DeepSeek

DeepSeek V4 Pro

DeepSeek V4 Pro — 1.6T-parameter MoE model with 49B active parameters, 1M context, advanced reasoning, coding, and long-horizon agentic workflows.

deepseek-v4-pro

Open in chat

Pricing

~99.6%

Input: $0.001338 / 1,000,000 tokens
Output: $0.002676 / 1,000,000 tokens
Cache read: $0.000112 / 1,000,000 tokens
Cache write: $0.001338 / 1,000,000 tokens

How pricing works

Discount history

99.6%Nov 9, 03:04 AM UTC

Nov 8, 03:35 AMNov 9, 03:04 AM UTC

Model details

Input: text
Output: text
Context window: 1,000,000 tokens
Maximum output: 128,000 tokens
Availability: $1.9KUncapped capacity
Updated: 11/9/2026, 3:06:18 AM UTC

Capacity is reserved when your request is accepted.

Capabilities

ChatStreamingTool callingReasoning

Supported parameters

max_tokenstemperaturetop_pfrequency_penaltypresence_penaltyrepetition_penaltymin_plogit_biaslogprobstop_logprobsstoptoolstool_choiceresponse_formatseedstructured_outputsinclude_reasoningreasoning