DeepSeek V4.1 Flash pricing.

prices as of · 54 providers · 61 prices

DeepSeek V4.1 Flash holds 1M tokens of context, reads images as well as text and has a reasoning mode. Open weights, so anyone may host it, which is why the prices below differ so much.

DeepSeek V4.1 Flash costs $0.15 in and $0.60 out per million tokens from DeepSeek; the cheapest price we can explain is $0.21 at TrustedRouter, checked 16 Sept 2026.

tool callingreads imagesreasoningstructured outputopen weights1M contextreleased 10 Sept 2026

DeepSeek list price

$1.05/M tokens

$0.15 in · $0.60 out

read · 70% below the market median

Cheapest price we can explain

$0.21/M tokens

$0.04 in · $0.08 out · 80% under list

TrustedRouter
View at TrustedRouter

read

What it costs for your work

pages a month

DeepSeek list price

$0.126a month

cheapest we can explain · TrustedRouter

$0.0304a month

difference

$0.0956saved

A page is about 600 tokens in and 60 out, a support reply 200 in and 300 out, an email 150 in and 250 out. Nothing else is counted: no cache discount, no batch rate, no free tier.

Every provider selling DeepSeek V4.1 Flash

Four groups, decided by the price and by what the provider publishes about it. Prices are per million tokens, and the share is that row against DeepSeek's price.

The maker's list price

1 price

What the lab that trained the model charges on its own API.

  • DeepSeek

    The price DeepSeek charges for the model it trained. Every row below is measured against it.

    $0.15 / $0.60in / out per M

    1.00×of list price

Cheaper, and we know why

3 prices

Below list, with a published reason: hosting the open weights, a regional price list, credits, a stated discount.

  • TrustedRouter

    Routes to a host serving the open weights; precision not disclosed.

    $0.04 / $0.08in / out per M

    0.20×of list price

  • AMD

    7% under the list price, an ordinary reseller margin.

    $0.14 / $0.28in / out per M

    0.67×of list price

  • Crof

    Serves the open weights at Q8_0, a lower precision than the maker's, so not quite the same product.

    1M context hereQ8_0 precisionCrof

    $0.10 / $0.50in / out per M

    0.76×of list price

Same price as the maker

52 prices

The same price the maker charges, sold by someone else.

  • NanoGPT

    4% above DeepSeek's price.

    $0.16 / $0.31in / out per M

    0.74×of list price

  • NanoGPT

    4% above DeepSeek's price.

    1M context hereNanoGPT

    $0.16 / $0.31in / out per M

    0.74×of list price

  • OpenRouter

    The same price DeepSeek charges.

    $0.15 / $0.60in / out per M

    1.00×of list price

  • Ollama Cloud

    The same price DeepSeek charges.

    $0.15 / $0.60in / out per M

    1.00×of list price

  • LLM Gateway

    The same price DeepSeek charges.

    1M context hereLLM Gateway

    $0.15 / $0.60in / out per M

    1.00×of list price

  • Vercel AI Gateway

    The same price DeepSeek charges.

    1M context hereVercel AI Gateway

    $0.15 / $0.60in / out per M

    1.00×of list price

  • Merge Gateway

    The same price DeepSeek charges.

    1M context here

    $0.15 / $0.60in / out per M

    1.00×of list price

  • ClinePass

    The same price DeepSeek charges.

    1M context here

    $0.15 / $0.60in / out per M

    1.00×of list price

  • OpenCode Go

    The same price DeepSeek charges.

    1M context here

    $0.15 / $0.60in / out per M

    1.00×of list price

  • Relace

    The same price DeepSeek charges.

    fp4 precision

    $0.15 / $0.60in / out per M

    1.00×of list price

  • Nous Portal

    The same price DeepSeek charges.

    $0.15 / $0.60in / out per M

    1.00×of list price

  • AIHubMix

    3% above DeepSeek's price.

