Back to Details

qianwen-model-selector

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese
Agent setup: If your agent doesn't auto-load skills (e.g. Claude Code), see agent-compatibility.md once per session.
Agent配置：如果你的Agent无法自动加载技能（例如Claude Code）， 请在每个会话中查看agent-compatibility.md。

Qwen Model Selector (Advisor)

Qwen模型选择器（顾问）

This skill operates in two modes:
  1. Interactive advisory — asks diagnostic questions to recommend the right model (see Diagnostic Flow).
  2. Cross-skill resolution — provides a fast-path model lookup for execution skills that need a model decision without user interaction (see recommendation-matrix.md).
Do not fabricate model names — only recommend models listed in this skill or returned by CLI. This skill is part of QianWen-AI/qianwen-ai.
本技能支持两种模式：
  1. 交互式咨询——通过诊断式提问推荐合适的模型（详见诊断流程）。
  2. 跨技能解析——为需要模型决策的执行技能提供快速模型查询路径，无需用户交互（详见recommendation-matrix.md）。
请勿编造模型名称——仅推荐本技能中列出或CLI返回的模型。 本技能属于QianWen-AI/qianwen-ai体系。

Skill directory

技能目录

Load on demand. Do not fetch external URLs unless the user explicitly asks for the latest data.
LocationPurpose
references/cli-usage.md
CLI-first data strategy: when to use CLI, 3-step login flow, display rules
references/error-handling.md
CLI error classification & recovery actions (auth, not-found, network, ...)
references/recommendation-matrix.md
Full model recommendation tables, Cross-Skill Resolution, Token Plan 团队版, Thinking
references/pricing-disclaimer.md
Pricing guidance + mandatory cost-estimation disclaimer (CN/EN) + console links
references/pricing.md
Pricing structural overview (offline snapshot)
references/model-list.md
Model catalog (offline snapshot)
references/sources.md
Official documentation URLs (manual lookup only)
references/agent-compatibility.md
Agent self-check for skill registration
按需加载。除非用户明确要求最新数据，否则请勿获取外部URL。
位置用途
references/cli-usage.md
CLI优先数据策略：CLI使用场景、三步登录流程、展示规则
references/error-handling.md
CLI错误分类与恢复操作（认证、未找到、网络等问题）
references/recommendation-matrix.md
完整模型推荐表、跨技能解析、Token Plan团队版、思维模式
references/pricing-disclaimer.md
定价指南 + 强制要求的成本估算免责声明（中/英文） + 控制台链接
references/pricing.md
定价结构概述（离线快照）
references/model-list.md
模型目录（离线快照）
references/sources.md
官方文档URL（仅手动查询使用）
references/agent-compatibility.md
Agent技能注册自检

Prerequisites

前置条件

QianWen CLI is strongly recommended — it is the authoritative real-time data source for model availability, pricing, and quotas. Verify with:
bash
qianwen version
If not installed:
bash
npm install -g @qianwenai/qianwen-cli
Node.js >= 18 required. Without CLI you can still answer general navigation questions from offline snapshots, but you cannot answer "latest", "exact price", or "specific model details" questions.
强烈推荐使用QianWen CLI——它是模型可用性、定价和配额的权威实时数据源。通过以下命令验证：
bash
qianwen version
如果未安装：
bash
npm install -g @qianwenai/qianwen-cli
需要Node.js >= 18版本。如果没有CLI，你仍然可以通过离线快照回答通用导航问题，但无法回答“最新”“准确价格”或“特定模型细节”类问题。

