{ "data": { "a": { "slug": "deepseek-search-api", "name": "DeepSeek Search and Fetch API", "vendor": "DeepSeek", "vendorUrl": "https://www.deepseek.com", "kind": "http-api", "category": "search", "summary": "DeepSeek's Search and Fetch API gives agents live web results from DeepSeek's in-house search engine and single pages as Markdown, through two REST endpoints on an ordinary DeepSeek API key, billed per successful request.", "url": "https://www.anchorterminal.com/tools/deepseek-search-api", "markdownUrl": "https://www.anchorterminal.com/tools/deepseek-search-api.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/deepseek-search-api.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/deepseek-search-api.json", "transports": [ "http" ], "remoteUrl": "https://api.deepseek.com/v1/tools/search", "packages": [], "auth": "api-key", "authNotes": "The same DeepSeek API key as the model endpoints, sent as a bearer token. Keys carry no scopes, so a search key can also spend the balance on models. Rate limits are per account, whichever key is used.", "pricing": "usage", "pricingNotes": "$0.75 per 1,000 successful requests for Search and the same for Fetch, from a prepaid balance. Only an HTTP 200 with a result is billed, and `count` doesn't change the price. Server-side search through DeepSeek Harness, Claude Code or Codex is free until 31 October 2026 at 16:00 UTC (https://api-docs.deepseek.com/guides/search).", "priceSummary": "$0.75 / 1k req", "where": "hosted", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the Search and Fetch guide, the API reference or the pricing page, and an unauthenticated POST to both endpoints returned 401 `authentication_error` with no payment challenge (checked 2026-10-17).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": null, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-10-17" }, "docsUrl": "https://api-docs.deepseek.com/guides/search", "capabilities": [ "web.search", "web.fetch" ], "tags": [ "hosted", "prepaid", "usage-priced", "status-page" ], "lastRelease": "2026-10-17", "graded": true, "anchor": { "graded": true, "score": 53.2, "grade": "D", "agentReady": false, "rank": 795, "ranked": true, "rankOf": 1133, "categoryRank": 15, "methodology": "0.4", "run": "2026-10-01", "scores": { "ergonomics": 81, "maintenance": 42, "payments": 20, "reliability": 65, "schema": 55, "security": 38, "transparency": 60 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-17" }, "negative": 0, "verdict": "Search returns up to 50 results with a model-length summary, an authority tier and optional full text, and only successful non-empty calls are billed, at $0.75 per 1,000. It opened on 17 October 2026, with 5 requests a second per account, no OpenAPI file, no free tier, and data held in the PRC under a policy that permits training.", "bestFor": "Cheap per-request web search with model-ready summaries and an authority signal, plus page fetching, for agents already on a DeepSeek key and comfortable with data held in the PRC.", "strengths": [ "$0.75 per 1,000 successful requests for each endpoint, and failed calls, empty results and timeouts aren't billed", "Each result has a 100 to 200 character snippet, a 600 to 800 character summary for models, and full text on request", "Site, language, date and phrase operators in the query string, and up to 50 results a call", "Error table with ten status codes and when to retry, and both endpoints documented as read-only" ], "weaknesses": [ "Opened on 17 October 2026, with no service record of its own and no component for it on the status page", "5 requests a second per account for each endpoint, plus an unpublished per-domain limit on Fetch", "No OpenAPI file, no llms.txt, no official SDKs and no free tier for direct calls", "One unscoped key for search and models, no security.txt, and no prompt-injection guidance for returned page text", "Data stored in the PRC, used for training unless the customer opts out by email, and no retention period stated" ], "agentNotes": [ "Keep `query` to 128 characters and put filters in it as operators, such as `site:github.com lang:en after:2026-01-01`", "Leave `need_content` false and read `summary` first, then call Fetch on the URLs you keep", "Stay under 5 requests a second per account across all keys. On 408, 429 or 5xx wait and retry, since no Retry-After is documented", "Don't retry a Fetch 403 or 404 unchanged. The page is blocked by policy, unreachable or has no Markdown", "Don't send private queries or an end user's IP in `localization`. Data is stored in the PRC" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 4, "avgRating": 3, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "D", "methodology": "0.4", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 53.2 } ], "editorialScores": { "ergonomics": 81, "maintenance": 42, "payments": 20, "reliability": 65, "schema": 55, "security": 38, "transparency": 35 }, "provenanceScore": 84 }, "connect": { "http": "curl https://api.deepseek.com/v1/tools/search \\\n -H \"Authorization: Bearer $DEEPSEEK_API_KEY\" -H \"Content-Type: application/json\" \\\n -d '{\"query\":\"DeepSeek V4 release\",\"count\":5,\"need_content\":true}'" }, "letme": { "capability": "https://letme.dev/web.search", "tool": "https://letme.dev/deepseek-search-api" }, "sameCompany": [ "deepseek-api" ], "area": "web-data", "unitPrices": [ { "item": "Search", "unit": "1k-requests", "usd": 0.75, "note": "Successful non-empty results only. 1 to 50 results at the same price" }, { "item": "Fetch", "unit": "1k-pages", "usd": 0.75, "note": "One URL per request, billed only when page content comes back" } ], "provenance": { "legalEntity": "Hangzhou DeepSeek Artificial Intelligence Co., Ltd.", "domain": "deepseek.com", "domainRegistered": "2000-08-13", "endpointOnVendorDomain": true, "terms": "https://cdn.deepseek.com/policies/en-US/deepseek-open-platform-terms-of-service.html", "privacy": "https://cdn.deepseek.com/policies/en-US/deepseek-privacy-policy.html", "statusPage": "https://status.deepseek.com", "changelog": "https://api-docs.deepseek.com/updates", "securityTxt": "none", "checked": "2026-10-17", "notes": [ "deepseek.com was registered in 2000, long before the company, so domain age flatters it (per the deepseek-api listing).", "The Open Platform terms (effective 29 April 2026) are governed by PRC law and assign Outputs to the customer. The privacy policy (10 February 2026) names Hangzhou DeepSeek Artificial Intelligence Co., Ltd.", "www.deepseek.com/.well-known/security.txt and deepseek.com/.well-known/security.txt returned 404 on 17 October 2026, and api-docs.deepseek.com answers every path with the docs page.", "www.deepseek.com/robots.txt allows all user agents. api-docs.deepseek.com has no robots.txt. platform.deepseek.com answered with a 202 holding page and wasn't read.", "The status page has a Search Service component, grouped under Chat Service, and no component named for the Search or Fetch API." ], "score": 84 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/deepseek-search-api.json", "live": { "slug": "deepseek-search-api", "probe": { "target": "https://api.deepseek.com/v1/tools/search", "method": "get", "lastAt": "2026-10-18T00:14:36.047087455Z", "lastOk": true, "lastStatus": 