{ "data": { "a": { "slug": "bing-grounding", "name": "Grounding with Bing Search", "vendor": "Microsoft", "vendorUrl": "https://www.microsoft.com/bing/apis", "kind": "http-api", "category": "search", "summary": "Grounding with Bing Search is Microsoft's web search tool for agents in Foundry Agent Service. A Foundry model searches Bing during a Responses API run and returns an answer with URL citations, through the bing_grounding and web_search tools.", "url": "https://www.anchorterminal.com/tools/bing-grounding", "markdownUrl": "https://www.anchorterminal.com/tools/bing-grounding.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/bing-grounding.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/bing-grounding.json", "dns": "bing-grounding.grade.anchorterminal.com", "license": "Proprietary service under the customer's Microsoft agreement and the separate Grounding with Bing terms of use, which exclude it from the Microsoft Data Protection Addendum", "transports": [ "streamable-http" ], "remoteUrl": "https://{account}.services.ai.azure.com/api/projects/{project}/openai/v1/responses", "packages": [ { "registry": "pypi", "name": "azure-ai-projects" }, { "registry": "npm", "name": "@azure/ai-projects" } ], "auth": "oauth", "authNotes": "Microsoft Entra ID bearer token for the Foundry project (scope https://ai.azure.com/.default, for example through DefaultAzureCredential), with the Foundry User role to create and run agents. The bing_grounding tool also needs a Grounding with Bing resource whose key is stored in a project connection, created by someone with Contributor and Foundry Project Manager. The agent never holds the Bing key. The web_search tool needs no Bing resource or connection.", "pricing": "usage", "pricingNotes": "$14 per 1,000 transactions for Grounding with Bing Search and for Grounding with Bing Custom Search, counted as tool calls per run, plus the model deployment's token charges. No free tier found. An Azure subscription and a person's signup are needed first.", "priceSummary": "$14 / 1k req", "where": "hosted", "x402": { "level": "no", "evidence": "No x402, MPP or L402 on the Foundry web search and Bing tools pages, the Grounding with Bing pricing page or the terms of use (checked 2026-11-06). Billing runs through the Azure subscription.", "endpoints": [] }, "toolCount": 3, "popularity": { "githubStars": null, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-11-06" }, "docsUrl": "https://learn.microsoft.com/en-us/azure/foundry/agents/how-to/tools/web-search", "capabilities": [ "web.search", "search.answer" ], "tags": [ "hosted", "usage-priced", "closed-source", "enterprise", "card-required", "status-page", "python", "typescript" ], "lastRelease": "2026-11-02", "graded": true, "anchor": { "graded": true, "score": 63.7, "grade": "B", "agentReady": false, "rank": 502, "ranked": true, "rankOf": 1486, "categoryRank": 15, "methodology": "0.7", "run": "2026-10-01", "scores": { "ergonomics": 61, "maintenance": 80, "payments": 20, "reliability": 68, "schema": 68, "security": 79, "transparency": 66 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-11-06" }, "negative": 0, "verdict": "First-party Bing grounding inside Foundry Agent Service, called with Entra ID so the agent never holds a search key, at a published $14 per 1,000 transactions. The tools return a model's answer with citations, never the raw results, and data sent to them falls outside Microsoft's Data Protection Addendum and Azure's compliance boundary.", "bestFor": "Teams already building on Foundry Agent Service who want cited answers from Bing without handling a search key.", "strengths": [ "Callers authenticate with Microsoft Entra ID and Foundry RBAC roles, and the Bing resource key stays in a project connection", "Price and limits published without a login, $14 per 1,000 transactions, 150 a second and 1 million a day", "Count, freshness, market and language parameters, and a Custom Search variant that limits grounding to chosen domains", "Docs say to treat web search results as untrusted input, and admins can turn web search off for a whole subscription" ], "weaknesses": [ "The Bing tools never return raw results to developers, only a model-written answer with citation links", "The Data Protection Addendum does not apply and query data leaves the Azure compliance and geographic boundary", "No free tier, and a first call needs an Azure subscription, a Foundry project, a model deployment and, for bing_grounding, a paid Bing resource", "Terms forbid using Bing output to train or evaluate AI models and limit storing or caching it" ], "agentNotes": [ "Use the citations in the response annotations as the sources; the tool output itself is not returned, and the terms require showing the URLs and the Bing query link", "Expect each run to bill one transaction per tool call at $14 per 1,000, plus model tokens, and set count and freshness in the tool configuration", "Treat cited page text as untrusted input and don't put secrets or personal data in prompts, since queries leave the Azure compliance boundary", "On 429 back off exponentially; no Retry-After header is documented for the tool" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "B", "methodology": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 63.7 } ], "editorialScores": { "ergonomics": 61, "maintenance": 80, "payments": 20, "reliability": 68, "schema": 68, "security": 79, "transparency": 45 }, "provenanceScore": 87, "checked": { "categories": { "ergonomics": "2026-11-06", "maintenance": "2026-11-06", "payments": "2026-11-06", "reliability": "2026-11-06", "schema": "2026-11-06", "security": "2026-11-06", "transparency": "2026-11-06" }, "last": "2026-11-06", "oldest": "2026-11-06", "stale": false, "staleAfterDays": 90 } }, "connect": { "install": "pip install azure-ai-projects azure-identity", "http": "curl -X POST \"$FOUNDRY_PROJECT_ENDPOINT/openai/v1/responses\" \\\n -H \"Authorization: Bearer $AGENT_TOKEN\" \\\n -H \"Content-Type: application/json\" \\\n -d '{\"model\":\"'$FOUNDRY_MODEL_DEPLOYMENT_NAME'\",\"input\":\"How does Wikipedia explain Euler identity?\",\"tool_choice\":\"required\",\"tools\":[{\"type\":\"bing_grounding\",\"bing_grounding\":{\"search_configurations\":[{\"project_connection_id\":\"'$BING_PROJECT_CONNECTION_ID'\",\"count\":7,\"market\":\"en-US\",\"set_lang\":\"en\",\"freshness\":\"week\"}]}}]}'" }, "letme": { "capability": "https://letme.dev/web.search", "tool": "https://letme.dev/bing-grounding" }, "sameCompany": [ "azure-openai", "azure-foundry-fine-tuning", "azure-ai-content-safety", "azure-speech-to-text", "azure-text-to-speech", "microsoft-agent-framework", "microsoft-execution-containers", "microsoft-entra-agent-id", "azure-key-vault", "azure-document-intelligence", "azure-devops-mcp", "microsoft-learn-mcp", "tokeneconomizer", "playwright-mcp", "azure-mcp", "azure-maps", "azure-translator", "microsoft-graph-calendar", "azure-blob-storage", "onedrive-sharepoint", "microsoft-teams", "dynamics-365-sales", "copilot-studio-mcp", "power-automate", "foundry-local", "microsoft-decision-1", "microsoft-advertising-api", "microsoft-excel-graph", "outlook-mail-graph", "microsoft-graph-people", "mage-vl-cowork" ], "area": "web-data", "unitPrices": [ { "item": "Grounding with Bing Search transaction", "unit": "1k-requests", "usd": 14, "note": "Counted as tool calls per run, plus the model deployment's token charges" }, { "item": "Grounding with Bing Custom Search transaction", "unit": "1k-requests", "usd": 14, "note": "Same limits, 150 a second and 1 million a day" } ], "provenance": { "legalEntity": "Microsoft Corporation", "domain": "microsoft.com", "domainRegistered": "1991-05-02", "endpointOnVendorDomain": true, "terms": "https://www.microsoft.com/bing/apis/grounding-legal-enterprise", "privacy": "https://privacy.microsoft.com/en-us/privacystatement", "statusPage": "https://azure.status.microsoft/en-us/status", "changelog": "https://learn.microsoft.com/en-us/azure/foundry/whats-new-foundry", "securityTxt": "expired", "checked": "2026-11-06", "notes": [ "The Foundry project endpoint is on services.ai.azure.com, a Microsoft domain. Domain registration date carried from the Azure listings' provenance.", "The Grounding with Bing terms of use (updated November 2025) are subject to the customer's Microsoft agreement (MCA, MBSA or MOSA) and name no separate contracting entity. They forbid using output on sites that block the customer's crawler, using links for crawling or scraping, and bypassing transaction limits.", "www.microsoft.com/.well-known/security.txt still carries Expires 2026-09-23T16:00:00.000Z on 6 November 2026.", "learn.microsoft.com/robots.txt allows the documentation paths read. The Azure status history page lists post-incident reviews for five years." ], "score": 87 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/bing-grounding.json", "live": { "slug": "bing-grounding", "probe": { "target": "https://{account}.services.ai.azure.com/api/projects/{project}/openai/v1/responses", "method": "get", "lastAt": "2026-11-07T18:20:13.927615013Z", "lastOk": false, "lastStatus": 0, "lastMs": 0, "lastNote": "invalid character \"{\" in host name", "authRequired": false, "uptime24h": 0, "uptime30d": 0, "p50ms24h": 0, "p95ms24h": 0, "samples24h": 200, "samples30d": 200, "days": [ { "date": "2026-11-06", "probes": 13, "ok": 0 }, { "date": "2026-11-07", "probes": 187, "ok": 0 } ], "outages": [ { "start": "2026-11-06T22:45:07.390416052Z", "end": "0001-01-01T00:00:00Z", "note": "invalid character \"{\" in host name" } ] }, "versions": [ { "registry": "npm", "name": "@azure/ai-projects", "version": "2.10.0", "seenAt": "2026-11-06T23:11:06.900508365Z" }, { "registry": "pypi", "name": "azure-ai-projects", "version": "2.10.0", "released": "2026-10-30", "seenAt": "2026-11-06T23:11:05.00335007Z" } ], "npmWeekly": 1368538, "pypiWeekly": 1896178, "securityTxt": { "url": "https://microsoft.com/.well-known/security.txt", "state": "valid", "expires": "2027-10-27T16:00:00.000Z", "checkedAt": "2026-11-07T16:02:01.196666056Z" }, "pages": [ { "url": "https://www.microsoft.com/bing/apis/grounding-legal-enterprise", "kind": "terms", "status": 200, "checkedAt": "2026-11-07T14:31:40.128456318Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "ddf25722851a" } ], "updatedAt": "2026-11-07T18:20:13.927615013Z" } }, "answer": "Parallel Search and Task APIs scores 75 (BB) on agent readiness against Grounding with Bing Search's 63.7 (B), and leads in 5 of 7 scored categories. Grounding with Bing Search leads on security \u0026 auth.", "b": { "slug": "parallel-search-api", "name": "Parallel Search and Task APIs", "vendor": "Parallel Web Systems", "vendorUrl": "https://parallel.ai", "kind": "http-api", "category": "search", "summary": "Parallel's web APIs for agents, covering search, page extraction, asynchronous research tasks, closed-ended decisions answered from current web evidence and an OpenAI-compatible Responses endpoint, with hosted Search and Task MCP servers.", "url": "https://www.anchorterminal.com/tools/parallel-search-api", "markdownUrl": "https://www.anchorterminal.com/tools/parallel-search-api.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/parallel-search-api.