The official release of the DeepSeek-V4-Flash API is now in public beta. The API calling method remains unchanged — simply set the model name to deepseek-v4-flash to use the latest version.
Significantly enhanced agent capabilities, with benchmark results far exceeding V4-Pro-Preview:
Note 1: For the Code Agent tasks in the public benchmark sets, the official DeepSeek-V4-Flash was tested using the DeepSeek Harness minimal mode (to be released soon) as the framework, with the max effort level, topp=0.95, and temperature=1.0
The official V4-Flash natively supports the Responses API format and is specifically adapted for Codex. For the specific configuration, please refer to the documentation.