Tavily vs Brave Search API

Agent access

1. ai-native userPoint an agent at llms.txt or agent-oriented docs

   weight 2 · round drawn
   Tavily✓fullprobed8/10

   Tavily hosts a working llms.txt (confirmed live via probe, HTTP 200) with agent-oriented CLI examples, plus an agent-setup SKILL.md and MCP server docs explicitly designed for agent consumption. missing for 10: independent third-party confirmation that agents successfully consume/act on the llms.txt content beyond Tavily's own docs.

   • [probe] “PROBE llms.txt: HTTP 200 at https://docs.tavily.com/llms.txt # Tavily Docs > Tavily is the web layer for AI agents: real-time web search, c…”
   • [claimed-docs] “tvly search "latest AI news" tvly extract "https://example.com" tvly crawl "https://docs.example.com" --depth 2 tvly research "compare React…”
   • [claimed-docs] “Read and execute tavily.com/agent-setup/SKILL.md”
   • [claimed-docs] “Let your coding agent install and configure Tavily for you.”
   • [claimed-docs] “Compatible with both Cursor and Claude Desktop! Tavily MCP is also compatible with any MCP client.”
   • [probe] “official MCP server documented at https://docs.tavily.com/documentation/mcp”

   proof ↗⚑ flag

   Brave Search API✓fullprobed8/10

   A live probe confirms llms.txt exists (HTTP 200) with agent-oriented framing describing the API's LLM-read capabilities, and docs explicitly reference agent-oriented resources like a Skills page compatible with numerous coding agents/IDEs, an official MCP server, and an LLM Context endpoint 'benchmarked as the most powerful Search API for AI.' missing for 10: individual page .md endpoints return 404 (no full llms-full.txt style per-page markdown), and no independent/community confirmation that agents successfully consume llms.txt in practice.

   • [probe] “PROBE llms.txt: HTTP 200 at https://api-dashboard.search.brave.com/llms.txt # Brave Search API > Independent search infrastructure for deve…”
   • [claimed-docs] “Skills work with Claude Code, Cursor, GitHub Copilot, Codex, Gemini CLI, VS Code, Windsurf, OpenClaw, Cline, Goose, Amp, Roo Code”
   • [claimed-docs] “An MCP server implementation that integrates the Brave Search API, providing comprehensive search capabilities including web search, local b…”
   • [claimed-docs] “Looking to power agents or chatbots? Use the LLM Context endpoint instead. The LLM Context endpoint is specifically built for machine consum…”
   • [probe] “PROBE docs-md: HTTP 404 at https://api-dashboard.search.brave.com/app/documentation.md”

   proof ↗⚑ flag

2. ai-native userRun the product headlessly / in CI for automation

   weight 2 · round drawn
   Tavily✓fullclaimed8/10

   Tavily is a REST API with SDKs (Python/JS) and a CLI (tvly search/extract/crawl/research) that can be run non-interactively from scripts or CI, with API keys, rate limits, and usage/logs endpoints suited to automated pipelines. missing for 10: no explicit CI/CD pipeline example (e.g., GitHub Actions) or independent report confirming headless CI usage.

   • [claimed-docs] “pip install tavily-python”
   • [claimed-docs] “tvly search "latest AI news" tvly extract "https://example.com" tvly crawl "https://docs.example.com" --depth 2 tvly research "compare React…”
   • [claimed-docs] “The Python SDK allows for easy interaction with the Tavily API, offering the full range of our search functionality directly from your Pytho…”
   • [claimed-docs] “Tavily's JavaScript SDK allows for easy interaction with the Tavily API, offering the full range of our search and extract functionalities d…”
   • [claimed-docs] “Environment Requests per minute (RPM) Development 100 Production 1,000”
   • [claimed-docs] “Retrieve per-request usage logs for the API keys under your account or organization.”
   • [claimed-docs] “tavily_client = TavilyClient(api_key="tvly-YOUR_API_KEY") response = tavily_client.search("Who is Leo Messi?")”

   proof ↗⚑ flag

   Brave Search API✓fullprobed8/10

   As a REST API accessed via API key and curl calls, Brave Search API is inherently headless and scriptable, with docs demonstrating curl-based requests, API key auth setup, and integration into automation platforms like n8n and MCP servers for agentic pipelines. Missing for 10: no explicit CI/CD pipeline example or rate-limit/CI-specific guidance, and no independent hands-on CI report.

   • [claimed-docs] “Get your API key and make your first request in minutes.”
   • [claimed-docs] “To fetch AI-generated descriptions for locations: curl "https://api.search.brave.com/res/v1/local/descriptions?ids=..."”
   • [claimed-docs] “This guide covers the steps to enable Brave Search via the official Brave Search community node in n8n.io, a flexible and community-driven a…”
   • [claimed-docs] “An MCP server implementation that integrates the Brave Search API, providing comprehensive search capabilities including web search, local b…”
   • [claimed-docs] “This guide will help you get set up with the Brave Search API in Dify, an open-source platform designed to simplify AI application developme…”
   • [probe] “official MCP server documented at https://github.com/brave/brave-search-mcp-server”

   proof ↗⚑ flag

3. ai-native userConnect an agent via an official MCP server

   weight 3 · round to Tavily
   Tavily✓fullprobed8/10

   Tavily documents an official MCP server providing tavily-search and tavily-extract tools, explicitly compatible with Cursor, Claude Desktop, and any MCP client, confirmed by a live docs page probe. Missing for 10: independent/hands-on third-party confirmation of MCP server reliability and no mention of the full tool set (crawl/map/research) being exposed via MCP.

   • [claimed-docs] “The Tavily MCP server provides: Seamless interaction with the tavily-search and tavily-extract tools”
   • [claimed-docs] “Compatible with both Cursor and Claude Desktop! Tavily MCP is also compatible with any MCP client.”
   • [claimed-docs] “The Tavily MCP server provides: * Seamless interaction with the tavily-search and tavily-extract tools”
   • [claimed-docs] “Compatible with both [Cursor](https://cursor.sh) and [Claude Desktop](https://claude.ai/download)! Tavily MCP is also compatible with any MC…”
   • [probe] “official MCP server documented at https://docs.tavily.com/documentation/mcp”

   proof ↗⚑ flag

   Brave Search API~partialprobed7/10

   Brave publishes an official MCP server (github.com/brave/brave-search-mcp-server) covering web/local/image/video/news search, LLM context, and summarization, plus a first-party guide for wiring it into Claude Desktop via MCP — solid evidence the axis is met. However, community evidence shows a real caveat: the standard/free API ToS prohibits using responses for AI inference, requiring a separate 'AI Inference' plan, which complicates the 'connect an agent' promise for typical users. Missing for 10: independent hands-on report of the MCP server working end-to-end, and official clarification resolving the ToS/plan conflict for agentic use.

   • [claimed-docs] “This guide covers the steps required to enable Brave Search as a tool to be used in the Claude desktop app using the Model Context Protocol …”
   • [claimed-docs] “An MCP server implementation that integrates the Brave Search API, providing comprehensive search capabilities including web search, local b…”
   • [claimed-docs] “Generates AI-powered summaries from web search results using Brave's summarization API...First perform a web search with `summary: true`, th…”
   • [probe] “official MCP server documented at https://github.com/brave/brave-search-mcp-server”
   • [community] “User noted Brave Search API free tier ToS states: 'These Terms of Use prohibit using responses for AI inference,' raising confusion since gu…”
   • [community] “Workaround suggested: Brave has a separate AI Inference plan that works fine with OpenClaw; users must cancel their standard plan and sign u…”

   proof ↗⚑ flag

4. ai-native userUse an official CLI

   weight 2 · round to Tavily
   Tavily~partialclaimed3/10

   The llms.txt docs excerpt shows CLI commands like `tvly search`, `tvly extract`, `tvly crawl`, `tvly research`, suggesting an official CLI named `tvly` exists, but there is no dedicated installation guide, README, or independent corroboration beyond this single snippet. missing for 10: dedicated CLI docs/install instructions, GitHub repo or package listing for the CLI, independent/hands-on confirmation of the tool.

   • [claimed-docs] “tvly search "latest AI news" tvly extract "https://example.com" tvly crawl "https://docs.example.com" --depth 2 tvly research "compare React…”

   proof ↗⚑ flag

   Brave Search API—none0/10

   The evidence pack documents an official MCP server, various integration guides, and 'Skills' for third-party CLIs (e.g., Gemini CLI, Claude Code) but no dedicated first-party Brave Search API CLI tool is mentioned anywhere.

   ⚑ flag

5. ai-native userDrive the product through a documented public API

   weight 3 · round to Tavily
   Tavily✓fullprobed9/10

   Tavily is fundamentally an API-first product with extensive documented REST endpoints (search, extract, crawl, map, research) plus official Python/JS SDKs, rate-limit docs, usage/logs endpoints, and keyless trial mode — all clearly aimed at programmatic/AI-native consumption. Missing for 10: a discoverable machine-readable OpenAPI/swagger spec (probe found 404s on standard paths), which would round out full API-native tooling.