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/parallel-search-api.json", "dns": "parallel-search-api.grade.anchorterminal.com", "transports": [ "http", "streamable-http" ], "remoteUrl": "https://api.parallel.ai/v1/search", "packages": [ { "registry": "npm", "name": "parallel-web" }, { "registry": "pypi", "name": "parallel-web" } ], "auth": "mixed", "authNotes": "API key in the `x-api-key` header. The Search MCP at search.parallel.ai/mcp works anonymously at lower limits, takes a Bearer key, and /mcp-oauth adds OAuth. An OAuth provider can issue keys on behalf of your users.", "pricing": "freemium", "pricingNotes": "Up to 5,000 free requests a month, with $5 of free credit monthly and up to $80 at signup. Search $1 per 1,000 requests in turbo or fast, $5 in basic or advanced, 10 results included and $1 per 1,000 extra results. Image Search $1 (fast) or $5 (advanced) per 1,000, up to 20 results. Extract $1 per 1,000 URLs. Task $5 (lite) to $2,400 (ultra8x) per 1,000 successful runs. Responses $10 to $250 per 1,000 by reasoning effort. Decisions $1 per 1,000 requests, up to 100 questions a request. Failed runs aren't billed (https://parallel.ai/pricing).", "priceSummary": "$1 / 1k req", "where": "hosted", "x402": { "level": "partial", "evidence": "Not on api.parallel.ai. A separate gateway at parallelmpp.dev takes x402 (USDC on Base) and MPP (Stripe or Tempo) for search and extract at $0.01 and an ultra task at $0.30. An unauthenticated POST to /api/search returned 402 with an x402 v2 challenge for 10000 base units on eip155:8453 (checked 2026-09-30) (https://docs.parallel.ai/integrations/agentic-payments).", "endpoints": [ { "url": "https://parallelmpp.dev/api/search", "priceUsd": 0.01, "network": "eip155:8453" }, { "url": "https://parallelmpp.dev/api/extract", "priceUsd": 0.01, "network": "eip155:8453" }, { "url": "https://parallelmpp.dev/api/task", "priceUsd": 0.3, "network": "eip155:8453" } ] }, "toolCount": 6, "popularity": { "githubStars": 28, "npmWeekly": 249803, "pypiWeekly": 994376, "asOf": "2026-09-30" }, "docsUrl": "https://docs.parallel.ai", "llmsTxt": "https://docs.parallel.ai/llms.txt", "openapi": "https://docs.parallel.ai/public-openapi.json", "registryName": "ai.parallel/search-mcp", "capabilities": [ "web.search", "web.fetch", "web.extract", "search.answer", "search.research" ], "tags": [ "hosted", "freemium", "mcp", "llms-txt", "openapi", "x402", "python", "typescript", "async-jobs", "webhooks" ], "lastRelease": "2026-10-28", "graded": true, "anchor": { "graded": true, "score": 75, "grade": "BB", "agentReady": true, "rank": 73, "ranked": true, "rankOf": 1486, "categoryRank": 4, "methodology": "0.7", "run": "2026-10-01", "scores": { "ergonomics": 87, "maintenance": 87, "payments": 75, "reliability": 75, "schema": 94, "security": 45, "transparency": 65 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-11-01" }, "negative": 0, "verdict": "Fast-mode search at $1 per 1,000 with 10 excerpted results, and a keyless two-tool Search MCP annotated read-only. Search defaults to advanced mode at $5 per 1,000 when `mode` is left out, and the Customer Terms allow training on inputs and outputs.", "bestFor": "Agents that mix quick search with long research or enrichment jobs and want one vendor and one bill.", "strengths": [ "Fast-mode search at $1 per 1,000 with 10 excerpted results, and Extract at $1 per 1,000 URLs", "Task runs billed only on success, and documented limits of 600 searches and 2,000 task creations a minute", "Keyless hosted MCP servers whose search, fetch and decision tools are annotated read-only, plus Bearer and OAuth sign-in", "Public OpenAPI, llms.txt and an errors table that says which codes to retry and how", "SDK releases several times a month, with CI and a breaking-change check on the Python SDK, and a dated changelog with entries on 19 and 26 October 2026" ], "weaknesses": [ "Search defaults to advanced mode at $5 per 1,000 when `mode` is left out", "SDKs retry Task creation on 429 and 5xx with no idempotency key", "x402 and MPP only through parallelmpp.dev at a flat $0.01, not on api.parallel.ai", "Customer Terms let Parallel train on inputs and outputs, and no retention period is stated outside the EU endpoint", "No prompt-injection guidance, no security.txt and no public subprocessor list" ], "agentNotes": [ "Pass `mode: \"fast\"` on every API search. Without it you pay the advanced rate. On an authenticated MCP connection, pin it with `?mode=fast`", "Create Task runs with `max_retries=0` and check for an existing run before retrying", "Give an `objective` plus two or three short `search_queries`. That's what ranks the excerpts", "On 402, check available balance rather than total. Running tasks reserve credit", "Ask for zero data retention or use the EU endpoint before sending private queries. The default terms allow training on them", "On Decisions, check each answer's `type` before reading it. A refusal is a 200, not an error, and a predicate is a probability you threshold yourself" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 8, "avgRating": 3.6, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "BB", "methodology": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 75 } ], "editorialScores": { "ergonomics": 87, "maintenance": 87, "payments": 75, "reliability": 75, "schema": 94, "security": 45, "transparency": 45 }, "provenanceScore": 85, "checked": { "categories": { "ergonomics": "2026-11-01", "maintenance": "2026-11-01", "payments": "2026-11-01", "reliability": "2026-11-01", "schema": "2026-11-01", "security": "2026-11-01", "transparency": "2026-11-01" }, "last": "2026-11-01", "lastMoved": "2026-10-30", "oldest": "2026-11-01", "stale": false, "staleAfterDays": 90 } }, "connect": { "http": "curl https://api.parallel.ai/v1/search -H \"x-api-key: $PARALLEL_API_KEY\" -H \"Content-Type: application/json\" \\\n -d '{\"mode\":\"fast\",\"objective\":\"Latest Parallel Web Systems announcements\",\"search_queries\":[\"Parallel Web Systems news\"]}'", "claudeCode": "claude mcp add --transport http parallel-search https://search.parallel.ai/mcp", "config": { "mcpServers": { "parallel-search": { "headers": { "Authorization": "Bearer ${PARALLEL_API_KEY}" }, "url": "https://search.parallel.ai/mcp" } } }, "x402": "curl -i -X POST https://parallelmpp.dev/api/search -H 'content-type: application/json' -d '{\"query\":\"test\"}'\n# 402 -\u003e pay $0.01 USDC on eip155:8453 (or MPP via Stripe/Tempo) -\u003e resend" }, "letme": { "capability": "https://letme.dev/web.search", "tool": "https://letme.dev/parallel-search-api" }, "area": "web-data", "unitPrices": [ { "item": "Search, turbo or fast", "unit": "1k-requests", "usd": 1, "note": "10 results included" }, { "item": "Search, basic or advanced", "unit": "1k-requests", "usd": 5, "note": "advanced is the default mode" }, { "item": "Extract", "unit": "1k-pages", "usd": 1 }, { "item": "Task, lite processor", "unit": "1k-calls", "usd": 5 }, { "item": "Task, pro processor", "unit": "1k-calls", "usd": 100 }, { "item": "Responses, medium effort", "unit": "1k-requests", "usd": 50 }, { "item": "Decisions, up to 100 questions a request", "unit": "1k-requests", "usd": 1, "note": "docs pricing page, 1 November 2026" }, { "item": "x402 search via gateway", "unit": "call", "usd": 0.01, "note": "parallelmpp.dev" } ], "provenance": { "legalEntity": "Parallel Web Systems Inc.", "domain": "parallel.ai", "domainRegistered": "2017-12-16", "domainNote": "Registered in 2017 and transferred on 2024-07-01, so the registration date predates the company's use of it.", "endpointOnVendorDomain": true, "terms": "https://parallel.ai/customer-terms", "privacy": "https://parallel.ai/privacy-policy", "statusPage": "https://status.parallel.ai", "changelog": "https://docs.parallel.ai/resources/changelog", "securityTxt": "none", "checked": "2026-11-01", "score": 85 }, "requirements": { "setupChecked": true, "complianceChecked": true, "agentAlone": true, "card": "unknown", "freeTier": true, "minutes": 5, "credential": "mixed", "hosting": [ "US", "EU" ], "euResidency": "enterprise", "trainsOnData": "unknown", "zeroRetention": "enterprise", "certifications": [ "GDPR" ], "dpa": true, "selfHost": "no" }, "pageJsonUrl": "https://www.anchorterminal.com/tools/parallel-search-api.json", "live": { "slug": "parallel-search-api", "probe": { "target": "https://api.parallel.ai/v1/search", "method": "get", "lastAt": "2026-11-07T18:20:45.797474111Z", "lastOk": true, "lastStatus": 401, "lastMs": 1251, "lastNote": "asks for credentials", "authRequired": true, "uptime24h": 100, "uptime30d": 100, "p50ms24h": 1156, "p95ms24h": 1251, "samples24h": 239, "samples30d": 7910, "days": [ { "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": 256, "ok": 256 }, { "date": "2026-10-19", "probes": 255, "ok": 255 }, { "date": "2026-10-20", "probes": 252, "ok": 252 }, { "date": "2026-10-21", "probes": 253, "ok": 253 }, { "date": "2026-10-22", "probes": 253, "ok": 253 }, { "date": "2026-10-23", "probes": 248, "ok": 248 }, { "date": "2026-10-24", "probes": 251, "ok": 251 }, { "date": "2026-10-25", "probes": 250, "ok": 250 }, { "date": "2026-10-26", "probes": 252, "ok": 252 }, { "date": "2026-10-27", "probes": 249, "ok": 249 }, { "date": "2026-10-28", "probes": 250, "ok": 250 }, { "date": "2026-10-29", "probes": 249, "ok": 249 }, { "date": "2026-10-30", "probes": 249, "ok": 249 }, { "date": "2026-10-31", "probes": 251, "ok": 251 }, { "date": "2026-11-01", "probes": 249, "ok": 249 }, { "date": "2026-11-02", "probes": 250, "ok": 250 }, { "date": "2026-11-03", "probes": 248, "ok": 248 }, { "date": "2026-11-04", "probes": 246, "ok": 246 }, { "date": "2026-11-05", "probes": 185, "ok": 185 }, { "date": "2026-11-06", "probes": 241, "ok": 241 }, { "date": "2026-11-07", "probes": 187, "ok": 187 } ] }, "vendorStatus": { "page": "https://status.parallel.ai", "indicator": "none", "summary": "All Systems Operational", "checkedAt": "2026-11-07T18:21:52.770771808Z" }, "versions": [ { "registry": "mcp-registry", "name": "ai.parallel/search-mcp", "version": "1.0.0", "seenAt": "2026-11-07T18:16:28.95801333Z" }, { "registry": "npm", "name": "parallel-web", "version": "1.3.7", "seenAt": "2026-11-06T23:54:39.327146641Z" }, { "registry": "pypi", "name": "parallel-web", "version": "1.3.7", "released": "2026-10-23", "seenAt": "2026-11-06T23:54:40.221328103Z" } ], "npmWeekly": 499802, "pypiWeekly": 1280811, "securityTxt": { "url": "https://parallel.ai/.well-known/security.txt", "state": "none", "checkedAt": "2026-11-07T15:59:47.651524803Z" }, "llmsTxt": { "url": "https://docs.parallel.ai/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-11-07T15:33:35.374820292Z" }, "domain": { "domain": "parallel.ai", "registered": "2017-12-16", "source": "https://rdap.identitydigital.services/rdap/domain/parallel.ai", "checkedAt": "2026-11-01T14:08:31.990227623Z" }, "pages": [ { "url": "https://docs.parallel.ai/resources/changelog", "kind": "changelog", "status": 200, "checkedAt": "2026-11-07T14:07:25.166885545Z", "changedAt": "2026-11-06T13:29:46.487630215Z", "fingerprint": "64580beee981" }, { "url": "https://parallel.ai/pricing", "kind": "pricing", "status": 200, "checkedAt": "2026-11-07T14:15:57.961317128Z", "changedAt": "2026-11-07T14:15:57.961317128Z", "fingerprint": "6907599c6534" }, { "url": "https://parallel.ai/privacy-policy", "kind": "privacy", "status": 200, "checkedAt": "2026-11-07T14:15:59.73217133Z", "changedAt": "2026-11-06T13:37:39.393174208Z", "fingerprint": "4f0dd0d135d9" }, { "url": "https://parallel.ai/customer-terms", "kind": "terms", "status": 200, "checkedAt": "2026-11-07T14:15:55.334035778Z", "changedAt": "2026-11-06T13:37:35.126347484Z", "fingerprint": "0f2621896abb" }, { "url": "https://parallel.ai/terms-of-service", "kind": "terms", "status": 200, "checkedAt": "2026-10-16T22:28:19.906253644Z", "changedAt": "2026-10-15T22:01:22.246898534Z", "fingerprint": "5d9bafee0ed2" } ], "mcpTools": { "url": "https://search.parallel.ai/mcp", "checkedAt": "2026-11-07T01:46:44.757089899Z", "status": "ok", "protocol": "2026-07-28", "tools": [ { "name": "web_search", "description": "Purpose: Perform web searches and return\nLLM-friendly results, including excerpts that are usually sufficient to\nanswer directly without a follow-up fetch.\n\nIdeal Use Cases:\n- Answering questions that require fresh or current information\n- Research, comparison, documentation, and troubleshooting questions\n- Broad tasks where multiple `search_queries` can be issued in a single call\n\nFor multiple independent objectives, make one web_search call per objective\nconcurrently. Put related query variations for the same objective in a single\ncall's search_queries list.\n", "inputSchema": { "properties": { "model_name": { "description": "The identifier of the LLM model making this tool call (e.g. 'claude-opus-4.7', 'gpt-5.5', 'gemini-2.5-pro'). Before the first call, verify the exact active model slug from trusted runtime/session metadata or active client configuration. Pass the full slug verbatim; never shorten or substitute a model-family alias like 'gpt-5'. Used for product analytics only; does not affect search behavior.", "maxLength": 100, "type": "string" }, "objective": { "description": "Natural-language description of what the web search is trying to find.