--- title: "Orbita" description: "Orbita is a private MVP search API for AI agents, returning clean, filtered source text in whole paragraphs, with links. Administrator access only; public launch is planned for 2027." url: "https://orbita.surf/landing/" --- # orbita WHAT YOUR AGENT GETS ## The link and the page’s *text.* Your agent sends a query and gets up to 25 sources. Each comes with its address, its title, the publication date when the site gives one, and the page text in whole paragraphs, without menus or ads. No need to open and clean the pages yourself. Over the API or a local MCP server. [API documentation](https://orbita.surf/landing/docs.html) Query Fast · 5 sources In Pydantic AI's Amazon backend, which setting beats the unified one, and how do I get the reserved level? 1. 01 pydantic.dev/docs/ai/models/bedrock/ ### AWS Bedrock Bedrock supports controlling the service tier to manage throughput and cost. You can use the unified `service_tier` field or the provider-specific `bedrock_service_tier` field. `bedrock_service_tier` takes precedence over the unified field when both are set. To request Bedrock’s 'reserved' tier (which requires a pre-purchased capacity reservation), set `bedrock_service_tier` directly — it isn’t reachable through the unified field. 2. 02 pydantic.dev/docs/ai/models/anthropic/ ### Anthropic 3. 03 pydantic.dev/docs/ai/models/openai/ ### OpenAI ## How long a search *takes.* One search at a time on the 5.85-million-page index of the benchmark below, server time from the request to the response. Fast **2.27s** median p95 · 2.42 s Standard **2.73s** median p95 · 3.08 s Deep **3.81s** median p95 · 4.72 s Measured on 24 October 2026 on a test server with the benchmark’s index: 60 questions per mode, the first 20 of SimpleQA, Natural Questions and TechQA-open. In the benchmark itself, 16 searches at once on one machine, the median was 2.68 s in Fast, 3.61 s in Standard and 5.03 s in Deep. Network time to the client is extra. 7 QUESTION SETS · 24 OCTOBER 2026 ## Orbita next to *Exa and Linkup.* The same 1,412 questions from seven sets for every service, and one check: is a correct answer in the text it returns. Each searched its own index: Exa and Linkup the whole web, Orbita a test index of 5.85 million pages built for this run (English Wikipedia and 1,927 other sites), not its smaller production index. On technical documentation, where Orbita has the pages, it is close to them or ahead; on general knowledge many answers are on pages it does not have. [Every question and the method](https://orbita.surf/landing/benchmarks.html) **The figures behind the charts. 24 October 2026: the share of questions whose answer appears in the text each service returned. Orbita Fast returns up to 5 results, Standard 10, Deep 25; Exa Auto and Linkup Standard 10. Exa and Linkup searched the whole web; Orbita its test index of 5.85 million pages, built for this run.** | Measure | Orbita Fast | Orbita Standard | Orbita Deep | Exa Auto | Linkup Standard | | --- | --- | --- | --- | --- | --- | | SimpleQA: answer in the returned text, % of 300 | 60.3 | 63.0 | 66.0 | 90.0 | 86.7 | | Natural Questions: answer in the returned text, % of 300 | 76.0 | 78.7 | 83.0 | 89.0 | 87.3 | | HotpotQA: answer in the returned text, % of 250 | 59.2 | 64.4 | 72.4 | 74.8 | 62.0 | | AA-Omniscience: answer in the returned text, % of 200 | 39.5 | 48.0 | 54.5 | 81.5 | 70.5 | | BrowseComp: answer in the returned text, % of 100 | 5.0 | 9.0 | 13.0 | 27.0 | 11.0 | | TechQA: answer in the returned text, % of 144 | 95.1 | 95.8 | 96.5 | 91.0 | 92.4 | | TechQA-open: answer in the returned text, % of 118 | 93.2 | 95.8 | 96.6 | 100.0 | 97.5 | PRICING ## What search and Fetch *cost.