DeepSeek search and fetch – $0.75 per 1000 successful requests

The Search API and the Fetch API give agents and RAG applications access to live web content:

Search API 和 Fetch API 为智能体和 RAG 应用提供了访问实时网络内容的能力：

Both are raw JSON APIs. They use the same bearer authentication as the DeepSeek API.

两者均为原始 JSON API。它们使用与 DeepSeek API 相同的持有者（bearer）身份验证。

The base URL is https://api.deepseek.com:

基础 URL 为 https://api.deepseek.com：

See the Search API Reference and Fetch API Reference for the complete request and response schemas.

请参阅 Search API 参考文档和 Fetch API 参考文档以获取完整的请求和响应模式。

Send your API key and the JSON content type in the request headers:

在请求头中发送您的 API 密钥和 JSON 内容类型：

Unknown fields in the request body are ignored.

请求体中的未知字段将被忽略。

The query is forwarded with its search syntax intact. The examples below combine operators with a search term; you can combine multiple operators in one query.

查询内容在转发时会保留其搜索语法。下方的示例将运算符与搜索词结合使用；您可以在一个查询中组合多个运算符。

A successful request returns HTTP 200 with a results array. A normal search with no matches returns an empty array.

成功的请求会返回 HTTP 200 以及一个结果数组。未匹配到结果的正常搜索会返回一个空数组。

Each item in results contains:

结果中的每一项包含：

Fetching is subject to the target site’s availability and access policies.

抓取操作受目标网站的可用性和访问策略限制。

Errors follow the OpenAI-compatible error format. The param field is always null.

错误遵循与 OpenAI 兼容的错误格式。param 字段始终为空（null）。

Search and Fetch are read-only. For HTTP 408, 429, or 5xx errors, wait and retry. For HTTP 402, top up your account before retrying. Do not retry other 4xx errors without changing the request.

Search 和 Fetch 为只读接口。对于 HTTP 408、429 或 5xx 错误，请等待并重试。对于 HTTP 402 错误，请在重试前为账户充值。在未更改请求的情况下，请勿重试其他 4xx 错误。

Search and Fetch are billed per successful request, not by tokens or by the number of returned results:

Search 和 Fetch 按成功请求计费，而非按 Token 或返回结果的数量计费：

A request is billable only when it returns HTTP 200 and produces a result (Search must return a non-empty results array, and Fetch must return page content). Failed requests, empty search results, and timeouts are not billed. count only controls how many results are returned and does not affect the per-request price.

仅当请求返回 HTTP 200 并产生结果时才计费（Search 必须返回非空结果数组，Fetch 必须返回页面内容）。失败的请求、空的搜索结果以及超时请求不计费。count 参数仅控制返回结果的数量，不影响单次请求的价格。

Note: when you use the DeepSeek API through DeepSeek Harness, Claude Code, or Codex, server-side tool calls already hit the Search and Fetch APIs. These calls are currently free of charge; per-request billing starts at 00:00 Beijing time on November 1, 2026.

注意：当您通过 DeepSeek Harness、Claude Code 或 Codex 使用 DeepSeek API 时，服务器端工具调用已经在使用 Search 和 Fetch API。这些调用目前免费；按请求计费将于北京时间 2026 年 11 月 1 日 00:00 开始。

For each account, Search and Fetch are limited independently, and traffic to one does not consume the other’s quota:

对于每个账户，Search 和 Fetch 是独立限制的，访问其中一个接口不会消耗另一个接口的配额：

The QPS (requests per second) limits are calculated at the account level, regardless of which API key is used, and are separate from the model concurrency limits. Requests above the account-level QPS limit receive HTTP 429. In addition to the account-level limit, Fetch is also subject to a per-domain QPS limit, and requests above that limit also receive HTTP 429.

QPS（每秒请求数）限制按账户级别计算，无论使用哪个 API 密钥，且与模型并发限制分开。超过账户级 QPS 限制的请求将收到 HTTP 429 错误。除账户级限制外，Fetch 还受限于特定域名的 QPS 限制，超过该限制的请求同样会收到 HTTP 429 错误。