Perplexity Sonar API vs Brave Search API

Agent access

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

   weight 2 · round to Perplexity Sonar API
   Perplexity Sonar API✓fullprobed9/10

   Direct probe evidence confirms llms.txt is live (HTTP 200) with an index pointing to agent-oriented docs, plus .md variants of docs pages and an OpenAPI spec are all directly fetchable, exactly matching the agent-consumable docs pattern; docs also explicitly reference agents/coding agents consuming these resources. Missing for 10: no independent third-party report of an agent actually successfully using llms.txt in practice.

   • [probe] “PROBE llms.txt: HTTP 200 at https://docs.perplexity.ai/llms.txt # Perplexity > Perplexity API documentation for building with the Agent API…”
   • [probe] “PROBE docs-md: HTTP 200 at https://docs.perplexity.ai/docs/getting-started/overview.md > ## Documentation Index > Fetch the complete documen…”
   • [probe] “PROBE openapi: HTTP 200 at https://docs.perplexity.ai/openapi.json — contains "openapi" key”
   • [claimed-docs] “Install and use Perplexity's pplx command-line interface for web search and query-relevant page snippets from your terminal or coding agent.”

   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
   Perplexity Sonar API✓fullprobed8/10

   Sonar API is fundamentally a REST/API product with official Python SDK (sync and async clients, httpx/aiohttp), CLI tool returning JSON for shell pipelines/agent tool calls, retries/error handling, and an OpenAPI spec — all directly enabling headless/CI automation. Docs explicitly call out CLI output as 'ready for shell pipelines and agent tool calls, with no code to write.' Missing for 10: no explicit CI/CD pipeline examples (e.g. GitHub Actions) or independent third-party report of running it in CI.

   • [claimed-docs] “You can now run Perplexity Search straight from your terminal. The Perplexity CLI returns the same ranked results as JSON, ready for shell p…”
   • [claimed-docs] “Install and use Perplexity's pplx command-line interface for web search and query-relevant page snippets from your terminal or coding agent.”
   • [github] “We provide support for streaming responses using Server Side Events (SSE).”
   • [github] “Certain errors are automatically retried 2 times by default, with a short exponential backoff.”
   • [github] “By default, the async client uses `httpx` for HTTP requests. However, for improved concurrency performance you may also use `aiohttp` as the…”
   • [github] “The library includes type definitions for all request params and response fields, and offers both synchronous and asynchronous clients power…”
   • [probe] “PROBE openapi: HTTP 200 at https://docs.perplexity.ai/openapi.json — contains "openapi" key”

   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 Perplexity Sonar API
   Perplexity Sonar API✓fullprobed8/10

   Perplexity Sonar API is not itself an agent but a service/API, so this axis applies; docs clearly document an official MCP server, both a Perplexity-hosted remote endpoint (api.perplexity.ai/mcp) and a local stdio server, plus tool-restriction configuration, allowing agents to connect via MCP. Missing for 10: independent/hands-on third-party confirmation of the MCP server working in practice beyond first-party docs.

   • [claimed-docs] “The Perplexity MCP Server enables AI assistants to access Perplexity's powerful search and reasoning capabilities directly within their work…”
   • [claimed-docs] “Remote MCP server (recommended): hosted by Perplexity at `https://api.perplexity.ai/mcp`. No installation, nothing to update, works with any…”
   • [claimed-docs] “Local MCP server: run the open-source server on your machine over stdio. Use this if your client only supports stdio servers or you need to …”
   • [claimed-docs] “To restrict which tools the model can call, disable tools by default and enable the ones you want”
   • [probe] “official MCP server documented at https://docs.perplexity.ai/docs/getting-started/integrations/mcp-server”

   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 Perplexity Sonar API
   Perplexity Sonar API✓fullclaimed8/10

   Perplexity documents an official 'pplx' CLI for search from the terminal or coding agent, explicitly designed for shell pipelines and agent tool calls (JSON output, no code required), which directly matches the ai-native/agentic story. Missing for 10: independent hands-on verification/community corroboration of the CLI beyond first-party docs, and more detail on install/distribution channels.

