invokeable()
← directory / models / deepseek-v4-pro-0813

DeepSeek V4 Pro 0813

model deepseek-v4-pro-0813

Draft entry — numbers not yet verified against primary sources.

1M
context
384K
max output
—
input
—
output
—
knowledge cutoff
1
providers

01Providers

ProviderProvider model IDIn $/MOut $/MContextStatus
DeepSeek API deepseek-v4-pro-0813 — — 1M live

02Invoke

provider
language

  

  



03Related
DeepSeek V4 Flash 07312026-07DeepSeek V4 Flash2026-04DeepSeek V4 Pro2026-04DeepSeek V3.22025-09DeepSeek-V3.12025-08DeepSeek V3 03242025-03


04Compare
vs DeepSeek V4 Flash 0731head-to-head


05Sources · where these numbers come from
  1. https://github.com/sst/models.dev
  2. https://api-docs.deepseek.com/quick_start/pricing
  3. https://huggingface.co/deepseek-ai
  4. https://api-docs.deepseek.com