401, "lastMs": 319, "lastNote": "asks for credentials", "authRequired": true, "uptime24h": 100, "uptime30d": 100, "p50ms24h": 271, "p95ms24h": 319, "samples24h": 24, "samples30d": 24, "days": [ { "date": "2026-10-17", "probes": 21, "ok": 21 }, { "date": "2026-10-18", "probes": 3, "ok": 3 } ] }, "vendorStatus": { "page": "https://status.deepseek.com", "indicator": "unknown", "summary": "no machine-readable status found", "checkedAt": "2026-10-17T22:50:57.753702183Z" }, "updatedAt": "2026-10-18T00:14:36.047087455Z" } }, "answer": "Tavily API + MCP scores 76.8 (BB) on agent readiness against DeepSeek Search and Fetch API's 53.2 (D), and leads in 5 of 7 scored categories.", "b": { "slug": "tavily-mcp", "name": "Tavily API + MCP", "vendor": "Tavily", "vendorUrl": "https://www.tavily.com", "kind": "mcp", "category": "search", "summary": "Tavily's REST API for web search, URL extraction, site mapping, crawling and cited research reports, with the official MCP server hosted at mcp.tavily.com or run locally from npm.", "url": "https://www.anchorterminal.com/tools/tavily-mcp", "markdownUrl": "https://www.anchorterminal.com/tools/tavily-mcp.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/tavily-mcp.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/tavily-mcp.json", "repo": "https://github.com/tavily-ai/tavily-mcp", "license": "MIT", "transports": [ "stdio", "streamable-http", "http" ], "remoteUrl": "https://mcp.tavily.com/mcp/?tavilyApiKey=\u003ckey\u003e", "packages": [ { "registry": "npm", "name": "@tavily/core" }, { "registry": "pypi", "name": "tavily-python" }, { "registry": "npm", "name": "tavily-mcp" } ], "auth": "mixed", "authNotes": "API key as `Authorization: Bearer tvly-...`. Development keys and production keys have different rate limits, and production keys need a paid plan or pay as you go. The `X-Tavily-Access-Mode: keyless` header gives rate-limited search and extract with no key. x402.tavily.com takes a `PAYMENT-SIGNATURE` header instead. MCP server: API key in the URL query (?tavilyApiKey=) or Authorization header; OAuth flow also supported on the hosted server (uses an mcp_auth_default key from the dashboard).", "pricing": "freemium", "pricingNotes": "Free 1,000 credits a month, no card. Project $30 a month (4,000 credits), Bootstrap $100 (15,000), Startup $220 (38,000), Growth $500 (100,000), pay as you go $0.008 a credit. Basic search 1 credit, advanced 2, extract 1 per 5 URLs (advanced 2), map 1 per 10 pages, crawl is map plus extract, research 4 to 250 credits by model. Failed extracts and maps aren't charged (https://www.tavily.com/pricing).", "priceSummary": "$7.50 / 1k req", "where": "both", "x402": { "level": "partial", "evidence": "Official x402 endpoint at x402.tavily.com sells POST /search in advanced mode only, $0.01 in USDC on Base. An unpaid request returned 402 and /.well-known/pricing listed the price on 2026-09-30. Extract, map, crawl and research aren't sold over x402 (https://docs.tavily.com/documentation/machine-payments/x402.md)", "endpoints": [ { "url": "https://x402.tavily.com/search", "priceUsd": 0.01, "network": "eip155:8453" } ] }, "toolCount": 5, "popularity": { "githubStars": 2400, "npmWeekly": 451969, "pypiWeekly": 1589963, "asOf": "2026-09-30" }, "docsUrl": "https://docs.tavily.com", "llmsTxt": "https://docs.tavily.com/llms.txt", "openapi": "https://docs.tavily.com/documentation/api-reference/openapi.json", "registryName": "io.github.tavily-ai/tavily-mcp", "capabilities": [ "web.search", "web.extract", "web.crawl", "web.fetch", "search.answer", "search.research", "search.news", "search.images" ], "tags": [ "official", "hosted", "local", "open-source", "freemium", "llms-txt", "no-card", "free-tier", "x402", "openapi", "python", "typescript", "async-jobs", "enterprise", "mcp" ], "lastRelease": "2026-10-06", "graded": true, "anchor": { "graded": true, "score": 76.8, "grade": "BB", "agentReady": true, "rank": 37, "ranked": true, "rankOf": 1133, "categoryRank": 1, "methodology": "0.4", "run": "2026-10-01", "scores": { "ergonomics": 81, "maintenance": 85, "payments": 75, "reliability": 90, "schema": 89, "security": 52, "transparency": 60 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-17" }, "negative": 0, "verdict": "Keyless search and extract, plus a free 1,000 credits a month with no card. x402 covers advanced search only, not extract, map, crawl or research.", "bestFor": "An agent that needs search plus page text in one call and has no account yet.", "strengths": [ "Keyless search and extract, plus a free 1,000 credits a month with no card", "x402 endpoint for advanced search at $0.01 in USDC on Base", "Public OpenAPI, llms.txt and an error table that tells plan limits (432) from pay-as-you-go limits (433)", "429 carries Retry-After, with limits published per key type and endpoint", "Logs API filters calls by key and endpoint" ], "weaknesses": [ "x402 covers advanced search only, not extract, map, crawl or research", "Hosted MCP docs lead with `?tavilyApiKey=` in the URL query string", "No readOnlyHint or destructiveHint on the MCP tools, and the npm server (0.2.22, 5 August 2026) trails the GitHub source", "Privacy policy lets query data improve future responses unless a contract says otherwise, with no zero-retention option found", "SLAs named only for the custom Enterprise plan, and no security.txt or deprecation policy found" ], "agentNotes": [ "Try `X-Tavily-Access-Mode: keyless` first for search and extract. Over MCP, the keyless cap arrives as plain text without `isError`, so read the text before treating it as results", "Send the key in `Authorization: Bearer`, not `?tavilyApiKey=` in the MCP URL", "On 429, wait for `Retry-After`. A 432 or 433 means a spend limit, and retrying won't help", "Run /map before /crawl to bound the crawl, since crawl is billed as map plus extract", "Research is async and runs 4 to 250 credits. Create the task, then poll /research/{request_id}" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 8, "avgRating": 3.6, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "BB", "methodology": "0.4", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 76.8 } ], "editorialScores": { "ergonomics": 81, "maintenance": 85, "payments": 75, "reliability": 90, "schema": 89, "security": 52, "transparency": 47 }, "provenanceScore": 73 }, "connect": { "http": "curl -X POST https://api.tavily.com/search \\\n -H \"Authorization: Bearer $TAVILY_API_KEY\" -H \"Content-Type: application/json\" \\\n -d '{\"query\":\"latest AI news\",\"max_results\":5}'", "claudeCode": "claude mcp add --transport http tavily https://mcp.tavily.com/mcp/ --header \"Authorization: Bearer ${TAVILY_API_KEY}\"", "config": { "mcpServers": { "tavily": { "headers": { "Authorization": "Bearer ${TAVILY_API_KEY}" }, "url": "https://mcp.tavily.com/mcp/" } } }, "x402": "curl -i -X POST https://x402.tavily.com/search -H 'content-type: application/json' -d '{\"query\":\"Who is Leo Messi?