Gemini 3 Pro Thinking API

google/gemini-3-pro-thinking
by Google DeepMindrelease date: 11/18/2025

Gemini 3 Pro Thinking is Google's most advanced multimodal LLM, offering deep reasoning, agentic capabilities, and 1M-token context for complex tasks.

$1/$6per 1M tokens
API documentation not available

Technical Specs

Context Length1,000,000
Release Date11/18/2025
Input Formats
textimagevideoaudiocode
Output Formats
textimagejson

Capabilities & Features

Capabilities
multimodal understanding (text, image, video, audio, code)advanced reasoningdynamic multi step and parallel hypothesis inferenceagentic (tool use, autonomous task execution)long context comprehension (up to 1M tokens, partial support for up to 2M)code generation and editingimage generation and editing (via Nano Banana Pro integration)structured and JSON outputscomplex document/video/chart analysisscreen and UI understandingenhanced instruction following
Supported File Types
.jpg.png.mp4.wav.pdf.txt.json.py.js
Gemini 3 Pro Thinking API - Cheap API - Google DeepMind - Defapi