DeepSeek launched DeepSeek-V4-Flash-Vision-Exp on its API: an experimental multimodal model that matches V4-Flash on text, agents, and reasoning, while jumping close to Claude Opus 4.8 on multimodal agent benchmarks. A free Files API and DeepSeek Harness 0.1.1 landed the same day, with images billed at up to 384 tokens each.

Key Takeaways

  • ✓Available now as model='deepseek-v4-flash-vision-exp' across Chat Completions, Messages, and Responses
  • ✓Multimodal agent scores leap toward Opus 4.8 while keeping V4-Flash-level text and tool use
  • ✓Free Files API lets teams upload an image once and reuse it by file_id across requests
ADSponsored