DeepSeek V4 is now available on Vercel AI Gateway with two model variants optimized for different use cases.
- •DeepSeek V4 Pro is designed for agentic coding, formal mathematical reasoning, and long-horizon workflows, handling feature development, bug fixing, and refactoring with tool use capabilities.
- •DeepSeek V4 Flash offers comparable reasoning performance to V4 Pro with a smaller parameter size, providing faster responses and lower API costs for high-volume workloads.
- •Both models feature a 1M token context window by default, enabling processing of large-scale documents and codebases.
- •Integration is straightforward through the AI SDK by setting the model parameter to deepseek/deepseek-v4-pro or deepseek/deepseek-v4-flash.
This summary was automatically generated by AI based on the original article and may not be fully accurate.
Google Cloud
The Hacker News
Vercel