Google logo

Gemma 3 4B Instruct


Gemma 3 4B Instruct is Google logoGoogle's language model with a 128K context window and up to 8K output tokens, available from 2 providers. An instruction-tuned 4B Gemma 3 open LLM with vision-language input, 128k context, and multilingual instruction-following.
Spec
Canonical IDgoogle-gemma-3-4b-instruct
TypeLanguage
StatusActive
CreatorGoogleGoogle
Providers
Context Window128K tokens
Max Output8K tokens
Input ModalitiesImageText
Output ModalitiesText
Parameters4B
Release Date · 1 year ago

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

ProviderStandardBatchFlexPriority
Input
$ / 1M
Output
$ / 1M
Input
$ / 1M
Output
$ / 1M
Input
$ / 1M
Output
$ / 1M
Input
$ / 1M
Output
$ / 1M
Amazon Bedrock logo
Amazon Bedrock
$0.040$0.080$0.020$0.040$0.020$0.040$0.070$0.140
DeepInfra logo
DeepInfra
$0.040$0.080

Cost Calculator

Preset:
Compares every provider & tier in USD

Versions

VersionReleasedContextInput / 1MOutput / 1MStatus
Gemma 4Available
Gemma 4 26B A4B ITAvailable
SEA-LION Gemma 4 27B IT8KAvailable
Gemma 3n 2B8KAvailable
Gemma 3 4B Instruct128KCurrent
Gemma 3 12B IT131K$0.040$0.100Available
Gemma 3 4B IT131K$0.040$0.080Available
Gemma 3Available
Gemma 3 12B Instruct128K$0.150$0.500Available
Gemma 3 1B InstructAvailable
Gemma 3 1B InstructAvailable

Model IDs