Back to every model

DeepSeek

DeepSeek V4 Pro 0813 API pricing and specs

DeepSeek's DeepSeek V4 Pro 0813: price per million tokens, context window, limits and capabilities, re-read from OpenRouter's model feed every 6 hours.

Input

$0.1035

Output

$4

Context

1M

DeepSeek V4 Pro 0813 costs $0.1035 per million input tokens and $4 per million output tokens. Cached input is billed at $0.10 per million, 3% less than fresh input.

Specifications

LabDeepSeek
Model iddeepseek/deepseek-v4-pro-0813
Input price$0.1035 per million tokens
Output price$4 per million tokens
Cached input price$0.10 per million tokens
Context window1,048,576 tokens (1M)
Maximum output393,216 tokens (384K)
Tool callingyes
Image inputno
Reasoningno
Intelligence index23.1
First listed12 August 2026

Models it replaced

The feeds list DeepSeek V4 Pro 0813 in place of deepseek/deepseek-v4-pro. Those models' own prices and limits were different; an article that names one of them describes the model it was written about.

DeepSeek's other models

ModelInput / 1MOutput / 1MContextListed
DeepSeek V4.1 Flash 1017$0.022$0.1921M17 October 2026
DeepSeek V4 Flash Vision Exp$0.2156$0.64681M21 August 2026
DeepSeek V4 Flash 0731$0.119$0.2381M31 July 2026
DeepSeek V3.2$0.26$0.38160K1 December 2025
DeepSeek V3.2 Exp$0.27$0.41160K29 September 2025
DeepSeek V3.1 Terminus$0.27$1160K22 September 2025
DeepSeek V3.1$0.25$0.95160K21 August 2025
R1 0528$0.50$2.15160K28 May 2025
DeepSeek V3 0324$0.29$1.14160K24 March 2025
DeepSeek V3$0.2574$1.0287160K26 December 2024

Where these numbers come from

Read from OpenRouter's listing of DeepSeek V4 Pro 0813 every 6 hours into the catalog Founden's builders choose their models from. Prices are OpenRouter's listed price per million tokens: for a lab's closed models that is the lab's own list price, and for an open-weight model it is the price of the host OpenRouter routes to by default, which can differ from the lab's own API and from other hosts. US dollars, before batch, volume or regional discounts. Every model.