Reader
Timeline1494StarredSettings

Feeds

AI

Anthropic NewsExponential ViewSimon Willison's Weblog10Vercel News1108

设计

AreslunaDaring Fireball26Geoffrey LittJim Nielsen’s Blog

思考

Essays - Benedict EvansSteve BlankZara Zhang
Cursor Changelog30Lenny's Podcast: Product | Career | Growth320

Select an article to read

AI Gateway 上线 Deepseek V4

Deepseek V4 on AI Gateway

Vercel News·Walter Korman·April 23, 2026

DeepSeek V4 is now available on .Vercel AI Gateway

There are 2 model variants: DeepSeek V4 Pro and DeepSeek V4 Flash. A 1M token context window is the default across both models.

DeepSeek V4 Pro focuses on 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. It also writes clear, well-structured long-form documents.

DeepSeek V4 Flash performs close to V4 Pro on reasoning and holds up on simpler agent tasks, with a smaller parameter size for faster responses and lower API cost. It's a good fit for high-volume workloads and latency-sensitive use cases.

To use DeepSeek V4, set model to or in the .deepseek/deepseek-v4-prodeepseek/deepseek-v4-flashAI SDK

AI Gateway provides a unified API for calling models, tracking usage and cost, and configuring retries, failover, and performance optimizations for higher-than-provider uptime. It includes built-in , , support, and intelligent provider routing with automatic retries.custom reportingobservabilityBring Your Own Key

Learn more about , view the or try it in our .AI GatewayAI Gateway model leaderboardmodel playground

Read more