Gemini 3 Pro Image

JSON →
google multimodal
textimage

The stable release of Google's Gemini 3 Pro model with native image understanding and generation.

context window 66K tokens
max output 33K tokens
input price $2 / 1M tokens
output price $12 / 1M tokens
visionstreamingcode-generationreasoningprompt-cachingjson-mode