DEEPSEEK_
deepseek-flash — the general-purpose model: a 1M token context, up to 384K output tokens, and image input, which needs no separate vision model. Thinks unless Thinking disables it.
deepseek-flash — the general-purpose model: a 1M token context, up to 384K output tokens, and image input, which needs no separate vision model. Thinks unless Thinking disables it.