Qwen Model Selector (Advisor)

Detecting Key Type

Run this command to detect the API key type (outputs token-plan, payg, or not-set):

python3 -c "
import os
from pathlib import Path
env_file = Path('.env')
if not env_file.exists():
    for parent in [Path.cwd()] + list(Path.cwd().parents):
        if (parent / '.git').exists() or (parent / 'skills').is_dir():
            env_file = parent / '.env'
            break
if env_file.exists():
    for line in env_file.read_text().splitlines():
        line = line.strip()
        if not line or line.startswith('#') or '=' not in line:
            continue
        k, v = line.split('=', 1)
        k, v = k.strip(), v.strip().strip('\"').strip(\"'\")
        if k in ('QIANWEN_API_KEY', 'DASHSCOPE_API_KEY') and k not in os.environ:
            os.environ[k] = v
key = os.environ.get('QIANWEN_API_KEY') or os.environ.get('DASHSCOPE_API_KEY') or ''
print('token-plan' if key.startswith('sk-sp-') else 'payg' if key else 'not-set')
"

Windows: If python3 is not available, use python. The multi-line -c string works in both PowerShell and CMD. Alternatively, save the snippet to a temporary .py file and run it.

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. Fetch the CDN recommendations first; if CDN access fails, use the local fallback.

Do not fabricate model names — only recommend models listed in the CDN model catalogs or returned by CLI. This skill is part of QianWen-AI/qianwen-ai.

Skill directory

Load on demand. Fetch the documented CDN model catalogs when model lists, defaults, or recommendations are needed. Do not fetch other external URLs unless the user explicitly asks for the latest data.

Every path under cdn/ is a local fallback, not the primary source. For cdn/<path>, first fetch https://alioth.alicdn.com/skills-info/models/<path> and use the local file only if that CDN request fails.

Prerequisites

QianWen CLI is strongly recommended — it is the authoritative real-time data source for model availability, pricing, and quotas. Verify with:

qianwen version

If not installed:

npm install -g @qianwenai/qianwen-cli

Node.js >= 18 is required for the CLI. Without CLI, you can still answer point-in-time general navigation and basic model-information questions from the CDN catalogs. You cannot verify current availability, exact current prices, capability-search results beyond the snapshot, or account-specific quota information.

Security & Credential Model

QianWen has two independent credential systems — never confuse them:

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.

Data Resolution Order

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.

Diagnostic Flow (Interactive Advisory)

Prerequisite: Complete Detecting Key Type above and narrow the candidate set before proceeding. All recommendations loaded from the CDN catalog must stay within the user's billing scope.

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?

Default Recommendations

Before recommending any model, check its exact ID against the official retirement list (id, expiredTime) and any CLI lifecycle result. Exclude scheduled or already retired models from defaults and recommendations, even if a catalog or plan still lists them. If the user explicitly selects one, disclose its retirement date and the announcement, suggest a supported replacement, and do not silently substitute it. If lifecycle data cannot be verified, say so; a snapshot alone is not proof of current availability.

Before choosing a default or recommending a model, fetch and read the current CDN recommendations linked above. For a Token Plan key, also read the Token Plan model catalog linked above and restrict candidates to it.

• If the user explicitly specifies a model, use it after verifying that it is available in the user's billing scope.
• Otherwise, match the strongest task signal first, then choose the appropriate quality, speed, or cost tier.
• If missing requirements would materially change the choice, compare the relevant domain options and ask the user to clarify.
• Preserve the selected model's documented thinking default unless the user or task requires an override; do not enable thinking merely as a generic default for simple tasks.

CLI Quick Reference

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 (sk-sp- keys): Once an active CLI session is established (device-flow login), qianwen usage commands report both pay-as-you-go usage and Token Plan seat allowance / shared-package Credits for the logged-in account. For purchasing shared packages, adjusting seats, or full billing history, direct the user to the Token Plan Subscription console. Token Plan model availability (text + image + video + TTS) is documented in the CDN Token Plan model catalog linked above.

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.

CLI Error Handling — Quick Guide

When CLI fails, classify first, recover, then retry. Never silently fall back to snapshots.

Full classification, signals, and example flows: error-handling.md.

Pricing & Cost Estimation (PAYG only)

Skip this section for Token Plan.

• Latest pricing: Run qianwen models info <model> --format json first; use the CDN pricing reference linked by pricing.md only as a 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.

Update Check

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.

Anti-Patterns

• Never fabricate model names — only recommend models listed in the CDN model catalogs or returned by CLI.
• Never infer the API key type from the request wording — use the configured Key or calling context.
• Never recommend a model outside the user's billing scope — Token Plan keys must only receive models from the Token Plan model catalog linked above; PAYG keys may use the full catalog. Violating this causes hard failures for the user.
• 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 arbitrary URLs or trigger web searches. Fetch the documented CDN model catalogs when model data is needed; access other online sources only when CLI + CDN catalogs 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).

References