   • [claimed-docs] “You can now run Perplexity Search straight from your terminal. The Perplexity CLI returns the same ranked results as JSON, ready for shell p…”
   • [claimed-docs] “You can now run Perplexity Search straight from your terminal. The [Perplexity CLI](/docs/cli/overview) returns the same ranked results as J…”
   • [claimed-docs] “Install and use Perplexity's pplx command-line interface for web search and query-relevant page snippets from your terminal or coding agent.”

   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 Perplexity Sonar API
   Perplexity Sonar API✓fullprobed9/10

   Perplexity Sonar API is extensively documented as a public API with OpenAPI spec, official SDKs (Python etc.), CLI, quickstart guides, and API reference for the Sonar/Search/Agent endpoints, confirmed by a live openapi.json probe and multiple docs. This directly matches the ai-native/agenticness story of driving the product through a documented public API. Missing for 10: independent third-party developer testimonials beyond one skeptical HN comment about model selection, which doesn't contradict API existence.

   • [claimed-docs] “Get web-grounded answers with built-in citations in one call, or access third-party models from OpenAI, Anthropic, Google, and xAI with web …”
   • [claimed-docs] “Install one of our official SDKs for a convenient, type-safe integration”
   • [claimed-docs] “You can now run Perplexity Search straight from your terminal. The Perplexity CLI returns the same ranked results as JSON, ready for shell p…”
   • [claimed-docs] “Generate an API key and make your first call in < 3 minutes.”
   • [probe] “PROBE openapi: HTTP 200 at https://docs.perplexity.ai/openapi.json — contains "openapi" key”
   • [github] “The library includes type definitions for all request params and response fields, and offers both synchronous and asynchronous clients power…”
   • [claimed-docs] “"citations": [ "<string>" ], "search_results": [”

   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
   Perplexity Sonar API—none0/10

   The evidence covers API key generation, rate-limit tiers, and tool-restriction for MCP servers, but there is no mention of scoped or least-privilege API credentials (e.g., per-key permissions, role-based scopes, restricted key creation for sub-agents). Nothing in the docs describes issuing narrowly-scoped keys for delegated agent use.

   ⚑ 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 Perplexity Sonar API
   Perplexity Sonar API✓fullclaimed8/10

   Docs explicitly point to official, type-safe SDKs (perplexity-sonar-docs-7/12), and there's a real Python SDK repo on GitHub with streaming, async/sync clients, typed responses, retries, and error handling (perplexity-sonar-gh-1 through gh-6), corroborating first-party claims with hands-on package evidence. Missing for 10: explicit confirmation of SDKs in multiple other languages (e.g., JS/TS, Go) beyond Python, and independent community usage reports of the SDKs themselves.

   • [claimed-docs] “Install one of our official SDKs for a convenient, type-safe integration”
   • [claimed-docs] “Install one of our [official SDKs](/docs/sdk/overview) for a convenient, type-safe integration”
   • [github] “We provide support for streaming responses using Server Side Events (SSE).”
   • [github] “Certain errors are automatically retried 2 times by default, with a short exponential backoff.”
   • [github] “When the API returns a non-success status code (that is, 4xx or 5xx response), a subclass of `perplexity.APIStatusError` is raised, containi…”
   • [github] “By default, the async client uses `httpx` for HTTP requests. However, for improved concurrency performance you may also use `aiohttp` as the…”
   • [github] “The library includes type definitions for all request params and response fields, and offers both synchronous and asynchronous clients power…”
   • [github] “search = client.search.create(query="latest AI developments 2024", max_results=5)”

   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
   Perplexity Sonar API—none0/10

   No evidence of any webhook/event subscription mechanism in the Sonar API docs; the product offers request/response APIs, SDKs, CLI, and MCP integration but nothing about outbound event notifications or webhooks.

   ⚑ 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 userGet AI-generated insights and suggestions from my data inside the product

   weight 2 · round to Brave Search API
   Perplexity Sonar API~partialclaimed5/10

   Sonar API provides building blocks (embeddings for RAG, Agent API with sandbox/code execution, structured output, web search tools) that a developer could use to build AI-generated insights over their own data, but it is a raw API/platform, not an end-user product with built-in ingestion or dashboard-style insight generation from 'my data'. missing for 10: native data-ingestion/connectors for a user's own datasets, a first-party UI or workflow that surfaces proactive insights/suggestions from stored user data, and independent evidence of this being used end-to-end for such insights.

