Gemini 1.5 Flash-8B - In-Depth Overview

Google · Gemini

Current

Model ID: google-gemini-1.5-flash-8b

Get all the details on Gemini 1.5 Flash-8B, an AI model from Google. This page covers its token limits, pricing structure, key capabilities such as multimodal_input, long_context, vision, available API code samples, and performance strengths.

Key Metrics

Input Limit

1M tokens

Output Limit

No data tokens

Input Cost

$0.04/1M

Output Cost

$0.15/1M

Sample API Code

import google.generativeai as genai

genai.configure(api_key="YOUR_API_KEY")

model = genai.GenerativeModel('gemini-1.5-flash-8b')

response = model.generate_content("Write a story about a magic backpack.")

print(response.text)

Required Libraries

google-generativeai

@google/generative-ai

Benchmarks

Benchmark	Score	Source	Notes
lmarena text	1213	lmarena.ai	Score for gemini-1.5-flash-8b-001
lmarena vision	1106	lmarena.ai	Score for gemini-1.5-flash-8b-001

Notes

Our smallest model for lower intelligence use cases, with a 1 million token context window. Pricing is tiered based on prompt size (<= 128k tokens vs > 128k tokens).