← Compare models
Open all in the calculator — adjust volume and token counts →
Gemini 3.1 Pro vs GPT-5.6 Luna
List-price comparison ·Gemini 3.1 Pro details ·GPT-5.6 Luna details
For a typical workload (100,000 requests / mo), GPT-5.6 Luna is the cheapest — 50% less than the priciest here ($360.00/mo vs $720.00/mo).
| Gemini 3.1 Pro | GPT-5.6 Luna | |
|---|---|---|
| Input / 1M tokens | $2.00 | $1.00 |
| Output / 1M tokens | $12.00 | $6.00 |
| Typical request (1,200 in + 400 out) | $0.0072 | $0.0036 |
| Context window | 1,048,576 tokens | 1050k tokens |
| Max output | 65,536 tokens | 128k tokens |
| Quality score | 93/100 | 95/100 |
| Tier | Flagship | Flagship |
| Provider | OpenAI |
Projected monthly cost
| Requests / mo | Gemini 3.1 Pro | GPT-5.6 Luna |
|---|---|---|
| 1,000 | $7.20 | $3.60 |
| 10,000 | $72.00 | $36.00 |
| 100,000 | $720.00 | $360.00 |
Gemini 3.1 Pro
Native audio, video, and document understanding with a ~1M token context window — strong fit for multi-modal RAG and large-document analysis.
Output token cost is steep relative to input, and the largest context windows can be slow to fill — chunk large documents where possible.
GPT-5.6 Luna
Auto-synced from OpenRouter — no editorial write-up yet.
More comparisons
Vendor list rates · per-request examples assume 1,200 input + 400 output tokens.