Changelog
What we've been shipping.
February 2026
LatestData Connectors
Pipe crawl results straight into S3, GCS, Google Sheets, Azure Blob, or Supabase as pages are found. Set the data_connectors param on any crawl request works alongside webhooks.
Better extraction quality
Bumped the max extraction rounds so the models have more room to produce clean structured output on complex pages.
January 2026
Relevance gate
When you use a prompt with AI extraction, pages that aren't relevant to your query get skipped before credits are charged. Big savings on broad crawls with targeted prompts.
AI usage tracking
Every AI extraction now logs token usage and deducts from your credits automatically. You can see per-request costs in the dashboard.
/ai/unblocker
New endpoint that combines AI extraction with anti-bot bypassing in one call. No separate config needed.
extraction_schema parameter
Pass a JSON schema via extraction_schema and the AI output conforms to it. Works with every extraction model.
AI pricing breakdown
Added a per-model token pricing table to the AI Studio pricing page.
December 2025
AI Search
/ai/search search the web and scrape results in a single call. AI extraction runs on each result page automatically. See the guide .
Dashboard refresh
Reworked the dashboard layout, fixed the cost breakdown display, improved mobile usability, and added a light mode option for the playground editor.
Multi-model fallback
If a model is temporarily unavailable, extractions now fall through to the next available model automatically. Nothing to configure it just works.
Guides
Shipped a guides section covering practical use cases first crawl, proxied scraping, AI pipelines, and more.
Empower any project with AI-ready data
Join thousands of developers using Spider to power their data pipelines.