Gemini 1.5 Flash
by
Model ID:
gemini-1.5-flash
Overview
Gemini 1.5 Flash is a fast and versatile multimodal model designed to handle diverse tasks efficiently. It supports various input types, including text, images, and audio, making it suitable for applications that require quick processing and adaptability across multiple formats.
Specializations
Designed for real-time applications, providing rapid responses suitable for interactive environments.
Optimized for efficiency, balancing performance with lower computational requirements.
Features enhanced natural language understanding for better context retention during conversations.
Integration Guide (Javascript)
To use this model through Portkey, follow these steps:
1. Install Portkey SDK:
npm install --save portkey-ai
2. Set up client with Portkey:
import Portkey from 'portkey-ai'
const portkey = new Portkey({
apiKey: "PORTKEY_API_KEY",
virtualKey: "VIRTUAL_KEY" // Google Virtual Key
})
3. Make a request:
const chatCompletion = await portkey.chat.completions.create({
messages: [
{ role: 'system', content: 'You are a quick assistant' },
{ role: 'user', content: 'Summarize quantum computing' }
],
model: 'gemini-flash',
});
console.log(chatCompletion.choices[0].message.content);
Live API Statistics and Performace Metrics
LMSys Arena Elo Score:
1227
Arena Score
LMSys Leaderboard Rank:
26
Arena Rank
Evaluates LLMs through a combination of user feedback and automated scoring systems.
Model Specifications
Release Date:
23/5/2024
Model Variants:
gemini-1.5-flash-latest
Max. Context Tokens:
1049K
Max. Output Tokens:
8K
Knowledge Cut-Off Date:
November 2023
MMLU:
67.3
%
License:
Proprietary
Technical Report/Model Card:
LMSys Elo Score
1227
Berkeley Function Calling Ability Score:
NaN
Pricing
$/Million Input Tokens
$
0.075
$/Million Output Tokens
$
0.3
Live updates via Portkey Pricing API. Coming Soon...
© 2024 Portkey, Inc. All rights reserved