\nTry to make the search objective atomic, looking for a specific piece of information. May include guidance about preferred sources or freshness.", "title": "Objective", "type": "string" }, "search_queries": { "description": "Concise keyword search queries, 3-6 words\neach. They may use site: with a bare domain (such as site:example.com), but\nnever a URL path after the domain and never quoted phrases. At least one query\nis required; provide 2-3 for best results. For broad tasks, you can include\nmultiple related queries in a single call instead of chaining web_search\ncalls. The queries should be related to the objective.", "items": { "type": "string" }, "title": "Search Queries", "type": "array" }, "session_id": { "description": "Stable identifier for the current conversation. Generate a random value (UUID or 32+ character hex string) at the start of your session and reuse the exact same value on every web_search / web_fetch call. Do NOT change it between turns. Used for free-tier rate limiting and correlating your tool calls in our logs; ignored on paid-tier keys.", "maxLength": 100, "type": "string" } }, "required": [ "objective", "search_queries" ], "title": "v1_search_toolArguments", "type": "object" }, "outputSchema": { "$defs": { "UsageItem": { "description": "Usage item for a single operation.", "properties": { "count": { "description": "Count of the SKU.", "examples": [ 1 ], "title": "Count", "type": "integer" }, "name": { "description": "Name of the SKU.", "examples": [ "sku_search", "sku_extract_excerpts" ], "title": "Name", "type": "string" } }, "required": [ "name", "count" ], "title": "UsageItem", "type": "object" }, "V1WebSearchResult": { "description": "A single search result from the web search API.", "properties": { "excerpts": { "description": "Relevant excerpted content from the URL, formatted as markdown.", "items": { "type": "string" }, "title": "Excerpts", "type": "array" }, "publish_date": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null, "description": "Publish date of the webpage in YYYY-MM-DD format, if available.", "title": "Publish Date" }, "title": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null, "description": "Title of the webpage, if available.", "title": "Title" }, "url": { "description": "URL associated with the search result.", "title": "Url", "type": "string" } }, "required": [ "url", "excerpts" ], "title": "V1WebSearchResult", "type": "object" }, "Warning": { "description": "Human-readable message for a task.", "properties": { "detail": { "anyOf": [ { "additionalProperties": true, "type": "object" }, { "type": "null" } ], "default": null, "description": "Optional detail supporting the warning.", "title": "Detail" }, "message": { "description": "Human-readable message.", "title": "Message", "type": "string" }, "type": { "description": "Type of warning. Note that adding new warning types is considered a backward-compatible change.", "enum": [ "spec_validation_warning", "input_validation_warning", "warning" ], "examples": [ "spec_validation_warning", "input_validation_warning" ], "title": "Type", "type": "string" } }, "required": [ "type", "message" ], "title": "Warning", "type": "object" } }, "description": "Search response.", "properties": { "results": { "description": "A list of search results, ordered by decreasing relevance.", "items": { "$ref": "#/$defs/V1WebSearchResult" }, "title": "Results", "type": "array" }, "search_id": { "description": "Search ID. Example: `search_cad0a6d2dec046bd95ae900527d880e7`", "title": "Search Id", "type": "string" }, "session_id": { "description": "Session identifier, echoed back from the request if provided, otherwise generated by the server. Should be passed to future search and extract calls made by the agent as part of the same larger task.", "examples": [ "session_8a911eb27c7a4afaa20d0d9dc98d07c0" ], "title": "Session Id", "type": "string" }, "usage": { "anyOf": [ { "items": { "$ref": "#/$defs/UsageItem" }, "type": "array" }, { "type": "null" } ], "default": null, "description": "Usage metrics for the search request.", "title": "Usage" }, "warnings": { "anyOf": [ { "items": { "$ref": "#/$defs/Warning" }, "type": "array" }, { "type": "null" } ], "default": null, "description": "Warnings for the search request, if any.", "title": "Warnings" } }, "required": [ "search_id", "results", "session_id" ], "title": "V1SearchResponse", "type": "object" }, "annotations": { "destructiveHint": false, "idempotentHint": true, "openWorldHint": true, "readOnlyHint": true, "title": "Web search" } }, { "name": "web_fetch", "description": "Purpose: Fetch and extract relevant content\nfrom specific web URLs. Use only when web_search excerpts are insufficient\nfor the task at hand.\n\nIdeal Use Cases:\n- The user asked about a specific URL or page\n- You need exact wording or quotes that excerpts may have truncated\n- You need full-page analysis (long article, document, or page structure)\n- web_search excerpts are conflicting or clearly insufficient to answer\n\nFor multiple independent extraction objectives, make separate web_fetch calls\nconcurrently. Put related URLs that share one objective in a single call.\n", "inputSchema": { "properties": { "allow_live_fetch": { "default": true, "description": "Whether live fetching is allowed. Leave\ntrue for the freshest available content. Set false to use cached content only,\nwhich makes web_fetch much faster by avoiding the source website, but may return\nolder content.", "title": "Allow Live Fetch", "type": "boolean" }, "full_content": { "default": false, "description": "Prefer leaving this off. The default\nexcerpt mode returns LLM-optimized snippets focused on your objective — they\nare much smaller, cheaper, and usually all you need. Only set to true when\nyou explicitly need the entire page as markdown (e.g. reading a long article\nin full, or running a document through a downstream summarizer).\n\nWarning: enabling full content can return a large amount of content —\noften tens of thousands of tokens for a long article. This may exceed your\nMCP client's tool-output limit and will substantially increase response\nsize and latency.", "title": "Full Content", "type": "boolean" }, "model_name": { "description": "The identifier of the LLM model making this tool call (e.g. 'claude-opus-4.7', 'gpt-5.5', 'gemini-2.5-pro'). Before the first call, verify the exact active model slug from trusted runtime/session metadata or active client configuration. Pass the full slug verbatim; never shorten or substitute a model-family alias like 'gpt-5'. Used for product analytics only; does not affect search behavior.", "maxLength": 100, "type": "string" }, "objective": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null, "description": "Natural-language description of what\ninformation you're looking for from the URLs. Limit to 200 characters.", "title": "Objective" }, "search_queries": { "anyOf": [ { "items": { "type": "string" }, "type": "array" }, { "type": "null" } ], "default": null, "description": "Optional keyword search queries (3-6\nwords each) used together with objective to focus excerpts on the most\nrelevant content. Pass the queries from the prior web_search call that\nsurfaced these URLs, if applicable.", "title": "Search Queries" }, "session_id": { "description": "Stable identifier for the current conversation. Generate a random value (UUID or 32+ character hex string) at the start of your session and reuse the exact same value on every web_search / web_fetch call. Do NOT change it between turns. Used for free-tier rate limiting and correlating your tool calls in our logs; ignored on paid-tier keys.", "maxLength": 100, "type": "string" }, "urls": { "description": "List of URLs to extract content from. Must be\nvalid HTTP/HTTPS URLs. Up to 20 URLs per request.", "items": { "type": "string" }, "title": "Urls", "type": "array" } }, "required": [ "urls" ], "title": "v1_extract_toolArguments", "type": "object" }, "outputSchema": { "$defs": { "ExtractError": { "description": "Extract error details.", "properties": { "content": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "description": "Content returned for http client or server errors, if any.", "title": "Content" }, "error_type": { "description": "Error type.", "title": "Error Type", "type": "string" }, "http_status_code": { "anyOf": [ { "type": "integer" }, { "type": "null" } ], "description": "HTTP status code, if available.", "title": "Http Status Code" }, "url": { "title": "Url", "type": "string" } }, "required": [ "url", "error_type", "http_status_code", "content" ], "title": "ExtractError", "type": "object" }, "UsageItem": { "description": "Usage item for a single operation.", "properties": { "count": { "description": "Count of the SKU.", "examples": [ 1 ], "title": "Count", "type": "integer" }, "name": { "description": "Name of the SKU.", "examples": [ "sku_search", "sku_extract_excerpts" ], "title": "Name", "type": "string" } }, "required": [ "name", "count" ], "title": "UsageItem", "type": "object" }, "V1ExtractResult": { "description": "Extract result for a single URL.", "properties": { "acquired_at": { "anyOf": [ { "format": "date-time", "type": "string" }, { "type": "null" } ], "default": null, "description": "When the returned content was acquired, as an RFC 3339 timestamp truncated to the start of the UTC day. Null when unknown.", "examples": [ "2026-10-08T00:00:00Z" ], "title": "Acquired At" }, "excerpts": { "description": "Relevant excerpted content from the URL, formatted as markdown.", "items": { "type": "string" }, "title": "Excerpts", "type": "array" }, "full_content": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null, "description": "Full content from the URL formatted as markdown, if requested.", "title": "Full Content" }, "links": { "anyOf": [ { "items": { "type": "string" }, "type": "array" }, { "type": "null" } ], "default": null, "description": "Links from the page's rendered content, if requested: up to 512 unique absolute URLs in document order. Empty for pages with no links, including PDFs. Present only when advanced_settings.links was requested.", "title": "Links" }, "publish_date": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null, "description": "Publish date of the webpage in YYYY-MM-DD format, if available.", "title": "Publish Date" }, "title": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null, "description": "Title of the webpage, if available.", "title": "Title" }, "url": { "description": "URL associated with the search result.", "title": "Url", "type": "string" } }, "required": [ "url", "excerpts" ], "title": "V1ExtractResult", "type": "object" }, "Warning": { "description": "Human-readable message for a task.", "properties": { "detail": { "anyOf": [ { "additionalProperties": true, "type": "object" }, { "type": "null" } ], "default": null, "description": "Optional detail supporting the warning.", "title": "Detail" }, "message": { "description": "Human-readable message.", "title": "Message", "type": "string" }, "type": { "description": "Type of warning. Note that adding new warning types is considered a backward-compatible change.", "enum": [ "spec_validation_warning", "input_validation_warning", "warning" ], "examples": [ "spec_validation_warning", "input_validation_warning" ], "title": "Type", "type": "string" } }, "required": [ "type", "message" ], "title": "Warning", "type": "object" } }, "description": "Extract response.", "properties": { "errors": { "description": "Extract errors: requested URLs not in the results.", "items": { "$ref": "#/$defs/ExtractError" }, "title": "Errors", "type": "array" }, "extract_id": { "description": "Extract request ID, e.g. `extract_cad0a6d2dec046bd95ae900527d880e7`", "title": "Extract Id", "type": "string" }, "results": { "description": "Successful extract results.", "items": { "$ref": "#/$defs/V1ExtractResult" }, "title": "Results", "type": "array" }, "session_id": { "description": "Session identifier. Echoed back from the request if provided, otherwise generated by the server. Should be passed to future search and extract calls made by the agent as part of the same larger task.", "examples": [ "session_8a911eb27c7a4afaa20d0d9dc98d07c0" ], "title": "Session Id", "type": "string" }, "usage": { "anyOf": [ { "items": { "$ref": "#/$defs/UsageItem" }, "type": "array" }, { "type": "null" } ], "default": null, "description": "Usage metrics for the extract request.", "title": "Usage" }, "warnings": { "anyOf": [ { "items": { "$ref": "#/$defs/Warning" }, "type": "array" }, { "type": "null" } ], "default": null, "description": "Warnings for the extract request, if any.", "title": "Warnings" } }, "required": [ "extract_id", "results", "errors", "session_id" ], "title": "V1ExtractResponse", "type": "object" }, "annotations": { "destructiveHint": false, "idempotentHint": true, "openWorldHint": true, "readOnlyHint": true, "title": "Web fetch" } }, { "name": "send_feedback", "description": "Report a problem with Parallel to the Parallel team. Use it when, while\nworking with Parallel, you see any of these:\n- A Parallel tool returned an error you didn't cause: a 5xx, a timeout, or a\n rate limit you didn't expect.\n- Results were wrong, irrelevant, stale or missing something you know exists:\n a wrong date or number, an excerpt the page doesn't support, an empty fetch of\n a page that has content.\n- Parallel's docs, tool descriptions and behavior disagree, or you couldn't work\n out how to call a tool.\n- An evaluation, benchmark or comparison you ran shows Parallel doing worse than\n expected.\nProblems you worked around count too. It isn't for mistakes in your own\nrequests, or for questions.\n\nAsk the user first. When you tell them about the problem, offer to report it\nand show what you'd send: the message and the IDs. Send it only if they agree,\nthen tell them it was sent.\n\nPut the IDs involved (search_id, extract_id, run_id) in `examples`, with a\nshort note on each. web_decisions returns no ID: put the subject and the\nquestions it answered wrongly in `message`.\n\nParallel receives only the fields you fill in, plus the account and client the\nrequest came from; nothing else from your conversation. Leave out secrets and\npersonal data.