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 Flash 0731 pricing

DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total. DeepSeek V4 Flash 0731 from DeepSeek costs $0.030 per 1M input tokens and $0.320 per 1M output tokens. Cached input is $0.016 per 1M. Context window 1,310,720 tokens.

API id deepseek-v4-flash-0731 · DeepSeek · source · updated 2026-09-25 · general-purpose

$0.030
Input / 1M tokens
$0.320
Output / 1M tokens
$0.016
Cached input / 1M
1.3M
Context window

DeepSeek V4 Flash 0731 specifications

Provider
DeepSeek
API id
deepseek-v4-flash-0731
Model type
general-purpose
Context window
1.3M tokens
Max output
944K tokens
Currency
USD
Price source
Provider API
Last checked
2026-09-25

Tags

  • fast

DeepSeek V4 Flash 0731 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
$0.030$0.016$0.320$0.35—
$0.030$0.016$0.320$0.35—
$0.140$0.030$0.280$0.42+20%

What DeepSeek V4 Flash 0731 costs in practice

Estimated cost at common usage volumes
WorkloadInput tokensOutput tokensEstimated cost
Short chat turn1,000500$0.0002
Document summary50,0002,000$0.0021
1M tokens in, 200K out1,000,000200,000$0.09

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

DeepSeek V4 Flash 0731 price history

RecordedInput /1MOutput /1M
2026-09-24$0.030$0.320
2026-09-22$0.040$0.640
2026-09-21$0.040$0.160
2026-09-20$0.040$0.080
2026-09-19$0.065$0.180
2026-09-16$0.060$0.120
2026-09-15$0.055$0.110
2026-09-14$0.060$0.120
2026-09-12$0.040$0.080
2026-09-08$0.065$0.180
2026-09-07$0.140$0.280
2026-08-30$0.065$0.180

Common questions

How much does DeepSeek V4 Flash 0731 cost per 1M tokens?
DeepSeek V4 Flash 0731 costs $0.030 per 1M input tokens and $0.320 per 1M output tokens on the standard tier. Cached input is $0.016 per 1M.
What is DeepSeek V4 Flash 0731's context window?
DeepSeek V4 Flash 0731 accepts up to 1,310,720 tokens in a single request, and can return up to 943,718 output tokens.
Where does this DeepSeek V4 Flash 0731 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 →