All Models
Gemma 4 31B
Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K token context window, configurable thinking/reasoning mode, native function...
Benchmarks
Available Providers (7)
| Provider | Model ID | Input Cost | Output Cost | Context | Max Output | Docs |
|---|---|---|---|---|---|---|
 Poe | google/gemma-4-31b | $0/MTok | $0/MTok | 262.1K | 8.2K | |
 OpenRouter | google/gemma-4-31b-it:free | $0/MTok | $0/MTok | 262.1K | 32.8K | |
 NanoGPT | google/gemma-4-31b-it | $0.10/MTok | $0.45/MTok | 262.1K | 131.1K | |
 CoreWeave | google/gemma-4-31B-it | $0.10/MTok | $0.34/MTok | 262.1K | 262.1K | |
 NovitaAI | google/gemma-4-31b-it | $0.14/MTok | $0.40/MTok | 262.1K | 131.1K | |
 Neuralwatt | gemma-4-31b | $0.14/MTok | $0.42/MTok | 262.1K | 16.4K | |
| NanoGPT | TEE/gemma4-31b | $0.40/MTok | $1/MTok | 262.1K | 131.1K |
Capabilities
Reasoning
Tool Calling
Attachments
Open Weights
Structured Output