Библиотека моделей

MiniMax M1 is a large language model in the MiniMax series, offering advanced reasoning, code generation, and multimodal capabilities.

Intern-S1 is a language model in the InternLM series, offering general-purpose reasoning, code generation, and multimodal capabilities.

Microsoft Phi-4 is a compact open-weight language model in the Phi series, optimized for reasoning, math, code generation, and efficient on-device or API deployment.

Alibaba Qwen Image is an image generation model in the Qwen series, offering advanced image generation capabilities.

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

Alibaba Qwen3-Next is an ultra-efficient next-gen architecture (80B total, 3B active) with hybrid attention and sparse MoE, designed for long-context training and inference at dramatically lower cost.

Alibaba Qwen3 Embedding is an embedding model in the Qwen series, optimized for text embedding and similarity tasks.

Alibaba Qwen3 Coder is a code-specialized variant in the Qwen series, optimized for code generation, debugging, and software development tasks.

Mistral Large 3 is Mistral AI's advanced multilingual frontier model, offering strong reasoning, coding, and instruction-following for production chat and agent workloads.

A compact language model by Mistral AI, optimized for efficient inference and general-purpose tasks.

Mistral AI Devstral 2 is a code-specialized variant in the Mistral series, optimized for code generation, debugging, and software development tasks.

Alibaba Qwen3 VL is a vision-language model in the Qwen series, offering advanced multimodal capabilities for image and text understanding.

Alibaba Qwen3 is the Qwen family's flagship LLM series with dense and MoE variants, seamless thinking/non-thinking modes, and leading open-source performance in math, code, and agent 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.