Gemini 3.6 Flash vs GPT-5.4 (batch)
Side-by-side API pricing and Artificial Analysis performance for Gemini 3.6 Flash (Google) and GPT-5.4 (batch) (OpenAI). Green cells mark the better value in each row.
Prices updated Sep 7, 2026, 3:33 PM UTC · refreshed hourly
| Gemini 3.6 Flash | GPT-5.4 (batch) OpenAI | |
|---|---|---|
| Pricing | ||
| Input $/1M | $0.75 | $1.25 |
| Output $/1M | $3.75 | $7.50 |
| Blended $/1M (3:1) | $1.50 | $2.81 |
| RAG example (30K in / 2K out) | $0.03 | $0.0525 |
| Quality & speed | ||
| Intelligence Index | 40.3 | 42.8 |
| Coding Index | 69.2 | 71.1 |
| Agentic Index | 30.3 | — |
| Output speed (tok/s) | 188 | 0 |
| Time to first token | 10.72s | 0s |
| Specs | ||
| Context window | 1.05M | 1.05M |
| Input modalities | text, image, video, file, audio | text, image, file |
FAQ
Which is cheaper, Gemini 3.6 Flash or GPT-5.4 (batch)?
Gemini 3.6 Flash has the lower blended API price at $1.50 per 1M tokens (3:1 input:output mix), versus $2.81 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), Gemini 3.6 Flash costs about $0.03 per request versus $0.0525. Also compare context windows: Gemini 3.6 Flash offers 1.05M and GPT-5.4 (batch) offers 1.05M.
Which scores higher on Artificial Analysis benchmarks?
GPT-5.4 (batch) leads on the Artificial Analysis Intelligence Index (42.8 vs 40.3). Check coding and agentic indices on this page for workload-specific tradeoffs.