Gemini 2.5 Flash Image

JSON →
google multimodal
textimage

A multimodal model from Google optimized for image understanding and generation tasks within the Gemini 2.5 Flash family.

context window 33K tokens
max output 33K tokens
input price $0.3 / 1M tokens
output price $2.5 / 1M tokens
visionstreamingcode-generationfunction-callingtool-useprompt-cachingjson-mode