gemini-3-flash-preview:cloud

Upstream reference: Gemini 3 Flash 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

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

Publisher sources

• Gemini 3 Flash Preview official documentation — Google. Checked 2026-11-02.

Links

Recorded references do not establish downloadable weights, licensing or current availability.

• Google AI / Google DeepMind — official site
• Ollama
• Provider page
• Official model announcement / documentation

Where gemini-3-flash-preview:cloud comes from

Named in 4 observation pages

• 31 cloud models × 3 wrappers on the same audit · V1
• Academic observation — 32 cloud models × Cline and Pi · V1
• Aider — 169 runs across 83 models · V1
• Cloud Models — three-judge autoresearch observation set · V1