Gemma 4 31B is Google's language model with a 256K context window, starting at $0.14 / 1M input and $0.4 / 1M output. Google DeepMind's 31B-parameter Gemma 4 open multimodal LLM, handling text and image inputs with text output.
Capabilities
Input2/5
Text✓
Image✓
Audio·
Video·
PDF·
Output1/5
Text✓
Image·
Audio·
Video·
Embedding·
Capabilities2/13
Reasoning✓
Adaptive Reasoning·
Function Calling✓
Parallel Function Calling·
Structured Outputs·
Native JSON Schema·
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching·
Assistant Prefill·
Pricing by Provider
US Dollar ($)
Per 1M tokens
| Provider | Standard | |
|---|---|---|
| Input $ / 1M | Output $ / 1M | |
| $0.14 | $0.4 | |
Cost Calculator
US Dollar ($)
Preset:
Cheapest Instances to Run It
Cloud GPU instances that can host Gemma 4 31B, 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 | 2× AMD Alveo U250 FPGA (64GB) | 128 GB | $3.30/hr | westus2 | ||
| g7e.2xlarge | RTX PRO Server 6000 | 96 GB | $3.36/hr | us-east-1 | ||
| Standard_NC24ads_A100_v4 | NVIDIA A100 | 80 GB | $3.67/hr | westus2 | ||
Versions
| Version | Released | Context | Input / 1M | Output / 1M | Status |
|---|---|---|---|---|---|
| Gemma 4 31B | — | 256K | $0.140 | $0.400 | Current |
| Gemma 4 26B A4B | — | 256K | $0.130 | $0.400 | Available |
| Gemma 4 31B | — | — | — | — | Available |
| Gemma 4 12B | — | — | — | — | Available |
| Gemma 4 26B A4B | — | — | — | — | Available |
| Gemma 4 E4B | — | — | — | — | Available |
| Gemma 4 E2B | — | 128K | $0.040 | $0.080 | Available |
| Gemma 4 E4B | — | — | — | — | Available |
| Gemma 4 E2B | — | — | — | — | Available |
| Gemma 4 | — | — | — | — | Available |
| Gemma 4 26B | — | 131K | $0.030 | $0.165 | Available |