GoogleReleased on Mar 15, 2024

Gemini 1.5 Flash 8B: Benchmarks, Pricing & Context Window

Gemini 1.5 Flash 8B is a language model from Google, released in March 2024, with multimodal input.

A multimodal model capable of processing audio, images, video, and text with high efficiency. Features JSON mode, function calling, code execution, and system instructions support. Optimized for fast inference with 8B parameters.

Input
TextImage
Output
Text

Gemini 1.5 Flash 8B pricing

Providers

Gemini 1.5 Flash 8B starts at $0.0700 per million input tokens and $0.300 per million output tokens via Google.

ProviderInput $/MOutput $/MMax InputMax OutputLatency sThroughputQuantInputOutput
Google logoGoogle
$0.0700$0.3001.0M8.2K
0.30
150 c/s

Gemini 1.5 Flash 8B API

API access coming soon

Gemini 1.5 Flash 8B will be available through our gateway shortly.

Gemini 1.5 Flash 8B examples

Recent arena outputs from Gemini 1.5 Flash 8B, picked from the highest-ranked matchups.

Gemini 1.5 Flash 8B license

Gemini 1.5 Flash 8B is released under the Proprietary license, which restricts commercial use, has 8.0B parameters, has a knowledge cutoff of October 2024.

License
Proprietary
Non-commercial
Parameters
8.0B
Knowledge cutoff
October 2024

Proprietary license - usage restrictions apply

FAQ

Common questions about Gemini 1.5 Flash 8B.

What is the Gemini 1.5 Flash 8B release date?

Gemini 1.5 Flash 8B was released on March 15, 2024 by Google.

Who created Gemini 1.5 Flash 8B?

Gemini 1.5 Flash 8B was created by Google.

How many parameters does Gemini 1.5 Flash 8B have?

Gemini 1.5 Flash 8B has 8.0 billion parameters.

What is the license for Gemini 1.5 Flash 8B?

Gemini 1.5 Flash 8B is released under the Proprietary license.

What is the knowledge cutoff date for Gemini 1.5 Flash 8B?

Gemini 1.5 Flash 8B has a knowledge cutoff of October 2024. This means the model was trained on data up to this date and may not have information about events after this time.

Is Gemini 1.5 Flash 8B multimodal?

Yes, Gemini 1.5 Flash 8B is a multimodal model that can process both text and images as input.