DeepSeek V4 Flash
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.
DeepSeek V4 Flash
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.
Ready to build with DeepSeek V4 Flash?
Get Started FreeParameters & options
Non-think for fast responses, High for complex problem-solving, Max to push reasoning to its fullest extent.
Nucleus sampling. Considers only tokens whose cumulative probability exceeds this threshold.
Limits sampling to the K most likely tokens at each step. Set to 0 to disable.
Minimum probability threshold relative to the most likely token.
Penalizes tokens that have already appeared in the output, encouraging new topics.
Penalizes tokens based on how often they have already appeared.
Penalizes repeated tokens. Values above 1 discourage repetition.
Explore similar models
Start building with DeepSeek V4 Flash
No API keys required. Create AI-powered workflows with DeepSeek V4 Flash in minutes — free.