API reference · WeChat Search

wechat-search/v2/search-videos

Integrate this model through SandBase's unified API, with production-ready schemas and examples.

APISynchronousOpen model
Production endpoint

Send your first request

OpenAI-compatible endpoint with unified authentication and usage tracking.

POSThttps://api.sandbase.ai/v1/run
Model IDwechat-search/v2/search-videos
01

Input Schema

7 parameters · 1 required · 6 optional

ParameterTypeRequiredDescription
keywordstringRequiredSearch keyword (1-100 chars) · Min length: 1 · Max length: 100
rawbooleanOptionalOptional, default True. True=raw search response; False=simplified parsing. · Default: true
sortunionOptionalOptional, default `default`. Sort — `default`/0 (relevance) / `latest`/1 (newest) / `hot`/2 (most liked); string key or integer, invalid values rejected (400). · Default: "default"
cursorunionOptionalOptional. Pagination cursor, same usage as universal search `/fetch_search`. Leave empty for the first page; for the next page pass back the `cursor` from the previous response (repeat the same `duration` / `sort` / `publish_time`).
offsetintegerOptionalOptional, default 0 (>=0). Pass `0` for the first page; use `cursor` to paginate (offset alone does not work). · Min: 0 · Default: 0
durationunionOptionalOptional, default `all`. Duration tier (Channels video only) — `all`/0 / `short`/1 (<5min) / `medium`/2 (5-10min) / `long`/3 (20min+); string key or integer, invalid values rejected (400). · Default: "all"
publish_timeunionOptionalOptional, default `all`. Publish time — `all`/0 / `day`/1 / `week`/2 / `half_year`/3; string key or integer, invalid values rejected (400). · Default: "all"
02

Output Schema

FieldTypeDescription
idstringUnique identifier for the generation task
statusstringTask status: pending, running, completed, failed, timeout
modelstringModel used for the generation
outputsarrayArray of output items
outputs[].urlstringURL of the generated artifact
outputs[].content_typestringMIME type (e.g. image/png, video/mp4)
errorobject | nullError details if failed, null on success
error.typestringMachine-readable error type code
error.messagestringHuman-readable error description
03

Code Examples

Ready-to-run snippets

const apiKey = process.env.SANDBASE_API_KEY;
const response = await fetch("https://api.sandbase.ai/v1/run", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${apiKey}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    "model": "wechat-search/v2/search-videos",
    "raw": true,
    "sort": "default",
    "offset": 0,
    "duration": "all",
    "publish_time": "all"
  }),
});

if (!response.ok) throw new Error(await response.text());
console.log(await response.json());