DeepSeek V4.1 Flash now available on AI Gateway

DeepSeek V4.1 Flash is now available on Vercel's AI Gateway, with native image understanding: it accepts text and images in the same request, so it can answer questions about screenshots, read charts, and pull information out of visual content.

• 1 million token context window, with responses up to 384,000 tokens
• Supports reasoning, tool use, and prompt caching
• A new architecture separates input processing from output generation, cutting the active computation needed at each stage

The model is available as deepseek/deepseek-v4.1-flash. To use it in Claude Code, Codex, Cursor, and other coding agents, install the latest Vercel CLI, run vercel ai-gateway setup, and select the model from the agent. See the announcement for details, or try it in the model playground.

Vercel

The platform for frontend developers — deploy, preview, and scale web apps and AI agents with zero config.

View Vercel →