Gemma 3 12B

Newer version available: Gemma 4 12B IT

Released
2025-03-12
Last refreshed
2026-10-26
Status
Researched 23d ago
Open weightsCommercial use: restrictedRAGLong contextClassificationJSON / Tool use
Google DeepMind releases · 52 in the last 12 months · this family litChangelog →
Specifications
Family
Gemma 3
Released
2025-03-12
Context
128K
Parameters
12B
Architecture
Decoder Only
Knowledge cutoff
2024-08
Specialization
general
Openness
Open weights
License
GemmaRestricted
Weights
Available
Code
Unknown
Created by

Pioneering artificial intelligence research.

London, United Kingdom
Founded 2014
Website
Pricing
Output / 1M
$0.100
Input / 1M
$0.050

Cheapest of 6 routes · Novita AI

About

Gemma 3 12B is Google DeepMind's Gemma 3 model. It offers a 128K-token context window with weights openly available for self-hosting.

Providers(6)

Compare all 6

Compare API pricing across 6 tracked provider routes for input and output tokens, batch, and cached reads when available.

ProviderInput / 1MOutput / 1MRoute
Novita AI$0.050$0.100
Serverless
GCP Vertex AI$0.040$0.130
Serverless
OpenRouter$0.050$0.150
Serverless
Fireworks AI$0.200$0.200
Serverless
AWS Bedrock$0.300$0.300
Serverless
Scheduled retirement: March 30, 2027
Cloudflare Workers AI$0.345$0.556
Serverless

Available via routers & gateways(14)

Capabilities

Structured Outputs

Benchmark peer barsfor RAG

Benchmark scores(3)

Scores are benchmark-specific and are direction-aware: the same numeric gap can mean very different outcomes across suites. Use the leaderboard context and this model's provider route to decide whether the winning margin is meaningful for your workload.
BenchmarkScoreVersionEvaluationSource
30.4v4Observed 2026-10-26
Configuration: Gemma-3-12b-it (Prompt)
Harness: BFCL V4 official evaluation (gorilla berkeley-function-call-leaderboard), Prompt mode
Evaluator: Gorilla LLM team (UC Berkeley)
Confidence: confirmed
Notes: BFCL V4 leaderboard (Last Updated 2026-04-12), entry 'Gemma-3-12b-it (Prompt)': rank 66, Overall Acc 30.43%; Multi Turn 5.75%, Web Search 4.00%, Memory 27.53%, Non-Live AST 79.44%, Live 74.24%, Irrelevance 70.29%. Retrieved 2026-10-26.
57.1RULER (128K) (accuracy)Observed 2026-10-26—
1331.0text creative_writing 2026-10-22Observed 2026-10-22
Configuration: Gemma 3 12B IT
Harness: LMArena blind pairwise human votes, Bradley-Terry
Evaluator: LMArena
Confidence: confirmed
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Gemma 3 12B IT' (category creative_writing in text/latest-00000-of-00001.parquet): rank 192 of 416, rating 1331.1 (95% CI 1308.0-1354.1), 600 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Source

Source: LMArena (lmarena.ai), CC BY 4.0

Migration checks

No linked migration route is available for this model yet.

Compare Gemma 3 12B with other models

Show all 3 popular comparisonssorted by 7-day search impressions