n4nAI
← Models
D

DeepSeek V4 Pro

deepseekReleased Apr 2026Hugging Face ↗

deepseek/deepseek-v4-pro

About

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,...

Context
1,048,576
Max output
384K
Tokenizer
DeepSeek
Knowledge cutoff
Input
text
Output
text

Pricing

per 1M tokens
Input
$1.74
Output
$3.46

Use this model

curl https://api.n4n.ai/v1/chat/completions \
  -H "Authorization: Bearer $N4N_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek/deepseek-v4-pro",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Authenticate with an API key from your console; prices above are per 1M tokens.

Providers

max context 1,048,576
ProviderInput $/1MOutput $/1M
Wandb wandb$1.74$3.46
Yuwu yuwu$1.74$3.46

Supported parameters

frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokensmin_ppresence_penaltyreasoningreasoning_effortrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p