Gemma 3 12B Instruct is Google's language model with a 131K context window and up to 16K output tokens, available from 6 providers, starting at $0.05 / 1M input and $0.1 / 1M output. An instruction-tuned 12B Gemma 3 LLM supporting vision-language inputs and 128k context.
Specifications
Canonical IDgoogle-gemma-3-12b-instruct
TypeLanguage
StatusActive
CreatorGoogleGoogle
Providers
Context Window131K tokens
Max Output16K tokens
Input ModalitiesImageText
Output ModalitiesText
Parameters12B
HuggingFace Likes707
HuggingFace Downloads (30d)2,516,014
HuggingFace Downloads (all-time)14,080,610
Release Date · 1 year ago
Knowledge Cutoff · 2 years ago

Capabilities

Input2/5
Text
Image
Audio·
Video·
PDF·
Output1/5
Text
Image·
Audio·
Video·
Embedding·
Capabilities4/13
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
ProviderStandardBatchFlexPriority
Input
$ / 1M
Output
$ / 1M
Input
$ / 1M
Output
$ / 1M
Input
$ / 1M
Output
$ / 1M
Input
$ / 1M
Output
$ / 1M
Amazon Bedrock logo
Amazon Bedrock
google.gemma-3-12b-it
$0.09$0.29$0.05$0.15$0.05$0.15$0.16$0.51
Cloudflare Workers AI logo
Cloudflare Workers AI
@cf/google/gemma-3-12b-it
$0.345$0.556
Crusoe
crusoe/google/gemma-3-12b-it
$0.1$0.1
DeepInfra logo
DeepInfra
deepinfra/google/gemma-3-12b-it
$0.05$0.1
Novita logo
Novita
novita/google/gemma-3-12b-it
$0.05$0.1
OpenRouter logo
OpenRouter
google/gemma-3-12b-it
$0.05$0.15

Cost Calculator

US Dollar ($)
Preset:

Cheapest Instances to Run It

Cloud GPU instances that can host Gemma 3 12B Instruct, ranked by cheapest on-demand price. The model needs about 29 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_NV16as_v4AzureAMD Radeon Instinct MI2532 GB$0.932/hrwestus2
Standard_NP10sAzureAMD Alveo U250 FPGA (64GB)64 GB$1.65/hrwestus2
g6e.xlargeAWSL40S45 GB$1.86/hrus-east-1
7 more instances can run Gemma 3 12B Instruct
Unlock the full ranked list and FP8 / INT4 quantization with a CloudPrice subscription.

Versions

VersionReleasedContextInput / 1MOutput / 1MStatus
Gemma 3 12B Instruct131K$0.050$0.100Current
Gemma 3 4B Instruct131K$0.040$0.080Available
Rnj 1 Instruct33KAvailable
Gemma EmbeddingAvailable

Model IDs

@cf/google/gemma-3-12b-it
accounts/fireworks/models/gemma-3-12b-it
crusoe/google/gemma-3-12b-it
deepinfra/google/gemma-3-12b-it
google-gemma-3-12b-instruct
google.gemma-3-12b-it
google/gemma-3-12b-it
google/gemma-3-12b-it:free
novita/google/gemma-3-12b-it