GPT-5.6 Luna (batch) vs GPT-5.6 Sol
One line per model: the best value available from any of its providers at each point, which is what a caller routing to the healthy endpoint would see.
CompareGPT-5.6 Luna (batch)GPT-5.6 Sol
| Model | Providers | Best uptime | Fastest p50 | Best p99 | Throughput | Context | Cheapest $/Mtok |
|---|---|---|---|---|---|---|---|
| GPT-5.6 Luna (batch) | 0/3 | — | — | — | — | 1.1M | $0.050 / $0.300 OpenAI |
| GPT-5.6 Sol | 5/7 | 100% Azure | 1.80s OpenAI | 9.24s OpenAI | 54 tps OpenAI | 1.1M | $1.25 / $7.50 OpenAI |
History
Availability
Best uptime available from any provider. Axis starts at 90%; it expands to 0 when a model falls below.
Time to first token
Fastest p50 available from any provider. Logarithmic axis.
Throughput
Best median tokens per second available.