DeepSeek

DeepSeek V4 Flash 0731 Fast

DeepSeek V4 Flash 0731 Fast is Venice’s low-latency serving profile for the 0731 DeepSeek V4 Flash checkpoint, with a 1M-token context window and reasoning, coding, tool, and structured-output support.

deepseek-v4-flash-0731-fast

Pricing

~62%

Input: $0.132895 / 1,000,000 tokens
Output: $0.26579 / 1,000,000 tokens
Cache read: $0.033224 / 1,000,000 tokens
Cache write: $0.132895 / 1,000,000 tokens

How pricing works

Discount history

62%Nov 8, 03:58 AM UTC

Nov 7, 11:59 PMNov 8, 03:58 AM UTC

Model details

Input: text
Output: text
Context window: 1,000,000 tokens
Maximum output: 32,768 tokens
Availability: $103.5Uncapped capacity
Updated: 11/8/2026, 4:00:11 AM UTC

Capacity is reserved when your request is accepted.

Capabilities

ChatStreamingWeb searchTool callingReasoningJSON mode

Supported parameters

frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokensmin_ppresence_penaltyreasoningreasoning_effortrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_atop_ktop_logprobstop_p