GPT-5.6 Luna (No Thinking)
no thinkPublic list price, verified 8h ago · batch jobs 50% off · cached input $0.02 /M
Benchmarks
math
AIME-style competition problems written specifically for the OTIS mock contest, then run as an evaluation by Epoch AI. Closer in spirit to the public AIME but with novel problems unlikely to appear in training data.
Reliability monitor
Loading drift signal…
Hosted endpoints
No third-party hosts tracked for this model — available only from its primary provider.
Effort variants
Same API model, different reasoning budget. Thinking / xHigh modes usually score better on reasoning benchmarks but emit many more output tokens per request. Higher effort is also an alternative to running a team of agents: check whether the extra points are worth the extra output.
| Variant | Index | vs this page | Blended $/M | Output tokens |
|---|---|---|---|---|
| GPT-5.6 Luna (No Thinking)no think | — | this page | $0.45 | 1× |
| GPT-5.6 Luna | 75.2 | — | $0.23 | 1× |
| GPT-5.6 Luna Propro | — | — | $0.23 | 10× |
Output tokens are the typical multiple of a standard answer that the cost calculator assumes for each effort level; hidden reasoning bills as output.