DeepSeek V3 0324
by DeepSeektext->text4 endpoints
Overview
DeepSeek V3, a 685B-parameter, mixture-of-experts model, is the latest iteration of the flagship chat model family from the DeepSeek team. It succeeds the DeepSeek V3 model and performs really well...
Capabilities
Text generation
Tool use / Function calling
Structured output
Prompt caching
Long context
Top-P sampling
Stop sequences
Deterministic seed
Modalities
Input
Text
Output
Text
Technical Specifications
Context Window
163.8K tokens
Max Output
65.5K tokens
Knowledge Cutoff
2024-07-31
Tokenizer
DeepSeek
Uptime (24h)
9730.3%
Supported Parameters
frequency_penaltylogit_biasmax_tokensmin_ppresence_penaltyrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_p
Pricing
Per 1M tokens
Input$0.27
Output$1.12
Cache read$0.14