DeepSeek V4 Flash Vision, an image-capable version of V4 Flash, is now available in Ana. It joins the Claude, GPT, and Kimi families in the model picker.
V4 Flash Vision reads charts, scanned documents, and screenshots alongside text, at the same low price as the base Flash model. That makes it the default choice for high-volume, routine work that happens to include an image: pulling numbers off a chart, reading a scanned invoice, or checking a screenshot against your data.
Enabling Access
DeepSeek V4 Flash Vision is available to all Ana users. To enable it for your organization, go to Settings > Models and toggle Enabled next to DeepSeek V4 Flash Vision.
Learn More
Full model configuration options are in our documentation.
