Transition to DeepSeek V4 API Model Names Before Deletion Deadline
Update model parameters to V4 titles to avoid service disruption.
Switch your API model parameters from legacy names to 'deepseek-v4-pro' or 'deepseek-v4-flash' before July 24, 2026.
The Scenario
You are a developer maintaining an AI-powered application and need to ensure your integration doesn't break when legacy models are retired.
Before & after
Users typically rely on default model names like 'deepseek-chat', but these legacy names will be discontinued on 2026-07-24, requiring name changes that could take 15-30 minutes of troubleshooting if forgotten.
Updating the model parameter to 'deepseek-v4-pro' or 'deepseek-v4-flash' takes less than 1 minute and ensures your application continues to function after the July 2026 cutoff.
The Prompt
Check your API integration code and replace occurrences of 'deepseek-chat' with 'deepseek-v4-flash' (for speed) or 'deepseek-v4-pro' (for performance). Ensure the base_url remains the same.
DeepSeek is replacing 'deepseek-chat' and 'deepseek-reasoner' with 'deepseek-v4-pro' and 'deepseek-v4-flash'. To maintain service, developers must update their API call parameters before the three-month transition period ends.
Source
Change Log | DeepSeek API Docs"The two legacy API model names, deepseek-chat and deepseek-reasoner, will be discontinued in three months (2026-07-24)."