Google: Gemma 3 27B

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 27B is Google's latest open source model, successor to [Gemma 2](google/gemma-2-27b-it)

Key Specifications
Cost
$$
Context
131K
Parameters
27B
Released
Mar 11, 2025
Speed
Ability
Reliability
Supported Parameters

This model supports the following parameters:

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

This model supports the following features:

Response Format
Performance Summary

Gemma 3 27B demonstrates competitive response times, performing among the faster models with a 50th percentile speed ranking. It offers cost-effective solutions, ranking in the 79th percentile for price. Notably, the model exhibits exceptional reliability, achieving a 100% success rate across all benchmarks, indicating consistent and usable responses. Across benchmark categories, Gemma 3 27B shows strong performance in Ethics, achieving perfect accuracy and being the most accurate model at its price point and speed. It also performs well in General Knowledge (98.0% accuracy) and Coding (89.0% accuracy, 71st percentile). Its Mathematics and Reasoning capabilities are solid, with 84.0% and 66.0% accuracy respectively. A significant weakness is observed in Instruction Following, where it achieved only 8.0% accuracy, placing it in the 23rd percentile. Email Classification is competent at 97.0% accuracy. Overall, Gemma 3 27B is a reliable and cost-effective model with strong ethical understanding and general knowledge, though its instruction following needs improvement.

Model Pricing

Current Pricing

Feature Price (per 1M tokens)
Prompt $0.07
Completion $0.26

Price History

Available Endpoints
Provider Endpoint Name Context Length Pricing (Input) Pricing (Output)
DeepInfra
DeepInfra | google/gemma-3-27b-it 131K $0.07 / 1M tokens $0.26 / 1M tokens
InoCloud
InoCloud | google/gemma-3-27b-it 131K $0.07 / 1M tokens $0.26 / 1M tokens
Nebius
Nebius | google/gemma-3-27b-it 110K $0.1 / 1M tokens $0.3 / 1M tokens
Kluster
Kluster | google/gemma-3-27b-it 64K $0.07 / 1M tokens $0.26 / 1M tokens
Parasail
Parasail | google/gemma-3-27b-it 131K $0.2 / 1M tokens $0.5 / 1M tokens
Novita
Novita | google/gemma-3-27b-it 32K $0.119 / 1M tokens $0.2 / 1M tokens
InferenceNet
InferenceNet | google/gemma-3-27b-it 128K $0.07 / 1M tokens $0.26 / 1M tokens
NCompass
NCompass | google/gemma-3-27b-it 32K $0.07 / 1M tokens $0.26 / 1M tokens
Chutes
Chutes | google/gemma-3-27b-it 96K $0.07 / 1M tokens $0.26 / 1M tokens
Phala
Phala | google/gemma-3-27b-it 53K $0.11 / 1M tokens $0.4 / 1M tokens
NCompass
NCompass | google/gemma-3-27b-it 131K $0.09 / 1M tokens $0.16 / 1M tokens
DeepInfra
DeepInfra | google/gemma-3-27b-it 131K $0.09 / 1M tokens $0.16 / 1M tokens
Benchmark Results
Benchmark Category Reasoning Strategy Free Executions Accuracy Cost Duration
Other Models by google