-feature multipliers, offers true pay-as-you-go from $5, refunds automatically on failed fetches, and starts you with 1,000 free credits. See the full Firecrawl comparison.

Is there a free tier and pay-as-you-go pricing?

Yes. Every new account gets 1,000 free credits with no credit card, and every endpoint is available on the free tier. Beyond that you can pay as you go from $5 — you are not forced onto a monthly subscription.

How is Ollagraph priced and metered?

Most endpoints cost a flat 1 credit per call and orchestrators cost 3. There are no 5× render or extract multipliers, so a JavaScript-rendered page costs the same as a static one. If an upstream fetch errors, the credit is refunded automatically before the response returns, so you only pay for successful calls.

Does Ollagraph provide an MCP server for AI agents?

Yes. The Ollagraph MCP server exposes all 223 endpoints as tools behind one key. Run pipx run ollagraph-mcp and Claude Desktop, Cursor, or any MCP client gets scrape, crawl, search, extract, and intelligence at once.

Do you store the content Ollagraph scrapes?

No. Ollagraph does not persist scraped page content. Requests are processed and returned; we keep usage metadata for billing and observability, not the pages themselves — the guarantee agent and enterprise workloads need.

Is Ollagraph a good Firecrawl alternative?

For teams that want more than markdown — search, extraction, domain intelligence, and vertical actors under one key — with pay-as-you-go pricing, refund-on-failure, and a 1,000-credit free tier, Ollagraph is a strong Firecrawl alternative. See the side-by-side comparison and pricing breakdown.

Ship agents that
actually understand the web.

Start free with 1,000 credits. No credit card. Production-ready in five minutes — and one platform you'll grow into, not out of.

Free tier is generous. No credit card. The whole catalog from day one.