一个 key、一个 OpenAI 兼容端点，覆盖全部已接入模型。下面的价格与可用率都取自真实目录。
共 31 个模型
Claude model for creative writing, analysis, and controlled agent workflows
claude-fable-5-1 文本模型。可用渠道、调用参数与价格详见模型详情。
Fast Claude model for responsive assistance, classification, and lightweight agents
High-end Claude for difficult coding, planning, and slower expert reasoning
Stronger Opus tier for advanced software work and high-stakes reasoning
Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents
Strongest Claude Opus model for coding, agents, and professional work
Claude workhorse for coding agents, careful analysis, and production cost control
Balanced Claude model for coding, analysis, agent workflows, and cost control
Seedance 2.0 视频生成；支持文本、图片、视频与音频参考。按返回的视频 token 计费，单价区分分辨率与参考视频。
Seedance 2.0 视频生成；支持文本、图片、视频与音频参考。按返回的视频 token 计费，单价区分分辨率与参考视频。
Seedance 2.0 Fast 视频生成；支持文本、图片、视频与音频参考。按返回的视频 token 计费，单价区分分辨率与参考视频。
Seedance 2.0 Mini 视频生成；支持文本、图片、视频与音频参考。按返回的视频 token 计费，单价区分分辨率与参考视频。
Seedance 2.5 视频生成；支持文本、图片、视频与音频参考。按返回的视频 token 计费，单价区分分辨率与参考视频。
Seedance 2.5 视频生成；支持文本、图片、视频与音频参考。按返回的视频 token 计费，单价区分分辨率与参考视频。
Fast Gemini workhorse for multimodal apps where latency and price matter
New Gemini flash lane bringing frontier-style multimodal reasoning to cheaper runs
Legacy model retained for compatibility with older integrations
Reasoning-first Gemini preview for agentic coding and complex problem solving
Fast Gemini model balancing multimodal reasoning, tool use, and cost
Flagship GLM model for long-horizon coding, agents, and complex project delivery
glm-5.3-flash 文本模型。可用渠道、调用参数与价格详见模型详情。
Default frontier GPT for coding, computer use, research, and knowledge work
Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows
