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...
Specifications
| Provider | |
|---|---|
| Context window | 262,144 tokens (262K) |
| Input price | $0.1 / 1M tokens |
| Output price | $0.34 / 1M tokens |
| Input modalities | image, text, video |
| Output modalities | text |
| Model ID | google/gemma-4-31b-it |
Pricing is per 1M tokens, indicative pricing via OpenRouter (updated 2026-08-22); a provider's own list price may differ.
Frequently asked questions
How much does Gemma 4 31B cost?
Indicative pricing (via OpenRouter, updated 2026-08-22) is $0.1 per 1M input tokens and $0.34 per 1M output tokens. A provider's own list price may differ. On Vincony, Gemma 4 31B is available on credit-based pricing alongside 800+ other models.
What is Gemma 4 31B's context window?
Gemma 4 31B supports a context window of up to 262,144 tokens (262K), which is how much text it can consider at once.
Who makes Gemma 4 31B?
Gemma 4 31B is built by Google. You can access it — and compare it against other providers' models — through Vincony's multi-model platform.
How do I use Gemma 4 31B?
You can use Gemma 4 31B directly through Google, or via Vincony, which aggregates 800+ models (including Gemma 4 31B) into one interface with side-by-side comparison and credit-based pricing.