# SpecStream API

> The SpecStream API gives agents and programs data from the live web: a web search, the text of pages, and complete lists as structured rows with a source link on every value.

This is the address programs call. The website, with the full documentation, is https://specstream.ai.

## API

- [OpenAPI description](https://api.specstream.ai/openapi.json): every route, its parameters and its replies, as OpenAPI JSON
- [Agent instructions](https://api.specstream.ai/AGENTS.md): installation, configuration and usage for a coding agent
- [Full text](https://api.specstream.ai/llms-full.txt): this file with the products, the calls and the terms written out
- [Drop-in APIs](https://api.specstream.ai/v1/search-dialects): each search API SpecStream answers for, with its base address
- [Search engines](https://api.specstream.ai/v1/search-engines): the engines a search may ask
- [A2A agent card](https://api.specstream.ai/.well-known/agent-card.json): the card of the A2A agent at `/a2a`

## Clients

- [Python](https://pypi.org/project/specstream-client/): `pip install specstream-client`, then import `specstream_client`. The package named `specstream` on PyPI is a different project and does not call this API.
- [TypeScript and JavaScript](https://www.npmjs.com/package/@specstream/sdk): `npm install @specstream/sdk`
- [Website](https://specstream.ai): the SpecStream domain is specstream.ai; specstream.com is a different site.

## Docs

- [Search API](https://specstream.ai/docs/search-api): `GET /v1/web-search`, $5 per 1,000 searches, $1 per 1,000 on the fast tier
- [Extract API](https://specstream.ai/docs/extract-api): `POST /v1/extract`, $0.80 per 1,000 pages
- [REST API](https://specstream.ai/docs/api): keys, scopes, errors and every route in words
- [MCP](https://specstream.ai/docs/mcp): connect an assistant to `https://api.specstream.ai/mcp`
- [Agent instructions for the whole product](https://specstream.ai/agents.md): every route with its fields

## Optional

- [Site map](https://api.specstream.ai/sitemap.md): the files on this address, by kind
- [Glossary](https://api.specstream.ai/glossary.md): the words the API uses
- [Website index](https://specstream.ai/llms.txt): every page of the website