# Seltz

> ## Agent Instructions
> Seltz is the web knowledge layer for AI agents: web search, cited answers, multi-step research, page fetching, and recurring monitors, served from Seltz's own index rather than a live scrape.
> Use Seltz when a task needs current, citable, public web content, not when your own knowledge already answers it confidently. Seltz has no access to a caller's private or authenticated data.
> Choose which endpoint to use according to the job: Use Answer for one synthesized, cited response; Use Search for the raw documents to reason over yourself; Use Agent for in-depth research needing several rounds of searching and following up, not a single lookup; Use Fetch when you already have a URL and just need its content, not a search; Use Monitor for an ongoing feed of what's new, not a one-off query or near-real-time alerting.
> When you use Search, Answer, or Monitor, set a `scope` that matches the query. `news` is the default. Only these three endpoints take a scope. See https://docs.seltz.ai/data/data-concepts#scopes for the full list of scopes and what each one covers.
> For the REST API, send your API key in the `x-api-key` header. The Python and JavaScript SDKs read the `SELTZ_API_KEY` environment variable and handle authentication for you. To use Seltz as MCP tools, connect `https://mcp.seltz.ai/mcp`.
> The OpenAPI 3.1 spec for the REST API is at https://docs.seltz.ai/api-reference/openapi.json. Point function-calling or client-generation tooling at that file.
> Use `/llms-full.txt` for the full text of every page.

