AI summary
Written by AI from the official notes. Check them for exact details.DeepSeek API introduces V4-Pro and V4-Flash models while discontinuing legacy models in three months.
- New models V4-Pro and V4-Flash available via OpenAI and Anthropic interfaces.
- Legacy models deepseek-chat and deepseek-reasoner will be discontinued on 2026-07-24.
- Base URL remains unchanged for accessing new models.
Why it matters: Users of DeepSeek API should transition to the new models to ensure continued service.
Full release notes
The DeepSeek API now supports V4-Pro and V4-Flash, available via both the OpenAI ChatCompletions interface and the Anthropic interface. To access the new models, the base_url remains unchanged, and the model parameter should be set to deepseek-v4-pro or deepseek-v4-flash.
The two legacy API model names, deepseek-chat and deepseek-reasoner, will be discontinued in three months (2026-07-24). During the current period, these two model names point to the non-thinking mode and thinking mode of deepseek-v4-flash, respectively.
For more details, please refer to this documentation.