   • [claimed-docs] “Execute a search query using Tavily Search.”
   • [claimed-docs] “Extract content from one URL or batch up to 20 URLs in one request. Successful URLs appear in results; per-URL failures appear in failed_res…”
   • [claimed-docs] “Tavily Crawl is a graph-based website traversal tool that can explore hundreds of paths in parallel with built-in extraction and intelligent…”
   • [claimed-docs] “Tavily Map traverses websites like a graph and can explore hundreds of paths in parallel with intelligent discovery to generate comprehensiv…”
   • [claimed-docs] “Tavily Research performs comprehensive research on a given topic by conducting multiple searches, analyzing sources, and generating a detail…”
   • [claimed-docs] “The Python SDK allows for easy interaction with the Tavily API, offering the full range of our search functionality directly from your Pytho…”
   • [claimed-docs] “Tavily's JavaScript SDK allows for easy interaction with the Tavily API, offering the full range of our search and extract functionalities d…”
   • [claimed-docs] “Environment Requests per minute (RPM) Development 100 Production 1,000”
   • [claimed-docs] “Get API key and account usage details”
   • [claimed-docs] “Retrieve per-request usage logs for the API keys under your account or organization.”
   • [github] “You can try Tavily without an API key. Instantiate `TavilyClient()` with no arguments and the SDK runs in keyless mode against the public Ta…”
   • [probe] “PROBE openapi: all candidate paths 404 (https://docs.tavily.com/openapi.json, https://docs.tavily.com/swagger.json, https://docs.tavily.com/…”

   proof ↗⚑ flag

   Brave Search API✓fullprobed8/10

   Brave Search API is explicitly documented as a REST/curl-based public API with API keys, extensive query parameters, and even an LLM-specific context endpoint benchmarked for AI agents; probe confirms live docs and llms.txt endpoint. Some caveats exist (no discoverable OpenAPI/swagger spec, and community notes ToS ambiguity around AI inference on the free tier requiring a separate AI plan), which slightly limit a fully frictionless agentic experience. missing for 10: machine-readable OpenAPI/swagger spec, and clean ToS alignment for AI-inference use without plan switching.

   • [claimed-docs] “Get your API key and make your first request in minutes.”
   • [claimed-docs] “Advanced Web search, with pre-extracted content that's optimized for AI agents, LLM grounding, and RAG pipelines.”
   • [claimed-docs] “Looking to power agents or chatbots? Use the LLM Context endpoint instead. The LLM Context endpoint is specifically built for machine consum…”
   • [probe] “PROBE llms.txt: HTTP 200 at https://api-dashboard.search.brave.com/llms.txt # Brave Search API > Independent search infrastructure for deve…”
   • [probe] “PROBE openapi: all candidate paths 404 (https://api-dashboard.search.brave.com/openapi.json, https://api-dashboard.search.brave.com/swagger.…”
   • [community] “User noted Brave Search API free tier ToS states: 'These Terms of Use prohibit using responses for AI inference,' raising confusion since gu…”
   • [community] “Workaround suggested: Brave has a separate AI Inference plan that works fine with OpenClaw; users must cancel their standard plan and sign u…”

   proof ↗⚑ flag

6. ai-native userIssue scoped/least-privilege API credentials for an agent

   weight 2 · round drawn
   Tavily—none0/10

   Evidence shows API-key authentication, project IDs and session/user identifiers for usage attribution, but nothing about issuing scoped or least-privilege credentials (e.g., read-only keys, permission-restricted keys, per-tool key scoping) for agents. missing for 10: any documentation of restricted-permission API keys, role/scope-based key creation, or agent-specific least-privilege credential issuance.

   • [claimed-docs] “You can attach a Project ID to your client to organize and track API usage by project. This is useful when a single API key is used across m…”
   • [claimed-docs] “You can attach session and user identifiers to your client for attribution and analytics across multi-step interactions and agent workflows.”
   • [claimed-docs] “Get API key and account usage details”

   proof ↗⚑ flag

   Brave Search API—none0/10

   The evidence shows only basic API key retrieval and general dashboard docs; there is no mention of scoped, role-based, or least-privilege credential issuance, key permissions, or agent-specific access controls. This is a reasonable axis for an API product, but no evidence supports it being delivered.

   • [claimed-docs] “Get your API key and make your first request in minutes.”

   proof ↗⚑ flag

7. ai-native userBuild against official SDKs

   weight 2 · round to Tavily
   Tavily✓fullprobed9/10

   Tavily ships official Python and JavaScript SDKs with rich, documented functionality (search, extract, crawl, map, research, QnA, RAG context) via pip/npm install and quick-start guides, plus reference docs covering auth, rate limits, project/session attribution, and proxy config. Missing for 10: independent/third-party corroboration beyond vendor docs and GitHub repo, and no official OpenAPI spec was found (probe returned 404s).

   • [claimed-docs] “pip install tavily-python”
   • [claimed-docs] “The Python SDK allows for easy interaction with the Tavily API, offering the full range of our search functionality directly from your Pytho…”
   • [claimed-docs] “Tavily's JavaScript SDK allows for easy interaction with the Tavily API, offering the full range of our search and extract functionalities d…”
   • [claimed-docs] “tavily_client = TavilyClient(api_key="tvly-YOUR_API_KEY") response = tavily_client.search("Who is Leo Messi?")”
   • [claimed-docs] “response = tavily_client.crawl("https://docs.tavily.com", instructions="Find all pages on the Python SDK")”
   • [claimed-docs] “response = tavily_client.map("https://docs.tavily.com")”
   • [claimed-docs] “response = tavily_client.research("What are the latest developments in AI?")”
   • [github] “Instantiate `TavilyClient()` with no arguments and the SDK runs in keyless mode against the public Tavily API. Keyless mode supports `search…”
   • [claimed-docs] “You can attach a Project ID to your client to organize and track API usage by project. This is useful when a single API key is used across m…”
   • [claimed-docs] “You can attach session and user identifiers to your client for attribution and analytics across multi-step interactions and agent workflows.”
   • [claimed-docs] “If you would like to specify a proxy to be used when making requests, you can do so by passing in a proxy parameter on client instantiation.”
   • [probe] “PROBE openapi: all candidate paths 404 (https://docs.tavily.com/openapi.json, https://docs.tavily.com/swagger.json, https://docs.tavily.com/…”

   proof ↗⚑ flag

   Brave Search API~partialprobed4/10

   Brave documents REST endpoints (curl examples) and an official MCP server (brave-search-mcp-server) for agent integration, plus OpenAI-SDK compatibility for the Answers endpoint, but there is no evidence of dedicated official client SDKs (Python/JS/Go packages) or a published OpenAPI spec — probes for openapi.json and docs.md both 404. Missing for 10: dedicated first-party language SDKs, published OpenAPI/spec artifacts, independent developer corroboration of SDK usage.

   • [claimed-docs] “An MCP server implementation that integrates the Brave Search API, providing comprehensive search capabilities including web search, local b…”
   • [claimed-docs] “Use the familiar OpenAI SDK for seamless integration”
   • [probe] “PROBE openapi: all candidate paths 404 (https://api-dashboard.search.brave.com/openapi.json, https://api-dashboard.search.brave.com/swagger.…”
   • [probe] “official MCP server documented at https://github.com/brave/brave-search-mcp-server”
   • [claimed-docs] “Skills work with Claude Code, Cursor, GitHub Copilot, Codex, Gemini CLI, VS Code, Windsurf, OpenClaw, Cline, Goose, Amp, Roo Code”

   proof ↗⚑ flag

8. ai-native userSubscribe to events via webhooks

   weight 2 · round drawn
   Tavily—none0/10

   Tavily's evidence pack covers search, extract, crawl, map, research APIs, SDKs, and an MCP server, but there is no mention of webhooks or event subscription mechanisms anywhere in the docs, GitHub, or probes; async research status must be polled via request ID rather than pushed via webhook.

   • [claimed-docs] “Retrieve the status and results of a research task using its request ID.”
   • [claimed-docs] “When using the Tavily Research API, you can stream responses in real-time by setting `stream: true` in your request.”
   • [probe] “PROBE llms.txt: HTTP 200 at https://docs.tavily.com/llms.txt # Tavily Docs > Tavily is the web layer for AI agents: real-time web search, c…”
   • [probe] “PROBE openapi: all candidate paths 404 (https://docs.tavily.com/openapi.json, https://docs.tavily.com/swagger.json, https://docs.tavily.com/…”

   proof ↗⚑ flag

   Brave Search API—none0/10

   Brave Search API is a request/response search API with an MCP server for agent tool use, but no evidence anywhere in the pack of a webhook/event subscription mechanism.

   ⚑ flag

Agentic features

1. ai-native userOperate the product with natural-language commands

   weight 2 · round to Brave Search API
   Tavily~partialprobed6/10

   Tavily's API accepts natural-language queries (search, research, crawl instructions) and its MCP server plus CLI (tvly search/extract/crawl/research) let AI-native users invoke it via natural-language-like commands rather than rigid syntax; instructions like crawl's 'Find all pages on the Python SDK' show NL-driven parameterization. missing for 10: no evidence of a true conversational/chat interface parsing arbitrary free-form user commands end-to-end, and no independent/hands-on verification beyond vendor docs and github readme.

