whichllm — Browse and compare AI model specs and pricing

NanoGPT

Gemini 3 Flash Thinking model ID, context window & pricing

gemini-flash

Quick facts

Model ID google/gemini-3-flash-preview-thinking
Source NanoGPT
Context Window 1048756
Pricing $0.50 input / $3.00 output per 1M tokens
Capabilities reasoning, temperature control

Model overview

Gemini 3 Flash Thinking is an AI model from NanoGPT with 1048756 token context window and text, image, audio input support.

Published pricing is $0.50 input and $3.00 output per 1M tokens.

  • Workloads that use text, image, audio inputs with text outputs.
  • Reasoning-heavy prompts where stepwise problem solving matters.
Model ID google/gemini-3-flash-preview-thinking
Provider NanoGPT
Family gemini-flash
Status -
Knowledge Cutoff 2025-01
Release Date 2025-12-17
Input Modalities text, image, audio
Output Modalities text
Context Window 1048756
Input Limit 1048756
Output Limit 65536
Tool Calling No
Reasoning Yes
Structured Output No
Temperature Control Yes
Open Weights No
Input Cost / 1M tokens $0.50
Output Cost / 1M tokens $3.00
Reasoning Cost / 1M tokens -
Cache Read Cost / 1M tokens $0.05
Cache Write Cost / 1M tokens -