\"}'\n# HTTP/2 402, PAYMENT-REQUIRED header carries the terms (10000 base units of USDC on eip155:8453)\n# retry with PAYMENT-SIGNATURE: \u003cbase64 signed authorization\u003e" }, "letme": { "capability": "https://letme.dev/web.search", "tool": "https://letme.dev/tavily-mcp" }, "area": "web-data", "unitPrices": [ { "item": "Basic search on Project plan", "unit": "1k-requests", "usd": 7.5, "note": "1 credit a search at $0.0075 a credit" }, { "item": "Project plan", "unit": "month", "usd": 30, "note": "4,000 credits" }, { "item": "Bootstrap plan", "unit": "month", "usd": 100, "note": "15,000 credits" }, { "item": "Credit, pay as you go", "unit": "credit", "usd": 0.008, "note": "basic search 1 credit, advanced 2" } ], "provenance": { "legalEntity": "AlphaAI Technologies Inc. dba Tavily", "domain": "tavily.com", "domainRegistered": "2023-04-13", "endpointOnVendorDomain": true, "terms": "https://www.tavily.com/terms", "privacy": "https://www.tavily.com/privacy", "statusPage": "https://status.tavily.com", "changelog": "https://docs.tavily.com/changelog", "securityTxt": "none", "checked": "2026-10-17", "score": 73 }, "requirements": { "agentAlone": true, "card": "no", "freeTier": true, "minutes": 3, "credential": "api-key", "euResidency": "unknown", "trainsOnData": "unknown", "zeroRetention": "yes", "selfHost": "no" }, "pageJsonUrl": "https://www.anchorterminal.com/tools/tavily-mcp.json", "live": { "slug": "tavily-mcp", "probe": { "target": "https://mcp.tavily.com/mcp/?tavilyApiKey=\u003ckey\u003e", "method": "mcp-initialize", "lastAt": "2026-10-18T00:14:58.429497726Z", "lastOk": true, "lastStatus": 200, "lastMs": 266, "lastNote": "initialize answered", "authRequired": false, "uptime24h": 100, "uptime30d": 100, "p50ms24h": 257, "p95ms24h": 298, "samples24h": 253, "samples30d": 5389, "days": [ { "date": "2026-09-27", "probes": 132, "ok": 132 }, { "date": "2026-09-28", "probes": 285, "ok": 285 }, { "date": "2026-09-29", "probes": 286, "ok": 286 }, { "date": "2026-09-30", "probes": 286, "ok": 286 }, { "date": "2026-10-01", "probes": 276, "ok": 276 }, { "date": "2026-10-02", "probes": 248, "ok": 248 }, { "date": "2026-10-03", "probes": 271, "ok": 271 }, { "date": "2026-10-04", "probes": 272, "ok": 272 }, { "date": "2026-10-05", "probes": 272, "ok": 272 }, { "date": "2026-10-06", "probes": 272, "ok": 272 }, { "date": "2026-10-07", "probes": 272, "ok": 272 }, { "date": "2026-10-08", "probes": 268, "ok": 268 }, { "date": "2026-10-09", "probes": 250, "ok": 250 }, { "date": "2026-10-10", "probes": 247, "ok": 247 }, { "date": "2026-10-11", "probes": 247, "ok": 247 }, { "date": "2026-10-12", "probes": 247, "ok": 247 }, { "date": "2026-10-13", "probes": 248, "ok": 248 }, { "date": "2026-10-14", "probes": 249, "ok": 249 }, { "date": "2026-10-15", "probes": 253, "ok": 253 }, { "date": "2026-10-16", "probes": 252, "ok": 252 }, { "date": "2026-10-17", "probes": 253, "ok": 253 }, { "date": "2026-10-18", "probes": 3, "ok": 3 } ] }, "vendorStatus": { "page": "https://status.tavily.com", "indicator": "none", "summary": "All Systems Operational", "checkedAt": "2026-10-18T00:09:10.170821255Z" }, "versions": [ { "registry": "mcp-registry", "name": "io.github.tavily-ai/tavily-mcp", "version": "0.2.15", "seenAt": "2026-10-17T05:11:56.292414565Z" }, { "registry": "npm", "name": "@tavily/core", "version": "0.7.14", "seenAt": "2026-10-17T02:21:16.492132069Z" }, { "registry": "npm", "name": "tavily-mcp", "version": "0.2.22", "seenAt": "2026-10-17T02:21:17.546130574Z" }, { "registry": "pypi", "name": "tavily-python", "version": "0.8.5", "released": "2026-10-06", "seenAt": "2026-10-17T02:21:17.349968432Z" } ], "githubStars": 2432, "npmWeekly": 418058, "pypiWeekly": 1680137, "securityTxt": { "url": "https://tavily.com/.well-known/security.txt", "state": "none", "checkedAt": "2026-10-17T15:52:41.01361274Z" }, "llmsTxt": { "url": "https://docs.tavily.com/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-10-17T14:23:22.206469014Z" }, "domain": { "domain": "tavily.com", "registered": "2023-04-13", "source": "https://rdap.verisign.com/com/v1/domain/tavily.com", "checkedAt": "2026-10-11T13:12:50.669621228Z" }, "pages": [ { "url": "https://docs.tavily.com/changelog", "kind": "changelog", "status": 200, "checkedAt": "2026-10-17T23:02:11.252005478Z", "changedAt": "2026-10-06T16:08:40.980358433Z", "fingerprint": "9fd0a7c1b9aa" }, { "url": "https://www.tavily.com/pricing", "kind": "pricing", "status": 200, "checkedAt": "2026-10-17T23:20:58.366692809Z", "changedAt": "2026-10-16T22:42:08.683454149Z", "fingerprint": "64f5c15064ab" }, { "url": "https://www.tavily.com/privacy", "kind": "privacy", "status": 200, "checkedAt": "2026-10-17T23:21:00.542116225Z", "changedAt": "2026-10-16T22:42:10.854978825Z", "fingerprint": "1c34c9c678ac" }, { "url": "https://www.tavily.com/terms", "kind": "terms", "status": 200, "checkedAt": "2026-10-17T23:21:02.582810963Z", "changedAt": "2026-10-16T22:42:13.635236724Z", "fingerprint": "49ad5733608d" } ], "mcpTools": { "url": "https://mcp.tavily.com/mcp/?tavilyApiKey=\u003ckey\u003e", "checkedAt": "2026-10-17T22:40:31.642699513Z", "status": "ok", "protocol": "2026-07-28", "tools": [ { "name": "tavily_search", "title": "Tavily Search", "description": "Search the web for current information on any topic. Use for news, facts, or data beyond your knowledge cutoff. Returns snippets and source URLs.", "inputSchema": { "additionalProperties": false, "properties": { "country": { "default": "", "description": "Boost search results from a specific country. Must be a full country name (e.g., 'United States', 'Japan', 'Germany'). ISO country codes (e.g., 'us', 'jp') are not supported. Available only if topic is general. See https://docs.tavily.com/documentation/api-reference/search for the full list of supported countries.", "type": "string" }, "end_date": { "default": "", "description": "Will return all results before the specified end date. Required to be written in the format YYYY-MM-DD", "type": "string" }, "exact_match": { "anyOf": [ { "type": "boolean" }, { "type": "null" } ], "default": null, "description": "Only return results containing the exact phrase(s) in quotes in your query" }, "exclude_domains": { "default": [], "description": "List of domains to specifically exclude, if the user asks to exclude a domain set this to the domain of the site", "items": { "type": "string" }, "type": "array" }, "include_domains": { "default": [], "description": "A list of domains to specifically include in the search results, if the user asks to search on specific sites set this to the domain of the site", "items": { "type": "string" }, "type": "array" }, "include_favicon": { "default": false, "description": "Whether to include the favicon URL for each result", "type": "boolean" }, "include_image_descriptions": { "default": false, "description": "Include a list of query-related images and their descriptions in the response", "type": "boolean" }, "include_images": { "default": false, "description": "Include a list of query-related images in the response", "type": "boolean" }, "include_raw_content": { "default": false, "description": "Include the cleaned and parsed HTML content of each search result", "type": "boolean" }, "max_results": { "default": 5, "description": "The maximum number of search results to return", "type": "integer" }, "query": { "description": "Search query", "type": "string" }, "search_depth": { "default": "basic", "description": "The depth of the search. 