   • [claimed-docs] “tavily_client.crawl("https://docs.tavily.com", instructions="Find all pages on the Python SDK")”
   • [claimed-docs] “response = tavily_client.crawl("https://docs.tavily.com", instructions="Find all pages on the Python SDK")”
   • [claimed-docs] “tvly search "latest AI news" tvly extract "https://example.com" tvly crawl "https://docs.example.com" --depth 2 tvly research "compare React…”
   • [claimed-docs] “The Tavily MCP server provides: Seamless interaction with the tavily-search and tavily-extract tools”
   • [probe] “official MCP server documented at https://docs.tavily.com/documentation/mcp”
   • [github] “Tavily Research Research lets you create comprehensive research reports on any topic, with aut”

   proof ↗⚑ flag

   Brave Search API✓fullcommunity8/10

   Brave Search API is explicitly built for natural-language queries and agentic consumption: the Rich Search API resolves natural queries like 'weather in london' (docs-49), the LLM Context/Answers endpoints are designed for machine/LLM consumption, and Brave ships an official MCP server plus 'Skills' that let Claude Code, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, Goose, Amp, Roo Code, etc. invoke the API purely via natural-language agent commands (docs-15, docs-45, docs-12, docs-37, docs-38). This directly supports an AI-native user operating the product conversationally through their agent of choice rather than hand-crafting API calls. Missing for 10: independent hands-on verification that these natural-language/agent integrations work smoothly in practice, and clarity on the ToS restriction on free-tier AI inference use noted in community discussion (comm-1/comm-2), which adds a minor licensing caveat rather than a capability failure.

   • [claimed-docs] “Gets the rich realtime result for the requested resource, ie. query like `weather in london`.”
   • [claimed-docs] “Skills work with Claude Code, Cursor, GitHub Copilot, Codex, Gemini CLI, VS Code, Windsurf, OpenClaw, Cline, Goose, Amp, Roo Code”
   • [claimed-docs] “This guide covers the steps required to enable Brave Search as a tool to be used in the Claude desktop app using the Model Context Protocol …”
   • [claimed-docs] “An MCP server implementation that integrates the Brave Search API, providing comprehensive search capabilities including web search, local b…”
   • [claimed-docs] “Looking to power agents or chatbots? Use the LLM Context endpoint instead. The LLM Context endpoint is specifically built for machine consum…”
   • [claimed-docs] “This guide explains how to equip OpenClaw with better exposure to the Brave Search API, giving agents access to crucial context and enhanced…”
   • [claimed-docs] “This guide will help you get set up with the Brave Search API in Dify, an open-source platform designed to simplify AI application developme…”
   • [community] “User noted Brave Search API free tier ToS states: 'These Terms of Use prohibit using responses for AI inference,' raising confusion since gu…”
   • [community] “Workaround suggested: Brave has a separate AI Inference plan that works fine with OpenClaw; users must cancel their standard plan and sign u…”

   proof ↗⚑ flag

Api quality

1. ai-native userExplore an interactive API reference with runnable examples

   weight 2 · round to Tavily
   Tavily~partialprobed5/10

   Tavily has a documented API reference with endpoint pages (search, extract, crawl, map, research) and code snippets, but there's no confirmed interactive/runnable console—an openapi.json probe returned 404s across candidate paths, suggesting no standard interactive spec-driven explorer. missing for 10: evidence of an actual interactive 'try it' console or sandbox with live runnable requests, a discoverable OpenAPI/Swagger spec, and independent confirmation of interactivity beyond static code examples.

   • [claimed-docs] “Execute a search query using Tavily Search.”
   • [claimed-docs] “Extract content from one URL or batch up to 20 URLs in one request. Successful URLs appear in results; per-URL failures appear in failed_res…”
   • [claimed-docs] “Tavily Crawl is a graph-based website traversal tool that can explore hundreds of paths in parallel with built-in extraction and intelligent…”
   • [claimed-docs] “Tavily Map traverses websites like a graph and can explore hundreds of paths in parallel with intelligent discovery to generate comprehensiv…”
   • [claimed-docs] “Tavily Research performs comprehensive research on a given topic by conducting multiple searches, analyzing sources, and generating a detail…”
   • [probe] “PROBE openapi: all candidate paths 404 (https://docs.tavily.com/openapi.json, https://docs.tavily.com/swagger.json, https://docs.tavily.com/…”

   proof ↗⚑ flag

   Brave Search API~partialprobed3/10

   The docs site has a structured API reference (per-endpoint pages like rich_search, local_pois, suggestions) and includes copy-pasteable curl examples, but there is no evidence of an interactive 'try-it' console or runnable code sandbox — probes for an OpenAPI/Swagger spec (a common backbone for interactive references) returned 404s. Missing for 10: evidence of a live/interactive request-runner UI, OpenAPI-based reference, or embedded runnable code examples beyond static curl snippets.

   • [claimed-docs] “Intelligent search suggestions to help users find what they’re looking for.”
   • [claimed-docs] “Gets the rich realtime result for the requested resource, ie. query like `weather in london`.”
   • [claimed-docs] “Get detailed information about points of interest.”
   • [claimed-docs] “Last 24 Hours (`pd`): Get the latest updates and recent content”
   • [probe] “PROBE openapi: all candidate paths 404 (https://api-dashboard.search.brave.com/openapi.json, https://api-dashboard.search.brave.com/swagger.…”
   • [probe] “PROBE docs-md: HTTP 404 at https://api-dashboard.search.brave.com/app/documentation.md”

   proof ↗⚑ flag

2. ai-native userDownload a machine-readable API spec (OpenAPI or equivalent)

   weight 2 · round drawn
   Tavily—none0/10

   Tavily has detailed API reference docs but an explicit probe for standard OpenAPI/Swagger spec locations (openapi.json, swagger.json, etc.) returned 404s, and no evidence pack item points to a downloadable machine-readable spec.

   • [probe] “PROBE openapi: all candidate paths 404 (https://docs.tavily.com/openapi.json, https://docs.tavily.com/swagger.json, https://docs.tavily.com/…”

   proof ↗⚑ flag

   Brave Search API—none0/10

   Direct probes for an OpenAPI/Swagger spec at all standard locations (openapi.json, swagger.json, etc.) returned 404, and no evidence item links to a downloadable machine-readable spec file; only a documentation site and an llms.txt summary page exist, not a formal API spec.

   • [probe] “PROBE openapi: all candidate paths 404 (https://api-dashboard.search.brave.com/openapi.json, https://api-dashboard.search.brave.com/swagger.…”
   • [probe] “PROBE docs-md: HTTP 404 at https://api-dashboard.search.brave.com/app/documentation.md”
   • [probe] “PROBE llms.txt: HTTP 200 at https://api-dashboard.search.brave.com/llms.txt # Brave Search API > Independent search infrastructure for deve…”

   proof ↗⚑ flag

3. ai-native userRely on versioned APIs with a documented deprecation policy

   weight 2 · round drawn
   Tavily—none0/10

   No evidence of API versioning scheme (e.g., v1/v2 paths) or any documented deprecation policy; OpenAPI spec probes returned 404s and no changelog/deprecation docs appear in the evidence pack.

   • [probe] “PROBE openapi: all candidate paths 404 (https://docs.tavily.com/openapi.json, https://docs.tavily.com/swagger.json, https://docs.tavily.com/…”

   proof ↗⚑ flag

   Brave Search API—none0/10

   The evidence pack contains extensive documentation of endpoints, features, and integrations, but nothing about API versioning scheme, version numbers, changelog, or a documented deprecation/sunset policy — a fair and applicable axis for any developer-facing API.

   ⚑ flag

1. ai-native userPerform bulk operations across many items at once

   weight 2 · round to Tavily
   Tavily✓fullclaimed7/10

   Tavily explicitly supports bulk operations: Extract can batch up to 20 URLs per request, and Crawl/Map can traverse and explore hundreds of paths in parallel graph-based traversal, plus Research performs multi-search comprehensive reports with async status retrieval. These directly satisfy 'bulk operations across many items' for an AI-native/automation use case. Missing for 10: no documented bulk/batch search across many queries in one call, and no independent hands-on benchmark confirming throughput at scale beyond vendor docs.

   • [claimed-docs] “Extract content from one URL or batch up to 20 URLs in one request. Successful URLs appear in results; per-URL failures appear in failed_res…”
   • [claimed-docs] “Tavily Crawl is a graph-based website traversal tool that can explore hundreds of paths in parallel with built-in extraction and intelligent…”
   • [claimed-docs] “Tavily Map traverses websites like a graph and can explore hundreds of paths in parallel with intelligent discovery to generate comprehensiv…”
   • [claimed-docs] “Tavily Research performs comprehensive research on a given topic by conducting multiple searches, analyzing sources, and generating a detail…”
   • [claimed-docs] “Retrieve the status and results of a research task using its request ID.”
   • [github] “Crawl lets you traverse a website's content starting from a base URL.”
   • [github] “Tavily Research Research lets you create comprehensive research reports on any topic, with aut”

   proof ↗⚑ flag

   Brave Search API~partialclaimed3/10

   The only evidence of bulk operations is the Local Search API accepting up to 20 location IDs in a single request for POI details/descriptions; there is no documented batch endpoint for submitting multiple search queries at once or any general bulk-processing capability across web/image/video/news search. Missing for 10: batch query submission across many search terms, bulk export/processing tooling, and any documented rate/throughput features for large-scale automated bulk use beyond the 20-ID POI limit.

   • [claimed-docs] “Use the id values to fetch detailed POI information from the Local Search API endpoints. The ids query parameter accepts up to 20 location I…”
   • [claimed-docs] “Use the `id` values to fetch detailed POI information from the Local Search API endpoints.”
   • [claimed-docs] “Get detailed information about points of interest.”

   proof ↗⚑ flag

Citation fidelity

1. developerRely on results carrying canonical URLs, titles, and published dates so my app can cite sources accurately

   weight 3 · round to Brave Search API
   Tavily—none0/10

   The evidence describes Tavily's search/extract/crawl endpoints and SDKs but never documents the actual result schema (URL, title, published date fields) returned by search results, so there's no evidence supporting reliable citation metadata for developers to build accurate citations.

