You can now access DeepSeek's latest models, DeepSeek V3.2 and DeepSeek V3.2 Speciale, via Vercel's with no other provider accounts required.AI Gateway DeepSeek V3.2 supports combined thinking and tool use, handling agent-style operations (tool calls) in both reasoning and non-reasoning modes. DeepSeek V3.2 Speciale is optimized for maximal reasoning performance, and is suited for complex task use cases but requires higher token usage and does not support tool use. To use the DeepSeek V3.2 models, set to the following in the :modelAI 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 , , and intelligent with automatic retries.observabilityBring Your Own Key supportprovider routing Read the , view the , or use DeepSeek V3.2 models directly in our .docsAI Gateway model leaderboardmodel playground Read more Non-thinking: deepseek/deepseek-v3.2 Thinking: deepseek/deepseek-v3.2-thinking Speciale: deepseek/deepseek-v3.2-speciale