* 01 ### Fast **1–5** results Quick facts, weather, rates and one command from the docs. **$1.99** New Search · per 1 000 **$2.99** Search + Compact 02 ### Standard **6–10** results Comparisons, error fixes, harder docs and this week’s news on a topic. **$3.99** New Search · per 1 000 **$5.99** Search + Compact 03 ### Deep **11–25** results A person, a company, a timeline or news across regions. **$7.99** New Search · per 1 000 **$12.99** Search + Compact 04 ### Auto **Auto** requested **Fast–Deep** resolved mode Orbita picks Fast, Standard or Deep for each query, within your limits. **$1.99–$7.99** resolved Search price **$2.99–$12.99** resolved Compact price Never exceeds max_mode or max_cost_usd 05 ### Fetch Any page, or a site section of up to 100 pages per request, as clean text in whole paragraphs. - Text from images (OCR) - JavaScript when needed - Every PDF page - Failed pages are free **$0.50** per 1,000 pages Exa · Parallel · You.com *$1* ### Fetch next to the others The whole page as clean text in whole paragraphs, text from images and every PDF page, at one price. The others return markdown. | Service · returns | Price per 1,000 pages · Without JavaScript | Price per 1,000 pages · With JavaScript | Price per 1,000 pages · Site crawl | Text from images | Failed pages | | --- | --- | --- | --- | --- | --- | | Orbita Fetch · whole page: clean text in whole paragraphs | **$0.50** | $0.50 | $0.50 | Included | Free | | Exa Contents · markdown | $1.00 | $1.00 | Subpages, price not published | Not stated | ? | | Parallel Extract · markdown | $1.00 | $1.00 | No | Not stated | ? | | You.com Contents · markdown, html | $1.00 | $1.00 | No | Not stated | ? | | Linkup Fetch · markdown | $1.00 | $5.00 | No | Not stated | Free | | Tavily Extract · markdown, text | $1.00–1.60 | $2.00–3.20 | $1.50–2.40 | No | Free | | Firecrawl · markdown, html, json | $0.60–3.80 | $0.60–3.80 | $0.60–3.80 | Not stated | 403 and 404 are billed | | Spider · markdown, text | ~$0.02–0.10 | ~$0.04–0.16 | ~$0.30 | Not stated | Free | | Scrapfly · markdown, text | $0.09–0.15 | $0.55–0.90 | $0.09–0.15 | Not stated | Free | USD per 1,000 pages, from each service's pricing pages on 21 October 2026. A range means the price depends on the plan: from the largest self-serve plan to pay as you go; for Spider, the averages from its own guide. ? means not published. Every mode returns sources with links and publication dates. Compact adds a controlled context pass. - New Search **$1.99–$7.99** - Search + Compact **$2.99–$12.99** - Linkup **$5** - Tavily **$5–8** - Exa **$7** USD per 1,000 successful searches. Failed requests are refunded. No paid checkout is connected yet. OUR PRINCIPLE ## The web can be endless. Search should not feel *chaotic.* --- [orbita](https://orbita.surf/landing/index.html) Search for AI that works with evidence. Search API for AI agents. Clean, filtered source text in whole paragraphs, with a link to every source. Private MVP · administrator access · public launch planned for 2027 **Product** [Open Orbita](https://orbita.surf/landing/app.html) [Modes and pricing](https://orbita.surf/landing/#price) **Builders** [Documentation](https://orbita.surf/landing/docs.html) [OpenAPI](https://orbita.surf/landing/openapi.json) [llms.txt](https://orbita.surf/landing/llms.txt) **Access** [Sign in](https://orbita.surf/landing/login.html) [Create account](https://orbita.surf/landing/signup.html) **Legal** [Legal & trust](https://orbita.surf/landing/legal.html) [Privacy](https://orbita.surf/landing/privacy.html) [Terms](https://orbita.surf/landing/terms.html) [Security](https://orbita.surf/landing/security.html) [Crawler & removals](https://orbita.surf/landing/crawler.html) ORBITA / LVIV / 2026 SEARCH API FOR AI AGENTS [Cookies](https://orbita.surf/landing/cookies.html) · [Subprocessors](https://orbita.surf/landing/subprocessors.html) Back to top ↑