   ⚑ flag

   Brave Search API~partialclaimed6/10

   Docs confirm results include titles and URLs (doc-40) and support date-based filtering/freshness (doc-3, doc-19), plus verifiable-source AI answers (doc-17, doc-27) and news search from trusted sources (doc-28), suggesting citation-relevant metadata is present. However, no evidence explicitly documents a 'published date' field per result or confirms 'canonical URL' normalization in the response schema, and no OpenAPI/schema reference or independent hands-on test verifies field consistency. Missing for 10: explicit per-result published-date field documentation, explicit canonical-URL guarantee, and independent corroboration of citation accuracy.

   • [claimed-docs] “Search for _humans_. Ranked titles, URLs, and short snippets for a results page, plus local and rich enrichments.”
   • [claimed-docs] “Web Search offers powerful date-based filtering to help you find the most relevant content”
   • [claimed-docs] “Last 24 Hours (`pd`): Get the latest updates and recent content”
   • [claimed-docs] “Answers grounded on a single search or multiple searches for better accuracy & reduced hallucinations.”
   • [claimed-docs] “AI-generated answers backed by real-time web search and verifiable sources.”
   • [claimed-docs] “Get real-time news articles from thousands of trusted sources worldwide.”

   proof ↗⚑ flag

2. data engineerRead a documented stance on robots.txt, content licensing, and permitted use of results

   weight 2 · round to Brave Search API
   Tavily—none0/10

   No evidence pack item documents Tavily's stance on robots.txt compliance, content licensing of crawled/extracted data, or permitted use of search/crawl results; only a general note about security/privacy validation layers (tavily-docs-18) touches trust but not this specific axis.

   ⚑ flag

   Brave Search API!disputedcontradicted3/10

   No documentation in the evidence pack addresses robots.txt handling or content licensing terms at all. On permitted use, community evidence shows a real contradiction: Brave's free-tier ToS reportedly prohibits using API responses for 'AI inference,' yet Brave's own official guides promote integrating the API with AI agents (OpenClaw, Claude MCP, Dify) — users had to discover a separate paid 'AI Inference plan' to comply, undercutting a clear, consistent documented stance. missing for 10: any explicit robots.txt policy, any content licensing/reuse terms, and a consistent (non-contradictory) permitted-use statement.

   • [community] “User noted Brave Search API free tier ToS states: 'These Terms of Use prohibit using responses for AI inference,' raising confusion since gu…”
   • [community] “Workaround suggested: Brave has a separate AI Inference plan that works fine with OpenClaw; users must cancel their standard plan and sign u…”
   • [claimed-docs] “This guide covers the steps required to enable Brave Search as a tool to be used in the Claude desktop app using the Model Context Protocol …”
   • [claimed-docs] “This guide explains how to equip OpenClaw with better exposure to the Brave Search API, giving agents access to crucial context and enhanced…”

   proof ↗⚑ flag

Ai consumption

1. ai-native userHave an agent run a multi-step research flow — search, extract contents, and synthesize — through one API

   weight 2 · round to Tavily
   Tavily✓fullclaimed8/10

   Tavily's single API/SDK exposes search, extract, crawl/map, and a dedicated research endpoint that itself performs multiple searches, source analysis, and report synthesis (tavily-docs-4,13,26,27,29), all accessible through one client/API key. This directly matches a multi-step search→extract→synthesize research flow callable by an agent. Missing for 10: independent/hands-on third-party validation of the research endpoint's synthesis quality and no evidence of chaining search+extract+research in a single documented end-to-end example.

   • [claimed-docs] “tavily_client.research("What are the latest developments in AI?")”
   • [claimed-docs] “response = tavily_client.research("What are the latest developments in AI?")”
   • [claimed-docs] “Tavily Research performs comprehensive research on a given topic by conducting multiple searches, analyzing sources, and generating a detail…”
   • [claimed-docs] “"mini" is optimized for targeted, efficient research and works best for narrow or well-scoped questions. "pro" provides comprehensive, multi…”
   • [claimed-docs] “When using the Tavily Research API, you can stream responses in real-time by setting `stream: true` in your request.”
   • [claimed-docs] “Extract web page content from one or more specified URLs using Tavily Extract.”
   • [claimed-docs] “Execute a search query using Tavily Search.”
   • [github] “Tavily Research Research lets you create comprehensive research reports on any topic, with aut”

   proof ↗⚑ flag

   Brave Search API~partialcommunity7/10

   Brave's docs show a coherent path for the story: Web Search for search, the LLM Context endpoint for pre-extracted, token-budgeted content ('no scraping'), and the Answers API/MCP summarization tool for synthesis, all under one API/account and exposed via an official MCP server with search+summarization tools. However, community evidence shows the free/standard tier ToS explicitly prohibits using responses for AI inference, requiring users to switch to a separate paid AI Inference plan to legitimately run this exact agentic search→extract→synthesize flow, which is a significant real-world caveat. Missing for 10: independent hands-on proof of a single API call/session chaining search, extraction, and synthesis end-to-end, and resolution of the ToS friction for standard-tier AI-native use.

   • [claimed-docs] “Looking to power agents or chatbots? Use the LLM Context endpoint instead. The LLM Context endpoint is specifically built for machine consum…”
   • [claimed-docs] “Pre-extracted page content for your LLM — no scraping, token-budgeted. This is the default for RAG, tools, and chatbots.”
   • [claimed-docs] “AI-generated answers backed by real-time web search and verifiable sources.”
   • [claimed-docs] “AI-generated answers backed by real-time web search and verifiable sources”
   • [claimed-docs] “Stream answers in real-time with pro”
   • [claimed-docs] “Use the familiar OpenAI SDK for seamless integration”
   • [claimed-docs] “Generates AI-powered summaries from web search results using Brave's summarization API...First perform a web search with `summary: true`, th…”
   • [claimed-docs] “Generates AI-powered summaries from web search results using Brave's summarization API.”
   • [claimed-docs] “An MCP server implementation that integrates the Brave Search API, providing comprehensive search capabilities including web search, local b…”
   • [community] “User noted Brave Search API free tier ToS states: 'These Terms of Use prohibit using responses for AI inference,' raising confusion since gu…”
   • [community] “Workaround suggested: Brave has a separate AI Inference plan that works fine with OpenClaw; users must cancel their standard plan and sign u…”

   proof ↗⚑ flag

Page contents

1. developerRetrieve full page text or markdown for results, not just snippets

   weight 3 · round to Tavily
   Tavily✓fullclaimed8/10

   Tavily Extract explicitly retrieves full page content (not just snippets) from one or more URLs, batching up to 20 per request, and is documented as a distinct endpoint separate from Search snippets; SDKs and MCP server expose this extract capability directly. Missing for 10: explicit confirmation of markdown-formatted output vs raw text, and independent third-party verification of extraction fidelity.

   • [claimed-docs] “Extract web page content from one or more specified URLs using Tavily Extract.”
   • [claimed-docs] “Extract content from one URL or batch up to 20 URLs in one request. Successful URLs appear in results; per-URL failures appear in failed_res…”
   • [github] “Instantiate `TavilyClient()` with no arguments and the SDK runs in keyless mode against the public Tavily API. Keyless mode supports `search…”
   • [claimed-docs] “The Tavily MCP server provides: * Seamless interaction with the tavily-search and tavily-extract tools”

   proof ↗⚑ flag

   Brave Search API✓fullclaimed7/10

   Brave's docs describe a dedicated LLM Context endpoint that returns 'pre-extracted page content for your LLM — no scraping, token-budgeted' with configurable token/URL limits, going beyond simple title/snippet results and explicitly built for machine consumption in RAG/agent pipelines. missing for 10: explicit format spec (markdown vs plain text) of the extracted content, and independent/hands-on third-party validation of extraction quality/fidelity

   • [claimed-docs] “Pre-extracted page content for your LLM — no scraping, token-budgeted. This is the default for RAG, tools, and chatbots.”
   • [claimed-docs] “Looking to power agents or chatbots? Use the LLM Context endpoint instead. The LLM Context endpoint is specifically built for machine consum…”
   • [claimed-docs] “Fine-tune the amount of context with configurable token and URL limits”
   • [claimed-docs] “Advanced Web search, with pre-extracted content that's optimized for AI agents, LLM grounding, and RAG pipelines.”

   proof ↗⚑ flag

2. developerGet structured output matching a JSON schema I define

   weight 2 · round drawn
   Tavily—none0/10

   No evidence in the pack mentions a JSON-schema-based structured output feature, response schema parameter, or Pydantic/type-safe output validation for search/extract/crawl/research endpoints; responses appear to be fixed JSON shapes rather than developer-defined schemas.

   ⚑ flag

   Brave Search API—none0/10

   The evidence pack shows Brave Search API returns fixed response schemas (JSON results for web/image/video/news/local/answers) and offers no mechanism for developers to define a custom JSON schema that outputs are validated/structured against; no OpenAPI/structured-output/schema-binding feature is documented (openapi probes return 404).

   • [probe] “PROBE openapi: all candidate paths 404 (https://api-dashboard.search.brave.com/openapi.json, https://api-dashboard.search.brave.com/swagger.…”
   • [claimed-docs] “Pre-extracted page content for your LLM — no scraping, token-budgeted. This is the default for RAG, tools, and chatbots.”
   • [claimed-docs] “Looking to power agents or chatbots? Use the LLM Context endpoint instead. The LLM Context endpoint is specifically built for machine consum…”

   proof ↗⚑ flag

3. data engineerCrawl subpages or entire sites starting from a search result

   weight 1 · round to Tavily
   Tavily✓fullclaimed8/10

   Tavily Crawl explicitly traverses a website's content starting from a base URL with graph-based parallel exploration and intelligent discovery, and Map generates full site maps similarly, both documented with SDK examples (tavily_client.crawl(...), tavily_client.map(...)). This directly satisfies crawling subpages/entire sites from a starting URL. Missing for 10: no independent/hands-on verification beyond vendor docs and GitHub README, and no explicit example of crawling starting directly from a search result URL (only from an arbitrary base URL).