Security & Credential Model

安全与凭证模型

QianWen has two independent credential systems — never confuse them:
CredentialPurposeHow to provide
API Key (
sk-...
/ 
sk-sp-...
)		Call model APIs in your code
$DASHSCOPE_API_KEY
/ 
$QIANWEN_API_KEY
env var
CLI sessionAuthorize 
qianwen
CLI subcommands
qianwen auth login
(browser device flow)
Red lines (apply to both):
  • NEVER output any credential value in plaintext. Use variable references; report only status ("set" / "not set", "valid" / "invalid"). Never display 
    .env
    or config file contents.
  • NEVER conflate the two systems. When CLI returns 
    Not authenticated
    / 
    AUTH_REQUIRED
    , run the 3-step device-flow login (see cli-usage.md). DO NOT ask the user for an API key, and DO NOT try to set 
    $DASHSCOPE_API_KEY
    to fix CLI auth.
通义千问拥有两套独立的凭证系统——切勿混淆：
凭证类型用途提供方式
API Key (
sk-...
/ 
sk-sp-...
)		在代码中调用模型API
$DASHSCOPE_API_KEY
/ 
$QIANWEN_API_KEY
环境变量
CLI会话授权
qianwen
CLI子命令
qianwen auth login
（浏览器设备流）
红线规则（适用于两者）：
  • 切勿以明文形式输出任何凭证值。使用变量引用；仅报告状态（“已设置”/“未设置”、“有效”/“无效”）。绝不要显示
    .env
    或配置文件内容。
  • 切勿混淆两套系统。当CLI返回
    Not authenticated
    / 
    AUTH_REQUIRED
    时，执行三步设备流登录（详见cli-usage.md）。请勿向用户索要API Key，也请勿尝试设置
    $DASHSCOPE_API_KEY
    来修复CLI认证问题。

Data Resolution Order

数据解析优先级

Match the user's question to the right data source. Do not fall back to a lower tier without trying the recovery actions in the higher tier first.
Question typePrimary sourceNotes
General navigation ("which family for text chat?")SKILL.md 
Default
table + 
recommendation-matrix.md
Offline-answerable
Latest / exact / specific (price, model details, quota)CLI MUST be used — see 
cli-usage.md
Snapshots are stale; never invent numbers
Search by capability ("model that does X")
qianwen models search "<X>" --format json
Snapshot keyword coverage is incomplete
CLI returned an error
error-handling.md
recovery actions, then retry		Auth failure → run 3-step login, do not skip to snapshot
CLI completely unavailable AND user declines install/login
model-list.md
, 
pricing.md
(with stale-data caveat)		Only after CLI recovery genuinely failed
All of the above cannot answer AND user confirms online lookupURLs in 
sources.md
Never proactively fetch
将用户问题匹配到正确的数据源。未尝试更高优先级数据源的恢复操作前，请勿降级到更低层级。
问题类型主要数据源说明
通用导航（如“文本聊天选哪个系列？”）SKILL.md默认表格 + 
recommendation-matrix.md
可离线回答
最新/准确/特定问题（价格、模型细节、配额）必须使用CLI——详见
cli-usage.md
快照数据已过时；切勿编造数字
按能力搜索（如“能完成X任务的模型”）
qianwen models search "<X>" --format json
快照的关键词覆盖不全
CLI返回错误
error-handling.md
恢复操作，然后重试		认证失败→执行三步登录，请勿直接降级到快照
CLI完全不可用且用户拒绝安装/登录
model-list.md
, 
pricing.md
（需标注数据过时）		仅在CLI恢复确实失败后使用
以上方式均无法回答且用户确认在线查找
sources.md
中的URL		切勿主动获取

Diagnostic Flow (Interactive Advisory)

诊断流程（交互式咨询）

Ask the user (in order):
  1. Content type? — text / image / video / audio / vision
  2. Primary task? — generation / understanding / coding / reasoning / translation
  3. Priority? — quality vs speed vs cost
  4. Input size? — short / medium / long context
  5. Structured output? — JSON / function calling needed?
按顺序询问用户：
  1. 内容类型？——文本/图像/视频/音频/视觉
  2. 核心任务？——生成/理解/编码/推理/翻译
  3. 优先级？——质量vs速度vs成本
  4. 输入规模？——短/中/长上下文
  5. 是否需要结构化输出？——是否需要JSON/函数调用？