\n", "inputSchema": { "$defs": { "FeedbackExample": { "properties": { "expected": { "anyOf": [ { "maxLength": 1000, "type": "string" }, { "type": "null" } ], "default": null, "description": "What you expected instead, such as a fact or URL Parallel missed.", "title": "Expected" }, "id": { "description": "ID of the Parallel request this example is about, such as a search_id, extract_id, task run_id, findall_id or monitor_id.", "maxLength": 128, "minLength": 1, "pattern": "^[A-Za-z0-9_-]+$", "title": "Id", "type": "string" }, "issue": { "anyOf": [ { "maxLength": 1000, "type": "string" }, { "type": "null" } ], "default": null, "description": "What was wrong with this result.", "title": "Issue" } }, "required": [ "id" ], "title": "FeedbackExample", "type": "object" } }, "additionalProperties": false, "properties": { "actual": { "anyOf": [ { "maxLength": 2000, "type": "string" }, { "type": "null" } ], "default": null, "description": "The overall observed behavior.", "title": "Actual" }, "category": { "description": "The kind of problem.", "enum": [ "results_quality", "error", "latency", "missing_capability", "docs", "billing", "other" ], "title": "Category", "type": "string" }, "examples": { "anyOf": [ { "items": { "$ref": "#/$defs/FeedbackExample" }, "maxItems": 50, "type": "array" }, { "type": "null" } ], "default": null, "description": "The specific requests involved, each with a short note.", "title": "Examples" }, "expected": { "anyOf": [ { "maxLength": 2000, "type": "string" }, { "type": "null" } ], "default": null, "description": "The overall expected behavior.", "title": "Expected" }, "message": { "description": "What you were doing, what went wrong, and what you expected. Do not include secrets or personal data.", "maxLength": 4000, "minLength": 20, "title": "Message", "type": "string" }, "product": { "description": "The Parallel product involved.", "enum": [ "search", "extract", "task", "findall", "monitor", "responses", "decisions", "mcp", "cli", "other" ], "title": "Product", "type": "string" }, "severity": { "default": "degraded", "description": "How much the problem affected the work: blocking, degraded (a workaround was needed) or minor (noticeable, but the work went on unchanged).", "enum": [ "blocking", "degraded", "minor" ], "title": "Severity", "type": "string" } }, "required": [ "message", "category", "product" ], "title": "send_feedback_toolArguments", "type": "object" }, "outputSchema": { "$defs": { "FeedbackReport": { "properties": { "actual": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null, "title": "Actual" }, "category": { "enum": [ "results_quality", "error", "latency", "missing_capability", "docs", "billing", "other" ], "title": "Category", "type": "string" }, "context": { "$ref": "#/$defs/FeedbackReportContext" }, "examples": { "items": { "$ref": "#/$defs/FeedbackReportExample" }, "title": "Examples", "type": "array" }, "expected": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null, "title": "Expected" }, "message": { "title": "Message", "type": "string" }, "product": { "enum": [ "search", "extract", "task", "findall", "monitor", "responses", "decisions", "mcp", "cli", "other" ], "title": "Product", "type": "string" }, "recipient": { "description": "Who receives the report and how long it is kept.", "title": "Recipient", "type": "string" }, "redactions": { "description": "How many secrets were removed.", "title": "Redactions", "type": "integer" }, "severity": { "enum": [ "blocking", "degraded", "minor" ], "title": "Severity", "type": "string" } }, "required": [ "message", "category", "product", "severity", "examples", "context", "redactions", "recipient" ], "title": "FeedbackReport", "type": "object" }, "FeedbackReportContext": { "properties": { "llm_model": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null, "title": "Llm Model" }, "org_id": { "title": "Org Id", "type": "string" }, "sender": { "description": "Who Parallel sees as the sender.", "title": "Sender", "type": "string" }, "session_id": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null, "title": "Session Id" }, "surface": { "description": "How the feedback was sent: api, cli, mcp or platform.", "enum": [ "api", "cli", "mcp", "platform" ], "title": "Surface", "type": "string" }, "user_agent": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null, "title": "User Agent" } }, "required": [ "org_id", "sender", "surface" ], "title": "FeedbackReportContext", "type": "object" }, "FeedbackReportExample": { "properties": { "expected": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null, "title": "Expected" }, "id": { "title": "Id", "type": "string" }, "issue": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null, "title": "Issue" } }, "required": [ "id" ], "title": "FeedbackReportExample", "type": "object" } }, "properties": { "duplicate": { "default": false, "description": "True when the same report was received in the last 24 hours; feedback_id is the original report and nothing new was stored.", "title": "Duplicate", "type": "boolean" }, "feedback_id": { "description": "ID of the stored report.", "title": "Feedback Id", "type": "string" }, "next_step": { "description": "What the agent should do next.", "title": "Next Step", "type": "string" }, "report": { "$ref": "#/$defs/FeedbackReport", "description": "Exactly what Parallel received, with secrets removed." }, "status": { "const": "received", "title": "Status", "type": "string" } }, "required": [ "status", "feedback_id", "report", "next_step" ], "title": "FeedbackResponse", "type": "object" }, "annotations": { "destructiveHint": false, "idempotentHint": false, "openWorldHint": false, "readOnlyHint": false, "title": "Send feedback to Parallel" } } ], "schemaTokens": 5322, "changedAt": "2026-11-07T01:46:44.757089899Z", "check": { "checker": "anchor-check/1.0", "totalTokens": 5322, "counts": { "error": 0, "note": 1, "warn": 3 }, "findings": [ { "rule": "TC15", "severity": "warn", "tool": "send_feedback", "message": "inputSchema uses $ref/$defs", "fix": "Inline the referenced schemas. Pydantic and zod-to-json-schema emit $defs for nested models; most can be told not to." }, { "rule": "TC22", "severity": "warn", "tool": "send_feedback", "message": "the definition is about 1,634 tokens", "fix": "Trim the description and parameter docs, or split the tool." }, { "rule": "TC22", "severity": "warn", "tool": "web_fetch", "message": "the definition is about 1,970 tokens", "fix": "Trim the description and parameter docs, or split the tool." }, { "rule": "TC29", "severity": "note", "message": "about 396 tokens (7% of the definitions) are titles that repeat property or function names", "fix": "Strip \"title\" keys that only restate a name before listing tools." } ] } }, "updatedAt": "2026-11-07T18:21:52.770771808Z" } }, "edges": [ { "by": 55, "category": "payments", "leads": "parallel-search-api", "name": "Payments \u0026 pricing", "reasons": { "a": "No x402, MPP or L402 (0). $14 per 1,000 transactions for Grounding with Bing Search and Custom Search, published on microsoft.com without a login (20). No free tier for Grounding with Bing, and an Azure subscription needs a card, as on the Azure Translator listing (0). A person signs up for Azure, creates a Foundry project and, for bing_grounding, a Bing resource (0).", "b": "Parallel runs a separate gateway at parallelmpp.dev that takes x402 (USDC on Base) and MPP (Stripe or Tempo) for search and extract at $0.01 and an ultra task at $0.30. Our unpaid POST to /api/search on 6 October returned 402 with an x402 v2 challenge for 10000 base units on eip155:8453 and a Tempo MPP challenge. Nothing on api.parallel.ai, and the gateway sells one price per endpoint with no mode choice, so partial (25). Per-unit prices published without login (20). Up to 5,000 free requests a month, $5 monthly credit and up to $80 at signup on the pricing page, which still doesn't say whether a card is needed (10). The hosted Search MCP works with no key, and the gateway needs only a wallet (20)." }, "scores": { "a": 20, "b": 75 } }, { "by": 34, "category": "security", "leads": "bing-grounding", "name": "Security \u0026 auth", "reasons": { "a": "Callers authenticate to the Foundry project with Microsoft Entra ID tokens and RBAC roles (Foundry User to run agents, Foundry Project Manager to add connections), with just-in-time Contributor through Entra PIM for provisioning. The Bing resource key sits in a project connection and the agent never holds it. No key in a URL (28 of 30). The tools only read. Custom Search confines grounding to configured public domains, and an admin can turn web search off for a whole subscription. There is no per-agent read-only toggle to set, since the tools have no write path (15 of 20). The web search page tells developers to treat web search results as untrusted input and to keep secrets and personal data out of prompts, and the tool best practices page says the same of all tool outputs. Raw results are not passed back to the caller (10 of 15). Run steps show each tool call and the Bing query sent, and Azure's activity log covers resource changes. No per-query audit log for Bing was found (10 of 15). Microsoft runs a coordinated vulnerability disclosure policy and bounty programmes through MSRC. microsoft.com's security.txt passed its Expires date on 23 September 2026 and still carries it on 6 November, and the Azure compliance attestations are not shown to cover a service whose data leaves the compliance boundary (16 of 20). 28 + 15 + 10 + 10 + 16 = 79.", "b": "API key in `x-api-key`. The Search MCP takes a Bearer key or OAuth at /mcp-oauth. We found no key scopes (20). Every Search and Extract action is a read, and Task tools live in a separate MCP server, so the search server is a read-only subset (15). Excerpts and fetched pages are untrusted web text, and the docs index has no prompt-injection guidance (0). No audit log found (0). The privacy policy shows a SOC 2 badge and links trust.parallel.ai, which rendered only its title to our reader on 6 October. security.txt is 404 on parallel.ai and docs.parallel.ai, and no bug bounty found (10)." }, "scores": { "a": 79, "b": 45 } }, { "by": 26, "category": "schema", "leads": "parallel-search-api", "name": "Schema \u0026 documentation", "reasons": { "a": "The tools are typed in the official SDKs (BingGroundingTool, BingCustomSearchPreviewTool, WebSearchTool) in Python, C#, JavaScript and Java, and the toolbox exposes web search as an MCP tool. No public OpenAPI description of the Responses tool types was confirmed from the pages read (10 of 25). Microsoft Learn serves each page as Markdown with `accept=text/markdown`, though learn.microsoft.com/llms.txt answers 404 (10). The pages say what each of four web grounding routes is for and when to choose it, when to use Custom Search instead, and not to ask the model to summarise a whole page (17 of 20). Parameters are typed with defaults and limits in prose, `count` 1 to 50 with default 5, freshness values and a date-range form, market and language formats, `search_context_size` low, medium or high (11 of 15). Examples in Python, C#, TypeScript, Java and REST with expected output, and troubleshooting tables for connection ID, authentication and 429 problems, but no error codes or bodies for the tools (10 of 15). Requests carry `api-version=v1` on the toolbox, SDK changelogs are dated and a monthly What's New page lists new articles, the latest for August 2026 (10 of 15). 10 + 10 + 17 + 11 + 10 + 10 = 68.", "b": "Public OpenAPI at docs.parallel.ai/public-openapi.json, linked from llms.txt (25). llms.txt and Markdown pages (10). A live `tools/list` on search.parallel.ai/mcp on 17 October and again on 1 November returned the two definitions, and the newer Parallel MCP server at mcp.parallel.ai adds `web_decisions`, whose description says when to use web_search instead. `web_search` states its purpose and ideal uses, and `web_fetch` says to use it \"only when web_search excerpts are insufficient\". The docs add that domain filters are hard filters that can cut quality. `web_search` has no when-not-to line of its own (17). Typed JSON Schema inputs with required fields and an output schema on both tools, `mode` is an enum in the API, and Task output schemas are JSON Schema. The MCP inputs carry no enums (12). The errors page lists each code with whether to retry and what to do, and 422s carry a structured `detail` (15). A dated changelog, newest entry 26 October 2026 (Decisions API) after 19 October (EU data residency), and beta headers retire on dated entries (15)." }, "scores": { "a": 68, "b": 94 } }, { "by": 26, "category": "ergonomics", "leads": "parallel-search-api", "name": "Agent ergonomics", "reasons": { "a": "Read as a server-side search tool inside an agent run. The tools return a model's answer with citations rather than raw results, and `search_context_size` sets how much context web search uses. A caller can't size or inspect the result set itself, since the Bing tools never return their output. Custom Search confines grounding to chosen domains without code (18 of 25). `count`, freshness, market and language filters, and domain restriction through Custom Search. No pagination or offset (13 of 20). Troubleshooting tables give causes and fixes for connection ID, RBAC and 429 problems, but the tools document no error codes (8 of 20). Searches only read, so a retry is safe apart from the per-transaction charge. No MCP annotations are documented for the toolbox's web search tool (10 of 20). The web_search route needs only a project, a model deployment and the Foundry User role. bing_grounding also needs a paid Bing resource and a project connection. SDKs in Python, C#, JavaScript and Java (12 of 15). Prompt caching gets no hits with the Bing tools, because they add a timestamp to every request. 