   • [github] “Crawl lets you traverse a website's content starting from a base URL.”
   • [claimed-docs] “Tavily Crawl is a graph-based website traversal tool that can explore hundreds of paths in parallel with built-in extraction and intelligent…”
   • [claimed-docs] “response = tavily_client.crawl("https://docs.tavily.com", instructions="Find all pages on the Python SDK")”
   • [claimed-docs] “tavily_client.crawl("https://docs.tavily.com", instructions="Find all pages on the Python SDK")”
   • [github] “Map lets you discover and visualize the structure of a website starting from a base URL.”
   • [claimed-docs] “Tavily Map traverses websites like a graph and can explore hundreds of paths in parallel with intelligent discovery to generate comprehensiv…”
   • [claimed-docs] “response = tavily_client.map("https://docs.tavily.com")”

   proof ↗⚑ flag

   Brave Search API—none0/10

   The evidence shows Brave Search API returns ranked results, site-specific search filters (site:), and pre-extracted per-result content for LLM consumption, but nothing about crawling subpages or traversing an entire site starting from a result. There is no sitemap-following, recursive crawl, or 'fetch all pages under this domain' capability documented anywhere in the docs or MCP server description.

   • [claimed-docs] “Site-specific searches: `site:github.com rust tutorials`”
   • [claimed-docs] “Use quotes for exact phrase matching: "climate change solutions" * Exclude terms with minus: javascript -jquery * Site-specific searches…”
   • [claimed-docs] “Pre-extracted page content for your LLM — no scraping, token-budgeted. This is the default for RAG, tools, and chatbots.”
   • [claimed-docs] “Our service crawls and indexes billions of web pages, ensuring fresh and accurate search results for your applications.”

   proof ↗⚑ flag

Query filters

1. developerRestrict or exclude specific domains from my search results

   weight 2 · round to Brave Search API
   Tavily—none0/10

   The evidence pack never mentions domain include/exclude filtering (no 'include_domains' or 'exclude_domains' parameters, or any similar filter) anywhere in the docs, SDK, or API reference excerpts provided; it only covers exact_match, crawl/map depth, research modes, and rate limits.

   ⚑ flag

   Brave Search API✓fullclaimed7/10

   Brave Search API supports domain exclusion/restriction via query operators like 'site:' and '-' minus exclusion, plus Goggles for custom boosting/demoting of specific websites and domains, giving developers multiple mechanisms to control which domains appear. missing for 10: no dedicated first-class 'exclude_domains' API parameter is documented (relies on query syntax and Goggles), and no independent/hands-on verification confirming reliability of these exclusion mechanisms in practice.

   • [claimed-docs] “Web Search supports Goggles, which allow you to apply custom re-ranking on top of search results. You can: Boost or demote specific websites…”
   • [claimed-docs] “Site-specific searches: `site:github.com rust tutorials`”
   • [claimed-docs] “Web Search supports Goggles, which allow you to apply custom re-ranking on top of search results. You can: * Boost or demote specific webs…”
   • [claimed-docs] “Use quotes for exact phrase matching: "climate change solutions" * Exclude terms with minus: javascript -jquery * Site-specific searches…”
   • [claimed-docs] “Web Search supports Goggles, which allow you to apply custom re-ranking on top of search results.”
   • [claimed-docs] “Goggles: Custom reranking & result filtering”

   proof ↗⚑ flag

2. developerRead per-result relevance scores to threshold what enters my pipeline

   weight 1 · round drawn
   Tavily—none0/10

   The evidence pack describes Tavily's search, extract, crawl, map, and research endpoints but never mentions a relevance/score field returned per result that a developer could use to threshold results. Missing for 10: any documentation of a numeric relevance score in the search response schema, and any guidance on filtering/thresholding by that score.

   • [claimed-docs] “Execute a search query using Tavily Search.”
   • [github] “Use exact_match=True to only return results containing the exact phrase(s) inside quotes”

   proof ↗⚑ flag

   Brave Search API—none0/10

   The docs describe ranking, re-ranking via Goggles, and filters like safesearch/date, but no evidence anywhere of a per-result numeric relevance/confidence score field that a developer could read and threshold on programmatically.

   ⚑ flag

Freshness

1. data engineerGet fresh results with date-range and recency filters backed by a frequently updated index

   weight 3 · round to Brave Search API
   Tavily—none0/10

   The evidence pack covers Tavily's search, extract, crawl, map, and research endpoints, rate limits, and MCP integration, but contains no mention of date-range parameters, recency/freshness filters, or index update frequency. Missing for 10: explicit date-range/time_range search parameters, recency filter documentation, and any claim about index freshness or update cadence.

   • [claimed-docs] “Execute a search query using Tavily Search.”
   • [github] “Use exact_match=True to only return results containing the exact phrase(s) inside quotes”
   • [claimed-docs] “tavily_client.search("Who is Leo Messi?")”

   proof ↗⚑ flag

   Brave Search API✓fullclaimed8/10

   Docs explicitly document date-range/recency filters (e.g. `pd` for last 24 hours, 'powerful date-based filtering'), news search for real-time articles, and claims of a frequently crawled/indexed billion-page index ensuring freshness. Missing for 10: independent/third-party benchmarking of index freshness or update frequency, and no explicit documentation of the full set of date-range operators beyond the 24-hour example.

   • [claimed-docs] “Last 24 Hours (`pd`): Get the latest updates and recent content”
   • [claimed-docs] “Web Search offers powerful date-based filtering to help you find the most relevant content”
   • [claimed-docs] “Our service crawls and indexes billions of web pages, ensuring fresh and accurate search results for your applications.”
   • [claimed-docs] “Get real-time news articles from thousands of trusted sources worldwide.”
   • [claimed-docs] “The Brave Search API gives you access to the same powerful, independent search index that powers Brave Search”

   proof ↗⚑ flag

2. data engineerQuery dedicated verticals like news, images, or finance through specific endpoints or category filters

   weight 2 · round to Brave Search API
   Tavily—none0/10

   The evidence pack describes Tavily's generic search, extract, crawl, map, and research endpoints, but nowhere mentions vertical-specific categories or filters such as news, images, or finance. Missing for 10: any documentation of a topic/category parameter (e.g., topic=news/finance), dedicated vertical endpoints, or image-specific search options.

   • [claimed-docs] “Execute a search query using Tavily Search.”
   • [claimed-docs] “tavily_client.search("Who is Leo Messi?")”
   • [github] “Map lets you discover and visualize the structure of a website starting from a base URL.”

   proof ↗⚑ flag

   Brave Search API✓fullprobed8/10

   Docs show dedicated vertical endpoints/categories including news ('real-time news articles from thousands of trusted sources'), images (billions of images with filtering), video search, local/POI search, and rich search verticals like sports/stocks/weather, alongside date-based freshness filters (pd/pw/pm/py) for recency. Missing for 10: a documented finance-specific endpoint (only general 'stocks' vertical mentioned) and independent third-party corroboration of vertical query behavior beyond first-party docs.

   • [claimed-docs] “Get real-time news articles from thousands of trusted sources worldwide.”
   • [claimed-docs] “Search through billions of images with advanced filtering and SafeSearch options.”
   • [claimed-docs] “Find video content from across the web with metadata and thumbnails.”
   • [claimed-docs] “Find geographic places — businesses, landmarks, POIs, cities, addresses, and more.”
   • [claimed-docs] “Rich Search API responses provide accurate, real-time information about the intent of the query. This data is sourced from 3rd-party API pro…”
   • [claimed-docs] “Last 24 Hours (`pd`): Get the latest updates and recent content”
   • [claimed-docs] “Web Search offers powerful date-based filtering to help you find the most relevant content”
   • [probe] “PROBE llms.txt: HTTP 200 at https://api-dashboard.search.brave.com/llms.txt # Brave Search API > Independent search infrastructure for deve…”

   proof ↗⚑ flag

Targeting

1. data engineerLocalize results by country, language, or location parameters

   weight 2 · round to Brave Search API
   Tavily—none0/10

   The evidence pack documents search, extract, crawl, map, research, and MCP capabilities but never mentions country, language, or geo-location filtering/localization parameters for search results. missing for 10: any documented country/language/location parameter, evidence of localized result sets, or docs referencing geographic targeting.

   ⚑ flag

   Brave Search API~partialclaimed6/10

   Docs confirm country-code targeting for web search and location-based features (POI search, local descriptions), supporting geographic localization. However, no explicit evidence of a language parameter for localization, so full multi-axis localization (country, language, location) isn't fully documented. missing for 10: explicit language-parameter documentation, independent verification of localization accuracy.

