GLM 5.2 is an AI model provided by Zhipu AI, accessible via the OpenAI-compatible API.
Context window
—
tokens
Max output
—
tokens
Input price
0.123 金币
0.176 金币
/ 1M tokens
Output price
0.431 金币
0.616 金币
/ 1M tokens
Replace base_url and api_key below with your own to call GLM 5.2. Fully OpenAI SDK compatible — no other code changes needed.
curl https://api.piomodel.com/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer sk-your-key" \
-d '{
"model": "glm-5.2",
"messages": [{"role": "user", "content": "Hello"}]
}'Q: How is GLM 5.2 priced?
A: Pay per token: $0.123 金币/M input, $0.431 金币/M output. No monthly fee, no minimum spend. Credits never expire.
Q: How do I integrate GLM 5.2? Any code changes?
A: Fully OpenAI-compatible — just swap base_url and api_key. Claude models also support the native Anthropic /v1/messages format. See the code snippets above.
Q: Is GLM 5.2 stable through PioMode?
A: All requests go through our API gateway (api.piomodel.com) with optimized third-party backbone routing. Average latency under 200ms, reliable under any network condition.
Q: What use cases does GLM 5.2 support?
A: General chat, generation, and reasoning. Refer to Zhipu AI's official documentation for specific capabilities.
Q: Does GLM 5.2 have a free tier?
A: New users get free credits after email verification, ready for immediate API testing. Top up from $10 afterwards, pay as you go.
Free credits on sign-up. Pay as you go. $10 minimum top-up, no expiration.