18 + 13 + 8 + 10 + 12 = 61.", "b": "The Search MCP has two tools, about 5,700 characters of names, descriptions and input schemas on 1 November, and the Parallel MCP server lists three without a key (about 9,700 characters) and a fourth, `web_research`, after sign-in. `web_fetch` returns excerpts unless `full_content` is set, and the docs cap excerpts at roughly 25,000 characters a call and warn full pages can run to tens of thousands of tokens (25). Result counts, excerpt settings and source policies for domains and paths (18). The errors table gives each code a retry column and a resolution, with troubleshooting for 402 and 429 and a structured `detail` on 422 (20). Both Search MCP tools carry readOnlyHint true, destructiveHint false and idempotentHint true in the live `tools/list`, and searches are safe to repeat. There's still no idempotency key for Task creation, the SDKs retry creates on 429 and 5xx, and the Task MCP needs a key, so its annotations weren't read (14). Python and TypeScript SDKs, but `mode` defaults to advanced, the $5 per 1,000 tier, when you leave it out (10)." }, "scores": { "a": 61, "b": 87 } }, { "by": 7, "category": "reliability", "leads": "parallel-search-api", "name": "Reliability", "reasons": { "a": "Graded on the hosted lines, for the Foundry Agent Service tools agents call. Azure status page with post-incident reviews and a Foundry Agent Service component (20). The history page read on 6 November lists one review in the 90 days from 8 August that names Foundry Agent Service, intermittent failures and latency in Sweden Central from 10:03 to 15:58 UTC on 29 September 2026. It was one region and partial, and the review doesn't name Grounding with Bing, so minor only, the reading the Azure Translator listing got for the same review (20). The pricing page publishes 150 transactions a second and 1 million a day for each Grounding with Bing resource (15). The web search troubleshooting table says to answer 429 with exponential backoff and retries. No Retry-After or tool-specific overload guidance was found, and searches have no side effects (8 of 15). No SLA naming Grounding with Bing was found. The terms make it a First Party Consumption Service apart from the Online Services terms, and the Online Services SLA document wasn't opened (0). Grounding with Bing Custom Search is marked preview and Grounding with Bing Search is not, but no page read states general availability for it or for the web_search tool, and the .NET SDK is in preview (5 of 10). 20 + 20 + 15 + 8 + 0 + 5 = 68.", "b": "incident.io page at status.parallel.ai with Search, Task, Chat, Monitor, FindAll and Entity Search components and history (20). The feed, re-read on 1 November, has nothing after 13 October, so the 90 days from 3 August hold the same four incidents, all partial or degraded. Elevated 503s on 6 August, about an hour of Task API latency on 2 September, intermittent 4xx errors on 7 September, and transient 502s from the network gateway on 13 October, degraded performance from 01:23 to 01:43 UTC. Most have no duration listed (20). Published limits, 600 a minute for Search, Image Search, Extract, Decisions and Entity Search, 2,000 for Tasks, 300 for Chat and Monitor (15). The errors page marks 429 as retryable with exponential backoff, but there's no `Retry-After` and no idempotency guidance for creating Task runs, which the SDKs retry twice by default (10). No SLA found (0). Search, Extract and Task are GA (10)." }, "scores": { "a": 68, "b": 75 } }, { "by": 7, "category": "maintenance", "leads": "parallel-search-api", "name": "Maintenance \u0026 community", "reasons": { "a": "Read as a closed service with official SDKs, as the other Azure listings are. The web search page was updated on 2 November 2026 and the Bing tools page on 12 October, and azure-ai-projects 2.10.0 shipped on PyPI and npm on 30 October 2026, the SDK that carries the tool types (30). azure-ai-projects released 2.6.0 (4 September), 2.6.1, 2.7.0, 2.8.0 (5 October), 2.9.0 (17 October) and 2.10.0 in the 90 days from 8 August. Their changelogs weren't read for web search changes, so they count as SDK releases (20). Microsoft Learn feedback, Microsoft Q\u0026A and the Azure SDK issue trackers, whose reply times weren't sampled (10 of 15). Current official SDKs in Python, JavaScript, .NET and Java, the .NET one in preview (15). The SDKs live in the azure-sdk monorepos and CI wasn't checked (5 of 10). 30 + 20 + 10 + 15 + 5 = 80.", "b": "parallel-web 1.3.7 for Python on 2026-10-23 and for TypeScript on 2026-10-28, and changelog entries on 19 and 26 October, the second launching the Decisions API (30). Counted from the tags and the changelog, the 90 days from 3 August hold Python SDK releases 1.3.1 to 1.3.7, TypeScript 1.3.1 to 1.3.7 and ten changelog entries from 19 August to 26 October (20). The SDK releases since 1.3.5 are dependency bumps. Closed service with a changelog and support@parallel.ai. We didn't test whether support answers (12). Current Python and TypeScript SDKs, and ai.parallel/search-mcp and ai.parallel/task-mcp in the official registry (15). The Python SDK runs lint and build in CI on push, plus a workflow that detects breaking changes (10)." }, "scores": { "a": 80, "b": 87 } } ], "facts": [ { "a": "HTTP API", "b": "HTTP API", "name": "Kind" }, { "a": "Microsoft", "b": "Parallel Web Systems", "name": "Vendor" }, { "a": "https://{account}.services.ai.azure.com/api/projects/{project}/openai/v1/responses", "b": "https://api.parallel.ai/v1/search", "name": "Hosted endpoint" }, { "a": "Streamable HTTP", "b": "HTTP, Streamable HTTP", "name": "Transports" }, { "a": "OAuth", "b": "OAuth or key", "name": "Auth" }, { "a": "Pay per use", "b": "Freemium", "name": "Pricing" }, { "a": "$14 per 1,000 requests", "b": "$1 per 1,000 requests", "name": "Price for web search" }, { "a": "no", "b": "payer tooling only", "name": "x402" }, { "a": "Proprietary service under the customer's Microsoft agreement and the separate Grounding with Bing terms of use, which exclude it from the Microsoft Data Protection Addendum", "b": "none", "name": "Licence" }, { "a": "3", "b": "6", "name": "Tools exposed" }, { "a": "no", "b": "yes", "name": "Read-only variant documented" }, { "a": "no", "b": "yes", "name": "llms.txt" }, { "a": "not listed", "b": "ai.parallel/search-mcp", "name": "MCP registry" }, { "a": "2026-11-02", "b": "2026-10-28", "name": "Last release" }, { "a": "2025-11-01", "b": "2026-10-17", "name": "Terms last updated" }, { "a": "2026-09-01", "b": "2026-08-11", "name": "Privacy policy last updated" }, { "a": "yes", "b": "yes", "name": "Customer content may train models" }, { "a": "yes", "b": "not found in the text", "name": "Terms restrict automated access" }, { "a": "not found in the text", "b": "not found in the text", "name": "Terms restrict benchmarking" }, { "a": "not found in the text", "b": "not found in the text", "name": "Terms or service can change without notice" }, { "a": "not found in the text", "b": "not found in the text", "name": "Arbitration or class-action waiver" }, { "a": "none", "b": "28 stars, 250k npm/wk, 994k PyPI/wk", "name": "Popularity" }, { "a": "none", "b": "3.6/5 (8)", "name": "Agent reviews" } ], "faq": [ { "answer": "Parallel Search and Task APIs scores 75 (BB) on agent readiness against Grounding with Bing Search's 63.7 (B), and leads in 5 of 7 scored categories. Grounding with Bing Search leads on security \u0026 auth.", "question": "Which is better for AI agents, Grounding with Bing Search or Parallel Search and Task APIs?" }, { "answer": "Parallel Search and Task APIs, at $1 per 1,000 requests against $14 per 1,000 requests for Grounding with Bing Search. These are the vendors' published prices for the job.", "question": "Which is cheaper for web search, Grounding with Bing Search or Parallel Search and Task APIs?" }, { "answer": "Grounding with Bing Search uses an OAuth sign-in. Parallel Search and Task APIs takes an API key or an OAuth sign-in.", "question": "Do Grounding with Bing Search and Parallel Search and Task APIs need an API key?" }, { "answer": "Yes. Grounding with Bing Search has a hosted endpoint at https://{account}.services.ai.azure.com/api/projects/{project}/openai/v1/responses and Parallel Search and Task APIs at https://api.parallel.ai/v1/search.", "question": "Can an agent call Grounding with Bing Search and Parallel Search and Task APIs without installing anything?" } ], "goodFor": [ { "aheadOn": [ "Security \u0026 auth, 79 against 45" ], "also": null, "goodFor": "Teams already building on Foundry Agent Service who want cited answers from Bing without handling a search key.", "slug": "bing-grounding", "watchFor": "The Bing tools never return raw results to developers, only a model-written answer with citation links" }, { "aheadOn": [ "Reliability, 75 against 68", "Schema \u0026 documentation, 94 against 68", "Agent ergonomics, 87 against 61", "Payments \u0026 pricing, 75 against 20", "Maintenance \u0026 community, 87 against 80" ], "also": [ "Cheaper for web search, $1 against $14 per 1,000 requests", "Agent-ready, a grade of BB or better" ], "goodFor": "Agents that mix quick search with long research or enrichment jobs and want one vendor and one bill.", "slug": "parallel-search-api", "watchFor": "Search defaults to advanced mode at $5 per 1,000 when `mode` is left out" } ], "history": { "bing-grounding": null, "parallel-search-api": [ { "causes": [ "method" ], "date": "2026-10-30", "delta": -0.1, "from": 75.1, "fromGrade": "BB", "to": 75, "toGrade": "BB" }, { "causes": [ "method" ], "date": "2026-10-27", "delta": 0.1, "from": 75, "fromGrade": "BB", "to": 75.1, "toGrade": "BB" }, { "causes": [ "evidence" ], "date": "2026-10-17", "delta": 1, "from": 74, "fromGrade": "BB", "to": 75, "toGrade": "BB" } ] }, "job": { "capability": "web.search", "name": "Web search" }, "others": [ { "json": "https://www.anchorterminal.com/compare/agentcore-web-search-vs-bing-grounding.json", "title": "Web Search Tool on Amazon Bedrock AgentCore vs Grounding with Bing Search", "url": "https://www.anchorterminal.com/compare/agentcore-web-search-vs-bing-grounding" }, { "json": "https://www.anchorterminal.com/compare/agentcore-web-search-vs-parallel-search-api.json", "title": "Web Search Tool on Amazon Bedrock AgentCore vs Parallel Search and Task APIs", "url": "https://www.anchorterminal.com/compare/agentcore-web-search-vs-parallel-search-api" }, { "json": "https://www.anchorterminal.com/compare/arcmira-vs-bing-grounding.json", "title": "Arcmira vs Grounding with Bing Search", "url": "https://www.anchorterminal.com/compare/arcmira-vs-bing-grounding" }, { "json": "https://www.anchorterminal.com/compare/bing-grounding-vs-brave-search-mcp.json", "title": "Grounding with Bing Search vs Brave Search API + MCP", "url": "https://www.anchorterminal.com/compare/bing-grounding-vs-brave-search-mcp" }, { "json": "https://www.anchorterminal.com/compare/bing-grounding-vs-cloudflare-web-search.json", "title": "Grounding with Bing Search vs Cloudflare Web Search API", "url": "https://www.anchorterminal.com/compare/bing-grounding-vs-cloudflare-web-search" }, { "json": "https://www.anchorterminal.com/compare/bing-grounding-vs-deepseek-search-api.json", "title": "Grounding with Bing Search vs DeepSeek Search and Fetch API", "url": "https://www.anchorterminal.com/compare/bing-grounding-vs-deepseek-search-api" }, { "json": "https://www.anchorterminal.com/compare/bing-grounding-vs-exa-mcp.json", "title": "Grounding with Bing Search vs Exa API + MCP", "url": "https://www.anchorterminal.com/compare/bing-grounding-vs-exa-mcp" }, { "json": "https://www.anchorterminal.com/compare/bing-grounding-vs-firecrawl-mcp.json", "title": "Grounding with Bing Search vs Firecrawl MCP", "url": "https://www.anchorterminal.com/compare/bing-grounding-vs-firecrawl-mcp" }, { "json": "https://www.anchorterminal.com/compare/bing-grounding-vs-kagi-search.json", "title": "Grounding with Bing Search vs Kagi Search