Back to modelsBuy Plan
DeepSeek
DeepSeek V4 Pro
DeepSeek-V4-Pro 是 DeepSeek 旗舰 MoE 模型，支持 100 万 token 上下文、最大输出 384K，默认思考模式，面向复杂推理、编程与 Agent 任务；支持 JSON 输出、Tool Calls、上下文缓存。
Quick Stats
Context
1049K
Max Output
384K
Provider
DeepSeek
Specs
1
Modalities
in textout text
Specs & List Price (per 1M tokens)
Quality
Input $1.791045Output $3.58209Cache read $0.014925
Recommended Plan
DeepSeek V4 Pro Starter Plan
Pay-as-you-go after top-up; $1 free credit for new users.
API Endpoint
Model ID
deepseek/deepseek-v4-procURL
curl https://intertoken.ai/v1/chat/completions \
-H "Authorization: Bearer $TOKENPORTAL_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "deepseek/deepseek-v4-pro",
"messages": [{"role": "user", "content": "Hello!"}]
}'Python
from openai import OpenAI
client = OpenAI(
base_url="https://intertoken.ai/v1",
api_key="$TOKENPORTAL_API_KEY",
)
resp = client.chat.completions.create(
model="deepseek/deepseek-v4-pro",
messages=[{"role": "user", "content": "Hello!"}],
)
print(resp.choices[0].message.content)Start using this model
Sign up free, get an API key, and make your first call in 30 seconds.