Gemma 4 is Google's language model with a 262K context window, starting at $0.372 / 1M input and $0.957 / 1M output. Google DeepMind's fourth-generation open multimodal LLM series, supporting text and image input with text output generation.
| Benchmarks | |
|---|---|
| GPQA | #377 |
| HLE | #418 |
| IFBench | #259 |
| Time to First Token | #162 |
| SciCode | #445 |
| LCR | #349 |
| TerminalBench Hard | #237 |
| TAU2 | #290 |
| Output TPS | #194 |
Capabilities
Input2/5
Text✓
Image✓
Audio·
Video·
PDF·
Output1/5
Text✓
Image·
Audio·
Video·
Embedding·
Capabilities5/13
Reasoning✓
Adaptive Reasoning·
Function Calling✓
Parallel Function Calling✓
Structured Outputs✓
Native JSON Schema·
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching✓
Assistant Prefill·
Pricing by Provider
US Dollar ($)
Per 1M tokens
| Provider | Standard | ||
|---|---|---|---|
| Input $ / 1M | Output $ / 1M | Cache Read $ / 1M | |
| $0.372 | $0.957 | $0.106 | |
Cost Calculator
US Dollar ($)
Preset:
Versions
| Version | Released | Context | Input / 1M | Output / 1M | Status |
|---|---|---|---|---|---|
| Gemma 4 | — | 262K | $0.372 | $0.957 | Current |
| Gemma 4 E4B | — | — | — | — | Available |
| Gemma 4 31B | — | 256K | $0.140 | $0.400 | Available |
| Gemma 4 12B | — | — | — | — | Available |
| Gemma 4 12B Instruct | — | 16K | $0.300 | $2.00 | Available |
| Gemma 4 26B | — | 131K | $0.030 | $0.165 | Available |
| Gemma 4 26B A4B | — | 262K | $0.050 | $0.290 | Available |
| Gemma 4 26B A4B | — | — | — | — | Available |
| Gemma 4 31B | — | — | — | — | Available |
| Gemma 4 31B IT Thinking | — | 262K | $0.150 | $0.400 | Available |
| Gemma 4 31B IT Turbo | — | 262K | $0.090 | $0.340 | Available |