AiCostCompare

Gemini 3.6 Flash vs GPT-5.6 Luna (batch)

Side-by-side API pricing and Artificial Analysis performance for Gemini 3.6 Flash (Google) and GPT-5.6 Luna (batch) (OpenAI). Green cells mark the better value in each row.

Prices updated Sep 6, 2026, 10:08 AM UTC · refreshed hourly

Gemini 3.6 Flash

Google

GPT-5.6 Luna (batch)

OpenAI

Pricing
Input $/1M$0.75$0.10
Output $/1M$3.75$0.60
Blended $/1M (3:1)$1.50$0.225
RAG example (30K in / 2K out)$0.03$0.0042
Quality & speed
Intelligence Index40.343.4
Coding Index69.271.4
Agentic Index30.342.9
Output speed (tok/s)186110
Time to first token11.51s104.28s
Specs
Context window1.05M1.05M
Input modalitiestext, image, video, file, audiofile, image, text

FAQ

Which is cheaper, Gemini 3.6 Flash or GPT-5.6 Luna (batch)?

GPT-5.6 Luna (batch) has the lower blended API price at $0.225 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 (batch) costs about $0.0042 per request versus $0.03. Also compare context windows: Gemini 3.6 Flash offers 1.05M and GPT-5.6 Luna (batch) offers 1.05M.

Which scores higher on Artificial Analysis benchmarks?

GPT-5.6 Luna (batch) leads on the Artificial Analysis Intelligence Index (43.4 vs 40.3). Check coding and agentic indices on this page for workload-specific tradeoffs.