Gemini 1.5 Pro

Authors / Google / Gemini 1.5 Pro

Gemini 1.5 Pro#

Stable version of Gemini 1.5 Pro, our mid-size multimodal model that supports up to 2 million tokens, released in May of 2024.

Developed by

Google

📋 Technical Specifications#

SpecificationValue
Model IDgemini-1.5-pro
Context Window1.0M tokens
Max Output8k tokens
Release Date2024-02-15
Open Weightsfalse

🎯 Capabilities#

Supports text generation and processing Can analyze and understand images Supported input modalities Supported output modalities Accepts tool definitions in requests Supports tool choice strategies (auto/none/required) Temperature sampling control Nucleus sampling (top-p) Top-k sampling Maximum token limit Stop sequences Alternative response formats JSON schema validation Response streaming

🌐 Provider Availability#

This model is available through the following providers with potential variations:

ProviderContextPricing (Input/Output)Notes
Google AI Studio1.0M$1.25 / $5.00

🔗 Related Resources#

Other Models by This Author#

  • Model that performs Attributed Question Answering.
  • Automl E2e
  • Automl Vision Image Classification
  • Automl Vision Image Object Detection
  • Bart Large Cnn
  • …and 181 more

Last Updated: 2025-10-21 23:55:57 UTC | Generated by ModelWiki