DeepSeek V4 Pro API pricing (August 2026)

Prices verified 4 Aug 2026

Base rate — bills 2x during Beijing peak hours (09:00-12:00 and 14:00-18:00 UTC+8).

Input
$0.435
per 1M tokens
Output
$0.870
per 1M tokens
Cached input
$0.00363
per 1M tokens
Batch discount
None
no batch API

What it costs at real volumes

A chat-shaped workload: 800 input tokens and 300 output tokens per request, no caching, no batch.

VolumePer requestPer monthPer year
10K requests/day$0.00061$185.38$2,224.56Adjust →
100K requests/day$0.00061$1,853.80$22.2KAdjust →
1M requests/day$0.00061$18.5K$222.5KAdjust →

Specifications

Provider
DeepSeek
Context window
1.0M tokens
Max output
384K tokens
Tier
frontier
Status
GA
Blended $/1M (3:1)
$0.544
Cache break-even hit rate
0% — caching always saves
Prices verified
4 Aug 2026

Source: DeepSeek pricing. Finitizer is not affiliated with DeepSeek.

Similar models

Other deepseek models

Closest prices elsewhere

Frequently asked questions

How much does DeepSeek V4 Pro cost per 1M tokens?

DeepSeek V4 Pro costs $0.435 per million input tokens and $0.870 per million output tokens at DeepSeek list prices. Output is 2.0x the input rate, so the input:output ratio of your workload drives the real cost more than the headline price.

Does DeepSeek V4 Pro support prompt caching?

Yes. Cached input is billed at $0.00363 per million tokens, 120x cheaper than uncached input. There is no cache-write premium, so caching is never a net loss.

What is the batch discount for DeepSeek V4 Pro?

DeepSeek V4 Pro does not offer a batch pricing tier.

What is DeepSeek V4 Pro's context window?

1.0M tokens of context with up to 384K output tokens per request. A larger context window raises the ceiling on what you can send, not the price per token — but filling it on every request is one of the most common causes of an unexpected bill.

Running DeepSeek V4 Pro in production?

Finitizer TokenOps attributes real token spend to teams, features, and prompts — so you find out which workload moved the bill before the invoice does.