INSIGHT AI

Source-linked text edition ·

DeepSeek V4.1 Flash adds native image inputs and a new prompt format

The written, source-linked counterpart to this video.

Published edition

7 source-linked editorial stories.

Updates

1. DeepSeek V4.1 Flash adds native image inputs and a new prompt format

DeepSeek released a multimodal model with up to one million tokens of context and MIT-licensed weights.

Proof: The source records 1M-token context.

Impact: Developers can evaluate image-and-text agent workloads using released weights and the documented prompt encoder.

Watch next: Check the next DeepSeek V4.1 Flash release note for rollout, availability, or quota changes.

Canonical host: huggingface.co

Watch from this story

Read full story

Video edition · Markdown edition

Source ledger