Библиотека моделей

Aion RP Llama 3.1 is a roleplay-tuned variant in the Aion series, optimized for character-driven dialogue and creative writing.

Nous Research Hermes 3 is a generalist instruct model fine-tuned on Meta Llama 3.1, with strong reasoning, roleplay, multi-turn chat, tool calling, and structured JSON output.

Meta Llama 3.1 extends the Llama 3 family with stronger reasoning, tool use, and long-context support across 8B to 405B scales.

Meta Llama 3.3 is an updated Llama 3 open model with improved instruction following, multilingual support, and efficient inference.

Meta Llama 3.3 Instruct is an instruction-tuned variant in the Llama series, optimized for following instructions and conversational tasks.

Dracarys Llama 3.1 Instruct is an instruction-tuned variant, optimized for following instructions and conversational tasks.

Usdcode Llama 3.1 Instruct is an instruction-tuned variant, optimized for following instructions and conversational tasks.

Meta Llama 3.1 Instruct is an instruction-tuned variant in the Llama series, optimized for following instructions and conversational tasks.

Meta Llama 3.3 Instruct Turbo is a fast and efficient language model in the Llama series, optimized for quick responses and high throughput.

Meta Llama 3.1 Instruct Turbo is a fast and efficient language model in the Llama series, optimized for quick responses and high throughput.

Meta Llama 3.2 Nemoretriever 300m Embed v1 is an embedding model, designed for generating vector representations of text for retrieval and semantic search.

MiniMax M2.7 is a large language model in the MiniMax series, offering advanced reasoning, code generation, and multimodal capabilities.

Google Gemini 3 Flash is a fast and efficient language model in the Gemini series, optimized for quick responses and high throughput.

Meta Llama 4 Scout is a large language model in the Llama series, offering advanced reasoning, code generation, and multimodal capabilities.

Zhipu GLM-5 is Zhipu flagship GLM series model with enhanced reasoning, agent capabilities, and strong performance on Chinese enterprise and coding scenarios.

MiniMax M2.5 is MiniMax's flagship text model for coding and agents, with SOTA-level programming and agentic performance, improved token efficiency, and fast high-TPS API deployment.