   • [claimed-docs] “Generate high-quality embeddings for semantic search and RAG pipelines.”
   • [claimed-docs] “Built-in tools | Perplexity-hosted capabilities: web search, URL fetch, people and finance search, and a code sandbox. Enable each by `type`…”
   • [claimed-docs] “The `sandbox` tool gives the agent an isolated Linux container to run real code and use the output in its answer — for results that must be …”
   • [claimed-docs] “Structured output makes the model return JSON that conforms to a schema you define, so you can deserialize it directly.”
   • [claimed-docs] “Use the Search API when you need raw results for your own processing. For an LLM-generated answer with citations, use the Agent API.”

   proof ↗⚑ flag

   Brave Search API✓fullcommunity7/10

   Brave Search API ships multiple AI-generated insight features directly on its own data: an Answers API with 'AI-generated answers backed by real-time web search and verifiable sources', AI-powered summarization from search results, an LLM Context endpoint optimized for agents, AI-generated POI/location descriptions, and search suggestions/spell-check. These are well documented across docs and the MCP server. However, community evidence shows the free tier's ToS explicitly prohibits using responses for AI inference, requiring users to switch to a separate AI Inference plan to legitimately use these AI features with agents. Missing for 10: independent hands-on validation of summarization/answer quality, and clearer first-party clarification reconciling the ToS restriction with the AI-agent-focused feature set.

   • [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] “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] “Looking to power agents or chatbots? Use the LLM Context endpoint instead. The LLM Context endpoint is specifically built for machine consum…”
   • [claimed-docs] “Get LLM generated descriptions about points of interest.”
   • [claimed-docs] “Intelligent search suggestions to help users find what they’re looking for.”
   • [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. ai-native userOperate the product with natural-language commands

   weight 2 · round to Brave Search API
   Perplexity Sonar API✓fullclaimed7/10

   The Agent API is explicitly designed around natural-language 'instructions' and 'input' fields, presets, and MCP integration so AI assistants and agents can drive the product purely via NL commands rather than rigid code paths, and the CLI/MCP server extend this to terminal and agent-tool contexts. missing for 10: independent or hands-on third-party verification that NL-driven agent behavior works reliably in practice, and no evidence of a conversational end-user interface beyond API/CLI/MCP docs.

   • [claimed-docs] “A `preset` gives you a working agent in one field.”
   • [claimed-docs] “`instructions` is the agent's **system prompt** — the rules that hold on every turn. `input` is the specific thing to do this turn.”
   • [claimed-docs] “Built-in tools | Perplexity-hosted capabilities: web search, URL fetch, people and finance search, and a code sandbox. Enable each by `type`…”
   • [claimed-docs] “Remote MCP server (recommended): hosted by Perplexity at `https://api.perplexity.ai/mcp`. No installation, nothing to update, works with any…”
   • [claimed-docs] “Local MCP server: run the open-source server on your machine over stdio. Use this if your client only supports stdio servers or you need to …”
   • [claimed-docs] “Install and use Perplexity's pplx command-line interface for web search and query-relevant page snippets from your terminal or coding agent.”

   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 Perplexity Sonar API
   Perplexity Sonar API~partialprobed6/10

   Docs include an OpenAPI spec (probe-3) and an interactive Playground where users can try the Search API without an API key (docs-14), plus a full API reference page (docs-23) — strong signals of an interactive reference experience. However, there's no explicit confirmation that the API reference pages themselves embed runnable/executable code examples (vs. just a separate Playground and static code snippets). Missing for 10: direct evidence of in-reference 'try it' runnable code blocks, independent user confirmation of the interactive reference experience.

   • [claimed-docs] “You can also [try Perplexity Search in the interactive Playground](https://console.perplexity.ai/project/playground/search) with no API key …”
   • [claimed-docs] “"citations": [ "<string>" ], "search_results": [”
   • [probe] “PROBE openapi: HTTP 200 at https://docs.perplexity.ai/openapi.json — contains "openapi" key”
   • [probe] “PROBE docs-md: HTTP 200 at https://docs.perplexity.ai/docs/getting-started/overview.md > ## Documentation Index > Fetch the complete documen…”

   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 to Perplexity Sonar API
   Perplexity Sonar API✓fullprobed9/10

   A probe confirms a machine-readable OpenAPI spec is live at https://docs.perplexity.ai/openapi.json (HTTP 200, contains 'openapi' key), directly satisfying the story, and this is corroborated by an llms.txt documentation index also returning 200. Missing for 10: independent/community confirmation of the OpenAPI spec's completeness or usage beyond the first-party probe.

