Google: Gemma 2 9B

Text input Text output Free Option
Author's Description

Gemma 2 9B by Google is an advanced, open-source language model that sets a new standard for efficiency and performance in its size class. Designed for a wide variety of tasks, it empowers developers and researchers to build innovative applications, while maintaining accessibility, safety, and cost-effectiveness. See the [launch announcement](https://blog.google/technology/developers/google-gemma-2/) for more details. Usage of Gemma is subject to Google's [Gemma Terms of Use](https://ai.google.dev/gemma/terms).

Key Specifications
Cost
$$
Context
8K
Parameters
9B
Released
Jun 27, 2024
Speed
Ability
Reliability
Supported Parameters

This model supports the following parameters:

Response Format Stop Seed Top P Max Tokens Temperature
Features

This model supports the following features:

Response Format
Performance Summary

Google's Gemma 2 9B demonstrates exceptional speed and competitive pricing, consistently ranking among the fastest and most cost-effective models across various benchmarks. This open-source language model, released on June 27, 2024, is designed for efficiency and broad application. In terms of performance across categories, Gemma 2 9B exhibits a significant strength in Ethics, achieving perfect 100% accuracy and ranking among the top three in speed for this task, making it the most accurate model at its price point and speed. It also shows reasonable performance in Email Classification with 94% accuracy. However, the model struggles considerably with Instruction Following and Reasoning, scoring 0% accuracy in one Instruction Following benchmark and 0% in Reasoning. Its performance in Hallucinations (28% accuracy) and Mathematics (24% accuracy) indicates areas for improvement, suggesting a tendency to generate incorrect information or difficulty with complex mathematical problems. General Knowledge and Coding also present as weaknesses, with accuracies of 58.5% and 13% respectively.

Model Pricing

Current Pricing

Feature Price (per 1M tokens)
Prompt $0.2
Completion $0.2

Price History

Available Endpoints
Provider Endpoint Name Context Length Pricing (Input) Pricing (Output)
Groq
Groq | google/gemma-2-9b-it 8K $0.2 / 1M tokens $0.2 / 1M tokens
Chutes
Chutes | google/gemma-2-9b-it 8K $0.01 / 1M tokens $0.02 / 1M tokens
Chutes
Chutes | google/gemma-2-9b-it 8K $0.01 / 1M tokens $0.02 / 1M tokens
Benchmark Results
Benchmark Category Reasoning Strategy Free Executions Accuracy Cost Duration
Other Models by google