All Models
Gemma 4 31B IT
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...
Available Providers (14)
| Provider | Model ID | Input Cost | Output Cost | Context | Max Output | Docs |
|---|---|---|---|---|---|---|
 Nvidia | google/gemma-4-31b-it | $0/MTok | $0/MTok | 256K | 16.4K | |
 CrofAI | gemma-4-31b-it | $0.10/MTok | $0.30/MTok | 262.1K | 262.1K | |
 routing.run | route/gemma-4-31b-it | $0.10/MTok | $0.30/MTok | 131.1K | 65.5K | |
 Lilac | google/gemma-4-31b-it | $0.11/MTok | $0.35/MTok | 262.1K | 262.1K | |
 OpenRouter | google/gemma-4-31b-it | $0.12/MTok | $0.35/MTok | 262.1K | 262.1K | |
 OrcaRouter | google/gemma-4-31b-it | $0.13/MTok | $0.38/MTok | 262.1K | 32.8K | |
 NEAR AI Cloud | google/gemma-4-31B-it | $0.13/MTok | $0.40/MTok | 262.1K | 32.8K | |
 Deep Infra | google/gemma-4-31B-it | $0.13/MTok | $0.38/MTok | 262.1K | 32.8K | |
 SiliconFlow | google/gemma-4-31B-it | $0.13/MTok | $0.40/MTok | 262.1K | 262.1K | |
 FastRouter | google/gemma-4-31b-it | $0.13/MTok | $0.38/MTok | 262.1K | 32.8K | |
 Vercel AI Gateway | google/gemma-4-31b-it | $0.14/MTok | $0.40/MTok | 262.1K | 131.1K | |
 NanoGPT | Gemma-4-31B-it | $0.31/MTok | $0.31/MTok | 262.1K | 16.4K | |
 Google | gemma-4-31b-it | —/MTok | —/MTok | 262.1K | 32.8K | |
 Merge Gateway | google/gemma-4-31b-it | —/MTok | —/MTok | 262.1K | 32.8K |
Capabilities
Reasoning
Tool Calling
Attachments
Open Weights
Structured Output