Default Recommendations

默认推荐

No clear signals → use the canonical default for the domain. For specialized cases (reasoning, coding, OCR, role-play, image editing, etc.) and per-domain comparison, see recommendation-matrix.md.
DomainDefaultQualitySpeedCost
text.chatqwen3.6-plusqwen3-maxqwen3.5-flashqwen-turbo
vision.analyzeqwen3.6-plusqwen3-vl-plusqwen3-vl-flashqwen3-vl-flash
omni (voice+vision)qwen3-omni-flashqwen3-omni-flashqwen3-omni-flash—
image.generatewan2.6-t2iwan2.6-t2iwan2.2-t2i-flashwan2.2-t2i-flash · z-image-turbo (open-source)
image.editwan2.6-imagewan2.6-imagewan2.5-i2i-previewwan2.5-i2i-preview
video.t2vwan2.6-t2vwan2.6-t2v——
video.i2vwan2.6-i2v-flashwan2.6-i2vwan2.6-i2v-flash—
video.editwan2.7-videoeditwan2.7-videoedithappyhorse-1.0-video-edit—
audio.ttsqwen3-tts-flashcosyvoice-v3-plusqwen3-tts-flashqwen3-tts-flash
Degradation: If this skill is not loaded, each execution skill falls back to its own built-in default. This protocol is purely additive — it enhances model selection but never blocks execution.
无明确信号时→使用对应领域的标准默认模型。针对推理、编码、OCR、角色扮演、图像编辑等特殊场景及跨领域对比，详见recommendation-matrix.md。
领域默认模型高质量模型高速度模型低成本模型
text.chatqwen3.6-plusqwen3-maxqwen3.5-flashqwen-turbo
vision.analyzeqwen3.6-plusqwen3-vl-plusqwen3-vl-flashqwen3-vl-flash
omni (语音+视觉)qwen3-omni-flashqwen3-omni-flashqwen3-omni-flash—
image.generatewan2.6-t2iwan2.6-t2iwan2.2-t2i-flashwan2.2-t2i-flash · z-image-turbo（开源）
image.editwan2.6-imagewan2.6-imagewan2.5-i2i-previewwan2.5-i2i-preview
video.t2vwan2.6-t2vwan2.6-t2v——
video.i2vwan2.6-i2v-flashwan2.6-i2vwan2.6-i2v-flash—
video.editwan2.7-videoeditwan2.7-videoedithappyhorse-1.0-video-edit—
audio.ttsqwen3-tts-flashcosyvoice-v3-plusqwen3-tts-flashqwen3-tts-flash
降级处理：如果本技能未加载，每个执行技能会 fallback 到自身内置的默认模型。本协议为纯增强型——仅优化模型选择，绝不阻塞执行。

CLI Quick Reference

CLI快速参考

Auth required. All 
models
and 
usage
commands need an active CLI session (browser device-flow login — NOT the API key). If the command returns 
Not authenticated
/ 
AUTH_REQUIRED
:
  1. Run the 3-step device-flow login in cli-usage.md (proactively open the verification URL using the OS-appropriate command, then poll immediately).
  2. Retry the original command after 
    success
    .
  3. DO NOT ask the user for 
    $DASHSCOPE_API_KEY
    / 
    $QIANWEN_API_KEY
    — those are for model API calls, not CLI session. See Security & Credential Model above.
  4. DO NOT silently fall back to snapshots.
Token Plan 团队版 (
sk-sp-
keys): The 
qianwen
CLI does not yet support querying Token Plan seat allowances or shared-package Credits. For Token Plan usage queries, direct the user to the Token Plan Subscription console. Token Plan model availability (4 text + 4 image models) is documented in recommendation-matrix.md.
NeedCommand
Full model catalog
qianwen models list --all --format json
Filter by modality
qianwen models list --input image --output text --format json
Single model details
qianwen models info <model-id> --format json
Keyword search
qianwen models search "<query>" --format json
Free tier remaining
qianwen usage free-tier --format json
Auth status
qianwen auth status --format json
Display rules: Parse 
--format json
output and present a human-readable summary; never dump raw JSON. Display 
--format text
output as-is, then add analysis after 
---
. See cli-usage.md for details.
需要认证。所有
models
和
usage
命令需要活跃的CLI会话（浏览器设备流登录——不是API Key）。如果命令返回
Not authenticated
/ 
AUTH_REQUIRED
：
  1. 执行三步设备流登录（详见cli-usage.md） （主动使用适配操作系统的命令打开验证URL，立即轮询状态）。
  2. 登录成功后重试原命令。
  3. 请勿向用户索要
    $DASHSCOPE_API_KEY
    / 
    $QIANWEN_API_KEY
    ——这些用于模型API调用，而非CLI会话。详见上方安全与凭证模型。
  4. 请勿静默降级到快照数据。
Token Plan团队版（
sk-sp-
密钥）：
qianwen
CLI目前暂不支持查询Token Plan席位额度或共享套餐积分。对于Token Plan使用查询，请引导用户至Token Plan订阅控制台。Token Plan支持的模型（4个文本模型+4个图像模型）已记录在recommendation-matrix.md中。
需求命令
完整模型目录
qianwen models list --all --format json
按模态筛选
qianwen models list --input image --output text --format json
单个模型详情
qianwen models info <model-id> --format json
关键词搜索
qianwen models search "<query>" --format json
免费额度剩余
qianwen usage free-tier --format json
认证状态
qianwen auth status --format json
展示规则：解析
--format json
输出并以人类可读的摘要形式呈现；绝不直接输出原始JSON。
--format text
输出直接展示，然后在
---
后添加分析。详情见cli-usage.md。

