deepseek/deepseek-v4-pro
DeepSeek's flagship V4 reasoning model. Strong coding and math with an explicit thinking mode, a native 1M-token context window at no surcharge, and a discounted prompt-cache hit rate. Best price/performance for heavy reasoning workloads.
Источник: deepseek_2026_08_official_peak · Проверено 2026-08-20
Чтение кэша $0.044/M · Запись кэша —/M
Для вызова модели через API используйте любой из ID.
deepseek/deepseek-v4-proЗамените заполнитель ONEHOP_KEY вашим API key. Создать →
from openai import OpenAI
client = OpenAI(
base_url="https://api.onehop.ai/v1",
api_key="<ONEHOP_KEY>",
)
completion = client.chat.completions.create(
model="deepseek/deepseek-v4-pro",
messages=[{"role": "user", "content": "What is the meaning of life?"}],
)
print(completion.choices[0].message.content)242 запросов за последние 30 дней