D
Gemma 4 31B Turbo
Gemma 4 31B Turbo, a language model from DeepInfra.
modelOverride: { model: "gemma-4-31b-turbo" }
GGoogle·served viaDeepInfra·Released May 2026
Pricing
- Input
- $0.090 / 1M
- Output
- $0.34 / 1M
- Cached input
- $0.050 / 1M
Specifications
- Context window
- 262,144 tokens
- Max output
- 16,384 tokens
- Released
- May 2026
- Model string
- google/gemma-4-31B-it-turbo
- Capabilities
- VisionMultimodalLow costOpen source
Use this model
await mindstudio.generateText({ message: "...", modelOverride: { model: "gemma-4-31b-turbo", }, });