DeepSeek V4 Pro pricing.

prices as of · 84 providers · 103 prices

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

DeepSeek V4 Pro costs $0.43 in and $0.87 out per million tokens from DeepSeek; the cheapest price we can explain is $1.05 at LLMTR, checked 16 Sept 2026.

tool callingreasoningstructured outputopen weights1M contextreleased 12 Aug 2026

DeepSeek list price

$2.18/M tokens

$0.43 in · $0.87 out

read · 39% below the market median

Cheapest price we can explain

$1.05/M tokens

$0.15 in · $0.60 out · 52% under list

LLMTR
View at LLMTR

read

What it costs for your work

pages a month

DeepSeek list price

$0.313a month

cheapest we can explain · LLMTR

$0.126a month

difference

$0.187saved

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 Pro

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.

    $0.43 / $0.87in / out per M

    1.00×of list price

Cheaper, and we know why

5 prices

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

  • LLMTR

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

    $0.15 / $0.60in / out per M

    0.48×of list price

  • TrustedRouter

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

    1M context hereTrustedRouter

    $0.16 / $0.63in / out per M

    0.51×of list price

  • Crof

    Hosts the open weights on its own servers, so the price is its own, not a resale. Precision not disclosed.

    $0.35 / $0.80in / out per M

    0.85×of list price

  • Crof

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

    Q8_0 precisionCrof

    $0.35 / $0.80in / out per M

    0.85×of list price

  • routing.run

    8% under the list price, an ordinary reseller margin.

    $0.40 / $1.40in / out per M

    1.20×of list price

Same price as the maker

90 prices

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

  • NVIDIA build

    NVIDIA build's catalog shows no price for this row, so there is nothing to compare.

    $0 / $0in / out per M

    0.00×of list price

  • EBCloud

    The same price DeepSeek charges.

    $0.43 / $0.86in / out per M

    0.99×of list price

  • TokenGo

    The same price DeepSeek charges.

    $0.43 / $0.87in / out per M

    1.00×of list price

  • Modelis

    The same price DeepSeek charges.

    $0.43 / $0.87in / out per M

    1.00×of list price

  • Auriko

    The same price DeepSeek charges.

    $0.43 / $0.87in / out per M

    1.00×of list price

  • LLM Gateway

    The same price DeepSeek charges.

    1M context hereLLM Gateway

    $0.43 / $0.87in / out per M

    1.00×of list price

  • Alibaba Cloud (China)

    The same price DeepSeek charges.

    $0.43 / $0.87in / out per M

    1.00×of list price

  • Pioneer

    The same price DeepSeek charges.

    $0.43 / $0.87in / out per M

    1.00×of list price

  • ZenMux

    The same price DeepSeek charges.

    $0.43 / $0.87in / out per M

    1.00×of list price

  • OrcaRouter

    The same price DeepSeek charges.

    $0.44 / $0.88in / out per M

    1.02×of list price

  • Nous Portal

    33% above DeepSeek's price.

    1M context hereNous Portal

    $0.58 / $1.74in / out per M

    1.60×of list price

  • RunInfra

    38% above DeepSeek's price.

    1M context here

    $0.60 / $1.90in / out per M

    1.70×of list price

  • Ollama Cloud

    52% above DeepSeek's price.

    1M context here

    $0.66 / $1.98in / out per M

    1.82×of list price

  • Ollama Cloud

    52% above DeepSeek's price.

    1M context here

    $0.66 / $1.98in / out per M

    1.82×of list price

  • Vercel AI Gateway

    52% above DeepSeek's price.

    $0.66 / $1.98in / out per M

    1.82×of list price

  • OpenCode Go

    52% above DeepSeek's price.

    $0.66 / $1.98in / out per M

    1.82×of list price

  • NanoGPT

    203% above DeepSeek's price.

    1M context hereNanoGPT

    $1.32 / $0.04in / out per M

    1.84×of list price

  • NanoGPT

    203% above DeepSeek's price.

    1M context hereNanoGPT

    $1.32 / $0.04in / out per M

    1.84×of list price

  • AIHubMix

    59% above DeepSeek's price.

    $0.69 / $2.08in / out per M

    1.91×of list price

  • above.dev

    67% above DeepSeek's price.

    $0.73 / $2.18in / out per M

    2.00×of list price

  • UnoRouter

    107% above DeepSeek's price.

    $0.90 / $1.80in / out per M

    2.07×of list price

  • StreamLake

    120% above DeepSeek's price.

    1M context herefp8 precision

    $0.96 / $1.91in / out per M

    2.20×of list price

  • ai&

    130% above DeepSeek's price.

    1M context hereai&

    $1 / $2.50in / out per M

    2.53×of list price

  • Ionstream

    121% above DeepSeek's price.

    1M context here

    $0.96 / $2.88in / out per M

    2.65×of list price

  • OpenRouter

    126% above DeepSeek's price.

    1M context hereOpenRouter

    $0.98 / $2.95in / out per M

    2.71×of list price

showing the 25 cheapest of 90 · every row in the open dataset

Cheaper, and nobody says why

2 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.

    $1 / $2in / out per M

    2.30×of list price

  • Featherless

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

    262k context hereFeatherless

    $1.60 / $3.20in / out per M

    3.68×of list price

Given away with limits

5 free tiers · never ranked

These providers give DeepSeek V4 Pro 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
  • SenseNova (China)
  • SCNet Token Plan
  • Volcengine Ark Coding Plan
  • Alibaba Token Plan (China)

Frequently asked

Who sells DeepSeek V4 Pro cheapest?
LLMTR, at $0.15 in and $0.60 out per million tokens, read on 16 Sept 2026. Routes to a host serving the open weights; precision not disclosed.
Is DeepSeek V4 Pro open weights?
Yes. DeepSeek publishes the weights, so anyone may host DeepSeek V4 Pro, which is why 84 providers sell it and why their prices differ so much.
How much context does DeepSeek V4 Pro hold?
1,000,000 tokens in one call, which is about 1M, and it can call your own functions.
How does DeepSeek V4 Pro compare with the rest of the market?
At $2.18 per million tokens, DeepSeek's price is 39% below the $3.55 median across the 337 text models we track.
More from DeepSeekDeepSeek V4 Flash 0731DeepSeek V3.2DeepSeek V4.1 FlashR1 0528Similar contextDeepSeek V4 Flash 0731GLM-5.2Kimi K3GLM-5.3-Flash