Preview release of Google's Gemini 3.1 Flash text-to-speech model for controllable speech generation, including inline Audio Tags, multilingual output, and SynthID watermarking.
Pricing
Model profile · Current snapshot
Input / 1M
$0.50
Output / 1M
$3.00
Blended / 1M
$1.13
Output TPS
185
TTFT (s)
5.52
Model Intelligence
Arena ranking
46
Benchmarkable
Yes
Model level
release
Intelligence Index
46.4
Coding Index
42.6
Math Index
97
MMLU Pro
0.89
GPQA
0.9
HLE
0.35
LiveCodeBench
0.91
SciCode
0.51
AIME 2025
0.97
IFBench
0.78
LCR
0.66
TerminalBench Hard
0.39
TAU2
0.8
Recent stories
1 linked story