一个 API 入口，接入文本、图像、视频与音频能力。
Near-Astra performance for complex coding, computer use, and professional work at a lower cost.
deepseek-v4.1-flash-1017，支持文本生成能力，可通过统一 API 接入。
deepseek-v4.1-flash，支持文本生成能力，可通过统一 API 接入。
October 17 update of DeepSeek V4.1 Flash with improved reasoning, coding, agentic tasks, and visual understanding
Claude model for long-running agentic coding and knowledge work
Claude workhorse for coding agents, careful analysis, and production cost control
Balanced GPT-5.6 model for capable, cost-efficient everyday work
Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents
Claude model for demanding reasoning and long-horizon agentic work
xAI's frontier model for long-running agents, coding, knowledge work, and visual projects
Claude model for creative writing, analysis, and controlled agent workflows
Fast Claude model for responsive assistance, classification, and lightweight agents
Multimodal Kimi model with 1M context and always-on reasoning for coding, 3D creation, financial research, and agentic work
Fast Claude model for everyday coding, agents, and knowledge work
GPT-6 Astra is OpenAI's most capable model for complex reasoning, coding, computer use, research, and document creation.
Everyday Claude agent model for coding, planning, browsing, and general work
OpenAI model for complex coding and agentic workflows
High-end Claude for difficult coding, planning, and slower expert reasoning
Strongest Claude Opus model for coding, agents, and professional work
Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows
GPT Image 2，支持图像生成能力，可通过统一 API 接入。
Stronger Opus tier for advanced software work and high-stakes reasoning
Fast, efficient model for visual reasoning, precise computer use, and clear, natural writing.
DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes
deepseek-v4-pro-0813，支持文本生成能力，可通过统一 API 接入。
gpt-image-2.5-sunburst，支持图像生成能力，可通过统一 API 接入。
gpt-image-2.5，支持图像生成能力，可通过统一 API 接入。
Fast Claude lane for lightweight agents, office tasks, and responsive chat
Flagship Claude model for deep reasoning, coding, and long-horizon agents
Balanced Claude model for coding, analysis, agent workflows, and cost control
Open flagship GLM for long-horizon coding agents and million-token context work
Flagship GLM model for long-horizon coding, agents, and complex project delivery
Default frontier GPT for coding, computer use, research, and knowledge work
xAI's Grok model for chat, coding, agentic tools, and lower hallucination risk
Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work
gpt-image-2.5-flare，支持图像生成能力，可通过统一 API 接入。
