Cracked AI Engineering

Gemini Live 2.5 Flash Preview Native Audio

Google

The Gemini Live 2.5 Flash Preview Native Audio AI model by Google offers developers a powerful tool for advanced reasoning and multimodal capabilities. With a context window of 131,072 tokens and the ability to process text, audio, video, and function calling, this model is perfect for complex AI applications. Priced at $0.5/M input and $2/M output tokens, it provides cutting-edge technology at an affordable rate.

Key Specifications

Context Window

131K tokens

Max Output Tokens

66K tokens

Input Pricing

$0.50

per million tokens

Output Pricing

$2.00

per million tokens

Capabilities

  • Text Generation
  • Audio Input
  • Video Understanding
  • Function Calling
  • Advanced Reasoning

Additional Details

Provider
Google
Release Date
June 17, 2025
Advanced Reasoning
Supported
Supported Input Types
text, audio, video

Compare with Similar Models