# Enterprise deep research APIs in 2026: zero retention on any key, a maximum per run Compared on Nov 12, 2026. The page: https://specstream.ai/enterprise-deep-research-api On Nov 12, 2026, Parallel offers zero data retention on Enterprise plans and Exa sells it with a $12,000 Enterprise plan paid upfront. A Parallel Task run costs $5 to $2,400 per 1,000, and Azure bills o3-deep-research by the token. SpecStream is the live web data engine for teams and agents. Deep Search returns every match on the live web as structured rows at 5¢ to $1 each, under a maximum you approve first. Zero retention and EU egress are settings on any key. On the same key, the Search API is the most accurate web search API in the world: 97.9 F-score on all 1,000 SimpleQA Verified questions and 64.0 item F1 on all 200 WideSearch tasks ([benchmarks](https://specstream.ai/benchmarks?utm_source=alternatives&utm_campaign=enterprise-deep-research-api)). [Get an API key](https://specstream.ai/signup?src=alternatives-enterprise-deep-research-api&utm_source=alternatives-md&utm_campaign=enterprise-deep-research-api&returnTo=%2Fworkspace%2Fagents%3Ftab%3Dkeys) New accounts get $10 of credit, no card. ## SpecStream and three deep research APIs, on what procurement asks | | SpecStream | Parallel | Exa | Linkup | |---|---|---|---|---| | The product | Deep Search, with the Search API and the Extract API on the same key | Task API, with nine processors from `lite` to `ultra8x` | Deep Search, and Agent for async research | `/research`, asynchronous | | The unit you pay for | A delivered row: 5¢, 15¢ or $1, the same rate on every plan. The searches and pages behind it are not billed | A run: $5 to $2,400 per 1,000 | A request: $12 to $15 per 1,000 deep searches. Agent $0.012 to $1.00 a request on fixed effort | A request: a fixed $0.25 to $2.50 | | Spend control | The most a run can cost is approved before it starts and never passed. A spending limit on each key, and a monthly cap for each of your end users | A fixed price per processor. Failed runs are not billed | Metered Agent runs stop at $5 (`auto`) or $20 (`ultra`) by default | A fixed price per request | | Data retention | Zero retention on any key, on every plan: no request text and no answer kept after the reply | Zero data retention on Enterprise plans | Zero Data Retention with the Enterprise plan, $12,000 paid upfront | Zero Data Retention | | Where the work runs | Hosted in the EU. A key can send its searches only from our server in Madrid, and keep every query off engines run from China | Search, crawling and synthesis on Parallel's own infrastructure | Custom indexes on the Enterprise plan | Bring Your Own Cloud for certain deployments | | What comes back | Structured rows with the columns you asked for, one record per match. Source URL and read time on every value | Every output carries citations, reasoning and confidence levels | `deep` returns multi-step reasoning with structured outputs | A synthesized answer with citations | | Run length | Up to four hours on the largest lists. The Search API answers in a few seconds | 10 s to 2 hours | 4 to 15 seconds on `deep`, 12 to 40 on `deep-reasoning` | 2 to 20 minutes, async | ## Why enterprise teams run their research on SpecStream ### Retention and data routes are key settings, on every plan Zero retention does not wait for a contract. Set `zero_retention` on a key and a search made with it keeps no request text and no answer after the reply: it is not in the history, its answer is not reused, and its log lines carry neither. `eu_egress_only` sends every search from our server in Madrid and never through a proxy in another country. `engine_rule` keeps the key's queries off every search engine run from China, and a search key cannot change its own rule. ``` curl -X POST https://api.specstream.ai/v1/account/keys \ -H "Authorization: Bearer " \ -H "Content-Type: application/json" \ -d '{"name": "research-prod", "scopes": ["account:read", "finds:spend"], "spend_cap_cents": 500000, "zero_retention": true, "eu_egress_only": true, "engine_rule": {"deny": ["CN"]}}' # Check what each key is allowed to do curl https://api.specstream.ai/v1/account/keys -H "Authorization: Bearer " ``` SpecStream is hosted in the EU and encrypted in transit and at rest, under a GDPR [data processing