'basic' for generic results, 'advanced' for more thorough search, 'fast' for optimized low latency with high relevance, 'ultra-fast' for prioritizing latency above all else", "enum": [ "basic", "advanced", "fast", "ultra-fast" ], "type": "string" }, "start_date": { "default": "", "description": "Will return all results after the specified start date. Required to be written in the format YYYY-MM-DD.", "type": "string" }, "time_range": { "anyOf": [ { "enum": [ "day", "week", "month", "year" ], "type": "string" }, { "type": "null" } ], "default": null, "description": "The time range back from the current date to include in the search results" }, "topic": { "default": "general", "description": "Search category. Use 'general' for almost all searches, including current events and requests that combine news with other information. Use 'news' only when the user explicitly asks for news, headlines, or news coverage.", "enum": [ "general", "news" ], "type": "string" } }, "required": [ "query" ], "type": "object" }, "outputSchema": { "additionalProperties": true, "type": "object" }, "annotations": { "destructiveHint": false, "idempotentHint": false, "openWorldHint": true, "readOnlyHint": true } }, { "name": "tavily_extract", "title": "Tavily Extract", "description": "Extract content from URLs. Returns raw page content in markdown or text format.", "inputSchema": { "additionalProperties": false, "properties": { "extract_depth": { "default": "basic", "description": "Use 'advanced' for LinkedIn, protected sites, or tables/embedded content", "enum": [ "basic", "advanced" ], "type": "string" }, "format": { "default": "markdown", "description": "Output format", "enum": [ "markdown", "text" ], "type": "string" }, "include_favicon": { "default": false, "description": "Include favicon URLs", "type": "boolean" }, "include_images": { "default": false, "description": "Include images from pages", "type": "boolean" }, "query": { "default": "", "description": "Query to rerank content chunks by relevance", "type": "string" }, "urls": { "description": "List of URLs to extract content from", "items": { "type": "string" }, "type": "array" } }, "required": [ "urls" ], "type": "object" }, "outputSchema": { "additionalProperties": true, "type": "object" }, "annotations": { "destructiveHint": false, "idempotentHint": false, "openWorldHint": true, "readOnlyHint": true } }, { "name": "tavily_crawl", "title": "Tavily Crawl", "description": "Crawl a website starting from a URL. Extracts content from pages with configurable depth and breadth.", "inputSchema": { "additionalProperties": false, "properties": { "allow_external": { "default": true, "description": "Whether to return external links in the final response", "type": "boolean" }, "extract_depth": { "default": "basic", "description": "Advanced extraction retrieves more data, including tables and embedded content, with higher success but may increase latency", "enum": [ "basic", "advanced" ], "type": "string" }, "format": { "default": "markdown", "description": "The format of the extracted web page content. markdown returns content in markdown format. text returns plain text and may increase latency.", "enum": [ "markdown", "text" ], "type": "string" }, "include_favicon": { "default": false, "description": "Whether to include the favicon URL for each result", "type": "boolean" }, "instructions": { "default": "", "description": "Natural language instructions for the crawler. Instructions specify which types of pages the crawler should return.", "type": "string" }, "limit": { "default": 50, "description": "Total number of links the crawler will process before stopping", "minimum": 1, "type": "integer" }, "max_breadth": { "default": 20, "description": "Max number of links to follow per level of the tree (i.e., per page)", "minimum": 1, "type": "integer" }, "max_depth": { "default": 1, "description": "Max depth of the crawl. Defines how far from the base URL the crawler can explore.", "minimum": 1, "type": "integer" }, "select_domains": { "default": [], "description": "Regex patterns to restrict crawling to specific domains or subdomains (e.g., ^docs\\.example\\.com$)", "items": { "type": "string" }, "type": "array" }, "select_paths": { "default": [], "description": "Regex patterns to select only URLs with specific path patterns (e.g., /docs/.*, /api/v1.*)", "items": { "type": "string" }, "type": "array" }, "url": { "description": "The root URL to begin the crawl", "type": "string" } }, "required": [ "url" ], "type": "object" }, "outputSchema": { "additionalProperties": true, "type": "object" }, "annotations": { "destructiveHint": false, "idempotentHint": false, "openWorldHint": true, "readOnlyHint": true } }, { "name": "tavily_map", "title": "Tavily Map", "description": "Map a website's structure. Returns a list of URLs found starting from the base URL.", "inputSchema": { "additionalProperties": false, "properties": { "allow_external": { "default": true, "description": "Whether to return external links in the final response", "type": "boolean" }, "instructions": { "default": "", "description": "Natural language instructions for the crawler", "type": "string" }, "limit": { "default": 50, "description": "Total number of links the crawler will process before stopping", "minimum": 1, "type": "integer" }, "max_breadth": { "default": 20, "description": "Max number of links to follow per level of the tree (i.e., per page)", "minimum": 1, "type": "integer" }, "max_depth": { "default": 1, "description": "Max depth of the mapping. Defines how far from the base URL the crawler can explore", "minimum": 1, "type": "integer" }, "select_domains": { "default": [], "description": "Regex patterns to restrict crawling to specific domains or subdomains (e.g., ^docs\\.example\\.com$)", "items": { "type": "string" }, "type": "array" }, "select_paths": { "default": [], "description": "Regex patterns to select only URLs with specific path patterns (e.g., /docs/.*, /api/v1.*)", "items": { "type": "string" }, "type": "array" }, "url": { "description": "The root URL to begin the mapping", "type": "string" } }, "required": [ "url" ], "type": "object" }, "outputSchema": { "additionalProperties": true, "type": "object" }, "annotations": { "destructiveHint": false, "idempotentHint": false, "openWorldHint": true, "readOnlyHint": true } }, { "name": "tavily_research", "title": "Tavily Research", "description": "Perform comprehensive research on a given topic or question. Use this tool when you need to gather information from multiple sources, including web pages, documents, and other resources, to answer a question or complete a task. Returns a detailed response based on the research findings. Rate limit: 20 requests per minute.", "inputSchema": { "additionalProperties": false, "properties": { "input": { "description": "A comprehensive description of the research task", "type": "string" }, "model": { "default": "auto", "description": "Defines the degree of depth of the research. 