deepseek-v4-flash
Common Name: DeepSeek V4 Flash
DeepSeek V4 Flash is a hybrid-thinking model with 1M context and 384K max output. It supports both non-thinking and thinking modes, with thinking enabled by default.
Specifications
Performance (7-day Average)
Pricing
Peak window (local): 01:00–04:00, 06:00–10:00
Performance Metrics (24h)
Similar Models
DeepSeek V4 Flash Vision Exp is the experimental vision variant of V4 Flash. Text capability matches the stable V4 Flash, and images are billed as token-equivalent. Supports 1M context and 384K max output.
DeepSeek V4 Pro is the higher-capability hybrid-thinking model in the V4 family. It supports both non-thinking and thinking modes, with 1M context and 384K max output.
GPT-5.6 Terra balances GPT-5.6 intelligence and cost for strong performance at lower price points.
GPT-5.4 is OpenAI's most capable frontier model for professional work, unifying GPT and Codex lines. Features native computer use, 1M+ context, and configurable reasoning effort (none to xhigh).