[KongchangAI]
ModelDeepSeek V4.1 Flash 1017 Ultrafast / deepseek/deepseek-v4.1-flash-1017-ultrafast

DeepSeek V4.1 Flash Ultrafast

An accelerated version of DeepSeek V4.1 Flash, offering high-speed inference through Fireworks' accelerated serverless endpoints, with generation speeds exceeding 1000 tokens per second and a context window of 1 million tokens. It is intended for interactive coding, reasoning and agentic workflows.

Source Articles