Back to all models
deepseek
deepseekDeepSeek: DeepSeek V4 Flash 0731 (batch)
DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total. This re-post-trained revision is suited for coding, reasoning, and agent workflows....
deepseek/deepseek-v4-flash-0731:batch
Context Size
1,048.576K
Input Price
7,200 pts/M443 Ks/M
Output Price
21,600 pts/M1,328 Ks/M
Architecture
Text
Supported Parameters
frequency_penaltyinclude_reasoninglogit_biasmax_tokensmin_ppresence_penaltyreasoningreasoning_effortrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_p
Details
TokenizerDeepSeek
Max Completion384,000 tokens
Provider Context1,048.576K tokens
ModeratedNo
CreatedJul 31, 2026