What is DeepSeek V4 Flash?
Tavory's live catalog currently lists DeepSeek V4 Flash from Deepinfra. The catalog describes it as deepseek v4 flash is an efficiency-focused moe model with 284b total parameters (13b active) and a 1m-token context window. it's tuned for fast inference and high-throughput use cases while still holding up on reasoning and coding tasks.. Availability, plan access and provider pricing can change and are checked again when a request is sent.
Good fit for
text and chat
reasoning and analysis