DeepSeek V4 Pro API Pricing & Cost Calculator

By TechCompare · Updated · How we check

DeepSeek V4 Pro at $1.32/$3.96 peak is a reasoning API. Its output rate is about 80% lower than the listed GPT-5.6 Sol output rate ($20/M versus $3.96/M), with 96.7% off cached input on top.

Calculator

Cost Comparison

Based on 100,000 input tokens (50% cached), 5,000 output tokens, and 100 requests.Prices come live from OpenRouter at each maker's own price where it's listed. Temporary deals are left out.

Loading model prices

DeepSeek V4 Pro's 0813 refresh is the GA version of the trillion-parameter reasoning model, now 17.5% cheaper on input than the spring preview at $1.32/$3.96 peak, with cached input at $0.044.

DeepSeek: DeepSeek V4 Pro 0813

Cheapest host: Alibaba

Input
$1.32
Output
$3.96
Cached
$0.044

per 1M tokens

Flex availableOff-peak available

Price checked 2026-11-19

How this is calculated

DeepSeek V4 Pro is priced at $1.32 per million input tokens and $3.96 per million output tokens at peak, with off-peak rates of $0.66/$1.98, 50% off input and 50% off output outside the weekday 01:00-04:00 and 06:00-10:00 UTC windows. Cached input at peak is $0.044 per million, 96.7% off. Context is 1M tokens with a 384K max output.

Verdict

The per-call math at 100K + 5K is $0.1518 peak, $0.0759 off-peak, versus $0.50 for GPT-5.6 Sol and $0.23 for Qwen 3.8 Max. That's 3.3x cheaper than GPT-5.6 Sol. The 96.7% cache discount drops cached input to $0.044/M, so agent loops with a stable system prompt pay $0.044/M on the cached part of the input. The April preview was $1.60/$3.20, so August's $1.32/$3.96 card is an input cut of 17.5% from the preview.

More API Standalones scenarios

Frequently asked questions

Is the 0813 refresh priced differently from the spring V4 Pro preview?
Yes. The April preview was $1.60/M input and $3.20/M output. The August 0813 GA refresh is $1.32/M input and $3.96/M output, so input dropped 17.5% while output rose 23.7%.
DeepSeek V4 Pro or Qwen 3.8 Max?
V4 Pro is $1.32/$3.96 peak versus Qwen 3.8 Max's $2.00/$6.00, and DeepSeek's cache discount is deeper (96.7% vs 87.5%). Qwen's batch tier ($1.15/$3.45) partially closes the gap for offline jobs. For the hardest reasoning benchmarks the two trade wins depending on the eval, so pick V4 Pro on raw price and caching, Qwen if you're in the Alibaba ecosystem.
What does off-peak scheduling save?
Off-peak takes 50% off input and 50% off output. V4 Pro off-peak is $0.66/M input and $1.98/M output versus $1.32/$3.96 peak. Peak windows are 01:00-04:00 and 06:00-10:00 UTC, so anything that queues outside those hours buys 2x the input tokens for the same spend.