Gemma 4 31B
Google's flagship open-weight model with Apache 2.0 license. Multimodal reasoning, function calling, and thinking capabilities.
ReasoningVisionToolsStructured outputAudioVideo
Context window
256K
Max output
8K
Input price
— /1M
Output price
— /1M
Benchmarks
Independent benchmark scores — composite indices for reasoning, coding, and math, plus individual eval scores where available.
Intelligence Index39.2
Coding Index38.7
GPQA Diamond
86%
Humanity's Last Exam
23%
SciCode
43%
IFBench
76%
Long-context reasoning
62%
Terminal-Bench Hard
36%
τ²-Bench Telecom
60%
See full leaderboard →Benchmarks via Artificial Analysis · View on AA
Available routes
The same Gemma 4 31B runs on 1 route through the Opper gateway. Each route has its own data-handling posture.
| Provider | Region | Zero data retention | Training | Logging | Contract | Input | Output |
|---|---|---|---|---|---|---|---|
| Gemini | US | None | Conditional | Abuse monitoring (window not specified in public docs) | PAYG | — | — |
Human review: Abuse-flagged only