Home/Models/deepseek-v4-pro
DeepSeekStableChecked 2026-07-12

deepseek-v4-pro pricing, context window, and cost calculator

A DeepSeek model with tracked cache-miss, cached-input, context-window, and maximum-output data.

Estimate this model's costCompare with another modelView provider pricingOfficial source ↗
Verified fields

Quick facts

ProviderDeepSeek
API model IDdeepseek-v4-pro
Default input / 1M$0.435
Default output / 1M$0.87
Context window1,000,000
Default profilestandard / cache miss
Acceptstext
Producestext
StatusStable
Maximum output384,000 tokens

Supported capabilities

  • Function calling
  • Structured outputs
  • Prompt caching
  • Reasoning
  • Prefix completion
  • FIM completion

Only capabilities explicitly tracked from provider documentation are shown.

Source-tracked rates

Verified pricing profiles

Amounts are USD per 1M tokens unless the column states an hourly storage unit.

ProfileInput / 1MCached input / 1MOutput / 1MNotes
standard / cache missDefault$0.435 USD$0.0036 USD$0.87 USDUsed for default estimates.
Workload estimate

deepseek-v4-pro cost calculator

Change the workload assumptions. The calculator uses the same shared pricing resolver as StackLens Compare.

Estimated monthly total$8.70
Monthly input cost
$4.35
Monthly output cost
$4.35
Per 1,000 requests
$0.87
Active profile
standard / cache miss

Estimate excludes untracked provider-specific charges.

Explicit assumptions

Common workload examples

Input only

1M input tokens

$0.435 under the standard.cache_miss profile, excluding output and other charges.

Output only

1M output tokens

$0.87 under the standard.cache_miss profile, excluding input and other charges.

Default workload

10,000 monthly requests

At 1,000 input and 500 output tokens per request: $8.70 under standard / cache miss.

Cache scenario

50% cached input

The same default workload with 50% cached input is estimated at $6.5431. Cache savings apply only to the tracked cached-input rate.

Tracked relationships

Related models

Previous model in this tracked familyDeepSeek V4 Flash non-thinkingDeepSeek
Verification

Sources and methodology

Pricing and limits are source-tracked and may change. Verify current values with the provider before making production purchasing decisions.

Calculator profile rule: standard.cache_miss is the verified default. Supports thinking and non-thinking modes. Context length and maximum output are tracked from the supplied official values.