Gemini 3.6 Flash vs GPT-5.6 Luna Pro
Side-by-side API pricing and Artificial Analysis performance for Gemini 3.6 Flash (Google) and GPT-5.6 Luna Pro (OpenAI). Green cells mark the better value in each row.
Prices updated Sep 13, 2026, 11:39 PM UTC · refreshed hourly
| Gemini 3.6 Flash | GPT-5.6 Luna Pro OpenAI | |
|---|---|---|
| Pricing | ||
| Input $/1M | $0.75 | $0.20 |
| Output $/1M | $3.75 | $1.20 |
| Blended $/1M (3:1) | $1.50 | $0.45 |
| RAG example (30K in / 2K out) | $0.03 | $0.0084 |
| Quality & speed | ||
| Intelligence Index | 34.3 | — |
| Coding Index | 69.2 | — |
| Agentic Index | 30.2 | — |
| Output speed (tok/s) | 222 | — |
| Time to first token | 15.35s | — |
| Specs | ||
| Context window | 1.05M | 1.05M |
| Input modalities | text, image, video, file, audio | file, image, text |
FAQ
Which is cheaper, Gemini 3.6 Flash or GPT-5.6 Luna Pro?
GPT-5.6 Luna Pro has the lower blended API price at $0.45 per 1M tokens (3:1 input:output mix), versus $1.50 for the other model. Prices are live from OpenRouter and refresh about hourly.
Which is better for RAG workloads?
For a typical RAG request (30K input / 2K output tokens), GPT-5.6 Luna Pro costs about $0.0084 per request versus $0.03. Also compare context windows: Gemini 3.6 Flash offers 1.05M and GPT-5.6 Luna Pro offers 1.05M.
Which scores higher on Artificial Analysis benchmarks?
Gemini 3.6 Flash leads on the Artificial Analysis Intelligence Index (34.3 vs —). Check coding and agentic indices on this page for workload-specific tradeoffs.