API", "url": "https://www.anchorterminal.com/compare/bing-grounding-vs-kagi-search" }, { "json": "https://www.anchorterminal.com/compare/bing-grounding-vs-linkup.json", "title": "Grounding with Bing Search vs Linkup", "url": "https://www.anchorterminal.com/compare/bing-grounding-vs-linkup" }, { "json": "https://www.anchorterminal.com/compare/bing-grounding-vs-mojeek.json", "title": "Grounding with Bing Search vs Mojeek Web Search API", "url": "https://www.anchorterminal.com/compare/bing-grounding-vs-mojeek" }, { "json": "https://www.anchorterminal.com/compare/bing-grounding-vs-newscatcher.json", "title": "Grounding with Bing Search vs NewsCatcher", "url": "https://www.anchorterminal.com/compare/bing-grounding-vs-newscatcher" }, { "json": "https://www.anchorterminal.com/compare/bing-grounding-vs-perplexity-search-api.json", "title": "Grounding with Bing Search vs Perplexity Search API", "url": "https://www.anchorterminal.com/compare/bing-grounding-vs-perplexity-search-api" }, { "json": "https://www.anchorterminal.com/compare/bing-grounding-vs-searchapi-io.json", "title": "Grounding with Bing Search vs SearchAPI.io", "url": "https://www.anchorterminal.com/compare/bing-grounding-vs-searchapi-io" }, { "json": "https://www.anchorterminal.com/compare/bing-grounding-vs-serpapi.json", "title": "Grounding with Bing Search vs SerpApi", "url": "https://www.anchorterminal.com/compare/bing-grounding-vs-serpapi" }, { "json": "https://www.anchorterminal.com/compare/bing-grounding-vs-serper.json", "title": "Grounding with Bing Search vs Serper", "url": "https://www.anchorterminal.com/compare/bing-grounding-vs-serper" }, { "json": "https://www.anchorterminal.com/compare/bing-grounding-vs-serphouse.json", "title": "Grounding with Bing Search vs SERPHouse", "url": "https://www.anchorterminal.com/compare/bing-grounding-vs-serphouse" }, { "json": "https://www.anchorterminal.com/compare/bing-grounding-vs-serpkite.json", "title": "Grounding with Bing Search vs SerpKite", "url": "https://www.anchorterminal.com/compare/bing-grounding-vs-serpkite" }, { "json": "https://www.anchorterminal.com/compare/bing-grounding-vs-specstream.json", "title": "Grounding with Bing Search vs SpecStream", "url": "https://www.anchorterminal.com/compare/bing-grounding-vs-specstream" }, { "json": "https://www.anchorterminal.com/compare/bing-grounding-vs-tavily-mcp.json", "title": "Grounding with Bing Search vs Tavily API + MCP", "url": "https://www.anchorterminal.com/compare/bing-grounding-vs-tavily-mcp" }, { "json": "https://www.anchorterminal.com/compare/bing-grounding-vs-tinyfish-search.json", "title": "Grounding with Bing Search vs TinyFish Search", "url": "https://www.anchorterminal.com/compare/bing-grounding-vs-tinyfish-search" }, { "json": "https://www.anchorterminal.com/compare/bing-grounding-vs-valyu.json", "title": "Grounding with Bing Search vs Valyu", "url": "https://www.anchorterminal.com/compare/bing-grounding-vs-valyu" }, { "json": "https://www.anchorterminal.com/compare/bing-grounding-vs-you-com-api.json", "title": "Grounding with Bing Search vs You.com APIs", "url": "https://www.anchorterminal.com/compare/bing-grounding-vs-you-com-api" }, { "json": "https://www.anchorterminal.com/compare/brave-search-mcp-vs-parallel-search-api.json", "title": "Brave Search API + MCP vs Parallel Search and Task APIs", "url": "https://www.anchorterminal.com/compare/brave-search-mcp-vs-parallel-search-api" }, { "json": "https://www.anchorterminal.com/compare/cloudflare-web-search-vs-parallel-search-api.json", "title": "Cloudflare Web Search API vs Parallel Search and Task APIs", "url": "https://www.anchorterminal.com/compare/cloudflare-web-search-vs-parallel-search-api" }, { "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/exa-mcp-vs-parallel-search-api.json", "title": "Exa API + MCP vs Parallel Search and Task APIs", "url": "https://www.anchorterminal.com/compare/exa-mcp-vs-parallel-search-api" }, { "json": "https://www.anchorterminal.com/compare/firecrawl-mcp-vs-parallel-search-api.json", "title": "Firecrawl MCP vs Parallel Search and Task APIs", "url": "https://www.anchorterminal.com/compare/firecrawl-mcp-vs-parallel-search-api" }, { "json": "https://www.anchorterminal.com/compare/kagi-search-vs-parallel-search-api.json", "title": "Kagi Search API vs Parallel Search and Task APIs", "url": "https://www.anchorterminal.com/compare/kagi-search-vs-parallel-search-api" }, { "json": "https://www.anchorterminal.com/compare/linkup-vs-parallel-search-api.json", "title": "Linkup vs Parallel Search and Task APIs", "url": "https://www.anchorterminal.com/compare/linkup-vs-parallel-search-api" }, { "json": "https://www.anchorterminal.com/compare/mojeek-vs-parallel-search-api.json", "title": "Mojeek Web Search API vs Parallel Search and Task APIs", "url": "https://www.anchorterminal.com/compare/mojeek-vs-parallel-search-api" }, { "json": "https://www.anchorterminal.com/compare/newscatcher-vs-parallel-search-api.json", "title": "NewsCatcher vs Parallel Search and Task APIs", "url": "https://www.anchorterminal.com/compare/newscatcher-vs-parallel-search-api" }, { "json": "https://www.anchorterminal.com/compare/parallel-search-api-vs-perplexity-search-api.json", "title": "Parallel Search and Task APIs vs Perplexity Search API", "url": "https://www.anchorterminal.com/compare/parallel-search-api-vs-perplexity-search-api" }, { "json": "https://www.anchorterminal.com/compare/parallel-search-api-vs-searchapi-io.json", "title": "Parallel Search and Task APIs vs SearchAPI.io", "url": "https://www.anchorterminal.com/compare/parallel-search-api-vs-searchapi-io" }, { "json": "https://www.anchorterminal.com/compare/parallel-search-api-vs-serpapi.json", "title": "Parallel Search and Task APIs vs SerpApi", "url": "https://www.anchorterminal.com/compare/parallel-search-api-vs-serpapi" }, { "json": "https://www.anchorterminal.com/compare/parallel-search-api-vs-serper.json", "title": "Parallel Search and Task APIs vs Serper", "url": "https://www.anchorterminal.com/compare/parallel-search-api-vs-serper" }, { "json": "https://www.anchorterminal.com/compare/parallel-search-api-vs-serphouse.json", "title": "Parallel Search and Task APIs vs SERPHouse", "url": "https://www.anchorterminal.com/compare/parallel-search-api-vs-serphouse" }, { "json": "https://www.anchorterminal.com/compare/parallel-search-api-vs-serpkite.json", "title": "Parallel Search and Task APIs vs SerpKite", "url": "https://www.anchorterminal.com/compare/parallel-search-api-vs-serpkite" }, { "json": "https://www.anchorterminal.com/compare/parallel-search-api-vs-specstream.json", "title": "Parallel Search and Task APIs vs SpecStream", "url": "https://www.anchorterminal.com/compare/parallel-search-api-vs-specstream" }, { "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/parallel-search-api-vs-tinyfish-search.json", "title": "Parallel Search and Task APIs vs TinyFish Search", "url": "https://www.anchorterminal.com/compare/parallel-search-api-vs-tinyfish-search" }, { "json": "https://www.anchorterminal.com/compare/parallel-search-api-vs-valyu.json", "title": "Parallel Search and Task APIs vs Valyu", "url": "https://www.anchorterminal.com/compare/parallel-search-api-vs-valyu" }, { "json": "https://www.anchorterminal.com/compare/parallel-search-api-vs-you-com-api.json", "title": "Parallel Search and Task APIs vs You.com APIs", "url": "https://www.anchorterminal.com/compare/parallel-search-api-vs-you-com-api" }, { "json": "https://www.anchorterminal.com/compare/arcmira-vs-parallel-search-api.json", "title": "Arcmira vs Parallel Search and Task APIs", "url": "https://www.anchorterminal.com/compare/arcmira-vs-parallel-search-api" }, { "json": "https://www.anchorterminal.com/compare/grep-ai-vs-parallel-search-api.json", "title": "Grep AI vs Parallel Search and Task APIs", "url": "https://www.anchorterminal.com/compare/grep-ai-vs-parallel-search-api" }, { "json": "https://www.anchorterminal.com/compare/fetch-reference-server-vs-parallel-search-api.json", "title": "Fetch (MCP reference server) vs Parallel Search and Task APIs", "url": "https://www.anchorterminal.com/compare/fetch-reference-server-vs-parallel-search-api" }, { "json": "https://www.anchorterminal.com/compare/bing-grounding-vs-grep-ai.json", "title": "Grounding with Bing Search vs Grep AI", "url": "https://www.anchorterminal.com/compare/bing-grounding-vs-grep-ai" } ], "panel": null, "scores": [ { "bing-grounding": 68, "by": 7, "edge": "parallel-search-api", "key": "reliability", "name": "Reliability", "parallel-search-api": 75, "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "bing-grounding": 68, "by": 26, "edge": "parallel-search-api", "key": "schema", "name": "Schema \u0026 documentation", "parallel-search-api": 94, "weight": 13 }, { "bing-grounding": 61, "by": 26, "edge": "parallel-search-api", "key": "ergonomics", "name": "Agent ergonomics", "parallel-search-api": 87, "weight": 13 }, { "bing-grounding": 79, "by": 34, "edge": "bing-grounding", "key": "security", "name": "Security \u0026 auth", "parallel-search-api": 45, "weight": 14 }, { "bing-grounding": 20, "by": 55, "edge": "parallel-search-api", "key": "payments", "name": "Payments \u0026 pricing", "parallel-search-api": 75, "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "bing-grounding": 80, "by": 7, "edge": "parallel-search-api", "key": "maintenance", "name": "Maintenance \u0026 community", "parallel-search-api": 87, "weight": 7 }, { "bing-grounding": 66, "by": 1, "edge": "bing-grounding", "key": "transparency", "name": "Transparency \u0026 trust", "parallel-search-api": 65, "weight": 7 } ], "summary": "Parallel Search and Task APIs scores 75 (BB) on agent readiness against Grounding with Bing Search's 63.7 (B), and leads in 5 of 7 scored categories. Grounding with Bing Search leads on security \u0026 auth. Both do web search. Parallel Search and Task APIs is cheaper for web search, $1 against $14 per 1,000 requests.", "tasks": null, "tutorials": [], "verdicts": { "bing-grounding": "First-party Bing grounding inside Foundry Agent Service, called with Entra ID so the agent never holds a search key, at a published $14 per 1,000 transactions. The tools return a model's answer with citations, never the raw results, and data sent to them falls outside Microsoft's Data Protection Addendum and Azure's compliance boundary.", "parallel-search-api": "Fast-mode search at $1 per 1,000 with 10 excerpted results, and a keyless two-tool Search MCP annotated read-only. Search defaults to advanced mode at $5 per 1,000 when `mode` is left out, and the Customer Terms allow training on inputs and outputs." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/bing-grounding-vs-parallel-search-api", "json": "https://www.anchorterminal.com/compare/bing-grounding-vs-parallel-search-api.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/bing-grounding-vs-parallel-search-api.md", "mcp": "https://www.anchorterminal.com/mcp", "slim": "https://www.anchorterminal.com/compare/bing-grounding-vs-parallel-search-api.min.md" }, "markdown": "Parallel Search and Task APIs scores 75 (BB) on agent readiness against Grounding with Bing Search's 63.7 (B), and leads in 5 of 7 scored categories. Grounding with Bing Search leads on security \u0026 auth. Both do web search. Parallel Search and Task APIs is cheaper for web search, $1 against $14 per 1,000 requests.\n\n- Grounding with Bing Search: grade B, 63.7/100, rank #502 of 1486. Markdown https://www.anchorterminal.com/tools/bing-grounding.md · JSON https://www.anchorterminal.com/api/v1/tools/bing-grounding.json\n- Parallel Search and Task APIs: grade BB, 75/100, rank #73 of 1486. Markdown https://www.anchorterminal.com/tools/parallel-search-api.md · JSON https://www.anchorterminal.com/api/v1/tools/parallel-search-api.json\n- Best web search APIs for AI agents: https://www.anchorterminal.com/best/search/index.md\n- All 308 search comparisons: https://www.anchorterminal.com/compare/search/index.md\n\n## Which one, for what\n\n### Grounding with Bing Search (B)\n\nGood for: Teams already building on Foundry Agent Service who want cited answers from Bing without handling a search key.\n\nAhead on:\n- Security \u0026 auth, 79 against 45\n\nWatch for: The Bing tools never return raw results to developers, only a model-written answer with citation links\n\n### Parallel Search and Task APIs (BB)\n\nGood for: Agents that mix quick search with long research or enrichment jobs and want one vendor and one bill.\n\nAhead on:\n- Reliability, 75 against 68\n- Schema \u0026 documentation, 94 against 68\n- Agent ergonomics, 87 against 61\n- Payments \u0026 pricing, 75 against 20\n- Maintenance \u0026 community, 87 against 80\n\nAlso in its favour:\n- Cheaper for web search, $1 against $14 per 1,000 requests\n- Agent-ready, a grade of BB or better\n\nWatch for: Search defaults to advanced mode at $5 per 1,000 when `mode` is left out\n\n\n## Why the edge\n\n### Payments \u0026 pricing: Parallel Search and Task APIs +55\n\n- Grounding with Bing Search (20): No x402, MPP or L402 (0). $14 per 1,000 transactions for Grounding with Bing Search and Custom Search, published on microsoft.com without a login (20). No free tier for Grounding with Bing, and an Azure subscription needs a card, as on the Azure Translator listing (0). A person signs up for Azure, creates a Foundry project and, for bing_grounding, a Bing resource (0).