GPT-5.6 Luna vs GPT-5.6 Luna Pro
API pricing, context, and independently measured performance, side by side.
GPT-5.6 Luna
OpenAI · released Jul 9, 2026
Best input$0.10 / MTok
Best output$0.60 / MTok
Context1.05M
Providers7
Fastest measured2.7s° TTFT · 203 tok/s
VisionToolsReasoningStructured outputPrompt caching
GPT-5.6 Luna Pro
OpenAI · released Jul 9, 2026
Best input$0.10 / MTok
Best output$0.60 / MTok
Context1.05M
Providers5
Fastest measured7.4s° TTFT · 928 tok/s
VisionToolsReasoningStructured outputPrompt caching
Cheapest providers, measuredUSD / MTOK
| MODEL | PROVIDER | INPUT | OUTPUT | TTFT | TPS | SMOKE |
|---|---|---|---|---|---|---|
| GPT-5.6 Luna |  OpenAI | $0.10 | $0.60 | 2.7s° | 203° tok/s | — |
| GPT-5.6 Luna |  Azure | $0.20 | $1.20 | 2.7s° | 47° tok/s | — |
| GPT-5.6 Luna |  Amazon Bedrock | $0.22 | $1.32 | — | — | — |
| GPT-5.6 Luna Pro | OpenAI | $0.10 | $0.60 | 7.4s° | 928° tok/s | — |
| GPT-5.6 Luna Pro | Azure | $0.20 | $1.20 | 9s° | 783° tok/s | — |
TTFT/TPS: ModelIndex-measured medians (P50, trailing 72h) · chat10k profile (~10K in / 200 out) · ° = measured via OpenRouter routing (adds a hop) · SMOKE: of 5 programmatic capability probes passed · methodology v1.1 — full details on each model page