Gemma 3 4B is Google's language model with a 128K context window and up to 8K output tokens, starting at $0.03 / 1M input and $0.08 / 1M output. A 4-billion-parameter Gemma 3 open-weight LLM balancing multimodal capability with compact size.
Specifications
Canonical IDgoogle-gemma-3-4b
TypeLanguage
StatusActive
CreatorGoogleGoogle
Providers
Context Window128K tokens
Max Output8K tokens
Input ModalitiesImage
Output ModalitiesText
Parameters4B
Benchmarks
Intelligence Index
1.1
#473
Math Index
12.7
#220
MMLU-Pro
0.4
#294
GPQA
0.3
#429
HLE
0.1
#268
LiveCodeBench
0.1
#291
AIME
0.1
#134
IFBench
0.3
#348
Time to First Token
0.00s
#109
SciCode
0.1
#417
MATH-500
0.8
#107
AIME 2025
0.1
#220
LCR
0.1
#322
TerminalBench Hard
0.0
#333
TAU2
0.0
#369
Output TPS
0.0
#378

Capabilities

Input1/5
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
ProviderStandard
Input
$ / 1M
Output
$ / 1M
LlamaGate
llamagate/gemma3-4b
$0.03$0.08

Cost Calculator

US Dollar ($)
Preset:

Versions

VersionReleasedContextInput / 1MOutput / 1MStatus
Gemma 4 31BAvailable
Gemma 4 26B A4BAvailable
Gemma 4 31BAvailable
Gemma 4 12BAvailable
Gemma 4 26B A4BAvailable
Gemma 4 E4BAvailable
Gemma 4 E2BAvailable
Gemma 4 E4BAvailable
Gemma 4 E2BAvailable
Gemma 4Available
Gemma 3 4B128K$0.030$0.080Current

Model IDs

gemma-3-4b
google-gemma-3-4b
llamagate/gemma3-4b