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 | codex-auto-review | gpt-5.6-sol |
|---|---|---|
| Input /1M | $75.00 | $5.00 |
| Output /1M | $75.00 | $30.00 |
| Cache write /1M | — | $6.25 |
| 1M input + 1M output total | $150 | $35.00 |
| Endpoints | codex-auto-review | gpt-5.6-sol |
|---|---|---|
| openai | ✓ | ✓ |
| openai-response | ✓ | ✓ |
| openai-response-compact | ✓ | ✓ |
| anthropic | ✓ | ✓ |
| gemini | ✓ | ✓ |
| openai-alpha-search | ✓ | ✓ |
On CompassApi, codex-auto-review and gpt-5.6-sol 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="codex-auto-review", # ← "gpt-5.6-sol"
messages=[{"role": "user", "content": "Hello"}],
)