Gemini 3 Pro Image

Stable

Google · Released 2026-06 · google/gemini-3-pro-image

Overview

Google DeepMind model offering a million-token context window, strong multimodal understanding and excellent cost efficiency at scale. Gemini 3 Pro Image supports up to 131K tokens of context, native vision input. Served through the FirmLink unified API with OpenAI-compatible endpoints.

Function CallingJSON ModeStreamingTextVisionImage Gen

API example

Fully OpenAI-compatible — just change the model field.

curl https://api.firmlinktech.com/v1/chat/completions \
  -H "Authorization: Bearer $FIRMLINK_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "google/gemini-3-pro-image",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'