whichllm — Browse and compare AI model specs and pricing

AIHubMix

Gemini 2.5 Pro

gemini-pro

Model ID gemini-2.5-pro
Provider AIHubMix
Family gemini-pro
Status -
Knowledge Cutoff 2025-04
Release Date 2025-09-15
Input Modalities text, image, audio, video
Output Modalities text
Context Window 2000000
Input Limit -
Output Limit 65000
Tool Calling Yes
Reasoning Yes
Structured Output -
Temperature Control Yes
Open Weights No
Input Cost / 1M tokens $1.25
Output Cost / 1M tokens $5.00
Reasoning Cost / 1M tokens -
Cache Read Cost / 1M tokens $0.31
Cache Write Cost / 1M tokens -