Библиотека моделей

DeepSeek V4 Pro is a large language model in the DeepSeek series, offering advanced reasoning, code generation, and multimodal capabilities.

DeepSeek V4 Flash is a fast, cost-efficient language model in the DeepSeek V4 family, optimized for low-latency chat, coding assistance, and high-throughput API workloads while retaining strong reasoning quality.

DeepSeek V4 is a large language model in the DeepSeek series, offering advanced reasoning, code generation, and multimodal capabilities.

DeepSeek R1 Distill Qwen is a reasoning model in the DeepSeek series, distilling R1 capabilities into the Qwen architecture for complex reasoning and analytical tasks.

DeepSeek R1 Distill Qwen 1.5B is a reasoning model in the DeepSeek series, designed for complex reasoning, problem-solving, and analytical tasks.

DeepSeek V2.5 is a language model in the DeepSeek series, offering general-purpose reasoning, code generation, and multimodal capabilities.

DeepSeek V3.2 is a large language model in the DeepSeek V3 series, offering advanced reasoning, code generation, and multimodal capabilities.

DeepSeek V3.1 is an open-weights style frontier model from DeepSeek with strong math, coding, and Chinese-English bilingual reasoning.

DeepSeek V3 Turbo is a fast and efficient language model in the DeepSeek series, optimized for quick responses and high throughput.

DeepSeek R1 Turbo is a reasoning model in the DeepSeek series, designed for complex reasoning, problem-solving, and analytical tasks.

DeepSeek Vision Reasoner is a reasoning model in the DeepSeek series, designed for complex reasoning, problem-solving, and analytical tasks.

DeepSeek V3.2 Reasoner is a reasoning model in the DeepSeek series, designed for complex reasoning, problem-solving, and analytical tasks.

DeepSeek Chat V3.1 is an instruction-tuned variant in the DeepSeek series, optimized for following instructions and conversational tasks.

DeepSeek Coder v2 Instruct is a code-specialized variant in the DeepSeek series, optimized for code generation, debugging, and software development tasks.

DeepSeek Prover v2 is a reasoning model in the DeepSeek series, designed for complex reasoning, problem-solving, and analytical tasks.

DeepSeek Coder Instruct is a code-specialized variant in the DeepSeek series, optimized for code generation, debugging, and software development tasks.

DeepSeek R1 MetaSearch is a reasoning model in the DeepSeek series, designed for complex reasoning, problem-solving, and analytical tasks.

DeepSeek OCR is an OCR model, specialized in extracting and understanding text from images and documents.

DeepSeek V3.1 Terminus is a Terminus-branded DeepSeek V3.1 variant tuned for stable long-context reasoning and code generation.

DeepSeek Reasoner is a reasoning model in the DeepSeek series, designed for complex reasoning, problem-solving, and analytical tasks.

DeepSeek R1 is a reasoning-focused language model in the DeepSeek series, designed for complex reasoning, problem-solving, and analytical tasks.

DeepSeek VL2 is a vision-language model in the DeepSeek series, optimized for multimodal understanding, visual reasoning, and image-text tasks.

DeepSeek Coder is a code-specialized language model in the DeepSeek series, optimized for code generation, completion, and software development tasks.

DeepSeek V3 is DeepSeek flagship MoE language model with 671B total parameters, delivering strong performance in reasoning, coding, and multilingual tasks at competitive inference cost.