ModelPickr

Compare / DeepSeek

DeepSeek · canonical pair

DeepSeek V4 Pro vs DeepSeek V4 Pro 0813

Alphabetical by model id, so this URL is the one to index. DeepSeek V4 Pro is deepseek/deepseek-v4-pro. DeepSeek V4 Pro 0813 is deepseek/deepseek-v4-pro-0813. Both are among the models the most providers list, inside the DeepSeek group.

A

DeepSeek V4 Pro

$13.86

per month at the reference workload

  • Reasoning
  • Tool use
  • Structured output
  • Long context
  • Open weights

vs

B

DeepSeek V4 Pro 0813

$6.93

per month at the reference workload

  • Reasoning
  • Tool use
  • Structured output
  • Long context
  • Open weights
100 requests a day, 2,000 input tokens and 500 output tokens, no cache hits. A light chat workload so the rate cards are comparable.
SpecDeepSeek V4 ProDeepSeek V4 Pro 0813
Monthly, reference workload$13.86$6.93
Input / 1M$1.32$0.66
Output / 1M$3.96$1.98
Cache read / 1M$0.042$0.022
Cache write / 1M——
Context1,000,0001,000,000
Max output384,000384,000
ReasoningYesYes
Tool callsYesYes
VisionNoNo
Open weightsYesYes
Providers5842
Released2026-04-242026-08-12

Same workload, your numbers

Prices are USD per 1M tokens. A month is 30 days. Cache hits use the cache-read rate when the model has one; otherwise the cache field is ignored.

DeepSeek V4 Pro costs $6.93 more per month than DeepSeek V4 Pro 0813 at these inputs.

monthly = requests/day × 30 × (input tokens × (1 − cache hit) × input price + input tokens × cache hit × cache-read price + output tokens × output price) ÷ 1,000,000