Description
GLM-4-32B-0414 is a 32B bilingual (Chinese-English) open-weight language model optimized for code generation, function calling, and agent-style tasks. Pretrained on 15T of high-quality and reasoning-heavy data, it was further refined using human preference alignment, rejection sampling, and reinforcement learning. The model excels in complex reasoning, artifact generation, and structured output tasks, achieving performance comparable to GPT-4o and DeepSeek-V3-0324 across several benchmarks.
API Usage Examples
OpenAI Compatible Endpoint
Use this endpoint with any OpenAI-compatible library. Model: THUDM: GLM 4 32B (thudm/glm-4-32b)
curl https://api.ridvay.com/v1/chat/completions -H "Content-Type: application/json" -H "Authorization: Bearer YOUR_API_KEY" -d '{
"model": "thudm/glm-4-32b",
"messages": [
{
"role": "user",
"content": "Explain the capabilities of the THUDM: GLM 4 32B model"
}
],
"temperature": 0.7,
"max_tokens": 1024
}'Supported Modalities
- Text
API Pricing
- Input: 0.55$ / 1M tokens
- Output: 1.66$ / 1M tokens
Token Limits
- Max Output: 32,000 tokens
- Max Context: 32,000 tokens
Subscription Tiers
- free
- pro
- ultimate