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...
Model details →Google: Gemma 4 31B (batch) vs PrismML: Ternary Bonsai 2 27B
PrismML: Ternary Bonsai 2 27B wins on 2 of 6 axes — pricing and capability skew in its favour for most workloads.
Bonsai 2 27B is a 27B-parameter reasoning model from PrismML derived from Qwen3.8-27B. It supports coding, mathematics, tool calling, and image understanding with a 262K-token context window. Ternary compression shrinks...
Model details →Side-by-side comparison
| Capability | Google: Gemma 4 31B (batch) | PrismML: Ternary Bonsai 2 27B | Winner |
|---|---|---|---|
| Context window Maximum number of input tokens the model can attend to in a single request. | 262K | 262K | Tie |
| Input price (per 1M) Cost per million input tokens billed by the provider. | $0.39 | $0.07 | 🏆 PrismML: Ternary Bonsai 2 27B |
| Output price (per 1M) Cost per million output tokens billed by the provider. | $0.97 | $0.50 | 🏆 PrismML: Ternary Bonsai 2 27B |
| Tool / function calling First-class support for emitting structured tool calls. | Yes | Yes | Tie |
| Vision input Accepts image inputs alongside text. | Yes | Yes | Tie |
| Reasoning mode Internal chain-of-thought / extended-thinking support. | Yes | Yes | Tie |
Frequently asked questions
Is Google: Gemma 4 31B (batch) better than PrismML: Ternary Bonsai 2 27B?
PrismML: Ternary Bonsai 2 27B wins on 2 of 6 axes — pricing and capability skew in its favour for most workloads.
What's the price difference between Google: Gemma 4 31B (batch) and PrismML: Ternary Bonsai 2 27B?
Input: $0.39 vs $0.07 per 1M tokens. Output: $0.97 vs $0.50 per 1M tokens.
What context windows do Google: Gemma 4 31B (batch) and PrismML: Ternary Bonsai 2 27B support?
Google: Gemma 4 31B (batch) supports up to 262K tokens. PrismML: Ternary Bonsai 2 27B supports up to 262K tokens.
Do both Google: Gemma 4 31B (batch) and PrismML: Ternary Bonsai 2 27B support tool calling?
Google: Gemma 4 31B (batch): yes. PrismML: Ternary Bonsai 2 27B: yes.