Deepseek V4 on AI Gateway

By Steven Van · 2026-04-23

Both variants default to a 1M token context window, with Flash trading some reasoning depth for speed and lower cost.

DeepSeek V4 is now available on Vercel's AI Gateway, in two variants: DeepSeek V4 Pro and DeepSeek V4 Flash. Both default to a 1M token context window.

DeepSeek V4 Pro is built for agentic coding, formal mathematical reasoning and long-horizon workflows. It handles feature development, bug fixing and refactoring across stacks, with tool use that works across harnesses like MCP workflows and agent frameworks, and it writes clear, well-structured long-form documents.
DeepSeek V4 Flash performs close to Pro on reasoning and holds up on simpler agent tasks, with a smaller parameter size for faster responses and lower API cost, aimed at high-volume and latency-sensitive workloads.

To use either model, set model to deepseek/deepseek-v4-pro or deepseek/deepseek-v4-flash in the AI SDK. Both appear on AI Gateway's model leaderboard.

Vercel

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

View Vercel →

Read the original announcement →