   • [claimed-docs] “Customize your web search results by specifying: **Country**: Target results from specific countries using 2-character country codes”
   • [claimed-docs] “To fetch AI-generated descriptions for locations: curl "https://api.search.brave.com/res/v1/local/descriptions?ids=..."”
   • [claimed-docs] “Use the id values to fetch detailed POI information from the Local Search API endpoints. The ids query parameter accepts up to 20 location I…”
   • [claimed-docs] “Use the `id` values to fetch detailed POI information from the Local Search API endpoints.”
   • [claimed-docs] “Get detailed information about points of interest.”
   • [claimed-docs] “Get LLM generated descriptions about points of interest.”

   proof ↗⚑ flag

1. ai-native userDo everything through the API that I can do in the UI

   weight 2 · round to Tavily
   Tavily✓fullprobed7/10

   Tavily's core functionality (search, extract, crawl, map, research, Q&A, RAG context) is fully exposed through the API/SDKs, and CLI/MCP integrations mirror this, suggesting the API is the primary interface with no UI-only features documented. However, there's no explicit comparison confirming full UI-API parity, and no public OpenAPI spec was found (404 on all probed paths), leaving some doubt about completeness of self-service API discovery. Missing for 10: explicit UI feature list to compare against API, and a public OpenAPI/swagger spec for full endpoint parity verification.

   • [claimed-docs] “tavily_client.search("Who is Leo Messi?")”
   • [claimed-docs] “Extract web page content from one or more specified URLs using Tavily Extract.”
   • [claimed-docs] “tavily_client.crawl("https://docs.tavily.com", instructions="Find all pages on the Python SDK")”
   • [claimed-docs] “tavily_client.research("What are the latest developments in AI?")”
   • [github] “Map lets you discover and visualize the structure of a website starting from a base URL.”
   • [github] “context = tavily_client.get_search_context(query="What happened during the Burning Man floods?")”
   • [github] “answer = tavily_client.qna_search(query="Who is Leo Messi?")”
   • [claimed-docs] “Execute a search query using Tavily Search.”
   • [claimed-docs] “Extract content from one URL or batch up to 20 URLs in one request. Successful URLs appear in results; per-URL failures appear in failed_res…”
   • [claimed-docs] “Tavily Crawl is a graph-based website traversal tool that can explore hundreds of paths in parallel with built-in extraction and intelligent…”
   • [claimed-docs] “Tavily Map traverses websites like a graph and can explore hundreds of paths in parallel with intelligent discovery to generate comprehensiv…”
   • [claimed-docs] “Tavily Research performs comprehensive research on a given topic by conducting multiple searches, analyzing sources, and generating a detail…”
   • [claimed-docs] “tvly search "latest AI news" tvly extract "https://example.com" tvly crawl "https://docs.example.com" --depth 2 tvly research "compare React…”
   • [probe] “PROBE openapi: all candidate paths 404 (https://docs.tavily.com/openapi.json, https://docs.tavily.com/swagger.json, https://docs.tavily.com/…”

   proof ↗⚑ flag

   Brave Search API~partialprobed6/10

   Docs show the API exposes most of the same verticals as the consumer Brave Search UI — web, image, video, news, local/POI, rich results (sports/stocks/weather), Goggles re-ranking, AI-generated answers/summarization, suggestions and spell-check — suggesting broad feature parity (docs-6,10,27-30,41-51). However there's no explicit vendor claim of full UI/API parity, no OpenAPI spec is discoverable (probe-3), and community evidence flags that the free-tier ToS actually prohibits AI-inference use of API responses, requiring a separate paid plan — a real-world caveat for AI-native use that the UI doesn't impose (comm-1, comm-2). Missing for 10: an explicit parity statement, evidence of UI-only features (e.g., personalization/history) being absent or present in API, and resolution of the ToS friction for AI use.

   • [claimed-docs] “Web Search supports Goggles, which allow you to apply custom re-ranking on top of search results. You can: Boost or demote specific websites…”
   • [claimed-docs] “To fetch AI-generated descriptions for locations: curl "https://api.search.brave.com/res/v1/local/descriptions?ids=..."”
   • [claimed-docs] “AI-generated answers backed by real-time web search and verifiable sources.”
   • [claimed-docs] “Get real-time news articles from thousands of trusted sources worldwide.”
   • [claimed-docs] “Search through billions of images with advanced filtering and SafeSearch options.”
   • [claimed-docs] “Find video content from across the web with metadata and thumbnails.”
   • [claimed-docs] “Find geographic places — businesses, landmarks, POIs, cities, addresses, and more.”
   • [claimed-docs] “Intelligent search suggestions to help users find what they’re looking for.”
   • [claimed-docs] “Intelligent spell checking to improve query quality and help users find what they’re looking for.”
   • [claimed-docs] “Gets the rich realtime result for the requested resource, ie. query like `weather in london`.”
   • [community] “User noted Brave Search API free tier ToS states: 'These Terms of Use prohibit using responses for AI inference,' raising confusion since gu…”
   • [community] “Workaround suggested: Brave has a separate AI Inference plan that works fine with OpenClaw; users must cancel their standard plan and sign u…”
   • [probe] “PROBE openapi: all candidate paths 404 (https://api-dashboard.search.brave.com/openapi.json, https://api-dashboard.search.brave.com/swagger.…”

   proof ↗⚑ flag

2. ai-native userRead the product's source under an open license

   weight 2 · round drawn
   Tavily—none0/10

   Tavily is a closed, hosted API/SaaS service; while a Python SDK client repo exists on GitHub, the evidence never states any open-source license or exposes the core Tavily service/backend source code. Missing for 10: explicit license grant, access to backend/service source, any statement of open-sourcing the core product.

   • [github] “Map lets you discover and visualize the structure of a website starting from a base URL.”
   • [github] “Instantiate `TavilyClient()` with no arguments and the SDK runs in keyless mode against the public Tavily API. Keyless mode supports `search…”

   proof ↗⚑ flag

   Brave Search API—none0/10

   The evidence pack shows Brave Search API is a proprietary, closed-source hosted API/service; only a companion MCP server wrapper is open source on GitHub, but that is a client integration tool, not the product's own source (search index, ranking, backend). No license or repository for the core Brave Search API itself is evidenced.

   ⚑ flag

Pricing clarity

1. developerRead documented rate limits and concurrency caps with a self-serve upgrade path

   weight 2 · round to Tavily
   Tavily~partialclaimed6/10

   Tavily's docs explicitly state RPM caps for Development (100) vs Production (1,000) environments, describe 429/retry-after behavior, and the pricing page shows a self-serve free tier and usage-based paid plans with a usage/logs API to track consumption — together implying a self-serve upgrade path from dev to production limits. However, there is no explicit concurrency-cap documentation or a clearly described step-by-step upgrade workflow beyond the environment distinction. Missing for 10: explicit concurrency limits, a documented step-by-step self-serve upgrade/billing flow.

   • [claimed-docs] “the API returns a `429 Too Many Requests` response with a `retry-after` header indicating the number of seconds to wait before making anothe…”
   • [claimed-docs] “Environment Requests per minute (RPM) Development 100 Production 1,000”
   • [claimed-docs] “`Production` 1,000”
   • [claimed-docs] “1,000 API credits / month No credit card required”
   • [claimed-docs] “Get API key and account usage details”
   • [claimed-docs] “Retrieve per-request usage logs for the API keys under your account or organization.”
   • [claimed-docs] “1,000 API credits / month ... No credit card required”
   • [claimed-docs] “You get 1,000 free API Credits every month. **No credit card required.**”

   proof ↗⚑ flag

   Brave Search API—none0/10

   No evidence in the pack documents specific rate limits, concurrency caps, or a self-serve upgrade flow; only tangential mentions of a 'standard' vs 'AI Inference' plan appear in a community post, with no linked docs on limits or upgrade mechanics.

   ⚑ flag

2. developerPrototype against the API on a free tier or free credits

   weight 2 · round to Tavily
   Tavily✓fullclaimed9/10

   Tavily offers 1,000 free API credits/month with no credit card required, plus a keyless SDK mode for search/extract to try before signing up, and clear rate limits for development tier prototyping. missing for 10: no independent/community corroboration of the free-tier experience beyond vendor docs.

   • [claimed-docs] “1,000 API credits / month ... No credit card required”
   • [claimed-docs] “1,000 API credits / month No credit card required”
   • [claimed-docs] “You get 1,000 free API Credits every month. **No credit card required.**”
   • [github] “Instantiate `TavilyClient()` with no arguments and the SDK runs in keyless mode against the public Tavily API. Keyless mode supports `search…”
   • [github] “You can try Tavily without an API key. Instantiate `TavilyClient()` with no arguments and the SDK runs in keyless mode against the public Ta…”
   • [github] “You can try Tavily without an API key. Instantiate `TavilyClient()` with no arguments and the SDK runs in keyless mode against the public Ta…”
   • [claimed-docs] “Environment Requests per minute (RPM) Development 100 Production 1,000”

   proof ↗⚑ flag

   Brave Search API!disputedcontradicted5/10

   Docs suggest quick API-key signup ('make your first request in minutes') implying a free tier exists, and community evidence confirms a free tier, but that same evidence shows the free tier's ToS explicitly bans using responses for AI inference — the core prototyping use case highlighted throughout Brave's own AI/agent-focused documentation — forcing developers to cancel and switch to a separate paid 'AI Inference' plan to legally prototype AI use cases.

   • [claimed-docs] “Get your API key and make your first request in minutes.”
   • [community] “User noted Brave Search API free tier ToS states: 'These Terms of Use prohibit using responses for AI inference,' raising confusion since gu…”
   • [community] “Workaround suggested: Brave has a separate AI Inference plan that works fine with OpenClaw; users must cancel their standard plan and sign u…”

   proof ↗⚑ flag

3. developerSee clear per-request or per-credit pricing without talking to sales

   weight 3 · round to Tavily
   Tavily~partialclaimed6/10

   Tavily's public pricing page confirms a self-serve, no-sales-required model: 1,000 free API credits/month with no credit card required and a 'pay only for what you use' model. However, the evidence pack does not show an explicit per-request/per-credit cost table or endpoint-specific credit pricing breakdown, so the exact cost transparency is only partially demonstrated. Missing for 10: a detailed per-endpoint credit-cost table, tier pricing breakdown beyond the free tier.