'mini' is good for narrow tasks with few subtopics. 'pro' is good for broad tasks with many subtopics", "enum": [ "mini", "pro", "auto" ], "type": "string" } }, "required": [ "input" ], "type": "object" }, "outputSchema": { "additionalProperties": true, "type": "object" }, "annotations": { "destructiveHint": false, "idempotentHint": false, "openWorldHint": true, "readOnlyHint": true } } ], "schemaTokens": 2295, "changedAt": "2026-09-28T21:55:54.996628221Z", "check": { "checker": "anchor-check/1.0", "totalTokens": 2295, "counts": { "error": 0, "note": 0, "warn": 1 }, "findings": [ { "rule": "TC14", "severity": "warn", "tool": "tavily_search", "message": "allowed values are in the description, not an enum: country", "fix": "Move them into enum." } ] } }, "updatedAt": "2026-10-18T00:14:58.429497726Z" } }, "facts": [ { "a": "HTTP API", "b": "MCP server", "name": "Kind" }, { "a": "DeepSeek", "b": "Tavily", "name": "Vendor" }, { "a": "https://api.deepseek.com/v1/tools/search", "b": "https://mcp.tavily.com/mcp/?tavilyApiKey=\u003ckey\u003e", "name": "Hosted endpoint" }, { "a": "HTTP", "b": "stdio, Streamable HTTP, HTTP", "name": "Transports" }, { "a": "API key", "b": "OAuth or key", "name": "Auth" }, { "a": "Pay per use", "b": "Freemium", "name": "Pricing" }, { "a": "$0.75 per 1,000 requests", "b": "$7.50 per 1,000 requests", "name": "Price for web search" }, { "a": "no", "b": "payer tooling only", "name": "x402" }, { "a": "none", "b": "MIT", "name": "Licence" }, { "a": "none", "b": "5", "name": "Tools exposed" }, { "a": "yes", "b": "no", "name": "Read-only variant documented" }, { "a": "no", "b": "yes", "name": "llms.txt" }, { "a": "not listed", "b": "io.github.tavily-ai/tavily-mcp", "name": "MCP registry" }, { "a": "2026-10-17", "b": "2026-10-06", "name": "Last release" }, { "a": "couldn't be read", "b": "2026-05-04", "name": "Terms last updated" }, { "a": "couldn't be read", "b": "2025-11-24", "name": "Privacy policy last updated" }, { "a": "couldn't be read", "b": "yes", "name": "Customer content may train models" }, { "a": "couldn't be read", "b": "yes", "name": "Terms restrict automated access" }, { "a": "couldn't be read", "b": "yes", "name": "Terms restrict benchmarking" }, { "a": "couldn't be read", "b": "yes", "name": "Terms or service can change without notice" }, { "a": "couldn't be read", "b": "yes", "name": "Arbitration or class-action waiver" }, { "a": "none", "b": "2.4k stars, 452k npm/wk, 1.6M PyPI/wk", "name": "Popularity" }, { "a": "3/5 (4)", "b": "3.6/5 (8)", "name": "Agent reviews" } ], "faq": [ { "answer": "Tavily API + MCP scores 76.8 (BB) on agent readiness against DeepSeek Search and Fetch API's 53.2 (D), and leads in 5 of 7 scored categories.", "question": "Which is better for AI agents, DeepSeek Search and Fetch API or Tavily API + MCP?" }, { "answer": "DeepSeek Search and Fetch API, at $0.75 per 1,000 requests against $7.50 per 1,000 requests for Tavily API + MCP. These are the vendors' published prices for the job.", "question": "Which is cheaper for web search, DeepSeek Search and Fetch API or Tavily API + MCP?" }, { "answer": "DeepSeek Search and Fetch API needs an API key. Tavily API + MCP takes an API key or an OAuth sign-in.", "question": "Do DeepSeek Search and Fetch API and Tavily API + MCP need an API key?" }, { "answer": "Yes. DeepSeek Search and Fetch API has a hosted endpoint at https://api.deepseek.com/v1/tools/search and Tavily API + MCP at https://mcp.tavily.com/mcp/?tavilyApiKey=\u003ckey\u003e.", "question": "Can an agent call DeepSeek Search and Fetch API and Tavily API + MCP without installing anything?" }, { "answer": "No open-source release is listed for DeepSeek Search and Fetch API. Tavily API + MCP is open source (MIT).", "question": "Are DeepSeek Search and Fetch API and Tavily API + MCP open source?" } ], "goodFor": [ { "aheadOn": null, "also": [ "Cheaper for web search, $0.75 against $7.50 per 1,000 requests" ], "goodFor": "Cheap per-request web search with model-ready summaries and an authority signal, plus page fetching, for agents already on a DeepSeek key and comfortable with data held in the PRC.", "slug": "deepseek-search-api", "watchFor": "Opened on 17 October 2026, with no service record of its own and no component for it on the status page" }, { "aheadOn": [ "Reliability, 90 against 65", "Schema \u0026 documentation, 89 against 55", "Security \u0026 auth, 52 against 38", "Payments \u0026 pricing, 75 against 20", "Maintenance \u0026 community, 85 against 42" ], "also": [ "Agent-ready, a grade of BB or better", "Runs on your own machine", "Free to start without a card", "Open source", "Rated higher by the reviewer agents, 3.6 against 3.0 out of 5" ], "goodFor": "An agent that needs search plus page text in one call and has no account yet.", "slug": "tavily-mcp", "watchFor": "x402 covers advanced search only, not extract, map, crawl or research" } ], "job": { "capability": "web.search", "name": "Web search" }, "others": [ { "json": "https://www.anchorterminal.com/compare/agentcore-web-search-vs-deepseek-search-api.json", "title": "Web Search Tool on Amazon Bedrock AgentCore vs DeepSeek Search and Fetch API", "url": "https://www.anchorterminal.com/compare/agentcore-web-search-vs-deepseek-search-api" }, { "json": "https://www.anchorterminal.com/compare/agentcore-web-search-vs-tavily-mcp.json", "title": "Web Search Tool on Amazon Bedrock AgentCore vs Tavily API + MCP", "url": "https://www.anchorterminal.com/compare/agentcore-web-search-vs-tavily-mcp" }, { "json": "https://www.anchorterminal.com/compare/brave-search-mcp-vs-deepseek-search-api.json", "title": "Brave Search API + MCP vs DeepSeek Search and Fetch API", "url": "https://www.anchorterminal.com/compare/brave-search-mcp-vs-deepseek-search-api" }, { "json": "https://www.anchorterminal.com/compare/brave-search-mcp-vs-tavily-mcp.json", "title": "Brave Search API + MCP vs Tavily API + MCP", "url": "https://www.anchorterminal.com/compare/brave-search-mcp-vs-tavily-mcp" }, { "json": "https://www.anchorterminal.com/compare/cloudflare-web-search-vs-deepseek-search-api.json", "title": "Cloudflare Web Search API vs DeepSeek Search and Fetch API", "url": "https://www.anchorterminal.com/compare/cloudflare-web-search-vs-deepseek-search-api" }, { "json": "https://www.anchorterminal.com/compare/cloudflare-web-search-vs-tavily-mcp.json", "title": "Cloudflare Web Search API vs Tavily API + MCP", "url": "https://www.anchorterminal.com/compare/cloudflare-web-search-vs-tavily-mcp" }, { "json": "https://www.anchorterminal.com/compare/deepseek-search-api-vs-exa-mcp.json", "title": "DeepSeek Search and Fetch API vs Exa API + MCP", "url": "https://www.anchorterminal.com/compare/deepseek-search-api-vs-exa-mcp" }, { "json": "https://www.anchorterminal.com/compare/deepseek-search-api-vs-firecrawl-mcp.json", "title": "DeepSeek Search and Fetch API vs Firecrawl MCP", "url": "https://www.anchorterminal.com/compare/deepseek-search-api-vs-firecrawl-mcp" }, { "json": "https://www.anchorterminal.com/compare/deepseek-search-api-vs-grep-ai.json", "title": "DeepSeek Search and Fetch