    1M context here

    $0.15 / $0.62in / out per M

    1.03×of list price

  • Requesty

    33% above DeepSeek's price.

    $0.20 / $0.60in / out per M

    1.14×of list price

  • DeepInfra

    33% above DeepSeek's price.

    $0.20 / $0.60in / out per M

    1.14×of list price

  • DeepInfra

    33% above DeepSeek's price.

    fp8 precisionDeepInfra

    $0.20 / $0.60in / out per M

    1.14×of list price

  • FastRouter

    33% above DeepSeek's price.

    $0.20 / $0.60in / out per M

    1.14×of list price

  • Fireworks AI

    47% above DeepSeek's price.

    $0.22 / $0.66in / out per M

    1.26×of list price

  • Morph

    30% above DeepSeek's price.

    fp8 precision

    $0.20 / $0.78in / out per M

    1.30×of list price

  • Vancine

    60% above DeepSeek's price.

    1M context here

    $0.24 / $0.96in / out per M

    1.60×of list price

  • Melious

    55% above DeepSeek's price.

    1M context here

    $0.23 / $1.16in / out per M

    1.77×of list price

  • CrossModel

    80% above DeepSeek's price.

    1M context here

    $0.27 / $1.08in / out per M

    1.80×of list price

  • Inference.net

    100% above DeepSeek's price.

    1M context hereInference.net

    $0.30 / $1in / out per M

    1.81×of list price

  • GMI Cloud

    90% above DeepSeek's price.

    1M context herefp8 precisionGMI Cloud

    $0.28 / $1.14in / out per M

    1.90×of list price

  • Reka

    93% above DeepSeek's price.

    262k context herefp4 precision

    $0.29 / $1.16in / out per M

    1.93×of list price

  • GreenPT

    70% above DeepSeek's price.

    1M context here

    $0.26 / $1.28in / out per M

    1.95×of list price

showing the 25 cheapest of 52 · every row in the open dataset

Cheaper, and nobody says why

3 prices · never ranked

Below list on a closed model with nothing to account for it. Shown, never ranked, never a pick.

  • Kenari

    We could not read this provider's prices reliably, so the row is listed but never ranked.

    $0.01 / $0.03in / out per M

    0.07×of list price

  • Featherless

    We could not read this provider's prices reliably, so the row is listed but never ranked.

    262k context hereFeatherless

    $0.30 / $1.20in / out per M

    2.00×of list price

  • Tinfoil

    We could not read this provider's prices reliably, so the row is listed but never ranked.

    $0.65 / $1.45in / out per M

    3.24×of list price

Given away with limits

2 free tiers · never ranked

These providers give DeepSeek V4.1 Flash away inside a quota of their own. A limit is not a price, so none of them counts as cheapest here or anywhere else on the site.

  • Alibaba Token Plan
  • Alibaba Token Plan (China)

Frequently asked

Who sells DeepSeek V4.1 Flash cheapest?
TrustedRouter, at $0.04 in and $0.08 out per million tokens, read on 16 Sept 2026. Routes to a host serving the open weights; precision not disclosed.
Is DeepSeek V4.1 Flash open weights?
Yes. DeepSeek publishes the weights, so anyone may host DeepSeek V4.1 Flash, which is why 54 providers sell it and why their prices differ so much.
How much context does DeepSeek V4.1 Flash hold?
1,048,576 tokens in one call, which is about 1M, and it can call your own functions.
How does DeepSeek V4.1 Flash compare with the rest of the market?
At $1.05 per million tokens, DeepSeek's price is 70% below the $3.55 median across the 337 text models we track.
More from DeepSeekDeepSeek V4 Flash 0731DeepSeek V4 ProDeepSeek V3.2R1 0528Similar contextDeepSeek V4 Flash 0731GLM-5.2DeepSeek V4 ProKimi K3Ranked in#4 in Cheapest models that read images#7 in Cheapest reasoning models