DeepSeek V4 Pro API Cost Calculator

DeepSeek's DeepSeek V4 Pro: $0.435/M input · $0.87/M output · $0.003625/M cached input. Price your own workload below.

Cached-input price is DeepSeek’s cache-hit rate.

Presets:

What DeepSeek V4 Pro costs in practice

WorkloadInputOutputCost
Short chat message500250$0.0004
10-page document + summary7,000500$0.0035
Agent / coding session50,00010,000$0.030
1M tokens in + 1M out1,000,0001,000,000$1.30

DeepSeek V4 Pro vs nearest rivals

Closest-priced alternatives on a mixed 10K-input / 2K-output request:

ModelInput $/MTokOutput $/MTokMixed request
DeepSeek V4 Pro$0.435$0.87$0.0061
GPT-5.6 Luna$0.2$1.2$0.0044
GPT-5 mini$0.25$2$0.0065
Gemini 2.5 Flash$0.3$2.5$0.0080

Frequently asked questions

How much does the DeepSeek V4 Pro API cost?

DeepSeek V4 Pro costs $0.435 per million input tokens and $0.87 per million output tokens, with cached input at $0.003625 per million (99% off). Note: Cached-input price is DeepSeek’s cache-hit rate.

How much does a typical chat message cost with DeepSeek V4 Pro?

A short chat message (about 500 input and 250 output tokens) costs roughly $0.0004 with DeepSeek V4 Pro. At 1,000 such requests a day, that is about $13.05 per month.

Is DeepSeek V4 Pro cheap compared to similar models?

DeepSeek V4 Pro has the #9 cheapest input rate of the 26 models we track. On a mixed workload (10K input / 2K output), it costs $0.0061 per request, versus $0.0044 for GPT-5.6 Luna and $0.0065 for GPT-5 mini.

Related

Compare all models at once ·Count tokens in your prompt

Last updated 2026-08-03. Prices verified againstDeepSeek's official pricing page; see themethodology.