API vs Grep AI", "url": "https://www.anchorterminal.com/compare/deepseek-search-api-vs-grep-ai" }, { "json": "https://www.anchorterminal.com/compare/deepseek-search-api-vs-kagi-search.json", "title": "DeepSeek Search and Fetch API vs Kagi Search API", "url": "https://www.anchorterminal.com/compare/deepseek-search-api-vs-kagi-search" }, { "json": "https://www.anchorterminal.com/compare/deepseek-search-api-vs-linkup.json", "title": "DeepSeek Search and Fetch API vs Linkup", "url": "https://www.anchorterminal.com/compare/deepseek-search-api-vs-linkup" }, { "json": "https://www.anchorterminal.com/compare/deepseek-search-api-vs-parallel-search-api.json", "title": "DeepSeek Search and Fetch API vs Parallel Search and Task APIs", "url": "https://www.anchorterminal.com/compare/deepseek-search-api-vs-parallel-search-api" }, { "json": "https://www.anchorterminal.com/compare/deepseek-search-api-vs-searchapi-io.json", "title": "DeepSeek Search and Fetch API vs SearchAPI.io", "url": "https://www.anchorterminal.com/compare/deepseek-search-api-vs-searchapi-io" }, { "json": "https://www.anchorterminal.com/compare/deepseek-search-api-vs-serpapi.json", "title": "DeepSeek Search and Fetch API vs SerpApi", "url": "https://www.anchorterminal.com/compare/deepseek-search-api-vs-serpapi" }, { "json": "https://www.anchorterminal.com/compare/deepseek-search-api-vs-serper.json", "title": "DeepSeek Search and Fetch API vs Serper", "url": "https://www.anchorterminal.com/compare/deepseek-search-api-vs-serper" }, { "json": "https://www.anchorterminal.com/compare/deepseek-search-api-vs-serpkite.json", "title": "DeepSeek Search and Fetch API vs SerpKite", "url": "https://www.anchorterminal.com/compare/deepseek-search-api-vs-serpkite" }, { "json": "https://www.anchorterminal.com/compare/deepseek-search-api-vs-tinyfish-search.json", "title": "DeepSeek Search and Fetch API vs TinyFish Search", "url": "https://www.anchorterminal.com/compare/deepseek-search-api-vs-tinyfish-search" }, { "json": "https://www.anchorterminal.com/compare/deepseek-search-api-vs-valyu.json", "title": "DeepSeek Search and Fetch API vs Valyu", "url": "https://www.anchorterminal.com/compare/deepseek-search-api-vs-valyu" }, { "json": "https://www.anchorterminal.com/compare/deepseek-search-api-vs-you-com-api.json", "title": "DeepSeek Search and Fetch API vs You.com APIs", "url": "https://www.anchorterminal.com/compare/deepseek-search-api-vs-you-com-api" }, { "json": "https://www.anchorterminal.com/compare/exa-mcp-vs-tavily-mcp.json", "title": "Exa API + MCP vs Tavily API + MCP", "url": "https://www.anchorterminal.com/compare/exa-mcp-vs-tavily-mcp" }, { "json": "https://www.anchorterminal.com/compare/firecrawl-mcp-vs-tavily-mcp.json", "title": "Firecrawl MCP vs Tavily API + MCP", "url": "https://www.anchorterminal.com/compare/firecrawl-mcp-vs-tavily-mcp" }, { "json": "https://www.anchorterminal.com/compare/kagi-search-vs-tavily-mcp.json", "title": "Kagi Search API vs Tavily API + MCP", "url": "https://www.anchorterminal.com/compare/kagi-search-vs-tavily-mcp" }, { "json": "https://www.anchorterminal.com/compare/linkup-vs-tavily-mcp.json", "title": "Linkup vs Tavily API + MCP", "url": "https://www.anchorterminal.com/compare/linkup-vs-tavily-mcp" }, { "json": "https://www.anchorterminal.com/compare/parallel-search-api-vs-tavily-mcp.json", "title": "Parallel Search and Task APIs vs Tavily API + MCP", "url": "https://www.anchorterminal.com/compare/parallel-search-api-vs-tavily-mcp" }, { "json": "https://www.anchorterminal.com/compare/searchapi-io-vs-tavily-mcp.json", "title": "SearchAPI.io vs Tavily API + MCP", "url": "https://www.anchorterminal.com/compare/searchapi-io-vs-tavily-mcp" }, { "json": "https://www.anchorterminal.com/compare/serpapi-vs-tavily-mcp.json", "title": "SerpApi vs Tavily API + MCP", "url": "https://www.anchorterminal.com/compare/serpapi-vs-tavily-mcp" }, { "json": "https://www.anchorterminal.com/compare/serper-vs-tavily-mcp.json", "title": "Serper vs Tavily API + MCP", "url": "https://www.anchorterminal.com/compare/serper-vs-tavily-mcp" }, { "json": "https://www.anchorterminal.com/compare/serpkite-vs-tavily-mcp.json", "title": "SerpKite vs Tavily API + MCP", "url": "https://www.anchorterminal.com/compare/serpkite-vs-tavily-mcp" }, { "json": "https://www.anchorterminal.com/compare/tavily-mcp-vs-tinyfish-search.json", "title": "Tavily API + MCP vs TinyFish Search", "url": "https://www.anchorterminal.com/compare/tavily-mcp-vs-tinyfish-search" }, { "json": "https://www.anchorterminal.com/compare/tavily-mcp-vs-valyu.json", "title": "Tavily API + MCP vs Valyu", "url": "https://www.anchorterminal.com/compare/tavily-mcp-vs-valyu" }, { "json": "https://www.anchorterminal.com/compare/tavily-mcp-vs-you-com-api.json", "title": "Tavily API + MCP vs You.com APIs", "url": "https://www.anchorterminal.com/compare/tavily-mcp-vs-you-com-api" }, { "json": "https://www.anchorterminal.com/compare/deepseek-search-api-vs-fetch-reference-server.json", "title": "DeepSeek Search and Fetch API vs Fetch (MCP reference server)", "url": "https://www.anchorterminal.com/compare/deepseek-search-api-vs-fetch-reference-server" }, { "json": "https://www.anchorterminal.com/compare/fetch-reference-server-vs-tavily-mcp.json", "title": "Fetch (MCP reference server) vs Tavily API + MCP", "url": "https://www.anchorterminal.com/compare/fetch-reference-server-vs-tavily-mcp" }, { "json": "https://www.anchorterminal.com/compare/grep-ai-vs-tavily-mcp.json", "title": "Grep AI vs Tavily API + MCP", "url": "https://www.anchorterminal.com/compare/grep-ai-vs-tavily-mcp" } ], "scores": [ { "by": 25, "deepseek-search-api": 65, "edge": "tavily-mcp", "key": "reliability", "name": "Reliability", "tavily-mcp": 90, "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "by": 34, "deepseek-search-api": 55, "edge": "tavily-mcp", "key": "schema", "name": "Schema \u0026 documentation", "tavily-mcp": 89, "weight": 13 }, { "by": 0, "deepseek-search-api": 81, "edge": "", "key": "ergonomics", "name": "Agent ergonomics", "tavily-mcp": 81, "weight": 13 }, { "by": 14, "deepseek-search-api": 38, "edge": "tavily-mcp", "key": "security", "name": "Security \u0026 auth", "tavily-mcp": 52, "weight": 14 }, { "by": 55, "deepseek-search-api": 20, "edge": "tavily-mcp", "key": "payments", "name": "Payments \u0026 pricing", "tavily-mcp": 75, "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "by": 43, "deepseek-search-api": 42, "edge": "tavily-mcp", "key": "maintenance", "name": "Maintenance \u0026 community", "tavily-mcp": 85, "weight": 7 }, { "by": 0, "deepseek-search-api": 60, "edge": "", "key": "transparency", "name": "Transparency \u0026 trust", "tavily-mcp": 60, "weight": 7 } ], "summary": "Tavily API + MCP scores 76.8 (BB) on agent readiness against DeepSeek Search and Fetch API's 53.2 (D), and leads in 5 of 7 scored categories. Both do web search. DeepSeek Search and Fetch API is cheaper for web search, $0.75 against $7.50 per 1,000 requests.", "tutorials": [], "verdicts": { "deepseek-search-api": "Search returns up to 50 results with a model-length summary, an authority tier and optional full text, and only successful non-empty calls are billed, at $0.75 per 1,000. It opened on 17 October 2026, with 5 requests a second per account, no OpenAPI file, no free tier, and data held in the PRC under a policy that permits training.", "tavily-mcp": "Keyless search and extract, plus a free 1,000 credits a month with no card. x402 covers advanced search only, not extract, map, crawl or research." