API reference · TikTok

tiktok/ads/search-ads

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 IDtiktok/ads/search-ads
01

Input Schema

12 parameters · 0 required · 12 optional

ParameterTypeRequiredDescription
likeintegerOptionalLike count filter, 1=All
pageintegerOptionalPage number, default 1
limitintegerOptionalItems per page, default 20, max 50
periodintegerOptionalTime period in days, e.g., 7, 30, 120, 180 days
keywordstringOptionalSearch keyword, optional, returns all ads if empty
industrystringOptionalIndustry ID list, multiple IDs separated by commas. Full industry ID list: https://github.com/TikHub/TikTok-Ads-Industry-Code
order_bystringOptionalSort method, "for_you"=Recommended, "likes"=Sort by likes
ad_formatintegerOptionalAd format, 1=Video ads
objectiveintegerOptionalAd objective, 1=All
search_idstringOptionalSearch ID (optional)
ad_languagestringOptionalAd language code, e.g., en, zh
country_codestringOptionalCountry code, e.g., US, UK, JP
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": "tiktok/ads/search-ads"
  }),
});

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