   • [claimed-docs] “1,000 API credits / month ... No credit card required”
   • [claimed-docs] “Pay only for what you use”
   • [claimed-docs] “1,000 API credits / month No credit card required”
   • [claimed-docs] “You get 1,000 free API Credits every month. **No credit card required.**”

   proof ↗⚑ flag

   Brave Search API—none0/10

   The evidence pack contains no docs or pages showing actual per-request or per-credit pricing figures, tiers, or a self-serve pricing table; the only related mentions are community references to a 'free tier' and a separate 'AI Inference plan' (brave-search-api-comm-1, brave-search-api-comm-2) that imply multiple plans exist but give no concrete pricing numbers or confirmation that pricing is disclosed without contacting sales.

   • [community] “User noted Brave Search API free tier ToS states: 'These Terms of Use prohibit using responses for AI inference,' raising confusion since gu…”
   • [community] “Workaround suggested: Brave has a separate AI Inference plan that works fine with OpenClaw; users must cancel their standard plan and sign u…”

   proof ↗⚑ flag

Scale throughput

1. data engineerSubmit batched or asynchronous jobs for high-volume query workloads

   weight 2 · round to Tavily
   Tavily~partialclaimed6/10

   Tavily's Research endpoint supports async job submission with request-ID based status polling and streaming, and Extract supports batching up to 20 URLs per request; rate-limit docs show RPM tiers and 429/retry-after handling for high-volume workloads. However there's no dedicated bulk/batch job queue for Search itself, no webhook/callback pattern for large offline jobs, and no explicit high-volume batch pricing guidance beyond per-credit usage. Missing for 10: a true batch-submission API for search queries, webhook/callback support for async job completion, and documented guidance/pricing for large-scale batch workloads.

   • [claimed-docs] “Tavily Research performs comprehensive research on a given topic by conducting multiple searches, analyzing sources, and generating a detail…”
   • [claimed-docs] “Retrieve the status and results of a research task using its request ID.”
   • [claimed-docs] “When using the Tavily Research API, you can stream responses in real-time by setting `stream: true` in your request.”
   • [claimed-docs] “Extract content from one URL or batch up to 20 URLs in one request. Successful URLs appear in results; per-URL failures appear in failed_res…”
   • [claimed-docs] “the API returns a `429 Too Many Requests` response with a `retry-after` header indicating the number of seconds to wait before making anothe…”
   • [claimed-docs] “Environment Requests per minute (RPM) Development 100 Production 1,000”

   proof ↗⚑ flag

   Brave Search API—none0/10

   No evidence of batch or asynchronous job submission for high-volume workloads; the API is documented as a synchronous per-query REST API with pagination via offset, not batch/async job endpoints. Pricing-limits related docs cover rate limiting/plans indirectly but nothing about job queuing or batch processing.

   ⚑ flag

1. ai-native userChoose where my data is stored (region/residency)

   weight 2 · round drawn
   Tavily—none0/10

   No evidence in the pack mentions data residency, regional storage options, or geographic control over where data is processed/stored; only security/privacy filtering (PII blocking) is mentioned, not data residency choice. Missing for 10: any mention of region selection, data residency guarantees, or geo-specific deployment options.

   ⚑ flag

   Brave Search API—none0/10

   No evidence in the pack mentions data residency, regional data storage options, or compliance/geo-storage controls for the Brave Search API—only search result targeting by country code (a query parameter, not data residency). This is a fair axis for an API service handling user queries, but no capability is documented.

   ⚑ flag

2. ai-native userPrevent my data from being used to train AI models

   weight 3 · round drawn
   Tavily—none0/10

   No evidence pack item addresses training-data opt-out or a policy preventing customer data from being used to train AI models; only PII/security filtering is mentioned, which is unrelated to model-training data usage.

   ⚑ flag

   Brave Search API—none0/10

   No evidence pack item addresses a user-facing control or policy for preventing personal data from being used to train AI models; the closest evidence (comm-1, comm-2) discusses ToS restrictions on using API *responses* for AI inference and a separate 'AI Inference' plan, not data-training opt-out.

   ⚑ flag

3. ai-native userControl data retention and deletion

   weight 2 · round drawn
   Tavily—none0/10

   No evidence in the pack addresses data retention policies, deletion controls, or user ability to manage stored data/logs beyond usage logging mentions; nothing documents a deletion/export mechanism.

   ⚑ flag

   Brave Search API—none0/10

   No evidence in the pack discusses data retention policies, deletion controls, or privacy settings a user could configure for the Brave Search API; the community evidence only concerns ToS restrictions on AI inference usage, not data retention/deletion.

   ⚑ flag

4. ai-native userOpt out of telemetry and usage tracking

   weight 2 · round drawn
   Tavily—none0/10

   No evidence Tavily documents any telemetry/usage-tracking opt-out mechanism; the only related docs (tavily-docs-33, tavily-docs-34) describe optional session/user/project identifiers for analytics attribution, not a way to disable tracking. Missing for 10: any documented telemetry opt-out setting, privacy policy language on data collection, or configuration flag to disable analytics.

   • [claimed-docs] “You can attach a Project ID to your client to organize and track API usage by project. This is useful when a single API key is used across m…”
   • [claimed-docs] “You can attach session and user identifiers to your client for attribution and analytics across multi-step interactions and agent workflows.”

   proof ↗⚑ flag

   Brave Search API—none0/10

   No evidence in the pack describes any telemetry opt-out, privacy settings, or usage-tracking controls for API consumers; the community item discusses ToS restrictions on AI inference use, not telemetry/tracking opt-out.

   ⚑ flag

Ai consumption

1. ai-native userPlug the API into an agent as a ready-made tool, with function-calling schemas and agent-framework integrations designed for direct tool-call consumption

   weight 3 · round to Tavily
   Tavily✓fullprobed8/10

   Tavily ships SDKs (Python/JS) designed explicitly for LLM/agent consumption (qna_search 'perfect for usage by LLMs', get_search_context for direct RAG feeding), plus an official MCP server compatible with any MCP client for tool-call integration, and clear API reference/OpenAPI-style endpoint docs for search/extract/crawl/map/research. missing for 10: no discoverable OpenAPI/JSON schema spec (probe found 404s) and no explicit named framework integrations (e.g., LangChain/LlamaIndex tool classes) cited in evidence.

   • [github] “This is how you get accurate and concise answers to questions, in one line of code. Perfect for usage by LLMs!”
   • [github] “you now have a context string that you can feed directly into your RAG Application”
   • [claimed-docs] “The Tavily MCP server provides: * Seamless interaction with the tavily-search and tavily-extract tools”
   • [claimed-docs] “Compatible with both Cursor and Claude Desktop! Tavily MCP is also compatible with any MCP client.”
   • [claimed-docs] “The Python SDK allows for easy interaction with the Tavily API, offering the full range of our search functionality directly from your Pytho…”
   • [claimed-docs] “Tavily's JavaScript SDK allows for easy interaction with the Tavily API, offering the full range of our search and extract functionalities d…”
   • [probe] “official MCP server documented at https://docs.tavily.com/documentation/mcp”
   • [probe] “PROBE openapi: all candidate paths 404 (https://docs.tavily.com/openapi.json, https://docs.tavily.com/swagger.json, https://docs.tavily.com/…”

   proof ↗⚑ flag

   Brave Search API~partialprobed7/10

   Brave ships an official MCP server plus guides for Claude Desktop, Open WebUI, n8n, Dify, OpenClaw and 'Skills' for Cursor/Copilot/Codex/etc., and a dedicated LLM Context endpoint explicitly built for machine/tool consumption — strong evidence of ready-made agent-framework tool integration. However, no OpenAPI/function-calling schema was found (probe returned 404s for openapi.json/swagger.json), and community reporting shows the standard/free plan's ToS explicitly prohibits using responses for AI inference, requiring a separate AI Inference plan for agent use — a real practical caveat on 'plug-and-play' tool use. Missing for 10: published OpenAPI/function-calling JSON schema, and clarity/first-party confirmation resolving the ToS friction for standard-tier agent use.

