TheRouter.aiTheRouter.ai
Back to Models

GLM-5.3

zaizai/glm-5.3

Z.AI GLM-5.3 — text-only flagship with a 1M-token context window and 128K maximum output. Reasoning is always on: the vendor documents three effort levels (low, high, max) and no longer supports disabling it.

Context Length
1M
Max Output
131K
Input Priceper 1M tokens
$1.51/ 1M tokens
Output Priceper 1M tokens
$4.75/ 1M tokens

Modalities

text→text

Pricing Breakdown

TypeRate
Input$1.51 / 1M tokens
Output$4.75 / 1M tokens

Supported Parameters

temperaturemax_tokenstop_ptoolstool_choiceresponse_formatstopreasoning_effort

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": "zai/glm-5.3",
    "messages": [
      {"role": "user", "content": "Summarize the key points from this input."}
    ]
  }'
Customer Support