​

Unified API Platform

The Unified API Platform is DumplingAI’s new /api/v2 surface. It sits alongside the existing Dumpling API rather than replacing it. Use it when you want:

• capabilities like google_search or scrape_page
• exact endpoints like firecrawl.scrape or dataforseo.dataforseo_labs_google_keyword_ideas
• one API key and one control surface for multiple managed providers

​

How it differs from the Dumpling API

​

Dumpling API (/api/v1)

Use /api/v1 when you want the existing endpoint-oriented Dumpling product:

• direct endpoint access
• the current API Playground
• the current endpoint docs and request shapes

​

Unified API Platform (/api/v2)

Use /api/v2 when you want the newer, agent- and developer-oriented platform model:

• simple capabilities for common jobs
• provider-native endpoints when the exact upstream API matters
• shared logging, policy, and spend controls across those lanes

​

Two main lanes

​

Capabilities

Capabilities are the default lane. Examples:

• google_search
• scrape_page
• get_youtube_transcript

Use them when you want DumplingAI to standardize the job and keep the request simple.

​

Providers and endpoints

Providers are vendor overview pages, and endpoints are the provider-native operations under them. Examples:

• firecrawl
• serper.search
• perplexity.search
• firecrawl.scrape
• dataforseo.dataforseo_labs_google_keyword_ideas

Use them when you want exact provider behavior and provider-specific output.

​

Best next steps

• Browse the Workbench
• Try a live request in Workbench
• Read the v2 API Reference
• Use the MCP Server if you want to connect from Claude Code, Codex, or Cursor