DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window. It is designed for fast inference and...
Specifications
- Provider
- DeepSeek
- Type
- Open-source / open-weight
- Modality
- text->text
- Context window
- 1,048,576
- Released
- April 24, 2026
Capabilities
Input: textOutput: textConfigurable reasoning effort
Strengths
frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokensmin_ppresence_penaltyreasoningreasoning_effortrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_atop_ktop_logprobstop_p
