Grounding with Bing Search vs DeepSeek Search and Fetch API

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&A 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.

DeepSeek Search and Fetch API 42

Closed service, per the 17 October check, not re-read on 4 November (terms pause). Opened on 17 October 2026, 18 days before this check (30). The change log's 17 October entry is the only dated one about Search or Fetch in the 90 days from 6 August (0 of 20). Dated change log, api-service@deepseek.com and a Discord server, not tested for replies (12 of 15). No official SDK (0 of 15). No SDK or package to assess (0 of 10). 30 + 0 + 12 + 0 + 0 = 42.

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.

DeepSeek Search and Fetch API 43

Per the 17 October check, not re-read on 4 November (terms pause). The ordinary DeepSeek bearer key, revocable, with no scopes, so a key used for search can also spend on models. No secret in a URL (20 of 30). Both endpoints only read, so there's nothing destructive to approve, but no search-only key (15 of 20). Results and fetched pages are untrusted web text. The change log says the engine filters 'SEO spam, GEO manipulation, and low-quality AIGC', with no technical detail and no prompt-injection guidance (3 of 15). No per-call log or audit log found in the docs. The platform console wasn't readable (0 of 15). Security programme 5 of 20 (was 0). The www.deepseek.com footer carries a Report Security Issue address, security@deepseek.com, per the 21 October reading used for DeepSeek's open-weight listings; no security.txt (404 on 17 October), disclosure policy, bug bounty or certification found. 20 + 15 + 3 + 0 + 5 = 43.

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.

DeepSeek Search and Fetch API 81

Per the 17 October check, not re-read on 4 November (terms pause). Responses can be sized with count and need_content, off by default, and each result carries both a short snippet and a 600 to 800 character summary. No field selection, and full content has no length cap stated (20 of 25). Site, language, date and phrase filters, up to 50 results, no pagination (15 of 20). Ten documented codes with what to do, 402 for an empty balance and 404 for an unfetchable page. param is always null and code repeats the type (17 of 20). Both endpoints are documented as read-only and safe to retry, and failed or empty calls aren't billed (20). Only query or url is required. No official SDKs, the docs use raw HTTP and Python requests (9 of 15). 20 + 15 + 17 + 20 + 9 = 81.

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.

DeepSeek Search and Fetch API 55

Per the 17 October check, not re-read on 4 November (terms pause). No OpenAPI file found. The API reference is rendered from a schema, but no spec is linked, and /openapi.json and /openapi.yaml on the docs host serve the docs page (0). No llms.txt, since api-docs.deepseek.com answered /llms.txt with HTML (0). The guide says what each endpoint is for and which result field suits a UI or a model, and gives the score thresholds for quality and authority, but not when to use Search content against a Fetch (14 of 20). Types, required fields, defaults and limits on every field, such as query 1 to 128 characters and count 1 to 50. Filters live inside the free-text query (13 of 15). curl and Python examples, an error body and a table of ten status codes with retry guidance. The reference shows only the 200 response (13 of 15). Dated change log and a /v1 path (15). 0 + 0 + 14 + 13 + 13 + 15 = 55.

Grounding with Bing Search 66

Closed service. The terms of use, updated November 2025, are separate from the Online Services terms and sit under the customer's Microsoft agreement (15 of 30). The docs and the terms agree that the Data Protection Addendum and the Product Terms' privacy and security terms don't apply, that Microsoft and the customer are independent controllers, and that the query and parameters leave the Azure compliance and geographic boundary. The terms defer storage and use of query data to the general Microsoft Privacy Statement and state no retention period (15 of 30). The Bing Search APIs retirement was announced on 16 May 2025 for 11 August 2025, under three months' notice, and the web search page marks the Deep Research tool deprecated with a replacement. Microsoft's lifecycle policy covers Azure services, but no deprecation terms for Grounding with Bing were found (10 of 20). Data location for Bing processing isn't stated, and no sub-processor list for it was found (5 of 20). 15 + 15 + 10 + 5 = 45.

DeepSeek Search and Fetch API 60

Per the 17 October check for the privacy policy, not re-read on 4 November (terms pause). Closed service with published terms under PRC law, which assign Outputs to the customer; the Open Platform terms (released 22 April, effective 29 April 2026) and the Terms of Use (last update 27 March 2026) were re-read on 4 November (15). The privacy policy of 10 February 2026 says personal data trains models unless you opt out by email and gives no retention period. It also says search runs on 'third-party APIs' that receive input keywords, which disagrees with the in-house engine described on 17 October, and nothing covers fetched URLs (5 of 30). No deprecation policy, and the only dated notice is the end of free server-side calls on 31 October (5 of 20). Data location disclosed as the PRC, third parties named only by category (10 of 20). 15 + 5 + 5 + 10 = 35.