Google: Gemma 4 31B (free)
GoogleGemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output.
Multimodal vision
TextVisionVideo
Specifications
| Vendor | |
| Family | |
| Context | 262.1K · 196.6k words（≈ a novella） |
| Max output | 262.1K · 196.6k words（≈ a novella） |
| Released | 2026-06-19 |
| Open source | No |
| Tool use | — |
Pricing across channels
per 1M tokens, USD
| Channel | Type | Input | Output | → |
|---|---|---|---|---|
| OpenRouter (auto) | Aggregator | $0 | $0 | visitAd |
OpenRouter API (auto-fetched)· 2026-06-19
Related models
Similar tier, vendor or price range