gemini-3-pro-preview:latest

Upstream reference: Gemini 3 Pro Preview

Publisher: Google

Google documents this preview model for multimodal input and text output, including text, image, video, audio and PDF inputs.

Publisher-described context, separate from Sigma5C observations and recorded catalog statistics.

Published upstream specifications

Published input token limit: 1,048,576 Source
Published output token limit: 65,536 Source
Published output modality: Text Source

Publisher-described uses

Multimodal understanding and text-generating applications described in Google’s model documentation. Source

Reference limitations

Preview model IDs and provider lifecycle are separate from the recorded cloud or latest alias. Source
Google marks Gemini 3 Pro Preview shut down on March 9, 2026; the historical page is not evidence of current endpoint availability. Source

A recorded tag and an upstream card association do not verify the deployed checkpoint, quantization, configured context or current hosted availability.