Changelog

It's been our most-requested feature for months: "give us an API for everything Zutrix does."

Today we're launching the Zutrix API — a complete public REST API that puts every Zutrix capability behind a single, clean endpoint: rank tracking, keyword research, site audits, backlinks, competitor analysis, AI search visibility, Magic Content, content tracking, traffic data, and reports.

If you can see it in your dashboard, you can now automate it.

New: The Zutrix API (v1)

One base URL — https://api.zutrix.com/v1 — and around 46 endpoints covering the full platform:

• Rank tracking — projects, tracked keywords, current positions with full history, ranking distribution, raw SERP snapshots, and on-demand refreshes

• Keyword research — suggestions from a seed keyword, every keyword a domain ranks for, and volume/CPC/difficulty metrics

• Site audits & Domain Explorer — run technical audits and pull authority metrics for any domain

• Backlinks & competitors — full backlink profiles with new/lost/broken detection, plus keyword and backlink gap analysis

• AI Search Visibility — how your brand shows up across leading AI models, over REST

• Magic Content & Content Tracker — create research-backed content documents and monitor content changes programmatically

• Traffic & Search Console — your connected GA4 and GSC data, one call away

• Reports, team, notifications — the operational layer, scriptable

JSON everywhere, snake_case fields, ISO-8601 dates, cursor pagination. Boring in the best possible way.

Built for the AI Era

We designed this API to be read by machines as comfortably as by humans — because the way SEO work gets done is changing.

Hand an AI agent a Zutrix API key and it can genuinely operate the platform:

• A public discovery index at GET /v1 and a full OpenAPI 3.1 spec at /v1/openapi.json let any agent orient itself with a single request — no SDK required

• Every error returns a stable machine-readable code plus a plain-language hint telling the caller what to do next

• Rate-limit headers, request IDs on every response, and quota introspection via GET /v1/usage mean agents can pace themselves instead of failing blindly

And if you're already using the Zutrix MCP server with Claude, Cursor, or other AI tools — same keys, same account, and the REST API is now the deeper layer underneath it.

New: API Key Management

Head to Settings → API in your dashboard to create up to 10 named API keys. Each key is shown once at creation, stored hashed on our side, and can be revoked at any time. Existing MCP and Looker Studio keys keep working exactly as before — no action needed.

A Proper Home for Developers

The API ships with a full documentation site at api-docs.zutrix.com — a five-minute quickstart, guides on authentication, rate limits, pagination and errors, a dedicated "Use with AI models" section, and a complete interactive API reference generated straight from the code, so it can never drift from reality.

Included in Every Paid Plan

No add-on, no separate API pricing. API calls share the same plan quotas as your dashboard — a SERP refresh or a site audit costs the same however you trigger it — plus a per-account requests-per-minute limit to keep things fair.

Get Started in 30 Seconds

1. Create a key in Settings → API

2. Make your first call:

curl https://api.zutrix.com/v1/me \ -H "Authorization: Bearer YOUR_API_KEY"

3. Explore everything else at api-docs.zutrix.com — or just point your AI agent at GET /v1 and let it explore for you.

Your rankings, your data, your workflows — now fully programmable. We can't wait to see what you build (and what your agents build for you).

Writing SEO content with AI is easy.

Writing content that actually matches search intent, covers the right topics, follows competitor patterns, and is ready for editorial review is much harder.

Today we’re launching Zutrix Magic Content, a new content editor built directly into Zutrix to help SEO teams go from keyword research to content brief, full article draft, optimization, and writer collaboration in one streamlined workflow.

New: Magic Content Editor

Magic Content brings SERP research, content briefing, AI-assisted writing, full content generation, real-time optimization, and writer collaboration into one focused workspace.

Start with a keyword, choose your country, language, and device, then let Zutrix analyze the real search landscape before the writing begins.

Magic Content helps you understand:

• Which competing pages are ranking

• How long competitor content typically is

• What heading structures are commonly used

• Which NLP terms and topics should be covered

• What questions and sections may be useful

• How close your draft is to the recommended content target

Instead of starting from a blank AI prompt, you start from a research-backed SEO brief.

Competitor-Backed Briefs

Before you write, Magic Content reviews selected SERP rivals and turns that data into practical editorial direction.

You get target word ranges, suggested headings, recommended topics, questions, and structure guidance based on what already works in the search results.

This makes the brief useful for both in-house teams and external writers: less guesswork, fewer disconnected drafts, and a clearer path from keyword to publishable content.

Full Content Generation From the Brief

Magic Content does not stop at creating a content brief.

Once the SERP analysis and brief are ready, Zutrix can generate a complete article draft based on the recommended structure, target topics, headings, and optimization signals.

This helps teams move from keyword research to a first full draft much faster, while still keeping the content grounded in the actual SERP data behind the brief.

Instead of asking AI to write from a generic prompt, Magic Content generates the article from a research-backed SEO brief that already includes competitor insights, recommended terms, content length guidance, and structural suggestions.

Writers and editors can then refine the generated draft, improve selected sections with AI actions, adjust tone, add brand expertise, and optimize the article score before publishing.

Real-Time Content Scoring

Optimization should not happen only after the article is finished.

Inside Magic Content, the content score updates while the draft changes. Writers can see word count, heading structure, recommended term coverage, and topic depth as they edit.

That means every paragraph can move the article closer to the target instead of leaving editors to fix everything at the end.

Selected-Text AI Actions

Magic Content also includes AI writing actions directly inside the editor.