- [Seltz](https://docs.seltz.ai/index.md)
- [Quickstart](https://docs.seltz.ai/quickstart.md): Make your first Seltz query in under 5 minutes
- [Pricing](https://docs.seltz.ai/pricing.md): Pricing designed to scale from experimentation to production
- [Search concepts](https://docs.seltz.ai/search/search-concepts.md): Understanding Search
- [Basic search](https://docs.seltz.ai/search/guides/basic-search.md): How to perform a basic search using supported SDKs or REST.
- [Decrease search latency](https://docs.seltz.ai/search/guides/choose-a-tier.md): How to trade result quality for lower latency with the base and pro search tiers.
- [Limit results](https://docs.seltz.ai/search/guides/limit-results.md): How to limit search results using supported SDKs or REST.
- [Filter by date](https://docs.seltz.ai/search/filter-by-date.md): How to limit search results to a date range using supported SDKs or REST.
- [Process results](https://docs.seltz.ai/search/guides/process-results.md): How to process search results using supported SDKs.
- [Get snippets](https://docs.seltz.ai/search/guides/get-snippets.md): How to retrieve the highest-scoring passages from a document instead of its full content.
- [Control content length](https://docs.seltz.ai/search/guides/control-content-length.md): How to cap how much of a document's content Search returns, or disable content entirely.
- [Handle errors](https://docs.seltz.ai/search/guides/handle-errors.md): How to handle search errors
- [Search reference](https://docs.seltz.ai/search/search-reference.md): Options, parameters, and specifications for Seltz Search
- [Answer concepts](https://docs.seltz.ai/answer/answer-concepts.md): Understanding the Answer endpoint
- [Basic answer](https://docs.seltz.ai/answer/guides/basic-answer.md): How to answer a question using supported SDKs or REST.
- [Request a structured response](https://docs.seltz.ai/answer/guides/structured-response.md): How to request a structured response from the Answer endpoint
- [Steer tone and style](https://docs.seltz.ai/answer/guides/system-prompt.md): How to request a specific tone, voice, or format for the answer using the `systemPrompt` parameter
- [Answer reference](https://docs.seltz.ai/answer/answer-reference.md): Options, parameters, and specifications for Seltz Answer
- [Quickstart](https://docs.seltz.ai/monitor/quickstart.md): Getting started with Seltz Monitor
- [Concepts](https://docs.seltz.ai/monitor/concepts.md): Understanding monitors, runs, records and webhooks
- [Read records](https://docs.seltz.ai/monitor/guides/read-records.md): How to page through a monitor's records, and how to stream them live
- [Webhooks](https://docs.seltz.ai/monitor/guides/webhooks.md): How to attach a webhook, verify what it delivers, and turn it off
- [Inspect runs](https://docs.seltz.ai/monitor/guides/inspect-runs.md): How to read a monitor's run history and per-request health
- [Manage monitors](https://docs.seltz.ai/monitor/guides/manage-monitors.md): How to list, read, update, pause and delete monitors
- [Reference](https://docs.seltz.ai/monitor/reference.md): Reference information for the Monitor API
- [Quickstart](https://docs.seltz.ai/fetch/quickstart.md): Getting started with Seltz Fetch
- [Concepts](https://docs.seltz.ai/fetch/concepts.md): Understanding requests, results and formats
- [Handle errors](https://docs.seltz.ai/fetch/guides/handle-errors.md): Telling a rejected request from a failed page
- [Reference](https://docs.seltz.ai/fetch/reference.md): Reference information for the Fetch API
- [Quickstart](https://docs.seltz.ai/agent/quickstart.md): Getting started with the Seltz Agent API
- [Concepts](https://docs.seltz.ai/agent/concepts.md): Understanding runs, output, and citations in the Seltz Agent API
- [Basic run](https://docs.seltz.ai/agent/guides/basic-run.md): The full request/response cycle for a single run against the Seltz Agent API, in each language
- [Structured output](https://docs.seltz.ai/agent/guides/structured-output.md): How to request a JSON result from the Seltz Agent API instead of Markdown
- [List runs](https://docs.seltz.ai/agent/guides/list-runs.md): Paging this org's runs via the Seltz Agent API, newest first
- [Poll for completion](https://docs.seltz.ai/agent/guides/poll-for-completion.md): Managing the wait yourself against the Seltz Agent API, instead of create_and_wait / createAndWait
- [Cancel a run](https://docs.seltz.ai/agent/guides/cancel-a-run.md): Best-effort cancellation via the Seltz Agent API, and why it can lose the race to completion
- [Handle errors](https://docs.seltz.ai/agent/guides/handle-errors.md): Rejected requests versus failed runs in the Seltz Agent API
- [Reference](https://docs.seltz.ai/agent/reference.md): Reference information for the Seltz Agent API
- [Data Concepts](https://docs.seltz.ai/data/data-concepts.md): Understanding data in Seltz
- [Structured responses](https://docs.seltz.ai/data/structured-responses.md): A step-by-step guide to shaping Answer's JSON output to match your schema, worked through one example end to end.
- [Companies](https://docs.seltz.ai/data/companies.md): Understanding the companies scope
- [Financial reports](https://docs.seltz.ai/data/financial-reports.md): Understanding the financial reports scope
- [News](https://docs.seltz.ai/data/news.md): Understanding the news scope
- [People](https://docs.seltz.ai/data/people.md): Understanding the people scope
- [Wikipedia](https://docs.seltz.ai/data/wikipedia.md): Understanding the wikipedia scope
