GLM-5.2
Zhipu GLM-5.2 flagship model for long-horizon coding and agentic engineering tasks with a 1M context window.
glm-5.2Get API keyContext window
1M
tokens
Max output
33k
tokens
Input
$0.55
per 1M tokens
Output
$1.78
per 1M tokens
Quick start
1curl https://api.vichar.io/v1/chat/completions \2 -H "Authorization: Bearer $VICHAR_API_KEY" \3 -H "Content-Type: application/json" \4 -d '{5 "model": "glm-5.2",6 "messages": [{"role": "user", "content": "Hello"}]7 }'
Supported parameters
- messages
- model
- stream
- stream_options
- temperature
- top_p
- max_tokens
- max_completion_tokens
- seed
- stop
- response_format
- tools
- tool_choice
- parallel_tool_calls
- reasoning
- reasoning_effort