Kimi K2.5
Kimi K2.5 is an advanced large language model with strong reasoning and upgraded native multimodality. It natively understands and processes text and images, delivering more accurate analysis, better instruction following, and stable performance across complex tasks. Designed for production use, Kimi K2.5 is ideal for AI assistants, enterprise applications, and multimodal workflows that require reliable and high-quality outputs.
Kimi K2.5
Kimi K2.5 is an advanced large language model with strong reasoning and upgraded native multimodality. It natively understands and processes text and images, delivering more accurate analysis, better instruction following, and stable performance across complex tasks. Designed for production use, Kimi K2.5 is ideal for AI assistants, enterprise applications, and multimodal workflows that require reliable and high-quality outputs.
Qwen3 Max 20260123
Qwen3-Max is a flagship large language model designed for ultra-long context understanding, powerful reasoning, and high-performance text and code generation, making it well suited for complex, large-scale, and production-grade AI applications.
MiniMax M2.1
MiniMax-M2.1 is a lightweight, state-of-the-art large language model optimized for coding, agentic workflows, and modern application development. With only 10 billion activated parameters, it delivers a major jump in real-world capability while maintaining exceptional latency, scalability, and cost efficiency.
GLM 4.7
GLM-4.7 is Z.AI’s latest flagship model, featuring upgrades in two key areas: enhanced programming capabilities and more stable multi-step reasoning/execution. It demonstrates significant improvements in executing complex agent tasks while delivering more natural conversational experiences and superior front-end aesthetics.
DeepSeek V3.2 Speciale
Fastest, most cost-effective model from DeepSeek Ai.
DeepSeek V3.2
DeepSeek V3.2 is a state-of-the-art large language model combining efficient sparse attention, strong reasoning, and integrated agent capabilities for robust long-context understanding and versatile AI applications.
KAT Coder Pro V1
KAT Coder Pro is KwaiKAT's most advanced agentic coding model in the KAT-Coder series. Designed specifically for agentic coding tasks, it excels in real-world software engineering scenarios, achieving 73.4% solve rate on the SWE-Bench Verified benchmark.
KAT Coder Exp-72b-101
KAT Coder is KwaiKAT's most advanced agentic coding model in the KAT-Coder series.
MiniMax-M2
MiniMax-M2 is a lightweight, state-of-the-art large language model optimized for coding, agentic workflows, and modern application development. With only 10 billion activated parameters, it delivers a major jump in real-world capability while maintaining exceptional latency, scalability, and cost efficiency.
DeepSeek V3.2 Exp
Fastest, most cost-effective model from DeepSeek Ai.
GLM 4.6
357B-parameter efficient MoE model from Zhipu AI.
Kimi-K2-Thinking
Kimi's latest and most powerful open-source model.
MiMo V2 Flash
Sem descrição
DeepSeek-V3-0324
DeepSeek's updated V3 model released on 03/24/2025.
DeepSeek-R1-0528
The advanced LLM
Qwen3-VL-235B-A22B-Instruct
Sem descrição
Tongyi DeepResearch 30B A3B
Open and Advanced Models.
Qwen3 30B A3B Instruct 2507
Qwen's latest and most powerful open-source model.
Qwen3 Next 80B A3B Thinking
Qwen's latest and most powerful open-source model.
Qwen3 Next 80B A3B Instruct
Qwen's latest and most powerful open-source model.
DeepSeek-V3.1
Deepseek's latest and most powerful open-source model.
Kimi-K2-Instruct-0905
Sem descrição
Kimi-K2-Instruct
Kimi's latest and most powerful open-source model.
Qwen3 8B
The latest Qwen reasoning model.
Qwen3 235B A22B Thinking 2507
The latest Qwen reasoning model.
Qwen3 VL 235B A22B Thinking
The latest Qwen reasoning model.
Qwen3 30B A3B
The latest Qwen reasoning model.
Qwen3 30B A3B Thinking 2507
The latest Qwen reasoning model.
Qwen2.5 7B Instruct
The latest Qwen model.
DeepSeek OCR
The latest Deepseek model.
Qwen3 32B
The latest Qwen reasoning model.
Qwen3 Coder
Qwen3-Coder is the code version of Qwen3.
Qwen3-235B-A22B-Instruct-2507
235B-parameter MoE thinking model in Qwen3 series.
GPT OSS 120b
117B-parameter MoE language model from OpenAI.
DeepSeek V3.1 Terminus
Deepseek's latest and most powerful open-source model.
LongCat Flash Chat
Meituan's latest and most powerful open-source model.