   • [probe] “PROBE openapi: HTTP 200 at https://docs.perplexity.ai/openapi.json — contains "openapi" key”
   • [probe] “PROBE llms.txt: HTTP 200 at https://docs.perplexity.ai/llms.txt # Perplexity > Perplexity API documentation for building with the Agent API…”
   • [probe] “PROBE docs-md: HTTP 200 at https://docs.perplexity.ai/docs/getting-started/overview.md > ## Documentation Index > Fetch the complete documen…”

   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
   Perplexity Sonar API—none0/10

   The evidence pack shows extensive API documentation, SDKs, an OpenAPI spec, and product features, but nowhere mentions API versioning scheme, a deprecation policy, model sunset timelines, or changelog practices. A community comment even notes model selection 'regressed' over time with no policy context given. No evidence supports this specific axis.

   ⚑ 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 drawn
   Perplexity Sonar API~partialclaimed3/10

   The Search API mentions 'multi-query search' (perplexity-sonar-docs-17), which hints at handling multiple queries in one call, but there's no explicit batch/bulk endpoint, no documentation of processing many items (e.g., a list of URLs, files, or embeddings) in a single request, and no examples of bulk automation workflows. Missing for 10: dedicated batch/bulk API endpoint, explicit bulk-item processing docs, and evidence of large-scale bulk usage patterns.

   • [claimed-docs] “Access real-time web search results with Perplexity's Search API. Get ranked results, domain filtering, multi-query search, and content extr…”
   • [claimed-docs] “Search context determines how much web information is retrieved. Higher context = more comprehensive results.”
   • [claimed-docs] “As you spend more on API credits over time, you automatically advance to higher tiers with increased rate limits.”

   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
   Perplexity Sonar API~partialclaimed4/10

   Docs confirm the API returns a `citations` array and a `search_results` object alongside answers, and the Search API returns 'ranked results' with content extraction, implying source metadata is present. However, the evidence pack never explicitly confirms canonical URL, title, and published-date fields in the schema (the API reference snippet is truncated before showing field names), so accuracy/completeness of that metadata for citation purposes is unverified. missing for 10: explicit schema documentation of title/url/date fields per search result, independent confirmation that returned URLs/dates are accurate and stable for citation.

   • [claimed-docs] “"citations": [ "<string>" ], "search_results": [”
   • [claimed-docs] “Access real-time web search results with Perplexity's Search API. Get ranked results, domain filtering, multi-query search, and content extr…”
   • [claimed-docs] “Use the Search API when you need raw results for your own processing. For an LLM-generated answer with citations, use the Agent API.”

   proof ↗⚑ 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
   Perplexity Sonar API—none0/10

   No evidence in the pack addresses robots.txt handling, content licensing terms, or a documented policy on permitted use of search results — only general API/product docs, SDK, and pricing information are present.

   ⚑ 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 Perplexity Sonar API
   Perplexity Sonar API✓fullclaimed8/10

   The Agent API supports building agents with built-in tools (web search, URL fetch, code sandbox), multi-step reasoning via Pro Search, structured output synthesis, and multi-turn context retention — covering search, extraction, and synthesis in one API call chain. missing for 10: independent/hands-on third-party validation of a full multi-step research flow end-to-end, and quantitative benchmarks on extraction fidelity.

   • [claimed-docs] “Pro Search enhances Sonar Pro with automated tool usage and multi-step reasoning. When enabled, the model can perform multiple web searches …”
   • [claimed-docs] “Built-in tools | Perplexity-hosted capabilities: web search, URL fetch, people and finance search, and a code sandbox. Enable each by `type`…”
   • [claimed-docs] “The `sandbox` tool gives the agent an isolated Linux container to run real code and use the output in its answer — for results that must be …”
   • [claimed-docs] “Structured output makes the model return JSON that conforms to a schema you define, so you can deserialize it directly.”
   • [claimed-docs] “For most multi-turn conversations, use `previous_response_id` to continue from a completed prior response without resending the conversation…”
   • [claimed-docs] “A `preset` gives you a working agent in one field.”
   • [claimed-docs] “Use the Search API when you need raw results for your own processing. For an LLM-generated answer with citations, use the Agent API.”

