Compare models
Put up to 4 models beside each other — token prices, context windows, capabilities and provider, from the same catalogue the model pages read.
- Gemma 4 31BGoogleRemove
| Attribute | Gemma 4 31Bgemma-4-31b-it |
|---|---|
| Pricing | |
| Input | $0.14 / 1M |
| Output | $0.40 / 1M |
| Cache Write (5m) | $0.14 / 1M |
| Cache Write (1h) | $0.14 / 1M |
| Cache Read | $0.14 / 1M |
| Web Search | $0 / 1M |
| Context | |
| Max context | 262.1K |
| Max output | N/A |
| Capabilities | |
| Vision | Yes |
| Function Calling | Yes |
| JSON Mode | Yes |
| Streaming | Yes |
| Catalogue | |
| Provider | |
| Category | chat |
| Charge type | Pay As You Go |
| Released | — |
| Description | |
| Summary | Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model, supporting text and image inputs with text outputs. It features a 256K token context window, configurable thinking/reasoning modes, native function calling, and broad multilingual support across 140+ languages. The model delivers strong performance in coding, reasoning, and document understanding, making it well suited for developer workflows, multilingual applications, and structured knowledge tasks. |