Gemma 4 Ultra 31B Instruct
Gemma 4 Ultra 31B Instruct is Google's language model. An ultra-speed instruction-tuned variant of the Gemma 4 31B model, optimized for high-throughput inference.
Capabilities
Input1/5
Text✓
Image·
Audio·
Video·
PDF·
Output1/5
Text✓
Image·
Audio·
Video·
Embedding·
Capabilities0/13
Reasoning·
Adaptive Reasoning·
Function Calling·
Parallel Function Calling·
Structured Outputs·
Native JSON Schema·
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching·
Assistant Prefill·
Cheapest Instances to Run It
Cloud GPU instances that can host Gemma 4 Ultra 31B Instruct, ranked by cheapest on-demand price. The model needs about 74 GB of GPU memory at FP16 precision (estimated from its parameter count), so treat the fit as guidance rather than a guarantee.
All clouds
FP16 (full precision)
US Dollar ($)
Instance | Cloud | GPU | VRAM | Price | Cheapest region | |
|---|---|---|---|---|---|---|
| Standard_NP20s |  Azure | 2× AMD Alveo U250 FPGA (64GB) | 128 GB | $3.30/hr | ||
| g7e.2xlarge |  AWS | RTX PRO Server 6000 | 96 GB | $3.36/hr | ||
| g2-standard-48 |  GCP | 4× nvidia-l4 | 96 GB | $3.99/hr | ||
Other Models
| Model | Tier | Released | Context | Input / 1M | Output / 1M |
|---|---|---|---|---|---|
| Gemma 4 31B | — | — | 256K | $0.140 | $0.400 |
| Gemma 4 26B A4B | — | — | 256K | $0.130 | $0.400 |
| Gemma 4 31B | — | — | — | — | — |
| Gemma 4 12B | — | — | — | — | — |
| Gemma 4 26B A4B | — | — | — | — | — |
| Gemma 4 E4B | — | — | — | — | — |
| Gemma 4 E2B | — | — | 128K | $0.040 | $0.080 |
| Gemma 4 | — | — | — | — | — |
| Gemma 4 E4B | — | — | — | — | — |
| Gemma 4 E2B | — | — | — | — | — |