>
G
Model Details
Model Access:
API access
Introduction
Gemini 1.0 Pro Vision supports text, image, and video as inputs. Max input tokens: 16,384 Max output tokens: 2,048 Max images per prompt: 16 Max video length: 2 minutes Max videos per prompt: 1 Training data: Up to February 2023
Benchmarking
Notes: To the extent that we believe Gemini 1 Pro was below 1e25 FLOP, Gemini 1 Pro Vision is unlikely to exceed it.
Training
Training Code AccessibilityAPI Access: https://console.cloud.google.com/vertex-ai/generative/multimodal/create/text?model=gemini-1.0-pro-vision-001
Authors
Gemini Team
Multimodal
Speech