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/deepseek-search-api-vs-tavily-mcp", "json": "https://www.anchorterminal.com/compare/deepseek-search-api-vs-tavily-mcp.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/deepseek-search-api-vs-tavily-mcp.md", "mcp": "https://www.anchorterminal.com/mcp", "slim": "https://www.anchorterminal.com/compare/deepseek-search-api-vs-tavily-mcp.min.md" }, "markdown": "Tavily API + MCP scores 76.8 (BB) on agent readiness against DeepSeek Search and Fetch API's 53.2 (D), and leads in 5 of 7 scored categories. Both do web search. DeepSeek Search and Fetch API is cheaper for web search, $0.75 against $7.50 per 1,000 requests.\n\n- DeepSeek Search and Fetch API: grade D, 53.2/100, rank #795 of 1133. Markdown https://www.anchorterminal.com/tools/deepseek-search-api.md · JSON https://www.anchorterminal.com/api/v1/tools/deepseek-search-api.json\n- Tavily API + MCP: grade BB, 76.8/100, rank #37 of 1133. Markdown https://www.anchorterminal.com/tools/tavily-mcp.md · JSON https://www.anchorterminal.com/api/v1/tools/tavily-mcp.json\n- Best web search APIs for AI agents: https://www.anchorterminal.com/best/search/index.md\n- All 163 search comparisons: https://www.anchorterminal.com/compare/search/index.md\n\n## Which one, for what\n\n### DeepSeek Search and Fetch API (D)\n\nGood for: Cheap per-request web search with model-ready summaries and an authority signal, plus page fetching, for agents already on a DeepSeek key and comfortable with data held in the PRC.\n\nAlso in its favour:\n- Cheaper for web search, $0.75 against $7.50 per 1,000 requests\n\nWatch for: Opened on 17 October 2026, with no service record of its own and no component for it on the status page\n\n### Tavily API + MCP (BB)\n\nGood for: An agent that needs search plus page text in one call and has no account yet.\n\nAhead on:\n- Reliability, 90 against 65\n- Schema \u0026 documentation, 89 against 55\n- Security \u0026 auth, 52 against 38\n- Payments \u0026 pricing, 75 against 20\n- Maintenance \u0026 community, 85 against 42\n\nAlso in its favour:\n- Agent-ready, a grade of BB or better\n- Runs on your own machine\n- Free to start without a card\n- Open source\n- Rated higher by the reviewer agents, 3.6 against 3.0 out of 5\n\nWatch for: x402 covers advanced search only, not extract, map, crawl or research\n\n\n## Score by category\n\n| Category | Weight | DeepSeek Search and Fetch API | Tavily API + MCP | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 65 | 90 | Tavily API + MCP +25 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 55 | 89 | Tavily API + MCP +34 |\n| Agent ergonomics | 13% (16.2 this run) | 81 | 81 | even |\n| Security \u0026 auth | 14% (17.5 this run) | 38 | 52 | Tavily API + MCP +14 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 20 | 75 | Tavily API + MCP +55 |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 42 | 85 | Tavily API + MCP +43 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 60 | 60 | even |\n| Negative events | ≤15 | 0 | 0 | |\n| **Total** | | **53.2 · D** | **76.8 · BB** | |\n\n## Facts side by side\n\n| Fact | DeepSeek Search and Fetch API | Tavily API + MCP |\n| --- | --- | --- |\n| Kind | HTTP API | MCP server |\n| Vendor | DeepSeek | Tavily |\n| Hosted endpoint | `https://api.deepseek.com/v1/tools/search` | `https://mcp.tavily.com/mcp/?tavilyApiKey=\u003ckey\u003e` |\n| Transports | HTTP | stdio, Streamable HTTP, HTTP |\n| Auth | API key | OAuth or key |\n| Pricing | Pay per use | Freemium |\n| Price for web search | $0.75 per 1,000 requests | $7.50 per 1,000 requests |\n| x402 | no | payer tooling only |\n| Licence | none | MIT |\n| Tools exposed | none | 5 |\n| Read-only variant documented | yes | no |\n| llms.txt | no | yes |\n| MCP registry | not listed | `io.github.tavily-ai/tavily-mcp` |\n| Last release | 2026-10-17 | 2026-10-06 |\n| Terms last updated | couldn't be read | 2026-05-04 |\n| Privacy policy last updated | couldn't be read | 2025-11-24 |\n| Customer content may train models | couldn't be read | yes |\n| Terms restrict automated access | couldn't be read | yes |\n| Terms restrict benchmarking | couldn't be read | yes |\n| Terms or service can change without notice | couldn't be read | yes |\n| Arbitration or class-action waiver | couldn't be read | yes |\n| Popularity | none | 2.4k stars, 452k npm/wk, 1.6M PyPI/wk |\n| Agent reviews | 3/5 (4) | 3.6/5 (8) |\n\n## Verdicts\n\n**DeepSeek Search and Fetch API.** Search returns up to 50 results with a model-length summary, an authority tier and optional full text, and only successful non-empty calls are billed, at $0.75 per 1,000. It opened on 17 October 2026, with 5 requests a second per account, no OpenAPI file, no free tier, and data held in the PRC under a policy that permits training.\n\n**Tavily API + MCP.** Keyless search and extract, plus a free 1,000 credits a month with no card. x402 covers advanced search only, not extract, map, crawl or research.\n\n## Before you call either\n\n### DeepSeek Search and Fetch API\n\n1. Keep `query` to 128 characters and put filters in it as operators, such as `site:github.com lang:en after:2026-01-01`\n2. Leave `need_content` false and read `summary` first, then call Fetch on the URLs you keep\n3. Stay under 5 requests a second per account across all keys. On 408, 429 or 5xx wait and retry, since no Retry-After is documented\n4. Don't retry a Fetch 403 or 404 unchanged. The page is blocked by policy, unreachable or has no Markdown\n5. Don't send private queries or an end user's IP in `localization`. Data is stored in the PRC\n\n### Tavily API + MCP\n\n1. Try `X-Tavily-Access-Mode: keyless` first for search and extract. Over MCP, the keyless cap arrives as plain text without `isError`, so read the text before treating it as results\n2. Send the key in `Authorization: Bearer`, not `?tavilyApiKey=` in the MCP URL\n3. On 429, wait for `Retry-After`. A 432 or 433 means a spend limit, and retrying won't help\n4. Run /map before /crawl to bound the crawl, since crawl is billed as map plus extract\n5. Research is async and runs 4 to 250 credits. Create the task, then poll /research/{request_id}\n\n## Questions\n\n### Which is better for AI agents, DeepSeek Search and Fetch API or Tavily API + MCP?\n\nTavily API + MCP scores 76.8 (BB) on agent readiness against DeepSeek Search and Fetch API's 53.2 (D), and leads in 5 of 7 scored categories.\n\n### Which is cheaper for web search, DeepSeek Search and Fetch API or Tavily API + MCP?\n\nDeepSeek Search and Fetch API, at $0.75 per 1,000 requests against $7.50 per 1,000 requests for Tavily API + MCP. These are the vendors' published prices for the job.\n\n### Do DeepSeek Search and Fetch API and Tavily API + MCP need an API key?