DeepSeek API launches simultaneously with V4-Pro and V4-Flash

On April 24, DeepSeek announced that DeepSeek API has been launched simultaneously with V4-Pro and V4-Flash, supporting the OpenAIChatCompletions interface and Anthropic interface. When accessing a new model, the base_url remains unchanged, and the model parameter needs to be changed to deepseek-v4-pro or deepseek-v4-flash. The maximum context length of V4-Pro and V4-Flash is 1M, and both support both non-thinking mode and thinking mode. The thinking mode supports the reasoning_effort parameter to set the thinking intensity (high/max). For complex Agent scenarios, it is recommended to use thinking mode and set the intensity to max. (East News Agency)