Fresh paint, wet floors — we're rebuilding CostOfToken into a cross-provider price comparison. Some corners are still under construction; the full version is coming up soon.

DeepSeek V4 Pro 0813 pricing

DeepSeek V4 Pro 0813 is a large-scale mixture-of-experts model from DeepSeek. This is the GA release of DeepSeek V4 Pro. DeepSeek V4 Pro 0813 from DeepSeek costs $0.111 per 1M input tokens and $4.44 per 1M output tokens. Cached input is $0.097 per 1M. Context window 1,048,576 tokens.

API id deepseek-v4-pro-0813 · DeepSeek · source · updated 2026-11-11 · general-purpose

$0.111
Input / 1M tokens
$4.44
Output / 1M tokens
$0.097
Cached input / 1M
1M
Context window

DeepSeek V4 Pro 0813 specifications

Provider
DeepSeek
API id
deepseek-v4-pro-0813
Model type
general-purpose
Context window
1M tokens
Max output
944K tokens
Currency
USD
Price source
Provider API
Last checked
2026-11-11

Tags

  • flagship

DeepSeek V4 Pro 0813 across providers

The same model, priced by every seller we track. Ranked by the cost of 1M input + 1M output tokens, standard tier; savings measured against buying from the vendor directly.

ProviderInput /1MCached /1MOutput /1M1M in + 1M outvs vendor
DeepSeekVendorCheapestviewing
$0.111$0.097$4.44$4.55—
$0.111$0.097$4.44$4.55—
$1.32$0.130$3.96$5.28+16%

What DeepSeek V4 Pro 0813 costs in practice

Estimated cost at common usage volumes
WorkloadInput tokensOutput tokensEstimated cost
Short chat turn1,000500$0.0023
Document summary50,0002,000$0.01
1M tokens in, 200K out1,000,000200,000$1.00

Estimates use the standard tier and ignore caching discounts, so real bills with repeated prompt prefixes are typically lower.

DeepSeek V4 Pro 0813 price history

RecordedInput /1MOutput /1M
2026-11-09$0.111$4.44
2026-11-08$0.111$4.44
2026-11-07$0.117$4.66
2026-11-06$0.111$4.44
2026-11-05$0.107$4.28
2026-11-04$0.115$4.60
2026-11-01$0.115$4.00
2026-10-31$0.660$1.98
2026-10-26$1.32$3.96
2026-10-24$0.660$1.98
2026-10-22$1.32$3.96
2026-10-17$0.660$1.98

Common questions

How much does DeepSeek V4 Pro 0813 cost per 1M tokens?
DeepSeek V4 Pro 0813 costs $0.111 per 1M input tokens and $4.44 per 1M output tokens on the standard tier. Cached input is $0.097 per 1M.
What is DeepSeek V4 Pro 0813's context window?
DeepSeek V4 Pro 0813 accepts up to 1,048,576 tokens in a single request, and can return up to 943,718 output tokens.
Is there a cheaper DeepSeek model than DeepSeek V4 Pro 0813?
Yes. DeepSeek V4 Flash 0423 is $0.090 per 1M input tokens versus $0.111 for DeepSeek V4 Pro 0813, with a 1,048,576 token context window.
Where does this DeepSeek V4 Pro 0813 price come from?
From the OpenRouter catalogue, because DeepSeek does not publish machine-readable pricing. OpenRouter is a reseller, so its rate can differ from DeepSeek's own — verify before committing spend.

Head-to-head comparisons

Other DeepSeek models

See all DeepSeek pricing →