DeepSeek
DeepSeek: DeepSeek V4 Flash
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 |
| Input pricing | $0.09/M tokens |
| Output pricing | $0.19/M tokens |
| Context length | 1.0M tokens |
| Input modalities | text |
| Output modalities | text |
| Tokenizer | DeepSeek |
| Content moderated | No |
| HuggingFace | deepseek-ai/DeepSeek-V4-Flash |
Supported Parameters
frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokensmin_ppresence_penaltyreasoningreasoning_effortrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p