Skip to main content

For AI agents: docs.octen.ai/resources/faqs.md

  1. How is Octen different from other search APIs?
Octen is built from the ground up for LLMs and agents. We offer industry-leading latency, SOTA search models, and real-time index updates. Our output structure is designed for LLM understanding and reasoning. For most use cases, you can directly use Octen without any additional processing.
  1. Should I use Pulse Search or Web Search?
Use Pulse Search when the query points at a known page, such as an official site, a login page, or a docs page, and speed or cost matters most. Use Web Search for news, fresh pages, long-tail questions, or when you need domain, time, or language filters.
  1. How do I connect Octen to my agent quickly?
Use Octen Agent Skills, the MCP server, or the CLI to add Octen to your agent in one step. See Octen Skills, Octen MCP Server, and Octen CLI.
  1. Can I request specific domains or content types to be indexed?
Enterprise customers can submit indexing requests. Contact support@octen.ai with your domains and use case.
  1. Can I use Octen with OpenAI SDK or LangChain/LlamaIndex?
Yes.
  1. Can I use Octen embeddings with other vector databases?
Yes. Octen embeddings are standard float vectors, compatible with all major vector databases.
  1. Can I make batch requests to improve throughput?
Embedding API supports batch input. Search API only supports single-query requests.
  1. How can I track my usage and spending?
The API platform provides real-time usage monitoring, credit consumption, and per-API-key usage breakdown.
  1. What happens when I run out of credits?
Requests that need balance return a 403 error until you top up. Web Search included in your Search Plan keeps working, and your QPS Plan is not affected.
  1. How do plan upgrades or downgrades work?
Upgrades take effect immediately, with unused time credited. Downgrades take effect at the end of the current period.
  1. Will my queries or data be used for model training?
No. Your queries and data are not used to train our models.
  1. How fresh are the search results? How often is the index updated?
Our index updates continuously in real-time (ingested in seconds and updated in minutes). Most results reflect the current state of web pages.
  1. Why are my search results different from what I expected?
Check your query phrasing, domain/date filters, and topic coverage. Try adjusting parameters or rephrasing your query.
  1. Can I filter results by domain, date, or language?
Yes. See the Web Search API Reference for details.
  1. How do I report a bug or request a new feature?
Email support@octen.ai

Last modified on November 10, 2026