🌟 2025.08.06#
🔹 claude-opus-4-1-20250805claude-opus-4-1-20250805: Anthropic's flagship Claude Opus 4.1 model, achieving major breakthroughs in programming, reasoning, and agent tasks, SWE-bench Verified reached 74.5%.
Significantly improved multi-file code refactoring, debugging accuracy, and detail-oriented reasoning capabilities. This model is suitable for demanding programming and reasoning scenarios.
We have also added fuhuapi-opus-4-1-20250805 for cursor calls.
claude-opus-4-1-20250805-thinkingclaude-opus-4-1-20250805-thinking: Claude Opus 4.1 supports extended thinking capabilities and provides deep thinking capabilities of up to 64K tokens.
Optimized for research, data analysis, and tool-assisted reasoning tasks, it offers powerful detail-oriented reasoning capabilities.
We've also added fuhuapi-opus-4-1-20250805-thinking specifically for cursor calls.
gpt-oss-120b: OpenAI's open-source 117B-parameter Mixture of Experts (MoE) model, designed for high-performance reasoning, proxying, and general production use cases.
gpt-oss-20b: An open-source 21B-parameter MoE model built on a 3.6B active parameter architecture optimized for low-latency inference and deployment on consumer hardware.
🔗 Usage Guide:#
✅ All models have been grouped by default, allowing you to flexibly call them according to different use cases and requirements, easily integrate them, and maximize their application value.🛠 Getting Started:#
Simply integrate into your system to unlock powerful capabilities. Leverage the unique strengths of each model to meet specialized needs in diverse fields.🔥 Experience the revolutionary capabilities of these groundbreaking models now! 🔥
For professional support or detailed inquiries, please contact our Customer Service team or visit our Technical Documentation Center. We look forward to your valuable feedback!Modified at 2025-10-15 14:03:59
