Product
DeepSeek V4 Pro: fiche technique, prix API et données
Updated
DeepSeekAI Models & LLMs
- Context window
- 1M tokens
- Maximum output
- 384k tokens
- Input cost per 1M tokens
- $1.32
- Output cost per 1M tokens
- $3.96
- Open weights (downloadable)
- Yes
Data sheet · DeepSeek V4 Pro
Every figure is quoted from the vendor's official page, with the date we read it. If a row is missing, the source does not state it and we do not estimate it.
Memory and answer length
- Context window
- 1M tokensRank 8 of 21
What it means and the source
How much text the model keeps in view in a single request, question and answer included. It matters for long documents and whole code projects. A token is a fragment of a word.
api-docs.deepseek.comOpens the source in a new tab Oct 23, 2026- Maximum output
- 384k tokensRank 1 of 16
What it means and the source
The longest answer it can write in one go: useful for reports, long code or translations of whole documents.
api-docs.deepseek.comOpens the source in a new tab Oct 23, 2026
API prices
- Input cost per 1M tokens
- $1.32Rank 8 of 21
What it means and the source
What it costs to have the model read a million tokens (your question, the documents, the code). It is the official list price, before discounts.
api-docs.deepseek.comOpens the source in a new tab Oct 23, 2026- Cached input cost per 1M tokens
- $0.044Rank 4 of 20
What it means and the source
The reduced price when part of the request is identical to one sent recently, for example the same instructions or the same document: the vendor keeps it in memory and charges less for it.
api-docs.deepseek.comOpens the source in a new tab Oct 23, 2026- Output cost per 1M tokens
- $3.96Rank 7 of 21
What it means and the source
What a million tokens written by the model cost. It usually costs more than the input and is the figure to watch when answers are long.
api-docs.deepseek.comOpens the source in a new tab Oct 23, 2026
Knowledge and abilities
- Calls tools and functions
- Yes12 models out of 23
What it means and the source
The model can call functions and tools (search, calculations, other applications) to take actions and not only write text: it matters for assistants and agents.
api-docs.deepseek.comOpens the source in a new tab Oct 23, 2026
Size and openness
- Parameters
- 1.7 trillion
What it means and the source
The size of the network: how many billions of learned values make it up. Bigger does not necessarily mean better, but it tells how much hardware it takes to run it yourself.
huggingface.coOpens the source in a new tab Oct 23, 2026- Open weights (downloadable)
- Yes7 models out of 23
What it means and the source
The model's weights can be downloaded: you can run it on your own servers, adapt it and decide where the data stays, within the licence terms.
huggingface.coOpens the source in a new tab Oct 23, 2026
Where it stands · DeepSeek V4 Pro
The same verified figures, next to those of the other catalogue models. Tap a model for the head-to-head.
Hardware to try AI at home
DeepSeek V4 Pro: just holding the weights in memory takes about 3,400 GB at 16-bit, 1,700 GB at 8-bit, 850 GB at 4-bit. Beyond 24 GB it is not a home-PC job: using it through an API makes more sense.Worked out from the billions of parameters the vendor states, not a measurement: context and the runtime need more memory.
Questions and answers
DeepSeek V4 Pro: how much does it cost through the API?
The official list price is $1.32 per 1M input tokens and $3.96 per 1M output tokens.
DeepSeek V4 Pro: how much text can it read at once?
The context window is 1M tokens. It can write answers of up to 384k tokens.
DeepSeek V4 Pro: can I run it on my own computer?
Yes, the vendor publishes the model's weights. Parameters: 1.7 trillion. Holding them in memory takes about 850 GB at 4-bit; context and the runtime need more memory.
L’essentiel
Sur DeepSeek V4 Pro, la donnée qui compte vraiment est Fenêtre de contexte : 1M. Je l’ai relevé chez DeepSeek – Models & Pricing. Parmi les 21 que j’ai vérifiés, 7 font mieux. L’autre chiffre à regarder est Coût par million de jetons en sortie : 3.96.
Les chiffres de DeepSeek V4 Pro
Je les ai classés par importance, avec la valeur et la position face aux autres que j’ai vérifiés.
Fenêtre de contexte : 1M. Position 8 sur les 21 que j’ai comparés.
Coût par million de jetons en sortie : 3.96. Position 7 sur les 21 que j’ai comparés.
Coût par million de jetons en entrée : 1.32. Position 8 sur les 21 que j’ai comparés.
Appelle des outils et des fonctions : 1. C’est la meilleure valeur parmi les 12 que j’ai comparés.
Coût d’entrée en cache par 1M de tokens (USD) : 0.044. Position 17 sur les 20 que j’ai comparés.
Open weights (downloadable) : 1. C’est la meilleure valeur parmi les 7 que j’ai comparés.
À qui il s’adresse
Choisis-le si Appelle des outils et des fonctions est ta priorité : 1, et aucun de ceux que j’ai vérifiés ne fait mieux.
Il te convient si tu cherches Open weights (downloadable) : 1.
Regarde ailleurs si ce qui compte pour toi est Fenêtre de contexte : ici c’est 1M, et 7 produits font mieux.
Pour aller plus loin
Sources
Ask Sir Compare:Explain these numbers to me
Reviews and tests
DeepSeek V4 Pro
Reviews and tests · DeepSeek V4 Pro
Reviews are not available yet.
What changed
- Page updated
Sir Compare’s letter
Updates on AI Models & LLMs? I’ll send them your way.
Pick what you care about: I only write when something new comes out — a guide, a news story, a verified price that drops.
Step 1 of 2
What are you into?
Pick as many as you like. Pick none and you get what’s new in every section.
- Only what you pick
- Never an empty email
- One click to leave