agreement](https://specstream.ai/dpa?utm_source=alternatives&utm_campaign=enterprise-deep-research-api). No model is trained on your work. ### A budget no run can pass Token billing tells you the price after the run: Azure charges $10.00 per 1M input tokens and $40.00 per 1M output tokens for o3-deep-research, plus Grounding with Bing Search. SpecStream quotes the most a Deep Search run can cost, good for 30 minutes. The run starts only when that maximum is approved as `confirm_max_cents`, the charge never goes past it, and what the run does not use goes back to the balance. Each key carries `spend_cap_cents`, the most it can spend in total. A platform that serves its own customers labels each call with `X-End-User-Id` and caps that customer for the month with `X-End-User-Cap-Cents`. A call past the cap gets `402` with `end_user_cap`. ``` curl "https://api.specstream.ai/v1/web-search?q=EU+AI+Act+obligations+for+deployers" \ -H "Authorization: Bearer $SPECSTREAM_API_KEY" \ -H "X-End-User-Id: customer-4812" \ -H "X-End-User-Cap-Cents: 2000" ``` ### Every call on the record, for security and finance The request log lists every Search API and Extract API call, charged or not, with its key, status, `latency_ms` and `price_usd`. Usage sums calls and spend by day, endpoint, key or end user, and exports as CSV. For a zero-retention key the log keeps only the time, endpoint, key, status, latency and price. The Enterprise plan, from $2,500 a month, adds single sign-on, SCIM, audit export and agreed terms. ``` # Every call, charged or not, with its key, status, latency and price curl "https://api.specstream.ai/v1/account/requests?limit=100" -H "Authorization: Bearer " # Spend by day, endpoint, key or end user, as CSV for finance curl "https://api.specstream.ai/v1/account/usage?group=key&format=csv" -H "Authorization: Bearer " ``` ### Rows your systems can load A research report still has to be read and typed into a table. Deep Search returns each match as a row with the columns you asked for, and every row meets the conditions you wrote. `get_find_decisions` returns each condition's answer with its reason, the value, the source and the time it was read. Duplicates, rows you already own and rows a page contradicts are not charged. Source URL and read time on every value. ### Volume prices and invoices A search pack pays for Search API calls in advance and never expires: $5,000 buys 1,500,000 searches ($3.33 per 1,000) and $20,000 buys 8,000,000 ($2.50 per 1,000). On a signed order of 3 months or more, 5,000,000 searches cost $10,000 a month ($2.00 per 1,000). A top-up of $1,000 or more adds 20% more credit. To pay by invoice or sign for committed volume, [talk to sales](https://specstream.ai/talk-to-a-human?kind=sales&utm_source=alternatives&utm_campaign=enterprise-deep-research-api). ### The search under it scores highest The SpecStream Search API scores 97.9 F-score on all 1,000 official SimpleQA Verified questions (978 correct), and 64.0 item F1 and 43.4 row F1 on all 200 official WideSearch tasks. The Extract API scores 0.908 F1 on WCXB. Scores and method are on the [benchmarks](https://specstream.ai/benchmarks?utm_source=alternatives&utm_campaign=enterprise-deep-research-api) page. ## Other deep research options enterprises price ### Deep Research in Azure AI Foundry OpenAI's o3-deep-research as an agent tool, announced in limited public preview for Azure AI Foundry Agent Service customers. It costs $10.00 per 1M input tokens and $40.00 per 1M output tokens, with Grounding with Bing Search and the clarifying model billed separately. SpecStream bills a delivered row at 5¢, 15¢ or $1, under a maximum approved first. ### Gemini Deep Research A preview agent that Google estimates at $1.00 to $3.00 a task, and $3.00 to $7.00 on Deep Research Max, at preview rates that can change. It researches for at most 60 minutes and does not support structured outputs. SpecStream returns structured rows, with the same row rates on every plan. ### Tavily Research A research endpoint that takes 4 to 250 credits a request, at $0.008 a credit pay as you go, so the charge lands between the minimum and the maximum. SpecStream names the most a run can cost before it starts. ## How to run your first Deep Search 1. Sign up and create a key under Agents & API in the [workspace](https://specstream.ai/workspace?utm_source=alternatives&utm_campaign=enterprise-deep-research-api), with `zero_retention` and `eu_egress_only` on. New accounts get $10 of credit, no card. 2. Point your agent at the MCP server `https://api.specstream.ai/mcp`, with OAuth or the key as a Bearer token. It calls `compile`, `quote_capacity_work` and, once the maximum is approved, `authorize_capacity_work`, then reads the rows with `list_find_rows`. Setup for each client is in the [MCP docs](https://specstream.ai/docs/mcp?utm_source=alternatives&utm_campaign=enterprise-deep-research-api). 