# Zhihu API for AI agents and LLMs: fewer tokens, called from Claude and Cursor (2026)

DataXAPI has 16 Zhihu endpoints, and what an AI reads of them through MCP takes 91% fewer tokens than the platform's raw JSON: a page of Zhihu search results is 194k tokens raw and 9,901 as the AI reads it. One key, no Zhihu account of yours. The free trial covers up to 333 calls; a failed call is not charged.

Updated 2026-11-06

## Why does an agent care how big an answer is?

Every token of a tool's answer goes into the agent's context and is paid for as input. Zhihu's raw JSON is made for its own app, with many fields nested deep. Across DataXAPI's 16 Zhihu endpoints, one recorded real response each, the raw JSON comes to 712k tokens and what an AI reads through MCP to 63k. With the context saved, an agent reads more pages and takes more steps in one conversation, and sooner.

Every platform uses the same names: the author in `author`, counts in `metrics`, the time in `published_at` as UTC, the next page in `page.next_cursor`. A field the platform does not give is listed in `meta.unavailable`, so the AI does not read it as 0.

## How do I connect it?

To connect: paste this to your AI assistant: “Read https://dataxapi.com/agents.md and set up DataXAPI here. My API key is dx_…; use it for every DataXAPI call.” A client that takes a remote MCP server can be given `https://api.dataxapi.com/mcp` with the header `Authorization: Bearer <key>` instead.

## What to ask once it is connected

Say what you want: the agent finds the endpoint and its price, then calls it; finding and reading parameters are free.

| You say | What it calls |
| --- | --- |
| Zhihu answers and articles on camping | `zhihu.posts.search` |
| The most upvoted answers to this question | `zhihu.questions.answers.list` |
| The comments under this answer | `zhihu.answers.comments.list` |
| Today's top 10 on Zhihu's hot list | `zhihu.trends.list` |

## What does it cost?

Paid per call; a failed call is not charged. A page of Zhihu search results is $0.0020; the free trial covers up to 333 calls. Give the agent its own key with a limit; `X-Max-Price` caps what one call may cost.

## Why DataXAPI

- Steady: endpoints were available 100% of the last 30 days, on a public status page you can check.
- Fast: a paid call took 1.7 seconds at the median over the last 7 days (counted 2026-11-06).
- Fewer tokens: across 16 endpoints on Zhihu, one recorded real response each, the platform's own JSON comes to 712k tokens and what an AI reads through DataXAPI's MCP server to 63k, 91% fewer; the JSON of a direct API call is 73% fewer too (counted 2026-11-06). Every platform answers in one shape: the author in `author`, counts in `metrics`, the next page in `page.next_cursor`, so another platform needs no new parser.
- See before you pay: every endpoint's page shows a recorded real response, field by field.
- Spending you control: a failed call is not charged; each key can have a limit, `X-Max-Price` caps one call, and the same `Idempotency-Key` within 24 hours is never charged twice.
- Ready for AI: a remote MCP server listed in the official MCP registry as `com.dataxapi/mcp`, usable from Claude, Cursor and ChatGPT.
- Free trial of up to 333 calls, no card.

## Endpoints

- [Zhihu content search](https://dataxapi.com/apis/zhihu/posts/search/) ($0.0020 / a call): Get a page of Zhihu answers and articles matching a search; either kind alone, by relevance, newest or most upvoted.
- [Zhihu question answers](https://dataxapi.com/apis/zhihu/questions/answers/list/) ($0.0020 / a call): Get the first 20 answers to a Zhihu question by ID or link, in Zhihu's own order: text, author, upvotes, comment and save counts. One page only.
- [Zhihu answer comments](https://dataxapi.com/apis/zhihu/answers/comments/list/) ($0.0020 / a call): Get a page of comments on a Zhihu answer: text, commenter, likes, reply count, time posted.
- [Zhihu hot list](https://dataxapi.com/apis/zhihu/trends/list/) ($0.0020 / a call): Get Zhihu's hot list: the questions on it, their rank, heat (approximate) and answer count; an entry's ID is its question's.

## How-to guides

- [Zhihu API in Python: questions and answers (2026)](https://dataxapi.com/guides/zhihu-api-python/)

## More about Zhihu

- [Zhihu API](https://dataxapi.com/apis/zhihu/)
- [What is x-zse-96 on Zhihu? (2026)](https://dataxapi.com/answers/zhihu-x-zse-96/)
- [My Zhihu scraper stopped working: what now? (2026)](https://dataxapi.com/answers/zhihu-scraper-not-working/)
- [How do I let my AI read Zhihu, Bilibili and Weibo? (2026)](https://dataxapi.com/answers/ai-read-zhihu-bilibili-weibo/)
- [What does Zhihu error 40362 mean? (2026)](https://dataxapi.com/answers/zhihu-40362/)
- [Zhihu API: questions, answers and comments (2026)](https://dataxapi.com/answers/zhihu-data-apis/)
- [Zhihu MCP server for Claude and Cursor (2026)](https://dataxapi.com/answers/zhihu-mcp/)
- [How to find Zhihu question and answer ids (2026)](https://dataxapi.com/answers/zhihu-question-answer-id/)

---

Catalog revision 9d3b7fa5a896745d. [HTML version](https://dataxapi.com/answers/zhihu-api-for-ai-agents/)