   • [claimed-docs] “An MCP server implementation that integrates the Brave Search API, providing comprehensive search capabilities including web search, local b…”
   • [claimed-docs] “This guide covers the steps required to enable Brave Search as a tool to be used in the Claude desktop app using the Model Context Protocol …”
   • [claimed-docs] “This guide covers the steps required to enable Brave Search as the default search engine in Open WebUI, a free and extensible self-hosted AI…”
   • [claimed-docs] “This guide covers the steps to enable Brave Search via the official Brave Search community node in n8n.io, a flexible and community-driven a…”
   • [claimed-docs] “This guide explains how to equip OpenClaw with better exposure to the Brave Search API, giving agents access to crucial context and enhanced…”
   • [claimed-docs] “This guide will help you get set up with the Brave Search API in Dify, an open-source platform designed to simplify AI application developme…”
   • [claimed-docs] “Skills work with Claude Code, Cursor, GitHub Copilot, Codex, Gemini CLI, VS Code, Windsurf, OpenClaw, Cline, Goose, Amp, Roo Code”
   • [claimed-docs] “Looking to power agents or chatbots? Use the LLM Context endpoint instead. The LLM Context endpoint is specifically built for machine consum…”
   • [probe] “PROBE openapi: all candidate paths 404 (https://api-dashboard.search.brave.com/openapi.json, https://api-dashboard.search.brave.com/swagger.…”
   • [probe] “official MCP server documented at https://github.com/brave/brave-search-mcp-server”
   • [community] “User noted Brave Search API free tier ToS states: 'These Terms of Use prohibit using responses for AI inference,' raising confusion since gu…”
   • [community] “Workaround suggested: Brave has a separate AI Inference plan that works fine with OpenClaw; users must cancel their standard plan and sign u…”

   proof ↗⚑ flag

Llm ready results

1. developerGet a sourced, LLM-generated answer to a query in a single API call

   weight 2 · round to Tavily
   Tavily✓fullclaimed8/10

   Tavily's qna_search (and its underlying Q&A search_depth) returns a single, sourced, LLM-generated direct answer in one API call, explicitly described as 'accurate and concise answers to questions, in one line of code. Perfect for usage by LLMs.' The search endpoint also supports an include_answer option returning a synthesized answer alongside sources. Missing for 10: no independent third-party benchmark of answer quality/accuracy, and no explicit example showing the 'answer' field returned alongside source URLs in the same response payload.

   • [github] “answer = tavily_client.qna_search(query="Who is Leo Messi?")”
   • [github] “This is how you get accurate and concise answers to questions, in one line of code. Perfect for usage by LLMs!”
   • [claimed-docs] “tavily_client.search("Who is Leo Messi?")”
   • [claimed-docs] “Execute a search query using Tavily Search.”

   proof ↗⚑ flag

   Brave Search API~partialcommunity6/10

   Brave documents a dedicated Answers endpoint that returns 'AI-generated answers backed by real-time web search and verifiable sources', with streaming and OpenAI-SDK compatibility, indicating a single-call sourced LLM answer is possible. However, the separate Summarizer feature explicitly requires two calls (search with summary:true, then fetch the summary key), and community evidence shows the free/standard plan's ToS forbids using responses for AI inference, requiring a separate AI Inference plan — a real-world caveat on using this for LLM-answer generation. Missing for 10: a concrete single-request/response example for the Answers endpoint, independent hands-on verification of answer quality/sourcing, and clarity on how the ToS/plan restriction affects typical developer usage.

   • [claimed-docs] “AI-generated answers backed by real-time web search and verifiable sources.”
   • [claimed-docs] “AI-generated answers backed by real-time web search and verifiable sources”
   • [claimed-docs] “Stream answers in real-time with pro”
   • [claimed-docs] “Use the familiar OpenAI SDK for seamless integration”
   • [claimed-docs] “Generates AI-powered summaries from web search results using Brave's summarization API...First perform a web search with `summary: true`, th…”
   • [community] “User noted Brave Search API free tier ToS states: 'These Terms of Use prohibit using responses for AI inference,' raising confusion since gu…”
   • [community] “Workaround suggested: Brave has a separate AI Inference plan that works fine with OpenClaw; users must cancel their standard plan and sign u…”

   proof ↗⚑ flag

2. developerGet results sized and ranked for direct use as LLM context in a RAG pipeline

   weight 3 · round to Tavily
   Tavily✓fullclaimed8/10

   Tavily's get_search_context explicitly produces a context string sized for direct RAG use ('you now have a context string that you can feed directly into your RAG Application'), and qna_search is described as tuned for concise LLM-consumable answers; docs also describe content validation layers improving result quality. missing for 10: no independent/third-party benchmark of ranking quality or context sizing tradeoffs beyond first-party claims.

   • [github] “you now have a context string that you can feed directly into your RAG Application”
   • [github] “context = tavily_client.get_search_context(query="What happened during the Burning Man floods?")”
   • [github] “This is how you get accurate and concise answers to questions, in one line of code. Perfect for usage by LLMs!”
   • [claimed-docs] “Requests pass through security, privacy, and content validation layers that block PII leakage, prompt injection, and malicious sources.”

   proof ↗⚑ flag

   Brave Search API~partialcommunity7/10

   Brave Search API ships a dedicated LLM Context endpoint described as pre-extracted, token-budgeted, and default for RAG/tools/chatbots, with configurable token/URL limits and an official MCP server exposing 'LLM context' as a tool — directly matching the story. However, community evidence shows the free tier's ToS explicitly prohibits using API responses for 'AI inference,' requiring purchase of a separate AI Inference plan to legitimately use this for RAG, which is a significant real-world caveat. Missing for 10: independent/hands-on benchmarks validating RAG output quality, and clarity resolving the ToS friction for standard-plan users.

   • [claimed-docs] “Pre-extracted page content for your LLM — no scraping, token-budgeted. This is the default for RAG, tools, and chatbots.”
   • [claimed-docs] “Looking to power agents or chatbots? Use the LLM Context endpoint instead. The LLM Context endpoint is specifically built for machine consum…”
   • [claimed-docs] “Fine-tune the amount of context with configurable token and URL limits”
   • [claimed-docs] “An MCP server implementation that integrates the Brave Search API, providing comprehensive search capabilities including web search, local b…”
   • [claimed-docs] “Generates AI-powered summaries from web search results using Brave's summarization API...First perform a web search with `summary: true`, th…”
   • [community] “User noted Brave Search API free tier ToS states: 'These Terms of Use prohibit using responses for AI inference,' raising confusion since gu…”
   • [community] “Workaround suggested: Brave has a separate AI Inference plan that works fine with OpenClaw; users must cancel their standard plan and sign u…”

   proof ↗⚑ flag

Retrieval modes

1. developerFind pages similar to a URL I already have

   weight 1 · round drawn
   Tavily—none0/10

   Tavily's evidence shows search (query-based), extract, crawl, and map (both traverse a site's own link structure from a base URL) but no capability to find other pages on the web that are semantically/topically similar to a given URL, which is the actual ask here. Crawl/Map only discover pages within the same site's domain, not similar external content.

   • [github] “Crawl lets you traverse a website's content starting from a base URL.”
   • [claimed-docs] “Tavily Crawl is a graph-based website traversal tool that can explore hundreds of paths in parallel with built-in extraction and intelligent…”
   • [github] “Map lets you discover and visualize the structure of a website starting from a base URL.”
   • [claimed-docs] “Tavily Map traverses websites like a graph and can explore hundreds of paths in parallel with intelligent discovery to generate comprehensiv…”

   proof ↗⚑ flag

   Brave Search API—none0/10

   No evidence of a 'find similar pages/URLs' or related-URL search feature; Brave Search API's documented capabilities (web, image, video, news, local, answers, LLM context, spell check, suggestions) do not include a similarity/related-page endpoint.

   ⚑ flag

2. developerChoose between keyword, neural, or hybrid retrieval modes per query

   weight 2 · round drawn
   Tavily—none0/10

   The evidence pack shows Tavily's search API supports exact-phrase matching (exact_match=True) but there is no documentation of selectable retrieval modes such as keyword vs neural vs hybrid search per query.

   • [github] “Use exact_match=True to only return results containing the exact phrase(s) inside quotes”

   proof ↗⚑ flag

   Brave Search API—none0/10

   The evidence pack describes filtering, ranking (Goggles), pagination, safesearch, and rich verticals, but there is no mention of selectable retrieval modes such as keyword vs neural vs hybrid search per query — Brave's API appears to expose a single indexed web search with re-ranking, not configurable retrieval algorithms.

   ⚑ flag

3. developerRun meaning-based semantic search that finds results keyword engines miss

   weight 3 · round to Tavily
   Tavily~partialclaimed5/10

   Tavily's search API accepts natural-language queries (e.g., 'Who is Leo Messi?') and the existence of an `exact_match=True` flag implies the default behavior is not strict keyword matching, suggesting some meaning-based ranking. However, no evidence explicitly documents embeddings, semantic ranking, or a comparison showing it surfaces results keyword search misses. Missing for 10: explicit documentation of semantic/embedding-based ranking methodology, benchmark or example showing recall beyond keyword search, and independent corroboration of search-quality claims.

   • [claimed-docs] “tavily_client.search("Who is Leo Messi?")”
   • [github] “Use exact_match=True to only return results containing the exact phrase(s) inside quotes”
   • [github] “answer = tavily_client.qna_search(query="Who is Leo Messi?")”
   • [github] “you now have a context string that you can feed directly into your RAG Application”

   proof ↗⚑ flag

   Brave Search API—none0/10

   The evidence describes Brave Search API as a keyword/index-based crawler service (crawls and indexes billions of pages, supports site:, quotes, exclusion operators) plus AI-generated summaries/answers layered on top of search results — nothing describes vector/embedding-based semantic retrieval that surfaces results a keyword engine would miss. AI Answers/LLM Context endpoints ground answers on existing keyword search results rather than performing meaning-based retrieval.

   • [claimed-docs] “Our service crawls and indexes billions of web pages, ensuring fresh and accurate search results for your applications.”
   • [claimed-docs] “Use quotes for exact phrase matching: "climate change solutions" * Exclude terms with minus: javascript -jquery * Site-specific searches…”
   • [claimed-docs] “Site-specific searches: `site:github.com rust tutorials`”
   • [claimed-docs] “Looking to power agents or chatbots? Use the LLM Context endpoint instead. The LLM Context endpoint is specifically built for machine consum…”
   • [claimed-docs] “Pre-extracted page content for your LLM — no scraping, token-budgeted. This is the default for RAG, tools, and chatbots.”

   proof ↗⚑ flag