For AI agents: docs.octen.ai/overview/introduction.md
Octen is the search infrastructure for AI: a real-time web search foundation that lets LLMs, agents, and apps reason with the world’s latest information. Going beyond traditional search, Octen spans the whole path from query to result: from Broad Search, which covers one question from multiple angles in a single call, to applications that deliver finished, cited answers and research reports. Octen is also multimodal end to end. Web pages, images, and videos can all be searched, embedded, and used to generate new content, so AI and agents can work with the web the way people actually see it.Why Octen
- Real-time by default. Minute-level index freshness, with second-level updates for fast-moving data such as stock prices and live sports.
- Built for AI consumption. Results return relevant highlights and clean full content directly, no crawling or parsing needed: ranked, token-efficient, LLM-ready.
- Fast and accurate. P50 search latency as low as 62ms; SOTA models top-ranked on search benchmarks (SimpleQA, FreshQA), text retrieval (RTEB #1 and #2), and multimodal retrieval (MMEB-v2).
- Multilingual and multimodal. Sites from across the globe in 100+ languages, with dedicated Image Search and Video Search beyond text.
- Specialized and flexible. Purpose-built modes for verticals such as news, plus per-request options that tune sources, time windows, and output format to your needs.
- Production-grade. Up to 500 QPS on Web Search with a subscription plan, and a 99.9% monthly uptime SLA on paid plans.
- Low cost. Search from $0.1 per 1,000 calls with Pulse Search, or $1 per 1,000 calls with Web Search, priced for high-volume production.
- One platform, full loop. Search, extract, embeddings, and research workflows behind a single API key.
APIs
Each API handles one capability. Start from the card that matches what you have and what you need back.Pulse Search
Input: A text queryOutput: Up to 10 likely URLs with titles, plus optional highlights and full contentBest for: Autocomplete, docs lookup, help pages, official sitesHow to use: Suggest destination pages as users type, or let an agent call it mid-thought to look up pages.
Broad Search
Input: A text queryOutput: Ranked web results for each sub-query, with relevant highlights and optional full contentBest for: Comparisons, research, topic surveys, multi-angle questionsHow to use: Feed the grouped results to a model to answer the whole question at once.
Web Search
Input: A text queryOutput: Ranked web results with relevant highlights, optional full contentBest for: Search bars, answer engines, news lookup, market or company trackingHow to use: Show the results directly, or pass the results to a model to generate grounded answers.
Image Search
Input: A text query or an imageOutput: Ranked image resultsBest for: Image lookup, visual referencesHow to use: Pass the results to a model as visual reference.
Video Search
Input: A text queryOutput: Ranked video resultsBest for: Video lookup, clip discovery, media previewsHow to use: Pass the results to a model to reference the matching video.Invite-only beta. Email support@octen.ai.
News Search
Input: A text queryOutput: Ranked news articles, with related coverage grouped into subjectsBest for: Breaking news, media monitoring, story trackingHow to use: Pass a subject to a model to cover a whole story in one read.
Business Search
Input: A text queryOutput: Ranked business results, plus entity cards for companies and peopleBest for: Company due diligence, people lookup, competitor comparisonHow to use: Read values directly from the entity cards, or pass them to a model as context.
Place Search
Input: A text query, plus the location of the requestOutput: Place cards, plus optional ranked web resultsBest for: Nearby recommendations, local lookup, trip planningHow to use: Read values directly from the place cards, or pass them to a model as context.
Extract
Input: One or more URLsOutput: Clean page content with optional highlights, page classification, and media resourcesBest for: Reading pages, cleaning articles, knowledge ingestionHow to use: Store, display, summarize, or pass the content to a model as context.
Embedding
Input: TextOutput: Text vectorsBest for: Semantic search, RAG, recommendationsHow to use: Convert text into vectors, store them in a vector database, and compare queries against vectors.
VL Embedding
Input: Text, images, videosOutput: Multimodal vectorsBest for: Cross-modal search, visual retrievalHow to use: Convert multimodal content into vectors so text, images, and videos can be searched or matched.
Applications
Use applications when you want to run a complete workflow.Answer
Input: A question or chat messagesOutput: A synthesized answer grounded in search results, with the sub-queries and sources usedBest for: Q&A, chat assistants, grounded answers with citationsHow to use: Send the user’s question. Octen returns the synthesized answer and its sources.
Search Agent
Input: A question or chat messagesOutput: A cited answer as Markdown, or as JSON in a schema you defineBest for: Fact lookup, structured data extraction, multi-step questionsHow to use: Send the user’s question. Octen searches and reads on its own, then returns the cited answer.
Deep Research
Input: A research questionOutput: A structured report with supporting evidence, optionally illustrated with images and videosBest for: Deep dives, strategic research, technical investigations, trend analysisHow to use: Enter a research question. Octen plans, searches over multiple rounds, and streams the final report.
Grounded Generation
Input: A generation promptOutput: Generated images or videos grounded in search resultsBest for: Fact-grounded visuals, illustrated explainersHow to use: Send a prompt. Octen generates grounded images or videos.
Auto Search
Input: A question, chat messages, or an image or video descriptionOutput: Model responses, generated images, or generated videosBest for: Chat assistants, agents, image and video generation, workloads that need fresh web knowledgeHow to use: Use the responses to build chat, agent, image, or video features.
Next Steps
Quickstart
Get an API key and make your first request.
Build with Coding Agent
Everything a coding agent needs to integrate Octen.
Try in Console
Run every API live in the Octen console.
API Reference
Full request/response schemas.
Last modified on November 6, 2026