Chat modelMultimodalPopular

Gemini 3 Pro

Multimodal model that reads scanned PDFs, screenshots and diagrams alongside text in the same conversation.

Attach a screenshot to a chat turn, or point a vision step at a scanned invoice, and Gemini reads the picture as part of the question rather than as an attachment somebody has to describe first.

That matters most at ingestion: a knowledge base full of scanned PDFs is unusable to a text-only model, and running plain OCR over it loses the layout that made the table readable in the first place.

Use Gemini 3 Pro in your own workspace.

Create a workspace, connect a source, and put this to work in a few minutes.

Book a demo →

Related entries

Claude Opus 4.5

Popular

Long-context reasoning model. The default for agents that plan multi-step work and read large documents end to end.

Chat modelReasoning

GPT-5

Popular

General-purpose chat model with strong function calling. A good fit for tool-heavy agents and structured extraction.

Chat modelTool use

Llama 4 Maverick

Open-weights model you can also run on your own hardware. A cheap default for high-volume, low-stakes answering.

Chat modelOpen weights