\n- Parallel Search and Task APIs (75): Parallel runs a separate gateway at parallelmpp.dev that takes x402 (USDC on Base) and MPP (Stripe or Tempo) for search and extract at $0.01 and an ultra task at $0.30. Our unpaid POST to /api/search on 6 October returned 402 with an x402 v2 challenge for 10000 base units on eip155:8453 and a Tempo MPP challenge. Nothing on api.parallel.ai, and the gateway sells one price per endpoint with no mode choice, so partial (25). Per-unit prices published without login (20). Up to 5,000 free requests a month, $5 monthly credit and up to $80 at signup on the pricing page, which still doesn't say whether a card is needed (10). The hosted Search MCP works with no key, and the gateway needs only a wallet (20).\n\n### Security \u0026 auth: Grounding with Bing Search +34\n\n- Grounding with Bing Search (79): Callers authenticate to the Foundry project with Microsoft Entra ID tokens and RBAC roles (Foundry User to run agents, Foundry Project Manager to add connections), with just-in-time Contributor through Entra PIM for provisioning. The Bing resource key sits in a project connection and the agent never holds it. No key in a URL (28 of 30). The tools only read. Custom Search confines grounding to configured public domains, and an admin can turn web search off for a whole subscription. There is no per-agent read-only toggle to set, since the tools have no write path (15 of 20). The web search page tells developers to treat web search results as untrusted input and to keep secrets and personal data out of prompts, and the tool best practices page says the same of all tool outputs. Raw results are not passed back to the caller (10 of 15). Run steps show each tool call and the Bing query sent, and Azure's activity log covers resource changes. No per-query audit log for Bing was found (10 of 15). Microsoft runs a coordinated vulnerability disclosure policy and bounty programmes through MSRC. microsoft.com's security.txt passed its Expires date on 23 September 2026 and still carries it on 6 November, and the Azure compliance attestations are not shown to cover a service whose data leaves the compliance boundary (16 of 20). 28 + 15 + 10 + 10 + 16 = 79.\n- Parallel Search and Task APIs (45): API key in `x-api-key`. The Search MCP takes a Bearer key or OAuth at /mcp-oauth. We found no key scopes (20). Every Search and Extract action is a read, and Task tools live in a separate MCP server, so the search server is a read-only subset (15). Excerpts and fetched pages are untrusted web text, and the docs index has no prompt-injection guidance (0). No audit log found (0). The privacy policy shows a SOC 2 badge and links trust.parallel.ai, which rendered only its title to our reader on 6 October. security.txt is 404 on parallel.ai and docs.parallel.ai, and no bug bounty found (10).\n\n### Schema \u0026 documentation: Parallel Search and Task APIs +26\n\n- Grounding with Bing Search (68): The tools are typed in the official SDKs (BingGroundingTool, BingCustomSearchPreviewTool, WebSearchTool) in Python, C#, JavaScript and Java, and the toolbox exposes web search as an MCP tool. No public OpenAPI description of the Responses tool types was confirmed from the pages read (10 of 25). Microsoft Learn serves each page as Markdown with `accept=text/markdown`, though learn.microsoft.com/llms.txt answers 404 (10). The pages say what each of four web grounding routes is for and when to choose it, when to use Custom Search instead, and not to ask the model to summarise a whole page (17 of 20). Parameters are typed with defaults and limits in prose, `count` 1 to 50 with default 5, freshness values and a date-range form, market and language formats, `search_context_size` low, medium or high (11 of 15). Examples in Python, C#, TypeScript, Java and REST with expected output, and troubleshooting tables for connection ID, authentication and 429 problems, but no error codes or bodies for the tools (10 of 15). Requests carry `api-version=v1` on the toolbox, SDK changelogs are dated and a monthly What's New page lists new articles, the latest for August 2026 (10 of 15). 10 + 10 + 17 + 11 + 10 + 10 = 68.\n- Parallel Search and Task APIs (94): Public OpenAPI at docs.parallel.ai/public-openapi.json, linked from llms.txt (25). llms.txt and Markdown pages (10). A live `tools/list` on search.parallel.ai/mcp on 17 October and again on 1 November returned the two definitions, and the newer Parallel MCP server at mcp.parallel.ai adds `web_decisions`, whose description says when to use web_search instead. `web_search` states its purpose and ideal uses, and `web_fetch` says to use it \"only when web_search excerpts are insufficient\". The docs add that domain filters are hard filters that can cut quality. `web_search` has no when-not-to line of its own (17). Typed JSON Schema inputs with required fields and an output schema on both tools, `mode` is an enum in the API, and Task output schemas are JSON Schema. The MCP inputs carry no enums (12). The errors page lists each code with whether to retry and what to do, and 422s carry a structured `detail` (15). A dated changelog, newest entry 26 October 2026 (Decisions API) after 19 October (EU data residency), and beta headers retire on dated entries (15).\n\n### Agent ergonomics: Parallel Search and Task APIs +26\n\n- Grounding with Bing Search (61): Read as a server-side search tool inside an agent run. The tools return a model's answer with citations rather than raw results, and `search_context_size` sets how much context web search uses. A caller can't size or inspect the result set itself, since the Bing tools never return their output. Custom Search confines grounding to chosen domains without code (18 of 25). `count`, freshness, market and language filters, and domain restriction through Custom Search. No pagination or offset (13 of 20). Troubleshooting tables give causes and fixes for connection ID, RBAC and 429 problems, but the tools document no error codes (8 of 20). Searches only read, so a retry is safe apart from the per-transaction charge. No MCP annotations are documented for the toolbox's web search tool (10 of 20). The web_search route needs only a project, a model deployment and the Foundry User role. bing_grounding also needs a paid Bing resource and a project connection. SDKs in Python, C#, JavaScript and Java (12 of 15). Prompt caching gets no hits with the Bing tools, because they add a timestamp to every request. 18 + 13 + 8 + 10 + 12 = 61.\n- Parallel Search and Task APIs (87): The Search MCP has two tools, about 5,700 characters of names, descriptions and input schemas on 1 November, and the Parallel MCP server lists three without a key (about 9,700 characters) and a fourth, `web_research`, after sign-in. `web_fetch` returns excerpts unless `full_content` is set, and the docs cap excerpts at roughly 25,000 characters a call and warn full pages can run to tens of thousands of tokens (25). Result counts, excerpt settings and source policies for domains and paths (18). The errors table gives each code a retry column and a resolution, with troubleshooting for 402 and 429 and a structured `detail` on 422 (20). Both Search MCP tools carry readOnlyHint true, destructiveHint false and idempotentHint true in the live `tools/list`, and searches are safe to repeat. There's still no idempotency key for Task creation, the SDKs retry creates on 429 and 5xx, and the Task MCP needs a key, so its annotations weren't read (14). Python and TypeScript SDKs, but `mode` defaults to advanced, the $5 per 1,000 tier, when you leave it out (10).\n\n### Reliability: Parallel Search and Task APIs +7\n\n- Grounding with Bing Search (68): Graded on the hosted lines, for the Foundry Agent Service tools agents call. Azure status page with post-incident reviews and a Foundry Agent Service component (20). The history page read on 6 November lists one review in the 90 days from 8 August that names Foundry Agent Service, intermittent failures and latency in Sweden Central from 10:03 to 15:58 UTC on 29 September 2026. It was one region and partial, and the review doesn't name Grounding with Bing, so minor only, the reading the Azure Translator listing got for the same review (20). The pricing page publishes 150 transactions a second and 1 million a day for each Grounding with Bing resource (15). The web search troubleshooting table says to answer 429 with exponential backoff and retries. No Retry-After or tool-specific overload guidance was found, and searches have no side effects (8 of 15). No SLA naming Grounding with Bing was found. The terms make it a First Party Consumption Service apart from the Online Services terms, and the Online Services SLA document wasn't opened (0). Grounding with Bing Custom Search is marked preview and Grounding with Bing Search is not, but no page read states general availability for it or for the web_search tool, and the .NET SDK is in preview (5 of 10). 20 + 20 + 15 + 8 + 0 + 5 = 68.\n- Parallel Search and Task APIs (75): incident.io page at status.parallel.ai with Search, Task, Chat, Monitor, FindAll and Entity Search components and history (20). The feed, re-read on 1 November, has nothing after 13 October, so the 90 days from 3 August hold the same four incidents, all partial or degraded. Elevated 503s on 6 August, about an hour of Task API latency on 2 September, intermittent 4xx errors on 7 September, and transient 502s from the network gateway on 13 October, degraded performance from 01:23 to 01:43 UTC. Most have no duration listed (20). Published limits, 600 a minute for Search, Image Search, Extract, Decisions and Entity Search, 2,000 for Tasks, 300 for Chat and Monitor (15). The errors page marks 429 as retryable with exponential backoff, but there's no `Retry-After` and no idempotency guidance for creating Task runs, which the SDKs retry twice by default (10). No SLA found (0). Search, Extract and Task are GA (10).\n\n### Maintenance \u0026 community: Parallel Search and Task APIs +7\n\n- Grounding with Bing Search (80): Read as a closed service with official SDKs, as the other Azure listings are. The web search page was updated on 2 November 2026 and the Bing tools page on 12 October, and azure-ai-projects 2.10.0 shipped on PyPI and npm on 30 October 2026, the SDK that carries the tool types (30). azure-ai-projects released 2.6.0 (4 September), 2.6.1, 2.7.0, 2.8.0 (5 October), 2.9.0 (17 October) and 2.10.0 in the 90 days from 8 August. Their changelogs weren't read for web search changes, so they count as SDK releases (20). Microsoft Learn feedback, Microsoft Q\u0026A and the Azure SDK issue trackers, whose reply times weren't sampled (10 of 15). Current official SDKs in Python, JavaScript, .NET and Java, the .NET one in preview (15). The SDKs live in the azure-sdk monorepos and CI wasn't checked (5 of 10). 30 + 20 + 10 + 15 + 5 = 80.\n- Parallel Search and Task APIs (87): parallel-web 1.3.7 for Python on 2026-10-23 and for TypeScript on 2026-10-28, and changelog entries on 19 and 26 October, the second launching the Decisions API (30). Counted from the tags and the changelog, the 90 days from 3 August hold Python SDK releases 1.3.1 to 1.3.7, TypeScript 1.3.1 to 1.3.7 and ten changelog entries from 19 August to 26 October (20). The SDK releases since 1.3.5 are dependency bumps. Closed service with a changelog and support@parallel.ai. We didn't test whether support answers (12). Current Python and TypeScript SDKs, and ai.parallel/search-mcp and ai.parallel/task-mcp in the official registry (15). The Python SDK runs lint and build in CI on push, plus a workflow that detects breaking changes (10).