megachangelog
Announcement

DeepSeek V4 Flash Vision Experimental now available on AI Gateway

DeepSeek V4 Flash Vision Experimental is now available on Vercel's AI Gateway, enabling users to submit images alongside text for vision-based tasks like describing pictures, reading text from screenshots, and analyzing charts. The model supports tool use, reasoning, and caching features.

is now available on AI Gateway.DeepSeek V4 Flash with vision

This model is an experimental version that accepts images alongside text. You can ask it to describe a picture, read text out of a screenshot, or work through a chart in the same request as your prompt. DeepSeek V4 Flash Vision Experimental now available on AI Gateway. Tool use, reasoning, and caching all work the same as before.

Use to get started:deepseek/deepseek-v4-flash-vision-exp

Images can be JPEG, PNG, GIF, or WebP. The format is read from the file's own bytes rather than its name or the you declare, so a mislabeled file still goes through.mediaType

The in the model ID marks this as an experimental release. Expect behavior to change, and keep a fallback model configured if it's on a production path.-exp

To use it in a , run to connect agents like Claude Code, Codex, OpenCode, Cursor, and Pi, then select inside the agent.coding agentvercel ai-gateway coding-agents setupdeepseek/deepseek-v4-flash-vision-exp

Try Deepseek V4 Flash Vision Experimental in the .model playground

AI Gateway reflects provider pricing with no markup and does not charge a platform fee on inference, including BYOK requests. on AI Gateway to see more.View all language models

Read more

ai-gatewaydeepseekvisionexperimentalmodels

Source: original entry ↗