Head to head
Meta: Muse Spark 1.2 vs Google: Gemini 3.5 Flash
Live prices, context windows, capabilities, and measured quality — updated continuously.
Side by side
| Metric | Meta: Muse Spark 1.2 Meta | Google: Gemini 3.5 Flash Google |
|---|---|---|
| Input $/M tokens | $1.25 | $1.50 |
| Output $/M tokens | $4.25 | $9.00 |
| Context window | 1.0M | 1.0M |
| Max output | — | 66K |
| WM Score | 86 | 81 |
| Benchmark quality | 87.4 | 79.6 |
| Hosts serving it | 1 | 2 |
| Throughput (tok/s) | 136 | 64 |
| Latency (ms) | 9412 | 782 |
| Vision | ||
| Tools | ||
| Reasoning | ||
| JSON mode |
Which should you pick?
Meta: Muse Spark 1.2 costs less per million input tokens — about 1.2× cheaper than Google: Gemini 3.5 Flash. Meta: Muse Spark 1.2 scores higher on measured quality. Prices here are live list prices; the same model can cost less on a different host, so check the model page for the cheapest offering.