   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 Brave Search API
   Perplexity Sonar API~partialclaimed4/10

   Docs mention the Search API offers "content extraction for developers" alongside ranked results and snippets (perplexity-sonar-docs-17), suggesting more than snippet-level text is retrievable, but the CLI docs explicitly describe only "query-relevant page snippets" (perplexity-sonar-docs-24) and no doc confirms full-page or markdown output format, schema, or size limits. Missing for 10: explicit API field/response example returning full page text or markdown, documentation of extraction depth/limits, and independent confirmation that returned content is full-page rather than truncated snippets.

   • [claimed-docs] “Access real-time web search results with Perplexity's Search API. Get ranked results, domain filtering, multi-query search, and content extr…”
   • [claimed-docs] “Install and use Perplexity's pplx command-line interface for web search and query-relevant page snippets from your terminal or coding agent.”
   • [claimed-docs] “Use the Search API when you need raw results for your own processing. For an LLM-generated answer with citations, use the Agent API.”

   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 to Perplexity Sonar API
   Perplexity Sonar API✓fullclaimed8/10

   Docs explicitly describe a 'Structured output' feature that 'makes the model return JSON that conforms to a schema you define, so you can deserialize it directly,' directly matching the story. Missing for 10: independent/hands-on corroboration beyond first-party docs, and no code sample showing the schema definition syntax in the evidence pack.

   • [claimed-docs] “Structured output makes the model return JSON that conforms to a schema you define, so you can deserialize it directly.”

   proof ↗⚑ 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 drawn
   Perplexity Sonar API—none0/10

   Evidence shows single-query search, URL fetch, and content-extraction tools (docs-17, docs-30, docs-38) but nothing about recursively crawling subpages or an entire site starting from a search result; no site-map/crawl-depth feature is documented.

   • [claimed-docs] “Access real-time web search results with Perplexity's Search API. Get ranked results, domain filtering, multi-query search, and content extr…”
   • [claimed-docs] “Built-in tools | Perplexity-hosted capabilities: web search, URL fetch, people and finance search, and a code sandbox. Enable each by `type`…”
   • [claimed-docs] “Use the Search API when you need raw results for your own processing. For an LLM-generated answer with citations, use the Agent API.”

   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
   Perplexity Sonar API~partialclaimed5/10

   Docs explicitly mention 'domain filtering' as a Search API feature and reference 'advanced filtering' of search results, indicating some domain include/exclude capability exists. However, there is no detailed documentation of the actual parameter/API syntax, allowed limits, or confirmation it supports exclusion specifically (vs just filtering to include). Missing for 10: explicit parameter documentation (e.g. search_domain_filter), examples of excluding domains, independent/hands-on verification of behavior.

   • [claimed-docs] “Access real-time web search results with Perplexity's Search API. Get ranked results, domain filtering, multi-query search, and content extr…”
   • [claimed-docs] “Get raw, ranked web search results with advanced filtering and real-time data.”

   proof ↗⚑ 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
   Perplexity Sonar API—none0/10

   Docs describe ranked web/search results, citations, and a search_results field, but nowhere do they document per-result relevance/confidence scores that a developer could use to threshold what enters a pipeline. Missing for 10: any documented score field in the API response schema, docs explaining score semantics, or examples of threshold-based filtering.

   • [claimed-docs] “Access real-time web search results with Perplexity's Search API. Get ranked results, domain filtering, multi-query search, and content extr…”
   • [claimed-docs] “"citations": [ "<string>" ], "search_results": [”
   • [claimed-docs] “Use the Search API when you need raw results for your own processing. For an LLM-generated answer with citations, use the Agent API.”

   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
   Perplexity Sonar API~partialclaimed4/10

   Docs claim 'real-time data' and 'advanced filtering'/'domain filtering' in the Search API, implying a fresh, filterable index, but no evidence explicitly documents date-range or recency-specific filter parameters or index update cadence. missing for 10: explicit documentation of recency/date-range filter parameters, evidence of index refresh frequency, independent verification of freshness.

   • [claimed-docs] “Get raw, ranked web search results with advanced filtering and real-time data.”
   • [claimed-docs] “Access real-time web search results with Perplexity's Search API. Get ranked results, domain filtering, multi-query search, and content extr…”
   • [claimed-docs] “Use the Search API when you need raw results for your own processing. For an LLM-generated answer with citations, use the Agent API.”

