COMPARE
Prices are what this site actually bills; performance comes from 30 days of real traffic. Updated automatically.
Real settlement price per million tokens; struck figures are upstream list prices.
| Metric | glm-5.2 | gpt-5.6-luna |
|---|---|---|
| Input /1M | $1.12$1.40 | $1.00 |
| Output /1M | $3.52$4.40 | $6.00 |
| Cached /1M | $0.208$0.260 | — |
| Cache write /1M | — | $1.25 |
| 1M input + 1M output total | $4.64 | $7.00 |
| Endpoints | glm-5.2 | gpt-5.6-luna |
|---|---|---|
| openai | ✓ | ✓ |
| openai-response | ✓ | ✓ |
| openai-response-compact | ✓ | ✓ |
| anthropic | ✓ | ✓ |
| gemini | ✓ | ✓ |
| openai-alpha-search | ✓ | ✓ |
On CompassApi, glm-5.2 and gpt-5.6-luna share the same OpenAI-compatible endpoint and the same API key — switching is a one-line model change, so you can run both and keep whichever fits.
client.chat.completions.create(
model="glm-5.2", # ← "gpt-5.6-luna"
messages=[{"role": "user", "content": "Hello"}],
)