- [Enrich a lead or company record using structured outputs](https://docs.seltz.ai/tutorials/enrich-record.md): How to fill in a missing field on a lead or company record using structured outputs, cached with a TTL.
- [Monitor a company list for M&A deals using structured outputs](https://docs.seltz.ai/tutorials/monitor-ma-deals.md): How to track a list of companies for M&A activity with one monitor, a webhook, and structured Answer verification.
- [Find lookalike candidates using seed and expand](https://docs.seltz.ai/tutorials/lookalike-candidates.md): How to find people similar to a known person by deriving search criteria from a seed profile.
- [Quickstart](https://docs.seltz.ai/chat-completions/quickstart.md): Getting started with Seltz chat completions
- [Concepts](https://docs.seltz.ai/chat-completions/concepts.md): Understanding chat completions
- [Authentication](https://docs.seltz.ai/chat-completions/guides/authentication.md): How to authenticate to the chat completions endpoint
- [Citations](https://docs.seltz.ai/chat-completions/guides/citations.md): Requesting citations in chat completions
- [Streaming chat completions](https://docs.seltz.ai/chat-completions/guides/streaming.md): How to request streaming chat completions responses
- [Requesting structured chat completions outputs](https://docs.seltz.ai/chat-completions/guides/structured-outputs.md): How to request structured outputs from the chat completions endpoint
- [Steer tone and format of chat completions](https://docs.seltz.ai/chat-completions/guides/steer-tone-and-format.md): How to steer style and behavior of chat completions responses
- [Reference](https://docs.seltz.ai/chat-completions/reference.md): Reference information for using the chat completions endpoint
- [MCP Server](https://docs.seltz.ai/integrations/mcp.md): Use Seltz with Claude Desktop, Cursor, Windsurf, and other MCP-compatible AI tools.
- [Anthropic Tool Calling](https://docs.seltz.ai/integrations/anthropic-tool-calling.md): Integrate Seltz search as a tool for Claude models using the Anthropic API.
- [OpenAI Tool Calling](https://docs.seltz.ai/integrations/openai-tool-calling.md): Integrate Seltz search as a tool for OpenAI models using the Chat Completions API.
- [Mistral Tool Calling](https://docs.seltz.ai/integrations/mistral-tool-calling.md): Integrate Seltz search as a tool for Mistral models using the Mistral AI API.
- [Zapier](https://docs.seltz.ai/integrations/zapier.md): Use Seltz web search in Zapier automations.
- [viaSocket](https://docs.seltz.ai/integrations/viasocket.md): Use Seltz web search in viaSocket flows to automate your workflows.
- [n8n](https://docs.seltz.ai/integrations/n8n.md): Use Seltz web search in n8n workflows with the Seltz community node.
- [Dify](https://docs.seltz.ai/integrations/dify.md): Add web search capabilities to your Dify workflows with the Seltz plugin.
- [Agno](https://docs.seltz.ai/integrations/agno.md): Build AI agents with Seltz search capabilities using the Agno framework.
- [Langroid](https://docs.seltz.ai/integrations/langroid.md): Add context-engineered web search to your Langroid agents with SeltzSearchTool.
- [LlamaIndex](https://docs.seltz.ai/integrations/llamaindex.md): Add web search capabilities to your LlamaIndex agents and RAG pipelines with SeltzToolSpec.
- [Installation](https://docs.seltz.ai/sdks/python/installation.md): Install the Seltz Python SDK.
- [Quickstart](https://docs.seltz.ai/sdks/python/quickstart.md): Make your first Seltz search in Python.
- [Client Reference](https://docs.seltz.ai/sdks/python/client.md): Complete Python SDK API reference.
- [Installation](https://docs.seltz.ai/sdks/javascript/installation.md): Install the Seltz JavaScript/TypeScript SDK.
- [Quickstart](https://docs.seltz.ai/sdks/javascript/quickstart.md): Make your first Seltz search in JavaScript/TypeScript.
- [Client Reference](https://docs.seltz.ai/sdks/javascript/client.md): Complete JavaScript/TypeScript SDK API reference.
- [cURL](https://docs.seltz.ai/sdks/rest/curl.md): Use the Seltz API with cURL.
- [Introduction](https://docs.seltz.ai/api-reference/introduction.md): The Seltz REST API for search, answers, monitors, page fetching, and agent runs
- [Errors](https://docs.seltz.ai/api-reference/errors.md): Error response shape and status codes for the Search and Answer endpoints
- [Search](https://docs.seltz.ai/api-reference/search.md)
- [Answer](https://docs.seltz.ai/api-reference/answer.md)
- [Fetch](https://docs.seltz.ai/api-reference/fetch.md)
- [Start run](https://docs.seltz.ai/api-reference/agent/start-run.md): Returns the new run in `pending` state. Poll it by id until `status` reaches a terminal state.
- [List runs](https://docs.seltz.ai/api-reference/agent/list-runs.md): The organization's runs, newest first. Pass one page's `next` as the following request's `after`.
- [Get run](https://docs.seltz.ai/api-reference/agent/get-run.md): Poll until `status` reaches a terminal state.
- [Cancel run](https://docs.seltz.ai/api-reference/agent/cancel-run.md): Stop a run that has not finished. Returns the run, unchanged if it had already ended, so cancelling is safe to retry.
- [Create monitor](https://docs.seltz.ai/api-reference/monitor/create-monitor.md)
- [List monitors](https://docs.seltz.ai/api-reference/monitor/list-monitors.md)
- [Get monitor](https://docs.seltz.ai/api-reference/monitor/get-monitor.md)
- [Update monitor](https://docs.seltz.ai/api-reference/monitor/update-monitor.md)
- [Delete monitor](https://docs.seltz.ai/api-reference/monitor/delete-monitor.md)
- [List records](https://docs.seltz.ai/api-reference/monitor/list-records.md)