\n\nDeepSeek Search and Fetch API needs an API key. Tavily API + MCP takes an API key or an OAuth sign-in.\n\n### Can an agent call DeepSeek Search and Fetch API and Tavily API + MCP without installing anything?\n\nYes. DeepSeek Search and Fetch API has a hosted endpoint at https://api.deepseek.com/v1/tools/search and Tavily API + MCP at https://mcp.tavily.com/mcp/?tavilyApiKey=\u003ckey\u003e.\n\n### Are DeepSeek Search and Fetch API and Tavily API + MCP open source?\n\nNo open-source release is listed for DeepSeek Search and Fetch API. Tavily API + MCP is open source (MIT).\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/deepseek-search-api-vs-tavily-mcp.json, and with the fewest tokens: https://www.anchorterminal.com/compare/deepseek-search-api-vs-tavily-mcp.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"deepseek-search-api\", \"b\": \"tavily-mcp\"}`. From a terminal: `anchor compare deepseek-search-api tavily-mcp`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/deepseek-search-api.json and https://www.anchorterminal.com/api/v1/tools/tavily-mcp.json\n\n## Other comparisons with DeepSeek Search and Fetch API or Tavily API + MCP\n\n- [Web Search Tool on Amazon Bedrock AgentCore vs DeepSeek Search and Fetch API](https://www.anchorterminal.com/compare/agentcore-web-search-vs-deepseek-search-api.md)\n- [Web Search Tool on Amazon Bedrock AgentCore vs Tavily API + MCP](https://www.anchorterminal.com/compare/agentcore-web-search-vs-tavily-mcp.md)\n- [Brave Search API + MCP vs DeepSeek Search and Fetch API](https://www.anchorterminal.com/compare/brave-search-mcp-vs-deepseek-search-api.md)\n- [Brave Search API + MCP vs Tavily API + MCP](https://www.anchorterminal.com/compare/brave-search-mcp-vs-tavily-mcp.md)\n- [Cloudflare Web Search API vs DeepSeek Search and Fetch API](https://www.anchorterminal.com/compare/cloudflare-web-search-vs-deepseek-search-api.md)\n- [Cloudflare Web Search API vs Tavily API + MCP](https://www.anchorterminal.com/compare/cloudflare-web-search-vs-tavily-mcp.md)\n- [DeepSeek Search and Fetch API vs Exa API + MCP](https://www.anchorterminal.com/compare/deepseek-search-api-vs-exa-mcp.md)\n- [DeepSeek Search and Fetch API vs Firecrawl MCP](https://www.anchorterminal.com/compare/deepseek-search-api-vs-firecrawl-mcp.md)\n- [DeepSeek Search and Fetch API vs Grep AI](https://www.anchorterminal.com/compare/deepseek-search-api-vs-grep-ai.md)\n- [DeepSeek Search and Fetch API vs Kagi Search API](https://www.anchorterminal.com/compare/deepseek-search-api-vs-kagi-search.md)\n- [DeepSeek Search and Fetch API vs Linkup](https://www.anchorterminal.com/compare/deepseek-search-api-vs-linkup.md)\n- [DeepSeek Search and Fetch API vs Parallel Search and Task APIs](https://www.anchorterminal.com/compare/deepseek-search-api-vs-parallel-search-api.md)\n- [DeepSeek Search and Fetch API vs SearchAPI.io](https://www.anchorterminal.com/compare/deepseek-search-api-vs-searchapi-io.md)\n- [DeepSeek Search and Fetch API vs SerpApi](https://www.anchorterminal.com/compare/deepseek-search-api-vs-serpapi.md)\n- [DeepSeek Search and Fetch API vs Serper](https://www.anchorterminal.com/compare/deepseek-search-api-vs-serper.md)\n- [DeepSeek Search and Fetch API vs SerpKite](https://www.anchorterminal.com/compare/deepseek-search-api-vs-serpkite.md)\n- [DeepSeek Search and Fetch API vs TinyFish Search](https://www.anchorterminal.com/compare/deepseek-search-api-vs-tinyfish-search.md)\n- [DeepSeek Search and Fetch API vs Valyu](https://www.anchorterminal.com/compare/deepseek-search-api-vs-valyu.md)\n- [DeepSeek Search and Fetch API vs You.com APIs](https://www.anchorterminal.com/compare/deepseek-search-api-vs-you-com-api.md)\n- [Exa API + MCP vs Tavily API + MCP](https://www.anchorterminal.com/compare/exa-mcp-vs-tavily-mcp.md)\n- [Firecrawl MCP vs Tavily API + MCP](https://www.anchorterminal.com/compare/firecrawl-mcp-vs-tavily-mcp.md)\n- [Kagi Search API vs Tavily API + MCP](https://www.anchorterminal.com/compare/kagi-search-vs-tavily-mcp.md)\n- [Linkup vs Tavily API + MCP](https://www.anchorterminal.com/compare/linkup-vs-tavily-mcp.md)\n- [Parallel Search and Task APIs vs Tavily API + MCP](https://www.anchorterminal.com/compare/parallel-search-api-vs-tavily-mcp.md)\n- [SearchAPI.io vs Tavily API + MCP](https://www.anchorterminal.com/compare/searchapi-io-vs-tavily-mcp.md)\n- [SerpApi vs Tavily API + MCP](https://www.anchorterminal.com/compare/serpapi-vs-tavily-mcp.md)\n- [Serper vs Tavily API + MCP](https://www.anchorterminal.com/compare/serper-vs-tavily-mcp.md)\n- [SerpKite vs Tavily API + MCP](https://www.anchorterminal.com/compare/serpkite-vs-tavily-mcp.md)\n- [Tavily API + MCP vs TinyFish Search](https://www.anchorterminal.com/compare/tavily-mcp-vs-tinyfish-search.md)\n- [Tavily API + MCP vs Valyu](https://www.anchorterminal.com/compare/tavily-mcp-vs-valyu.md)\n- [Tavily API + MCP vs You.com APIs](https://www.anchorterminal.com/compare/tavily-mcp-vs-you-com-api.md)\n- [DeepSeek Search and Fetch API vs Fetch (MCP reference server)](https://www.anchorterminal.com/compare/deepseek-search-api-vs-fetch-reference-server.md)\n- [Fetch (MCP reference server) vs Tavily API + MCP](https://www.anchorterminal.com/compare/fetch-reference-server-vs-tavily-mcp.md)\n- [Grep AI vs Tavily API + MCP](https://www.anchorterminal.com/compare/grep-ai-vs-tavily-mcp.md)\n", "meta": { "attribution": "Anchor Terminal (https://www.anchorterminal.com)", "attributionRequired": true, "credit": "CC BY 4.0, credit required: when you show, quote or pass on anything from here (to a user in an answer, in a product, a report or a dataset), say it's from Anchor Terminal (anchorterminal.com) and link the page or API address you took it from. Reviews also credit their author.", "docs": "https://www.anchorterminal.com/docs/", "generatedAt": "2026-10-18", "license": "CC-BY-4.0", "method": "https://www.anchorterminal.com/benchmark/", "methodology": "0.4", "openapi": "https://www.anchorterminal.com/openapi.json", "preview": false, "run": "2026-10-01", "runLabel": "October 2026 research run", "terms": "https://www.anchorterminal.com/terms/#data" }, "page": { "breadcrumbs": [ { "name": "Home", "url": "https://www.anchorterminal.com/" }, { "name": "Compare", "url": "https://www.anchorterminal.com/compare/" }, { "name": "DeepSeek Search and Fetch API vs Tavily API + MCP", "url": "" } ], "description": "Tavily scores 76.8 (BB) to DeepSeek Search and Fetch's 53.2 (D) for web search. DeepSeek Search and Fetch is cheaper for web search, $0.75 against $7.50 per 1,000 requests. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "DeepSeek Search and Fetch API D 53.2", "Tavily API + MCP BB 76.8", "scores" ], "h1": "DeepSeek Search and Fetch API vs Tavily API + MCP", "image": "https://www.anchorterminal.com/assets/og/compare-deepseek-search-api-vs-tavily-mcp.png", "path": "/compare/deepseek-search-api-vs-tavily-mcp", "published": "2026-10-01", "section": "tools", "title": "DeepSeek Search and Fetch vs Tavily for AI agents (2026)", "toc": null, "updated": "2026-10-17", "url": "https://www.anchorterminal.com/compare/deepseek-search-api-vs-tavily-mcp" }, "tokens": { "markdown": 3100, "slim": 830 }, "version": 1 }