Gemini 1.5 Pro

Gemini 1.5 Pro

by

Google

Model ID:

gemini-1.5-pro

Use This Model

Frequently Asked Questions

  1. What are the key features that distinguish Gemini 1.5 Pro from other models in the Gemini family?
    Advanced reasoning capabilities, extensive context handling up to 64k tokens, and robust multimodal processing abilities.

  2. How does Gemini 1.5 Pro's performance compare to GPT-4?
    Shows competitive performance especially in reasoning tasks but may not consistently outperform GPT-4 across all benchmarks.

  3. What is the maximum context window size for Gemini 1.5 Pro?
    Up to 64k tokens

  4. How does Gemini 1.5 Pro handle complex reasoning and coding tasks?
    Effectively manages complex reasoning and coding tasks through enhanced algorithms designed to understand intricate queries.

  5. What multimodal capabilities does Gemini 1.5 Pro offer?
    Supports both textual and visual data inputs efficiently, making it suitable for applications requiring rich media interactions.

  6. Is Gemini 1.5 Pro available for public use, and if so, what is its pricing structure?
    Yes, it is available for public use with a flexible pricing structure that varies based on usage levels and specific deployment needs.

Still have questions?

Cant find the answer you’re looking for? Please chat to our friendly team.

Get In Touch

Model Specifications

Release Date:

23/5/2024

Model Variants:

gemini-1.5-pro-latest

Max. Context Tokens:

2097K

Max. Output Tokens:

8K

Knowledge Cut-Off Date:

November 2023

MMLU:

75.8

%

License:

Proprietary

Technical Report/Model Card:

LMSys ELo Score

1259

Berkeley Function Calling Ability Score:

52.53

Pricing

$/Million Input Tokens

$

1.25

$/Million Output Tokens

$

5

Live updates via Portkey Pricing API. Coming Soon...

© 2024 Portkey, Inc. All rights reserved

Gemini 1.5 Pro

Gemini 1.5 Pro

by

Google

Model ID:

gemini-1.5-pro

Chat

Vision

Speech to text