- [List runs](https://docs.seltz.ai/api-reference/monitor/list-runs.md)
- [Get run](https://docs.seltz.ai/api-reference/monitor/get-run.md)
- [List run requests](https://docs.seltz.ai/api-reference/monitor/list-run-requests.md): The only place a customer can tell *this query failed* from *there was genuinely nothing new*: records are a stream of positives, and absence cannot be inferred from presences.
- [List run records](https://docs.seltz.ai/api-reference/monitor/list-run-records.md): Exists so that no consumer does arithmetic on a record id: a webhook carries a run's record range as a bound, not a dense sequence.
- [OpenAPI Specification](https://docs.seltz.ai/api-reference/openapi-spec.md): Generate clients from our OpenAPI specification.
- [Configurable content and snippet limits](https://docs.seltz.ai/changelog/2026-09-configure-fields.md): fields.content and fields.snippets now accept a config object, not just true or false.
- [New Data Scope: Financial Reports](https://docs.seltz.ai/changelog/2026-09-financial-reports.md): Search and Answer can now scope results to financial reports — 18.7 million SEC filings dating back to 1994, chunked and indexed for precise, retrieval-ready results.
- [Effort Levels for Agent](https://docs.seltz.ai/changelog/2026-09-agent-effort.md): Control how much research depth an Agent run applies with the new effort parameter, from a fast low pass to an exhaustive max run.
- [Snippets for Search](https://docs.seltz.ai/changelog/2026-09-search-snippets.md): Request a document's highest-scoring passages instead of, or alongside, its full content.
- [New Data Scope: Financial Reports](https://docs.seltz.ai/changelog/2026-09-financial-reports.md): Search and Answer can now scope results to financial reports — 18.7 million SEC filings dating back to 1994, chunked and indexed for precise, retrieval-ready results.
- [Introducing Agent](https://docs.seltz.ai/changelog/2026-09-agent.md): Turn a question into a cited, in-depth answer. Agent plans its own searches, follows up on what it finds, and keeps going until it has enough, rather than stopping after one grounding search.
- [Search Tiers: Base and Pro](https://docs.seltz.ai/changelog/2026-09-search-tiers.md): Trade result quality for lower latency with the new tier parameter — pro is the quality-oriented default, base is the latency-oriented option.
- [Introducing Fetch](https://docs.seltz.ai/changelog/2026-09-fetch.md): Turn up to 20 URLs into LLM-ready Markdown in one call. Fetch returns one result per URL, keyed by the URL you sent.
- [Introducing Monitor](https://docs.seltz.ai/changelog/2026-09-monitor.md): Turn a set of searches into a feed. Monitor re-runs your searches on a cadence and delivers only what's new, with an optional webhook so you don't have to poll.
- [New Data Scopes: People, Companies, and Wikipedia](https://docs.seltz.ai/changelog/2026-08-data-scopes.md): Search and Answer can now scope results to dedicated people, company, and Wikipedia indexes, not just news.
- [System Prompt for Answer](https://docs.seltz.ai/changelog/2026-08-answer-system-prompt.md): Steer how an answer is written — tone, voice, format — with the new system_prompt parameter, while grounding and citations stay in force.
- [Structured Output for Answer](https://docs.seltz.ai/changelog/2026-08-answer-structured-output.md): Pass an OpenAI-style response_format to /answer and get the answer back as JSON matching your own schema, with citations intact.
- [Answer Pro Tier](https://docs.seltz.ai/changelog/2026-07-answer-pro.md): Select the answer tier with the new model parameter — seltz-pro runs agentic RAG over a single grounding search.
- [OpenAI-Compatible Chat Completions](https://docs.seltz.ai/changelog/2026-05-chat-completions.md): Seltz now serves an OpenAI-compatible /v1/chat/completions endpoint for web-grounded RAG.
- [Answer Endpoint](https://docs.seltz.ai/changelog/2026-05-answer-endpoint.md): Get direct, natural-language answers grounded in live web search, with citations.
- [n8n Community Node](https://docs.seltz.ai/changelog/2026-04-n8n-node.md): Seltz is now available as an n8n community node for workflow automation.
- [Langroid Integration](https://docs.seltz.ai/changelog/2026-03-langroid-integration.md): Seltz is now available as a search provider in the Langroid multi-agent framework.
- [LlamaIndex Integration](https://docs.seltz.ai/changelog/2026-02-llamaindex-integration.md): Add web search capabilities to your LlamaIndex agents and RAG pipelines.
- [Dify Integration](https://docs.seltz.ai/changelog/2026-01-dify-integration.md): Add web search capabilities to your Dify workflows with the Seltz plugin.
- [Agno Integration](https://docs.seltz.ai/changelog/2026-01-agno-integration.md): Build AI agents with Seltz search capabilities using the Agno framework.
- [TypeScript SDK](https://docs.seltz.ai/changelog/2026-01-typescript-sdk.md): First stable release of the official Seltz TypeScript SDK.
- [MCP Server](https://docs.seltz.ai/changelog/2025-12-mcp-server.md): Introduction of the official Seltz MCP server for AI-native integrations.
- [Python SDK](https://docs.seltz.ai/changelog/2025-12-python-sdk.md): First stable release of the official Seltz Python SDK.

## OpenAPI Specs

- [openapi](/api-reference/openapi.json)

## Optional

- [Playground](https://console.seltz.ai/playground)
- [About](https://seltz.ai/about)
- [Book a Call](https://cal.com/antonio-mallia-c7uyfc/seltz-intro-call)


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.