We introduce our first-generation reasoning models, DeepSeek-R1-Zero and DeepSeek-R1. DeepSeek-R1-Zero, a model trained via large-scale reinforcement learning (RL) without supervised fine-tuning (SFT) as a preliminary step, demonstrated remarkable performance on reasoning. With RL, DeepSeek-R1-Zero naturally emerged with numerous powerful and interesting reasoning behaviors. However, DeepSeek-R1-Zero encounters challenges such as endless repetition, poor readability, and language mixing. To address these issues and further enhance reasoning performance, we introduce DeepSeek-R1, which incorporates cold-start data before RL. DeepSeek-R1 achieves performance comparable to OpenAI-o1 across math, code, and reasoning tasks. To support the research community, we have open-sourced DeepSeek-R1-Zero, DeepSeek-R1, and six dense models distilled from DeepSeek-R1 based on Llama and Qwen. DeepSeek-R1…
@cf/deepseek-ai/deepseek-v4-pro-0813Семейство: deepseek-thinkingКонтекст (макс.): 1,05 млн токеновВвод: текст; вывод: текстВозможности: рассуждение, инструменты, структурированный выводПоставщики: Cloudflare Workers AI
Источник каталога: https://models.dev/api.json. Получено: 01.11.2026 01:19 UTC. Цены и лимиты — данные источника; перед использованием проверяйте условия поставщика.