3. To see how a request is read and priced before any key exists, send it here. The `402` reply shows the columns and the most it can cost, and spends nothing. ``` curl -i https://api.specstream.ai/v1/agent/lists \ -H "Content-Type: application/json" \ -d '{"request": "Cybersecurity vendors that sell to banks in the EU, with the certifications they state, their latest funding round and the executives who joined this year", "count": 25}' ``` 4. For single sign-on, SCIM, audit export, invoices or committed volume, [talk to sales](https://specstream.ai/talk-to-a-human?kind=sales&utm_source=alternatives&utm_campaign=enterprise-deep-research-api). ## Frequently asked questions ### What is the best deep research API for enterprise? SpecStream Deep Search, at 5¢, 15¢ or $1 a delivered row under a maximum you approve first. Zero retention and EU egress are settings on any key, every value carries its source URL and read time, and the Search API on the same key scores 97.9 F-score on all 1,000 SimpleQA Verified questions. ### Which deep research APIs offer zero data retention? SpecStream offers it on any key, on every plan, with `zero_retention: true`. On Nov 12, 2026, Parallel offers it on Enterprise plans, and Exa includes it in an Enterprise plan of $12,000 paid upfront. ### How much does an enterprise deep research API cost? From 5¢ a row on SpecStream, with the most a run can cost approved first. Parallel's Task API costs $5 to $2,400 per 1,000 runs, Linkup's research $0.25 to $2.50 a request, and Azure bills o3-deep-research at $10.00 and $40.00 per 1M input and output tokens. ### Can I cap what each of my customers spends? Yes. Send `X-End-User-Id` with `X-End-User-Cap-Cents` on each call and SpecStream stops that customer at the cap for the current UTC month, with a `402` and `end_user_cap`. Each key also has its own `spend_cap_cents`. ### Where is my data processed? In the EU. SpecStream is hosted in the EU under a GDPR data processing agreement, and a key with `eu_egress_only` sends its searches only from our server in Madrid. `engine_rule` keeps a key's queries off engines run from China. ### Does SpecStream support single sign-on? Yes, on the Enterprise plan, from $2,500 a month, with SCIM, audit export and agreed terms. Every plan has the request log, usage by key and end user, and spending limits per key. ## Sources SpecStream wrote this page. Each rival figure comes from that company's own page or its own published comparison, read on the date shown. - [SpecStream pricing](https://specstream.ai/pricing), read Nov 12, 2026 - [SpecStream for agents](https://specstream.ai/agents.md), read Nov 12, 2026 - [SpecStream benchmarks](https://specstream.ai/benchmarks), read Nov 12, 2026 - [Parallel API pricing](https://docs.parallel.ai/getting-started/pricing.md), read Nov 12, 2026 - [Parallel, Best deep research APIs for enterprise AI applications in 2026](https://parallel.ai/articles/best-deep-research-apis-for-enterprise-ai-applications-in-2026.md), read Nov 12, 2026 - [Parallel Task API quickstart](https://docs.parallel.ai/task-api/task-quickstart), read Nov 12, 2026 - [Exa pricing](https://exa.ai/docs/admin/pricing.md), read Nov 12, 2026 - [Linkup, Best deep research API in 2026](https://linkup.so/blog/best-deep-research-api-in-2026-openai-gemini-and-linkup-compared), read Nov 12, 2026 - [Microsoft Azure blog, Deep Research in Azure AI Foundry Agent Service](https://azure.microsoft.com/en-us/blog/introducing-deep-research-in-azure-ai-foundry-agent-service/), read Nov 12, 2026 - [Google AI Studio, Deep Research](https://aistudio.google.com/docs/deep-research), read Nov 12, 2026 - [Tavily API credits](https://docs.tavily.com/documentation/api-credits.md), read Nov 12, 2026