DeepSeek

DeepSeek V4 Pro

Chat
deepseek/deepseek-v4-pro
ComparerCommencer

DeepSeek V4 Pro is a large-scale Mixture-of-Experts model from DeepSeek with 1.6T total parameters and 49B activated parameters, supporting a 1M-token context window. It is designed for advanced reasoning, coding, and long-horizon agent workflows, with strong performance across knowledge, math, and software engineering benchmarks.

1M fenêtre de contexte
384K tokens de sortie max
Publié: 2026-04-24
Protocoles supportés:OpenAIopenaiAnthropicanthropic
Fournisseurs disponibles:AzureAzureDeepSeekDeepSeekBaiLianAliyun
Capacités:Function CallingPrompt Caching

Providers

BaiLianAliyun
Tokens d'entrée
$1.74/M
Tokens de sortie
$3.48/M
Lecture cache
$0.15/M
Recherche web
$0.01/R
Protocols
Anthropicanthropic
AzureAzure
Tokens d'entrée
$0.45/M
Tokens de sortie
$0.88/M
Lecture cache
$0.0037/M
Protocols
OpenAIopenai/v1/chat/completions/v1/responses
DeepSeekDeepSeek
Tokens d'entrée
$0.45/M
Tokens de sortie
$0.88/M
Lecture cache
$0.0037/M
Protocols
OpenAIopenai/v1/chat/completions
Anthropicanthropic

Exemples de code

from openai import OpenAI


client = OpenAI(
    base_url="https://api.ofox.ai/v1",
    api_key="YOUR_OFOX_API_KEY",
)


response = client.chat.completions.create(
    model="deepseek/deepseek-v4-pro",
    messages=[
        {"role": "user", "content": "Hello!"}
    ],
)


print(response.choices[0].message.content)

Modèles associés

Plus de DeepSeek

DeepSeek
DeepSeek V4 Flash
$0.14/M/$0.28/M
DeepSeek
DeepSeek V3.2
$0.29/M/$0.43/M

Modèles similaires

Minimax
MiniMax: MiniMax M3
$0.6/M/$2.4/M
Qwen
Qwen3.7 Plus
$0.4/M/$1.6/M
Claude
Anthropic: Claude Opus 4.8
$5/M/$25/M

Questions fréquentes

DeepSeek V4 Pro sur Ofox.ai coûte $0.45/M par million de tokens d'entrée et $0.88/M par million de tokens de sortie. Paiement à l'usage, sans frais mensuels.