import { Fragment } from 'react' import CodeEditor from '@/components/CodeEditor' import { Heading } from '@/components/Heading' import { useLanguage } from '@/i18n/context' const BASELINE = new Set([ 'gpt-5.1', 'claude-haiku-4.5', 'gemini-3-flash', 'deepseek-3.2', 'qwen3.5-plus', ]) // Models grouped by brand, newest first const MODEL_GROUPS: Record = { OpenAI: ['gpt-5.2', 'gpt-5.1', 'gpt-5', 'gpt-5-mini', 'gpt-4.1', 'gpt-4.1-mini'], Qwen: [ 'qwen3.5-plus', 'qwen3.5-flash', 'qwen3-coder-next', 'qwen-3-max', 'qwen-3-plus', 'qwen3:14b (ollama)', ], DeepSeek: ['deepseek-3.2'], Google: ['gemini-3-pro', 'gemini-3-flash', 'gemini-2.5'], Anthropic: [ 'claude-opus-4.6', 'claude-opus-4.5', 'claude-sonnet-4.5', 'claude-haiku-4.5', 'claude-sonnet-3.5', ], xAI: ['grok-4.1-fast', 'grok-4', 'grok-code-fast'], MoonshotAI: ['kimi-k2.5'], 'Z.AI': ['glm-5', 'glm-4.7'], } const ModelBadge = ({ model, baseline }: { model: string; baseline?: boolean }) => (
{model} {baseline && }
) export default function Models() { const { isZh } = useLanguage() return (

{isZh ? '模型' : 'Models'}

{isZh ? '当前支持符合 OpenAI 接口规范且支持 tool call 的模型,包括公有云服务和私有部署方案。' : 'Supports models that comply with OpenAI API specification and support tool calls, including public cloud services and private deployments.'}

{/* Models Section */}
{isZh ? '已测试模型' : 'Tested Models'}

{isZh ? '推荐使用 ToolCall 能力强的轻量级模型。' : 'Recommended: Fast, lightweight models with strong ToolCall capabilities.'}

{Object.entries(MODEL_GROUPS).map(([brand, models]) => ( {brand}
{models.map((model) => ( ))}
))}
{/* Tips Section */}

{isZh ? '提示' : 'Tips'}

  • {isZh ? 'ToolCall 能力较弱的模型可能返回错误的格式,常见错误能够自动恢复,建议设置较高的 temperature' : 'Models with weaker ToolCall capabilities may return incorrect formats. Common errors usually auto-recover. Higher temperature recommended'}
  • {isZh ? '小模型或者无法适应复杂 Tool 定义的模型,通常效果不佳' : 'Small models or those unable to handle complex tool definitions typically perform poorly'}
{/* Security Section */}

{isZh ? '🔐 生产环境鉴权建议' : '🔐 Production Authentication'}

{isZh ? '⚠️ 永远不要把真实的 LLM API Key 发布到前端代码' : '⚠️ Never commit real LLM API Keys to your frontend code'}

{isZh ? '后端代理转发' : 'Backend Proxy Pattern'}

{isZh ? '在后端搭建一个 LLM 流量转发接口,该接口使用与你网站上其他接口相同的鉴权方式,例如:' : 'Set up a backend LLM proxy endpoint that uses the same authentication method as other APIs in your website, such as:'}

  • {isZh ? '• Session/Cookie 会话认证' : '• Session/Cookie-based authentication'}
  • {isZh ? '• OIDC (OpenID Connect) 单点登录' : '• OIDC (OpenID Connect) single sign-on'}
  • {isZh ? '• 临时 Access Key 或 JWT Token' : '• Temporary Access Key or JWT Token'}
{/* Configuration Section */}
{isZh ? '配置方式' : 'Configuration'}
{/* Free Testing API Section */}
{isZh ? '免费测试接口' : 'Free Testing API'}

{isZh ? '以下免费测试接口仅供 PageAgent.js 和 PageAgent Extension 的技术评估使用。有速率限制,可能随时变更。请勿用于生产环境。' : 'The following free testing endpoints are provided for technical evaluation of PageAgent.js and PageAgent Extension only. Rate-limited, subject to change. Not for production use.'}

Qwen (Alibaba Cloud China)

{isZh ? '通过阿里云函数计算(中国大陆)转发至百炼 Qwen 模型' : 'Proxied via Alibaba Cloud FC (Mainland China) to BaiLian Qwen models'} {' · '} {isZh ? '使用条款' : 'Terms of Use'}

{isZh ? '⚠️ 仅供技术评估和研发用途,禁止用于生产环境。数据通过中国大陆服务器处理。请勿输入任何个人身份信息或敏感数据。使用即表示您同意' : '⚠️ Strictly for technical evaluation and R&D only. Data is processed via servers in Mainland China. Do not input any PII or sensitive data. By using this API you agree to the'}{' '} {isZh ? '使用条款' : 'Terms of Use'}

{/* Ollama Section */}
Ollama

{isZh ? '已在 Ollama 0.15 + qwen3:14b (RTX3090 24GB) 上测试通过。' : 'Tested on Ollama 0.15 with qwen3:14b (RTX3090 24GB).'}

{isZh ? '⚠️ 注意事项' : '⚠️ Important Notes'}

  • {isZh ? '确保 OLLAMA_ORIGINS 设置为 * 以避免 403 错误' : 'Add * to OLLAMA_ORIGINS to avoid 403 errors'}
  • {isZh ? '小于 10B 参数的模型通常效果不佳' : 'Models smaller than 10B are unlikely to be strong enough'}
  • {isZh ? '需要支持 tool_call 的模型' : 'Requires tool_call capable models'}
  • {isZh ? '确保上下文长度大于输入 token 数,否则 Ollama 会静默截断 prompt。普通页面约需 15k token,随步骤增加。默认 4k 上下文长度无法正常工作' : 'Ensure context length exceeds input tokens, or Ollama will silently truncate prompts. ~15k tokens for a typical page, increases with steps. Default 4k context length will NOT work'}
    • $env:OLLAMA_CONTEXT_LENGTH=64000; ollama serve
) }