   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
   Perplexity Sonar API~partialclaimed4/10

   Docs mention a built-in 'finance search' tool and general domain/content filtering in the Search API, showing some vertical/category targeting, but there is no evidence of dedicated endpoints or filters for news or images verticals specifically. missing for 10: dedicated news endpoint/filter, dedicated images endpoint/filter, explicit documentation of category-based filtering beyond finance/people/web/URL/sandbox tools.

   • [claimed-docs] “Built-in tools | Perplexity-hosted capabilities: web search, URL fetch, people and finance search, and a code sandbox. Enable each by `type`…”
   • [claimed-docs] “Access real-time web search results with Perplexity's Search API. Get ranked results, domain filtering, multi-query search, and content extr…”
   • [claimed-docs] “Get raw, ranked web search results with advanced filtering and real-time data.”

   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
   Perplexity Sonar API—none0/10

   The evidence pack describes domain filtering, multi-query search, search context tuning, and content extraction, but no citation mentions country, language, or location-based localization parameters for the Sonar/Search/Agent APIs. This is a plausible axis for a web-search API, but no supporting evidence exists in the pack.

   ⚑ 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 drawn
   Perplexity Sonar API~partialclaimed6/10

   The Sonar/Agent API exposes a very wide surface — search, agent orchestration, MCP server (remote and local), CLI, SDKs, sandboxed code execution, structured output, model fallback, profiles — suggesting most capabilities are API-accessible and even API-first, with a playground for exploration. However, none of the evidence explicitly compares API capabilities against the consumer chat UI (e.g., Spaces, Threads, Collections, personalization features), so full UI-parity is not directly demonstrated. Missing for 10: explicit statement or evidence that all consumer-UI-only features (e.g., Spaces, saved threads, UI personalization) are also exposed via API, and independent confirmation of parity.

   • [claimed-docs] “You can now run Perplexity Search straight from your terminal. The Perplexity CLI returns the same ranked results as JSON, ready for shell p…”
   • [claimed-docs] “Install and use Perplexity's pplx command-line interface for web search and query-relevant page snippets from your terminal or coding agent.”
   • [claimed-docs] “Built-in tools | Perplexity-hosted capabilities: web search, URL fetch, people and finance search, and a code sandbox. Enable each by `type`…”
   • [claimed-docs] “The `sandbox` tool gives the agent an isolated Linux container to run real code and use the output in its answer — for results that must be …”
   • [claimed-docs] “Remote MCP server (recommended): hosted by Perplexity at `https://api.perplexity.ai/mcp`. No installation, nothing to update, works with any…”
   • [claimed-docs] “Local MCP server: run the open-source server on your machine over stdio. Use this if your client only supports stdio servers or you need to …”
   • [claimed-docs] “A profile is a reusable, versioned configuration that you save and manage. ... Select a profile by ID instead of repeating the full configur…”
   • [claimed-docs] “You can also [try Perplexity Search in the interactive Playground](https://console.perplexity.ai/project/playground/search) with no API key …”

   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
   Perplexity Sonar API—none0/10

   Perplexity Sonar API is a closed commercial API; the evidence shows SDKs and a local MCP server are open-source components, but there is no evidence the core Sonar/Agent API source or models are released under an open license, so a user cannot read the product's source.

   ⚑ 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 Perplexity Sonar API
   Perplexity Sonar API~partialclaimed6/10

   Docs describe a dedicated rate-limits/usage-tiers page where spending automatically and permanently upgrades your tier (self-serve, no manual request needed), which covers rate limits and an upgrade path. However, no evidence explicitly documents concurrency caps or specific per-tier numeric limits. Missing for 10: explicit concurrency cap documentation, concrete per-tier RPM/RPS figures, independent confirmation of the auto-upgrade mechanism.

   • [claimed-docs] “As you spend more on API credits over time, you automatically advance to higher tiers with increased rate limits.”
   • [claimed-docs] “As you spend more on API credits over time, you automatically advance to higher tiers with increased rate limits. Higher tiers unlock signif…”
   • [claimed-docs] “As you spend more on API credits over time, you automatically advance to higher tiers with increased rate limits... once you reach a tier, y…”

   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 Brave Search API
   Perplexity Sonar API—none0/10

   The evidence shows an API key signup flow and a no-key-required Playground for testing, but no documentation of a free tier, free trial credits, or free quota for the Sonar API itself — rate-limit tiers are described as advancing with paid spend, not free usage. missing for 10: explicit free credits/free tier terms, any trial credit amount, or free-usage rate limits for new developers.

