Google: Gemma 2 9B vs RAG-MedQA-SFT

Side-by-side comparison of API pricing, context window, latency, and benchmark performance. Data refreshed daily from provider APIs and ModelStop's own latency probes.

Key Differences

💰RAG-MedQA-SFT is 100% cheaper than Google: Gemma 2 9B

Comparison Overview

Price (lower is better), Speed/Latency (lower is better), Performance (higher is better)

Detailed Comparison

💰 Cost

RAG-MedQA-SFT is Infinity% cheaper

Why choose between them?

Google: Gemma 2 9B: Best value

RAG-MedQA-SFT: Best value

Spec	Google: Gemma 2 9B	RAG-MedQA-SFT
Provider	google	rag-gym
Input price / 1M tokens	$0.03	Free
Output price / 1M tokens	$0.09	—
Context window	8k tokens	—
Latency (p50)	—	—
Best benchmark score	—	—
Open source	No	No

Google: Gemma 2 9B

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...

Full details →

RAG-MedQA-SFT

Open-source RAG-MedQA-SFT model from rag-gym — available for download and self-hosting on Hugging Face.

Full details →

Want to swap in a different model or estimate monthly costs?

Open in comparison tool Cost calculator