StarSeaAPI
glm-4.5-air vs glm-4.7
| glm-4.5-air | glm-4.7 | |
|---|---|---|
| Providers | Zhipu AI | Zhipu AI |
| Input $/M | $0.12 | $0.30 |
| Output $/M | $0.30 | $1.21 |
| Output multiplier | ×2.50 | ×4.00 |
| Context window | 128K tokens | 200K tokens |
| Intelligence index | — | — |
| Coding index | — | 45.3 |
What the numbers mean
glm-4.5-air is roughly 2.5× cheaper on input than glm-4.7. If your workload passes the quality bar on the cheaper model, that gap compounds across every request; route to glm-4.7 deliberately rather than by default.
Tags: glm-4.5-air — Chat, Reasoning, Coding · glm-4.7 — Chat, Reasoning, Coding
Code
from openai import OpenAI
client = OpenAI(base_url="https://starseaapi.com/v1", api_key="sk-...")
# glm-4.5-air
client.chat.completions.create(model="glm-4.5-air", messages=[{"role":"user","content":"Hi"}])
# glm-4.7
client.chat.completions.create(model="glm-4.7", messages=[{"role": "user", "content": "Hi"}])