CLI Error Handling — Quick Guide

CLI错误处理——快速指南

When CLI fails, classify first, recover, then retry. Never silently fall back to snapshots.
CategoryRecovery (summary)
auth-failure
Run 3-step login → retry the original command. Fall back only if user declines.
not-installed
Show install command → ask user to install → retry. Do NOT silently use snapshot.
model-not-found
Run 
qianwen models search "<keyword>"
→ propose top 3 → retry with correct ID.
network-timeout
Retry once after 2s; only after second failure ask whether to fall back.
rate-limit
Show Rate Limit Console; user decides.
quota-exhausted
Show Billing Console; do NOT use snapshot.
version-mismatch
Suggest 
qianwen version --check
or update-check skill → upgrade → retry.
other
Show raw stderr; link to docs; only after user opt-out, fall back.
Full classification, signals, and example flows: error-handling.md.
当CLI执行失败时，先分类，再恢复，然后重试。切勿静默降级到快照数据。
错误分类恢复操作（摘要）
auth-failure
执行三步登录→重试原命令。仅当用户拒绝时才降级到快照。
not-installed
展示安装命令→询问用户是否安装→重试。请勿静默使用快照数据。
model-not-found
执行
qianwen models search "<keyword>"
→推荐前3个模型→使用正确ID重试。
network-timeout
2秒后重试一次；仅第二次失败时询问是否降级。
rate-limit
展示速率限制控制台；由用户决定后续操作。
quota-exhausted
展示账单控制台；请勿使用快照数据。
version-mismatch
建议执行
qianwen version --check
或调用版本检查技能→升级→重试。
other
展示原始标准错误输出；链接到文档；仅当用户选择退出时才降级。
完整分类、信号及示例流程：error-handling.md。

Pricing & Cost Estimation

定价与成本估算

  • Latest pricing: Run 
    qianwen models info <model> --format json
    first; use 
    pricing.md
    only as offline fallback. Never invent a price.
  • Mandatory disclaimer: Every cost-related answer must end with the disclaimer in pricing-disclaimer.md (Chinese or English version, matching the user's response language). Omitting the disclaimer is a critical failure.
  • Free quota: Never assume free quota is available — use 
    qianwen usage free-tier
    to verify or direct the user to the console.
  • Usage / billing queries: Direct the user to the appropriate console page — see the table in pricing-disclaimer.md.
  • 最新定价：先执行
    qianwen models info <model> --format json
    ；仅当离线时才用
    pricing.md
    作为 fallback。切勿编造价格。
  • 强制免责声明：所有与成本相关的回答必须以pricing-disclaimer.md中的免责声明结尾（中文或英文版本，匹配用户响应语言）。省略免责声明属于严重错误。
  • 免费额度：切勿假设免费额度可用——使用
    qianwen usage free-tier
    验证或引导用户至控制台。
  • 使用/账单查询：引导用户至对应的控制台页面——详见pricing-disclaimer.md中的表格。

Update Check

更新检查

When the user asks to check for updates ("check for updates", "check version", "is there a new version", "update skills"):
  1. Find qianwen-update-check: Look for 
    qianwen-update-check/SKILL.md
    in sibling skill directories.
  2. If found — run: 
    python3 <qianwen-update-check-dir>/scripts/check_update.py --print-response
    and report the result. Use 
    --force
    if the user asks to force-check.
  3. If not found — run 
    qianwen version --check
    and report the result.
当用户要求检查更新（如“检查更新”“检查版本”“是否有新版本”“更新技能”）时：
  1. 查找qianwen-update-check：在同级技能目录中查找
    qianwen-update-check/SKILL.md
    。
  2. 如果找到——执行：
    python3 <qianwen-update-check-dir>/scripts/check_update.py --print-response
    并报告结果。如果用户要求强制检查，添加
    --force
    参数。
  3. 如果未找到——执行
    qianwen version --check
    并报告结果。