Highlight a section and ask Zutrix to:

• Expand a paragraph

• Rewrite a weak section

• Simplify the wording

• Improve clarity

• Make the tone sharper

• Add more useful detail while preserving the article structure

The goal is not to replace human review. It is to keep useful AI assistance inside the editorial workflow, where writers can accept, adjust, or reject suggestions with context.

Writer Sharing Links

Agencies, founders, and content managers can now share a dedicated writer link without giving collaborators full Zutrix account access.

External writers can open the brief, edit the draft, and see the optimization score they need to improve the article.

Your billing, dashboard, projects, and private account areas stay protected.

This is especially useful when you want to hand off a content brief to a freelancer, client-side writer, or editorial teammate without moving everything into separate docs.

Title & Meta Support

Magic Content also helps prepare the article for publishing by supporting SEO titles and meta descriptions from the keyword and article context.

Instead of writing metadata in a separate tool, teams can keep the brief, draft, optimization score, title, and meta workflow together.

Why This Matters

Most AI writers start with a prompt.

Magic Content starts with the SERP.

That difference matters because SEO content is not just about producing words. It is about matching intent, covering the right entities, structuring the article properly, and giving editors enough control to add expertise, examples, sources, and final judgment before publishing.

Magic Content is designed for SEO teams that want AI speed without losing editorial control.

What You Can Do With This

• Create a content brief from live SERP competitors before assigning the article.

• Generate a complete article draft from the SEO brief.

• Give your writer a controlled link without sharing your Zutrix account.

• See whether the draft is under-covered before publishing.

• Use AI to improve selected sections without rewriting the whole article.

• Check title, meta, headings, word count, and topic coverage in one workspace.

• Move from keyword to publish-ready article without stitching together five separate tools.

Zutrix Magic Content connects SERP research, briefing, full draft generation, AI editing, scoring, metadata, and collaboration so your team can create better SEO content with more momentum and more control.

Open Magic Content from your Zutrix dashboard and turn your next keyword into a researched, scored, writer-ready article.

— The Zutrix Team

Tracking whether your brand gets mentioned in AI responses is only half the story. The other half — arguably the more actionable half — is which URLs the AIs are actually sending users to. Today we're shipping the biggest update to AI Visibility since launch.

🔗 New: URLs & Rankings Tab

For every tracked keyword, you can now see exactly which URLs each AI model cites in its response — automatically classified:

• Your URLs — links pointing back to your own domain. These are gold; the AI equivalent of an organic #1.

• Competitor URLs — pages on the competitor domains you've configured. This is your visibility gap, made measurable.

• Other sources — third-party domains the models referenced (review sites, marketplaces, comparison articles).

Each domain expands to show every distinct URL cited, with model badges showing exactly which AI linked to which page. Hover to see the full path. Click to open it.

📊 Why This Matters

When a user asks ChatGPT "what's the best CRM for small business," the model doesn't just give a list — it often links to specific product pages, comparison articles, or review sites. Until now, the only way to find those URLs was to read through 8 AI responses by hand.

Now you get a domain-grouped, model-attributed view at a glance — plus a Brand URL Coverage stat that shows what fraction of the 8 models actually linked to your domain at least once.

⚡ Inline Keyword Analysis (No More Modal)

Click any keyword in your project — the row expands in place to reveal:

• A glanceable strip of 8 model logos with citation-status dots

• AI Responses — the raw text each model returned

• URLs & Rankings — the new domain/URL view above

• Insights — performance summary + improvement ideas

Multiple keywords can be open at once. No popup, no scroll-lock. Click again to collapse.

🔄 On-Demand Re-tracking

You no longer have to wait until Sunday's automatic sync to refresh a keyword. Each keyword has a 2× per day re-track quota — click the refresh button on any row, or use Re-track All at the project level to refresh everything that has quota remaining.

The 8-model query typically completes in 10–30 seconds; the page polls automatically so fresh results appear without reloading.

The weekly Sunday sync runs exactly as before — the daily quota only applies to manual button clicks, not to the automatic schedule.

🤖 Refreshed Model Lineup

We've updated the tracked models to the latest catalog:

• Claude Sonnet 4.6 — Anthropic

• GPT-5.5 — OpenAI (new)

• Gemini 3.1 Pro — Google

• Gemini 3.5 Flash — Google (new)

• Gemini 2.5 Flash — Google

• DeepSeek V4 Pro — DeepSeek (new)

• Llama 4 Maverick — Meta

• Mistral Large 3 — Mistral AI

Historical tracking data remains fully viewable — model labels gracefully fall back to legacy IDs where needed.

🧭 A Note on Methodology

We deliberately do not enable web-search-augmented model calls on these queries. The whole point of AI Visibility is to measure what the models know from their training data — that's what a real ChatGPT or Claude user gets when they ask a question without explicitly turning on search.

Enabling live web search would turn this into a Google-ranking proxy. The citations you see come from the model's organic memory, prompted to prefer specific product or category pages when known, with strict instructions not to invent URLs.

💡 What You Can Do With This

• "Are any of the 8 AIs actually linking to our product page, or just our homepage?"

• "Which competitors are getting linked when users ask AIs about our category?"

• "Did our recent llms.txt + structured-data work move the needle? Re-track now and compare."

• "Show me a third-party domain that every model cites — we should reach out to them."

• "Which keywords are at 0/8 brand URL coverage? Those are the AI-SEO priorities."

AI search is rewriting the rules of discovery — and URL citations are the first concrete, measurable signal of what the AIs are actually showing users today. This is the most actionable view of AI Visibility we've shipped yet.

— The Zutrix Team