Last updated: 16/04/2025

Google Vertex AIOfficial Docs

Gemini 1.5 Flash 8B Experimental 0924

gemini-1.5-flash-8b-exp-0924

active

Gemini 1.5 Flash 8B Experimental 0924

This experimental release of the Gemini 1.5 Flash-8B model is the smallest and most cost-effective Flash model in the Gemini 1.5 family, with a context window of 1,000,000 tokens. It supports a wide range of capabilities including Text, Image, Video, Audio, Transcription, and Text-to-Speech, making it a versatile choice for various AI applications. While this is an experimental model, it has been replaced by the more stable Gemini-1.5-flash-8b-001 version.

Supports a 1,000,000 token context window. Handles Text, Image, Video, Audio, Transcription, Text-to-Speech inputs and outputs. Supports fine-tuning for custom applications.

Additional Information

Notes

This is an experimental model with a context length of 1,000,000 tokens. It is the smallest and most cost-effective Flash model in the Gemini 1.5 family. It has been replaced by the stable version Gemini-1.5-flash-8b-001.

Model Timeline

Launch Date

9/24/2024

Last Updated

9/24/2024

Capabilities

Text

Input Pricing

$0.00001875/ KTok

Context: 1,000,000 tokens
Long context: 128,000 + @ 0.0000375x

Output Pricing

$0.000075/ KTok

Vision Capabilities

Image

Input Pricing

$0.00002 /image

Video

Input Pricing

$0.00002/second

Audio

Input Pricing

$ 0.00012 /minute

Generation Pricing

Not available

Text-to-Speech

Text-to-Speech Pricing

$0.000075/1k characters

Embeddings

Embeddings Pricing

$0.000025/1k tokens

Fine-Tuning

Fine-Tuning Pricing

$8.00/MTok training

Flatten your repo for AI in seconds

Flatten repos. Prompt faster. One click → one GPT-ready file

Free Online & Desktop