Google logo

Gemma 3 4B


Gemma 3 4B is Google's language model with a 128K context window and up to 8K output tokens, starting at $0.030 / 1M input and $0.080 / 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
6.3
#454
Coding Index
2.9
#356
Math Index
12.7
#220
MMLU-Pro
0.4
#294
GPQA
0.3
#412
HLE
0.1
#251
LiveCodeBench
0.1
#291
AIME
0.1
#134
IFBench
0.3
#330
Time to First Token
SciCode
0.1
#401
MATH-500
0.8
#107
AIME 2025
0.1
#220
LCR
0.1
#306
TerminalBench Hard
0.0
#317
TAU2
0.1
#350
Output TPS
0.0
#366

Capabilities

Input1/5
TextΒ·
Imageβœ“
AudioΒ·
VideoΒ·
PDFΒ·
Output1/5
Textβœ“
ImageΒ·
AudioΒ·
VideoΒ·
EmbeddingΒ·
Capabilities2/13
ReasoningΒ·
Adaptive ReasoningΒ·
Function Callingβœ“
Parallel Function CallingΒ·
Structured Outputsβœ“
Native JSON SchemaΒ·
Web SearchΒ·
URL ContextΒ·
Computer UseΒ·
Code ExecutionΒ·
File SearchΒ·
Prompt CachingΒ·
Assistant PrefillΒ·

Pricing by Provider

ProviderStandard
Input
$ / 1M
Output
$ / 1M
Other/Llamagate
llamagate/gemma3-4b
$0.030$0.080

Cost Calculator

Preset:
Compares every provider & tier in USD

Versions

VersionReleasedContextInput / 1MOutput / 1MStatus
Gemma 4 31Bβ€”β€”β€”β€”Available
Gemma 4 31Bβ€”β€”β€”β€”Available
Gemma 4 26B A4Bβ€”β€”β€”β€”Available
Gemma 4 26B A4Bβ€”β€”β€”β€”Available
Gemma 4 E4Bβ€”β€”β€”β€”Available
Gemma 4 E2Bβ€”β€”β€”β€”Available
Gemma 4 E4Bβ€”β€”β€”β€”Available
Gemma 4 E2Bβ€”β€”β€”β€”Available
Gemma 4β€”β€”β€”β€”Available
Gemma 4 E4B Instructβ€”β€”β€”β€”Available
Gemma 3 4Bβ€”128K$0.030$0.080Current

Model IDs