Zhipu IDs, OpenAI wire format
Send zhipu/glm-5 on Chat Completions. No extra GLM SDK for the happy path.
GLM-5 through GLM-4.7 on the same OpenAI-compatible endpoint as DeepSeek and Qwen. Built for coding and agent workloads.
Why SupaNexus
Send zhipu/glm-5 on Chat Completions. No extra GLM SDK for the happy path.
GLM-5 for flagship agent/coding work; GLM-4.7 when you want a proven production coding model.
Mix GLM with DeepSeek or Qwen under the same project key and spend cap.
Catalog
Public API IDs use the zhipu/ vendor prefix. Always send the full ID.
| Model | Public API ID | Context | Best for |
|---|---|---|---|
| GLM-5 | zhipu/glm-5 | 200K | FlagshipCodingAgents |
| GLM-5.2 | zhipu/glm-5.2 | 1M | FlagshipLong context |
| GLM-5.1 | zhipu/glm-5.1 | 200K | ChatAgents |
| GLM-4.7 | zhipu/glm-4.7 | 200K | CodingProduction |
Live rates are in the developer console. See also homepage pricing · console catalog
Quickstart
Official OpenAI SDK. Model ID zhipu/glm-5.
https://api.supanexus.ai/v1
Python
from openai import OpenAI
client = OpenAI(
base_url="https://api.supanexus.ai/v1",
api_key="sk-snx-...",
)
response = client.chat.completions.create(
model="zhipu/glm-5",
messages=[{"role": "user", "content": "Hello!"}],
)
print(response.choices[0].message.content)
FAQ
Vendor prefix, SKU choice, and compatibility.
SupaNexus Public API IDs are vendor/model. GLM is published under Zhipu, so the prefix is zhipu/.
Start with zhipu/glm-5 for new agent and coding work. zhipu/glm-4.7 remains a strong production coding SKU. zhipu/glm-5.2 when you need the 1M context window.
Yes. https://api.supanexus.ai/v1 plus a SupaNexus project key.
Same Chat Completions client. Swap the model ID to zhipu/glm-5.