All AI models · LLM benchmarks · Methodology

Gemini 3 Flash (Preview) (Google Vertex AI)

New Gemini flash lane bringing frontier-style multimodal reasoning to cheaper runs

Model facts

Context window
1.05M tokens
Maximum output
66K tokens
Cheapest paid input
$0.5 per 1M tokens
Cheapest paid output
$3 per 1M tokens
Open weights
no
Providers
1

Capabilities and modalities

reasoning, tool calling, structured output, attachments, temperature control, text, image, audio, video, pdf.

Observed price history

  • 2026-08-24: $0.5 input / $3 output per 1M tokens

API providers

  • LLM Gateway — model id google-vertex/gemini-3-flash-preview; $0.5 input / $3 output per 1M tokens; provider documentation