|
gptkbp:instanceOf
|
large language model
|
|
gptkbp:announced
|
gptkb:Google
|
|
gptkbp:API
|
https://ai.google.dev/gemini-api/docs/models/gemini
|
|
gptkbp:architecture
|
gptkb:transformation
|
|
gptkbp:availableOn
|
gptkb:Google_AI_Studio
gptkb:Vertex_AI
2024-05
Gemini API
|
|
gptkbp:cloudBased
|
gptkb:Google_Cloud
|
|
gptkbp:context
|
1 million tokens
|
|
gptkbp:contrastsWith
|
gptkb:Gemini_1.5_Pro
|
|
gptkbp:developedBy
|
gptkb:Google
|
|
gptkbp:hasModel
|
gptkb:Gemini
|
|
https://www.w3.org/2000/01/rdf-schema#label
|
Gemini 1.5 Flash
|
|
gptkbp:input
|
gptkb:illustrator
gptkb:text
audio
|
|
gptkbp:language
|
English
multilingual
|
|
gptkbp:notableFor
|
high speed
large context window
lower cost than Gemini 1.5 Pro
|
|
gptkbp:output
|
gptkb:text
structured data
|
|
gptkbp:purpose
|
cost efficiency
fast inference
multimodal tasks
|
|
gptkbp:relatedTo
|
gptkb:Gemini_1.0
gptkb:Gemini_1.5_Pro
|
|
gptkbp:releaseDate
|
2024-05
|
|
gptkbp:supports
|
text input
image input
audio input
|
|
gptkbp:tradeoff
|
faster but less capable than Gemini 1.5 Pro
|
|
gptkbp:uses
|
summarization
chatbots
data extraction
document analysis
multimodal reasoning
|
|
gptkbp:bfsParent
|
gptkb:Google_I/O_2024
|
|
gptkbp:bfsLayer
|
8
|