Gemini 3.1 Pro Preview
Gemini 3.1 Pro Preview.
Input
Output
Context
1049K
Max Output
66K
Parameters
-
Technical Specifications
Model TypeChat
Context Window1,048,576 tokens
Max Output Tokens65,536 tokens
ParametersNot available
Release DateFeb 19, 2026
Training CutoffJan 1, 2025
Licenseproprietary
Open SourceNo
Input Modalities
AudioImageTextVideo
Output Modalities
Text
Capabilities
Benchmarks
Artificial Analysis
44.7%
HLE
72.7%
AA-LCR
94.1%
GPQA
95.6%
Tau2-Bench
77.1%
IFBench
58.9%
SciCode
16.5%
Tau2 Banking
68.8
Coding
46.5
Intelligence
53.8%
Terminal-Bench Hard
73.8%
Terminal-Bench 2.1
137
Speed (tok/s)
24.9
TTFA (s)
24.9
TTFT (s)
Resources & Links
proprietary, Proprietary - API access only
More Models by Google
Related Tools
Data sourced from official provider APIs and documentation
Last updated: Jul 15, 2026
Your AI stack shouldn't stand still.
Every month new models become cheaper, faster, and more capable. Inferbase ensures your application automatically benefits without changing a single API call.