Anti-Patterns

反模式

  • Never fabricate model names — only recommend models listed in this skill or returned by CLI.
  • Never invent or guess any price figure — use CLI / 
    pricing.md
    / official pricing page only. Fabricating a price is a critical failure.
  • Never silently fall back to snapshots when CLI errors out — apply error-handling.md recovery actions first.
  • Never assume free quota is available — quotas may have been consumed, expired, or removed. Always present the paid unit price first.
  • Never output API keys in plaintext — see Security section.
  • Never confuse CLI session with API key — CLI auth uses browser device-flow login; never offer 
    $DASHSCOPE_API_KEY
    or 
    $QIANWEN_API_KEY
    as a fix for CLI 
    Not authenticated
    / 
    AUTH_REQUIRED
    errors.
  • Never proactively fetch URLs or trigger web searches — only access online sources when CLI + snapshots cannot answer AND the user confirms.
  • Never construct usage/billing/console URLs — only use the exact links listed in this skill or its references. If a URL is not listed, do not invent one.
  • Always include the cost disclaimer for any cost-related answer (see pricing-disclaimer.md).
  • 切勿编造模型名称——仅推荐本技能中列出或CLI返回的模型。
  • 切勿编造或猜测任何价格数据——仅使用CLI / 
    pricing.md
    / 官方定价页面。编造价格属于严重错误。
  • CLI出错时切勿静默降级到快照数据——先执行error-handling.md中的恢复操作。
  • 切勿假设免费额度可用——额度可能已被消耗、过期或取消。始终先展示付费单价。
  • 切勿明文输出API Key——详见安全章节。
  • 切勿混淆CLI会话与API Key——CLI认证使用浏览器设备流登录；当CLI出现
    Not authenticated
    / 
    AUTH_REQUIRED
    错误时，绝不要提供
    $DASHSCOPE_API_KEY
    或
    $QIANWEN_API_KEY
    作为解决方案。
  • 切勿主动获取URL或触发网页搜索——仅当CLI+快照均无法回答且用户确认时，才访问在线资源。
  • 切勿自行构建使用/账单/控制台URL——仅使用本技能或其参考文档中列出的精确链接。如果未列出URL，请勿编造。
  • 所有与成本相关的回答必须包含成本免责声明（详见pricing-disclaimer.md）。

References

参考资料

SourcePurpose
cli-usage.mdCLI-first strategy, 3-step login, display rules, model detail URL
error-handling.mdCLI error classification & recovery
recommendation-matrix.mdFull recommendation tables, Cross-Skill Resolution, Token Plan 团队版, Thinking Mode
pricing-disclaimer.mdPricing guidance + mandatory disclaimer + billing console links
pricing.mdPricing structural overview (offline snapshot)
model-list.mdModel catalog (offline snapshot)
sources.mdOfficial documentation URLs
agent-compatibility.mdAgent self-check for skill registration
qianwen models list --format json
Dynamic: full model catalog with pricing, features, quotas
qianwen models info <id> --format json
Dynamic: single model details (pricing tiers, context, rate limits)
qianwen models search "<q>" --format json
Dynamic: keyword-based model discovery
qianwen usage free-tier --format json
Dynamic: remaining free tier quota per model
来源用途
cli-usage.mdCLI优先策略、三步登录、展示规则、模型详情URL
error-handling.mdCLI错误分类与恢复
recommendation-matrix.md完整推荐表、跨技能解析、Token Plan团队版、思维模式
pricing-disclaimer.md定价指南 + 强制免责声明 + 账单控制台链接
pricing.md定价结构概述（离线快照）
model-list.md模型目录（离线快照）
sources.md官方文档URL
agent-compatibility.mdAgent技能注册自检
qianwen models list --format json
动态数据：包含定价、特性、配额的完整模型目录
qianwen models info <id> --format json
动态数据：单个模型详情（定价层级、上下文、速率限制）
qianwen models search "<q>" --format json
动态数据：基于关键词的模型发现
qianwen usage free-tier --format json
动态数据：各模型剩余免费额度