   • [claimed-docs] “You can also [try Perplexity Search in the interactive Playground](https://console.perplexity.ai/project/playground/search) with no API key …”
   • [claimed-docs] “Generate an API key and make your first call in < 3 minutes.”
   • [claimed-docs] “As you spend more on API credits over time, you automatically advance to higher tiers with increased rate limits. Higher tiers unlock signif…”

   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 Perplexity Sonar API
   Perplexity Sonar API~partialclaimed6/10

   Perplexity publishes a dedicated pricing page (search context, Pro Search, credit-tier rate limits) and lets developers self-serve by generating an API key in minutes without contacting sales, implying transparent self-serve pricing. However the evidence pack never shows actual per-request or per-credit dollar figures, so we can't confirm the pricing is fully itemized/clear from what's provided. Missing for 10: concrete $/request or $/credit rate tables, confirmation that all model/tool usage (sandbox, MCP, agent tools) is separately priced and disclosed publicly.

   • [claimed-docs] “Pro Search enhances Sonar Pro with automated tool usage and multi-step reasoning. When enabled, the model can perform multiple web searches …”
   • [claimed-docs] “Search context determines how much web information is retrieved. Higher context = more comprehensive results.”
   • [claimed-docs] “As you spend more on API credits over time, you automatically advance to higher tiers with increased rate limits.”
   • [claimed-docs] “As you spend more on API credits over time, you automatically advance to higher tiers with increased rate limits. Higher tiers unlock signif…”
   • [claimed-docs] “When using tools with the Agent API:”
   • [claimed-docs] “Generate an API key and make your first call in < 3 minutes.”

   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 drawn
   Perplexity Sonar API—none0/10

   The evidence covers synchronous SDK calls, streaming (SSE), retries, rate-limit tiers, and model routing/fallback, but nowhere mentions batch job submission or an asynchronous job/queue API for high-volume workloads — the async client mentioned is just a non-blocking HTTP client, not a batch-job system. No documentation of batch endpoints, job polling, or bulk submission exists in the pack.

   ⚑ 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
   Perplexity Sonar API—none0/10

   No evidence in the pack mentions data residency, region selection, or data storage location controls for the Sonar API; this is an applicable axis for an API/cloud service but no documentation addresses it.

   ⚑ 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
   Perplexity Sonar API—none0/10

   No evidence in the pack addresses data usage for training, opt-out settings, or a privacy/data-retention policy for API data; nothing in the docs pack mentions training-data opt-out at all.

   ⚑ 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
   Perplexity Sonar API—none0/10

   No evidence in the pack addresses data retention policies, deletion controls, or privacy/data-handling settings for the Sonar API; the docs cover search, agents, MCP, routing, and SDKs but nothing about controlling stored data or deleting logs/history.

   ⚑ 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
   Perplexity Sonar API—none0/10

   No evidence in the pack addresses telemetry opt-out or usage-tracking controls for the Sonar API; nothing mentions privacy settings, data retention toggles, or telemetry configuration.

   ⚑ 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 Perplexity Sonar API
   Perplexity Sonar API✓fullprobed8/10

   Perplexity ships an official MCP server (remote and local/stdio) that exposes its search/reasoning as agent-consumable tools, plus OpenAPI schema, official SDKs with type-safe function signatures, built-in tools (web search, sandbox, URL fetch) designed for tool-call consumption within the Agent API, and integration with Anthropic's Messages API MCP connector. This directly matches the story of plugging the API into an agent via ready-made schemas/integrations. Missing for 10: independent third-party validation of agent-framework interop (e.g. LangChain/AutoGen adapters) and hands-on developer reports confirming smooth tool-call schema usage beyond vendor docs.

