Intelligence Index
0129.4
> 62% OF MODELS
Google
Gemma 4 31B
Updated: June 2026
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
- Context
- 262K
- Input
- $0.12/M
- Output
- $0.35/M
Capabilities
VISIONTEXTWEBCODINGTHINKINGWRITING
Similarly Priced Models
| Model | Provider | Context | Input Price | Output Price |
|---|---|---|---|---|
| Qwen3 30B A3B | Qwen | 131K | $0.12/M | $0.5/M |
| Qwen3 VL 8B Thinking | Qwen | 256K | $0.117/M | $1.365/M |
| Qwen3 VL 30B A3B Thinking | Qwen | 131K | $0.13/M | $1.56/M |
| Qwen3 VL 30B A3B Instruct | Qwen | 262K | $0.13/M | $0.52/M |
| Qwen3 VL 32B Instruct | Qwen | 262K | $0.104/M | $0.416/M |
Performance Metrics
Coding Index
0238.7
> 81% OF MODELS
Agentic Index
0340.9
> 63% OF MODELS
Average Response Performance
- Output Speed
- 34.1 tok/s
- Time To First Token
- 1.11s
- Time To First Answer Token
- 52.05s
- End To End Response Time
- 66.72s
DATA SOURCE: Artificial Analysis