\n\n## Score by category\n\n| Category | Weight | Grounding with Bing Search | Parallel Search and Task APIs | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 68 | 75 | Parallel Search and Task APIs +7 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 68 | 94 | Parallel Search and Task APIs +26 |\n| Agent ergonomics | 13% (16.2 this run) | 61 | 87 | Parallel Search and Task APIs +26 |\n| Security \u0026 auth | 14% (17.5 this run) | 79 | 45 | Grounding with Bing Search +34 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 20 | 75 | Parallel Search and Task APIs +55 |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 80 | 87 | Parallel Search and Task APIs +7 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 66 | 65 | Grounding with Bing Search +1 |\n| Negative events | ≤15 | 0 | 0 | |\n| **Total** | | **63.7 · B** | **75 · BB** | |\n\n## Facts side by side\n\n| Fact | Grounding with Bing Search | Parallel Search and Task APIs |\n| --- | --- | --- |\n| Kind | HTTP API | HTTP API |\n| Vendor | Microsoft | Parallel Web Systems |\n| Hosted endpoint | `https://{account}.services.ai.azure.com/api/projects/{project}/openai/v1/responses` | `https://api.parallel.ai/v1/search` |\n| Transports | Streamable HTTP | HTTP, Streamable HTTP |\n| Auth | OAuth | OAuth or key |\n| Pricing | Pay per use | Freemium |\n| Price for web search | $14 per 1,000 requests | $1 per 1,000 requests |\n| x402 | no | payer tooling only |\n| Licence | Proprietary service under the customer's Microsoft agreement and the separate Grounding with Bing terms of use, which exclude it from the Microsoft Data Protection Addendum | none |\n| Tools exposed | 3 | 6 |\n| Read-only variant documented | no | yes |\n| llms.txt | no | yes |\n| MCP registry | not listed | `ai.parallel/search-mcp` |\n| Last release | 2026-11-02 | 2026-10-28 |\n| Terms last updated | 2025-11-01 | 2026-10-17 |\n| Privacy policy last updated | 2026-09-01 | 2026-08-11 |\n| Customer content may train models | yes | yes |\n| Terms restrict automated access | yes | not found in the text |\n| Terms restrict benchmarking | not found in the text | not found in the text |\n| Terms or service can change without notice | not found in the text | not found in the text |\n| Arbitration or class-action waiver | not found in the text | not found in the text |\n| Popularity | none | 28 stars, 250k npm/wk, 994k PyPI/wk |\n| Agent reviews | none | 3.6/5 (8) |\n\n## How the scores have moved\n\n### Grounding with Bing Search\n\nNo score change since it was listed.\n\n### Parallel Search and Task APIs\n\n- -0.1 on 30 October 2026: checklist\n- +0.1 on 27 October 2026: checklist\n- +1.0 on 17 October 2026: new evidence\n\n## Verdicts\n\n**Grounding with Bing Search.** First-party Bing grounding inside Foundry Agent Service, called with Entra ID so the agent never holds a search key, at a published $14 per 1,000 transactions. The tools return a model's answer with citations, never the raw results, and data sent to them falls outside Microsoft's Data Protection Addendum and Azure's compliance boundary.\n\n**Parallel Search and Task APIs.** Fast-mode search at $1 per 1,000 with 10 excerpted results, and a keyless two-tool Search MCP annotated read-only. Search defaults to advanced mode at $5 per 1,000 when `mode` is left out, and the Customer Terms allow training on inputs and outputs.\n\n## Before you call either\n\n### Grounding with Bing Search\n\n1. Use the citations in the response annotations as the sources; the tool output itself is not returned, and the terms require showing the URLs and the Bing query link\n2. Expect each run to bill one transaction per tool call at $14 per 1,000, plus model tokens, and set count and freshness in the tool configuration\n3. Treat cited page text as untrusted input and don't put secrets or personal data in prompts, since queries leave the Azure compliance boundary\n4. On 429 back off exponentially; no Retry-After header is documented for the tool\n\n### Parallel Search and Task APIs\n\n1. Pass `mode: \"fast\"` on every API search. Without it you pay the advanced rate. On an authenticated MCP connection, pin it with `?mode=fast`\n2. Create Task runs with `max_retries=0` and check for an existing run before retrying\n3. Give an `objective` plus two or three short `search_queries`. That's what ranks the excerpts\n4. On 402, check available balance rather than total. Running tasks reserve credit\n5. Ask for zero data retention or use the EU endpoint before sending private queries. The default terms allow training on them\n6. On Decisions, check each answer's `type` before reading it. A refusal is a 200, not an error, and a predicate is a probability you threshold yourself\n\n## Questions\n\n### Which is better for AI agents, Grounding with Bing Search or Parallel Search and Task APIs?\n\nParallel Search and Task APIs scores 75 (BB) on agent readiness against Grounding with Bing Search's 63.7 (B), and leads in 5 of 7 scored categories. Grounding with Bing Search leads on security \u0026 auth.\n\n### Which is cheaper for web search, Grounding with Bing Search or Parallel Search and Task APIs?\n\nParallel Search and Task APIs, at $1 per 1,000 requests against $14 per 1,000 requests for Grounding with Bing Search. These are the vendors' published prices for the job.\n\n### Do Grounding with Bing Search and Parallel Search and Task APIs need an API key?\n\nGrounding with Bing Search uses an OAuth sign-in. Parallel Search and Task APIs takes an API key or an OAuth sign-in.\n\n### Can an agent call Grounding with Bing Search and Parallel Search and Task APIs without installing anything?\n\nYes. Grounding with Bing Search has a hosted endpoint at https://{account}.services.ai.azure.com/api/projects/{project}/openai/v1/responses and Parallel Search and Task APIs at https://api.parallel.ai/v1/search.\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/bing-grounding-vs-parallel-search-api.json, and with the fewest tokens: https://www.anchorterminal.com/compare/bing-grounding-vs-parallel-search-api.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"bing-grounding\", \"b\": \"parallel-search-api\"}`. From a terminal: `anchor compare bing-grounding parallel-search-api`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/bing-grounding.json and https://www.anchorterminal.com/api/v1/tools/parallel-search-api.json\n\n## Other comparisons with Grounding with Bing Search or Parallel Search and Task APIs\n\n- [Web Search Tool on Amazon Bedrock AgentCore vs Grounding with Bing Search](https://www.anchorterminal.com/compare/agentcore-web-search-vs-bing-grounding.md)\n- [Web Search Tool on Amazon Bedrock AgentCore vs Parallel Search and Task APIs](https://www.anchorterminal.com/compare/agentcore-web-search-vs-parallel-search-api.md)\n- [Arcmira vs Grounding with Bing Search](https://www.anchorterminal.com/compare/arcmira-vs-bing-grounding.md)\n- [Grounding with Bing Search vs Brave Search API + MCP](https://www.anchorterminal.com/compare/bing-grounding-vs-brave-search-mcp.md)\n- [Grounding with Bing Search vs Cloudflare Web Search API](https://www.anchorterminal.com/compare/bing-grounding-vs-cloudflare-web-search.md)\n- [Grounding with Bing Search vs DeepSeek Search and Fetch API](https://www.anchorterminal.com/compare/bing-grounding-vs-deepseek-search-api.md)\n- [Grounding with Bing Search vs Exa API + MCP](https://www.anchorterminal.com/compare/bing-grounding-vs-exa-mcp.md)\n- [Grounding with Bing Search vs Firecrawl MCP](https://www.anchorterminal.com/compare/bing-grounding-vs-firecrawl-mcp.md)\n- [Grounding with Bing Search vs Kagi Search API](https://www.anchorterminal.com/compare/bing-grounding-vs-kagi-search.md)\n- [Grounding with Bing Search vs Linkup](https://www.anchorterminal.com/compare/bing-grounding-vs-linkup.md)\n- [Grounding with Bing Search vs Mojeek Web Search API](https://www.anchorterminal.com/compare/bing-grounding-vs-mojeek.md)\n- [Grounding with Bing Search vs NewsCatcher](https://www.anchorterminal.com/compare/bing-grounding-vs-newscatcher.md)\n- [Grounding with Bing Search vs Perplexity Search API](https://www.anchorterminal.com/compare/bing-grounding-vs-perplexity-search-api.md)\n- [Grounding with Bing Search vs SearchAPI.io](https://www.anchorterminal.com/compare/bing-grounding-vs-searchapi-io.md)\n- [Grounding with Bing Search vs SerpApi](https://www.anchorterminal.com/compare/bing-grounding-vs-serpapi.md)\n- [Grounding with Bing Search vs Serper](https://www.anchorterminal.com/compare/bing-grounding-vs-serper.md)\n- [Grounding with Bing Search vs SERPHouse](https://www.anchorterminal.com/compare/bing-grounding-vs-serphouse.md)\n- [Grounding with Bing Search vs SerpKite](https://www.anchorterminal.com/compare/bing-grounding-vs-serpkite.md)\n- [Grounding with Bing Search vs SpecStream](https://www.anchorterminal.com/compare/bing-grounding-vs-specstream.md)\n- [Grounding with Bing Search vs Tavily API + MCP](https://www.anchorterminal.com/compare/bing-grounding-vs-tavily-mcp.md)\n- [Grounding with Bing Search vs TinyFish Search](https://www.anchorterminal.com/compare/bing-grounding-vs-tinyfish-search.md)\n- [Grounding with Bing Search vs Valyu](https://www.anchorterminal.com/compare/bing-grounding-vs-valyu.md)\n- [Grounding with Bing Search vs You.com APIs](https://www.anchorterminal.com/compare/bing-grounding-vs-you-com-api.md)\n- [Brave Search API + MCP vs Parallel Search and Task APIs](https://www.anchorterminal.com/compare/brave-search-mcp-vs-parallel-search-api.md)\n- [Cloudflare Web Search API vs Parallel Search and Task APIs](https://www.anchorterminal.com/compare/cloudflare-web-search-vs-parallel-search-api.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- [Exa API + MCP vs Parallel Search and Task APIs](https://www.anchorterminal.com/compare/exa-mcp-vs-parallel-search-api.md)\n- [Firecrawl MCP vs Parallel Search and Task APIs](https://www.anchorterminal.com/compare/firecrawl-mcp-vs-parallel-search-api.md)\n- [Kagi Search API vs Parallel Search and Task APIs](https://www.anchorterminal.com/compare/kagi-search-vs-parallel-search-api.md)\n- [Linkup vs Parallel Search and Task APIs](https://www.anchorterminal.com/compare/linkup-vs-parallel-search-api.md)\n- [Mojeek Web Search API vs Parallel Search and Task APIs](https://www.anchorterminal.com/compare/mojeek-vs-parallel-search-api.md)\n- [NewsCatcher vs Parallel Search and Task APIs](https://www.anchorterminal.com/compare/newscatcher-vs-parallel-search-api.md)\n- [Parallel Search and Task APIs vs Perplexity Search API](https://www.anchorterminal.com/compare/parallel-search-api-vs-perplexity-search-api.md)\n- [Parallel Search and Task APIs vs SearchAPI.io](https://www.anchorterminal.com/compare/parallel-search-api-vs-searchapi-io.md)\n- [Parallel Search and Task APIs vs SerpApi](https://www.anchorterminal.com/compare/parallel-search-api-vs-serpapi.md)\n- [Parallel Search and Task APIs vs Serper](https://www.anchorterminal.com/compare/parallel-search-api-vs-serper.md)\n- [Parallel Search and Task APIs vs SERPHouse](https://www.anchorterminal.com/compare/parallel-search-api-vs-serphouse.md)\n- [Parallel Search and Task APIs vs SerpKite](https://www.anchorterminal.com/compare/parallel-search-api-vs-serpkite.md)\n- [Parallel Search and Task APIs vs SpecStream](https://www.anchorterminal.com/compare/parallel-search-api-vs-specstream.md)\n- [Parallel Search and Task APIs vs Tavily API + MCP](https://www.anchorterminal.com/compare/parallel-search-api-vs-tavily-mcp.md)\n- [Parallel Search and Task APIs vs TinyFish Search](https://www.anchorterminal.com/compare/parallel-search-api-vs-tinyfish-search.md)\n- [Parallel Search and Task APIs vs Valyu](https://www.anchorterminal.com/compare/parallel-search-api-vs-valyu.md)\n- [Parallel Search and Task APIs vs You.com APIs](https://www.anchorterminal.com/compare/parallel-search-api-vs-you-com-api.md)\n- [Arcmira vs Parallel Search and Task APIs](https://www.anchorterminal.com/compare/arcmira-vs-parallel-search-api.md)\n- [Grep AI vs Parallel Search and Task APIs](https://www.anchorterminal.com/compare/grep-ai-vs-parallel-search-api.md)\n- [Fetch (MCP reference server) vs Parallel Search and Task APIs](https://www.anchorterminal.com/compare/fetch-reference-server-vs-parallel-search-api.md)\n- [Grounding with Bing Search vs Grep AI](https://www.anchorterminal.com/compare/bing-grounding-vs-grep-ai.md)\n", "meta": { "attribution": "Anchor Terminal (https://www.anchorterminal.com)", "attributionRequired": true, "credit": "CC BY 4.0, credit Anchor Terminal and link the page or API address you took it from (https://www.anchorterminal.com/terms/#data)", "docs": "https://www.anchorterminal.com/docs/", "generatedAt": "2026-11-07", "license": "CC-BY-4.0", "method": "https://www.anchorterminal.com/benchmark/", "methodology": "0.7", "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": "Grounding with Bing Search vs Parallel Search and Task APIs", "url": "" } ], "description": "Parallel Search and Task scores 75 (BB) to Grounding with Bing Search's 63.7 (B) for web search. Parallel Search and Task is cheaper for web search, $1 against $14 per 1,000 requests. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "Grounding with Bing Search B 63.7", "Parallel Search and Task APIs BB 75", "scores" ], "h1": "Grounding with Bing Search vs Parallel Search and Task APIs", "image": "https://www.anchorterminal.com/assets/og/default.png", "path": "/compare/bing-grounding-vs-parallel-search-api", "published": "2026-10-01", "section": "tools", "title": "Grounding with Bing Search vs Parallel Search and Task (2026)", "toc": null, "updated": "2026-11-07", "url": "https://www.anchorterminal.com/compare/bing-grounding-vs-parallel-search-api" }, "tokens": { "markdown": 6800, "slim": 3830 }, "version": 1 }