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 V4.1 Flash pricing

DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture. DeepSeek V4.1 Flash from DeepSeek costs $0.300 per 1M input tokens and $1.20 per 1M output tokens. Cached input is $0.006 per 1M. Context window 1,048,576 tokens.

API id deepseek-v4.1-flash · DeepSeek · source · updated 2026-09-25 · general-purpose

$0.300
Input / 1M tokens
$1.20
Output / 1M tokens
$0.006
Cached input / 1M
1M
Context window

DeepSeek V4.1 Flash specifications

Provider
DeepSeek
API id
deepseek-v4.1-flash
Model type
general-purpose
Context window
1M tokens
Max output
393K tokens
Currency
USD
Price source
Provider API
Last checked
2026-09-25

Tags

  • fast
  • vision

DeepSeek V4.1 Flash 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
$0.300$0.006$1.20$1.50—
$0.300$0.006$1.20$1.50—
$0.300$0.006$1.20$1.50—

What DeepSeek V4.1 Flash costs in practice

Estimated cost at common usage volumes
WorkloadInput tokensOutput tokensEstimated cost
Short chat turn1,000500$0.0009
Document summary50,0002,000$0.02
1M tokens in, 200K out1,000,000200,000$0.54

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

DeepSeek V4.1 Flash price history

RecordedInput /1MOutput /1M
2026-09-25$0.300$1.20
2026-09-24$0.140$0.420
2026-09-23$0.059$0.600
2026-09-21$0.300$1.20
2026-09-19$0.150$0.600
2026-09-14$0.300$1.20
2026-09-13$0.300$1.20
2026-09-12$0.150$0.600
2026-09-11$0.300$1.20

Common questions

How much does DeepSeek V4.1 Flash cost per 1M tokens?
DeepSeek V4.1 Flash costs $0.300 per 1M input tokens and $1.20 per 1M output tokens on the standard tier. Cached input is $0.006 per 1M.
What is DeepSeek V4.1 Flash's context window?
DeepSeek V4.1 Flash accepts up to 1,048,576 tokens in a single request, and can return up to 393,216 output tokens.
Is there a cheaper DeepSeek model than DeepSeek V4.1 Flash?
Yes. DeepSeek V3 0324 is $0.250 per 1M input tokens versus $0.300 for DeepSeek V4.1 Flash, with a 163,840 token context window.
Where does this DeepSeek V4.1 Flash 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 →