This model always redirects to the latest model in the DeepSeek V4 Flash family.
Drop-in code to call this model. OpenRouter's API is OpenAI-compatible — most SDKs work by just swapping the base URL. The only thing that changes between models is the model slug below.
This model always redirects to the latest model in the DeepSeek V4 Flash family.
DeepSeek V4 Flash Latest costs $0.0765/M input tokens and $0.153/M output tokens, with separate rates for Cache Read at $0.0153/M tokens.
DeepSeek V4 Flash Latest has a 1,310,720 token context window. It supports up to 262,144 completion tokens.
Yes. DeepSeek V4 Flash Latest accepts tools and tool_choice for function calling. It also supports structured outputs via a JSON schema in response_format.
DeepSeek V4 Pro 0813, DeepSeek V4 Pro 0423, DeepSeek V4 Flash 0423 and 8 more are other text models from DeepSeek.
DeepSeek V4 Flash Latest was released on August 1, 2026.