Google: Gemma 3 12B

Text input Image input Text output Free Option
Author's Description

Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities, including structured outputs and function calling. Gemma 3 12B is the second largest in the family of Gemma 3 models after [Gemma 3 27B](google/gemma-3-27b-it)

Key Specifications
Cost
$$
Context
131K
Parameters
12B
Released
Mar 13, 2025
Speed
Ability
Reliability
Supported Parameters

This model supports the following parameters:

Stop Presence Penalty Top P Temperature Seed Min P Response Format Frequency Penalty Max Tokens
Features

This model supports the following features:

Response Format
Performance Summary

Gemma 3 12B, Google's latest multimodal AI model, demonstrates exceptional speed, consistently ranking among the fastest models across various benchmarks. Its pricing is highly competitive, placing it in the 87th percentile for cost-efficiency. Furthermore, the model exhibits outstanding reliability with a 99% success rate, indicating minimal technical failures and consistent response delivery. In terms of performance across categories, Gemma 3 12B shows strong capabilities in Classification, achieving 99% accuracy in Email Classification, notably being the most accurate among models of comparable speed. It also performs well in General Knowledge and Ethics, scoring 97% and 98% accuracy respectively, indicating a broad understanding and adherence to ethical principles. While its Coding performance is solid at 85% accuracy, its Instruction Following capabilities appear to be a notable weakness, with one benchmark showing 0% accuracy and another at 19%. Reasoning performance is moderate at 60.4% accuracy. Overall, Gemma 3 12B stands out for its speed, cost-effectiveness, and reliability, making it a strong contender for tasks requiring efficient and dependable classification and knowledge retrieval, despite some limitations in complex instruction following.

Model Pricing

Current Pricing

Feature Price (per 1M tokens)
Prompt $0.05
Completion $0.1

Price History

Available Endpoints
Provider Endpoint Name Context Length Pricing (Input) Pricing (Output)
DeepInfra
DeepInfra | google/gemma-3-12b-it 131K $0.05 / 1M tokens $0.1 / 1M tokens
Cloudflare
Cloudflare | google/gemma-3-12b-it 80K $0.35 / 1M tokens $0.56 / 1M tokens
Chutes
Chutes | google/gemma-3-12b-it 96K $0.0481 / 1M tokens $0.193 / 1M tokens
Benchmark Results
Benchmark Category Reasoning Free Executions Accuracy Cost Duration
Other Models by google