Back to Models

GLM Search Std

zhipuzhipu/search-std

Cheapest citation-aware web search from BigModel.

search-std is the entry-level search engine from Zhipu BigModel. Every call returns up to ten ranked web pages with title, URL, and a content snippet, billed at a flat $0.0036 per request β€” no token math.

Use it when you need fast, low-cost retrieval grounding for a chat agent, blog summariser, or research assistant. Responses arrive wrapped in an OpenAI-style chat completion with `url_citation` annotations, so any client that already parses OpenAI tool output can adopt it without a rewrite.

Citation annotations
Each result is exposed as a `url_citation` annotation with `start_index`/`end_index` pointing into the rendered markdown body.
Per-request billing
$0.0036 per call. `usage.web_search_requests: 1` on success β€” no prompt/completion tokens.
OpenAI-compatible envelope
Returned as a standard `chat.completion`. Existing OpenAI SDKs work unchanged.
Trilingual content
Indexes Chinese, English, and other-language content out of the same query.
When to use
Low-budget grounding for chat answers, daily-digest builders, and anywhere you only need a handful of links and don't care about engine provenance.
When not to use
Avoid if you need source-engine selection (Sogou vs Quark vs Pro) or richer content snippets β€” use search-pro / search-pro-sogou / search-pro-quark instead.
Pricing: Flat $0.0036 per call. No token charges.
Read the web-search tutorial β†’
Context Length
8K
Max Output
--
Request Priceper request
$0.0036/ request

Modalities

text→text

Pricing Breakdown

TypeRate
Request$0.0036 / request

Supported Parameters

search_recency_filtersearch_domain_filtercontent_size

API Usage Examples

Use the global api.therouter.ai endpoint shown below for new integrations; the legacy China accelerated endpoint is retired.

cURL
curl https://api.therouter.ai/v1/chat/completions   -H "Content-Type: application/json"   -H "Authorization: Bearer $THE_ROUTER_API_KEY"   -d '{
    "model": "zhipu/search-std",
    "messages": [
      {"role": "user", "content": "Summarize the key points from this input."}
    ]
  }'
Customer Support