   • [claimed-docs] “The Perplexity MCP Server enables AI assistants to access Perplexity's powerful search and reasoning capabilities directly within their work…”
   • [claimed-docs] “Remote MCP server (recommended): hosted by Perplexity at `https://api.perplexity.ai/mcp`. No installation, nothing to update, works with any…”
   • [claimed-docs] “Local MCP server: run the open-source server on your machine over stdio. Use this if your client only supports stdio servers or you need to …”
   • [claimed-docs] “Use Perplexity's tools in a Messages API request with the MCP connector:”
   • [claimed-docs] “Built-in tools | Perplexity-hosted capabilities: web search, URL fetch, people and finance search, and a code sandbox. Enable each by `type`…”
   • [probe] “PROBE openapi: HTTP 200 at https://docs.perplexity.ai/openapi.json — contains "openapi" key”
   • [probe] “official MCP server documented at https://docs.perplexity.ai/docs/getting-started/integrations/mcp-server”
   • [github] “The library includes type definitions for all request params and response fields, and offers both synchronous and asynchronous clients power…”

   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 Perplexity Sonar API
   Perplexity Sonar API✓fullclaimed9/10

   Docs explicitly describe getting web-grounded answers with built-in citations in one API call (Sonar/Agent API), with a quickstart to make the first call in under 3 minutes, and the API reference shows a response schema with 'citations' and 'search_results' fields. Docs even distinguish this from the raw Search API, clarifying that the sourced LLM-generated answer use case is served by the Sonar/Agent endpoints. missing for 10: independent hands-on developer verification of citation quality/accuracy beyond vendor docs.

   • [claimed-docs] “Get web-grounded answers with built-in citations in one call, or access third-party models from OpenAI, Anthropic, Google, and xAI with web …”
   • [claimed-docs] “"citations": [ "<string>" ], "search_results": [”
   • [claimed-docs] “Generate an API key and make your first call in < 3 minutes.”
   • [claimed-docs] “Use the Search API when you need raw results for your own processing. For an LLM-generated answer with citations, use the Agent API.”

   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 Perplexity Sonar API
   Perplexity Sonar API✓fullclaimed8/10

   Docs explicitly market a Search API returning 'raw, ranked web search results' for developer processing, distinct from the answer-generating Agent API, with domain filtering, multi-query search, and content extraction designed for RAG use, plus embeddings generation for semantic search/RAG pipelines. SDKs, CLI, and structured citations/search_results fields support direct ingestion into a RAG context window. missing for 10: no independent benchmark or hands-on evidence of chunk sizing/token-length suitability for context windows, and no explicit documentation of result truncation or size controls tailored to LLM context limits.

   • [claimed-docs] “Get raw, ranked web search results with advanced filtering and real-time data.”
   • [claimed-docs] “Generate high-quality embeddings for semantic search and RAG pipelines.”
   • [claimed-docs] “Access real-time web search results with Perplexity's Search API. Get ranked results, domain filtering, multi-query search, and content extr…”
   • [claimed-docs] “Use the Search API when you need raw results for your own processing. For an LLM-generated answer with citations, use the Agent API.”
   • [claimed-docs] “"citations": [ "<string>" ], "search_results": [”

   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
   Perplexity Sonar API—none0/10

   The evidence pack covers web search, embeddings, MCP integration, agent tooling, and code sandboxing, but there is no mention of a 'find similar pages/URLs' or URL-based similarity search feature anywhere in the docs.

   ⚑ 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
   Perplexity Sonar API—none0/10

   The evidence describes search context size, domain filtering, and multi-query search, but no documentation mentions selectable retrieval modes such as keyword, neural, or hybrid search per query.

   ⚑ 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 Perplexity Sonar API
   Perplexity Sonar API~partialclaimed6/10

   Docs explicitly mention embeddings 'for semantic search and RAG pipelines' and web search with ranked/filtered results, supporting meaning-based retrieval beyond keyword matching, but the evidence never shows benchmark or hands-on proof that this semantic search surfaces results keyword engines miss. Missing for 10: independent/hands-on evidence comparing semantic vs keyword recall, detail on embedding model quality/architecture, and concrete examples of semantic-only matches.

   • [claimed-docs] “Generate high-quality embeddings for semantic search and RAG pipelines.”
   • [claimed-docs] “Get raw, ranked web search results with advanced filtering and real-time data.”
   • [claimed-docs] “Access real-time web search results with Perplexity's Search API. Get ranked results, domain filtering, multi-query search, and content extr…”
   • [claimed-docs] “Search context determines how much web information is retrieved. Higher context = more comprehensive results.”

   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