TPSTokens Per Second

Gemini 1.5 Flash

Google DeepMind🇺🇸 United States
deprecated

Fast Gemini 1.5 variant. Superseded by Gemini 2.0 Flash.

Compare with other models →
Context window1000K tokens
Input / 1M tokens$0.075
Output / 1M tokens$0.3

Version History

gemini-1.5-flash-001major

Gemini 1.5 Flash brings 1M context to production at low cost. Optimized for high-throughput summarization and grounding tasks.