Qwen text chat: OpenAI-compatible API skill
Chat, code and function-call with Qwen models through the OpenAI-compatible API
- What
- Chat, code and function-call with Qwen models through the OpenAI-compatible API
- Cost
- Free
- Needs
- Python 3.9+; a QianWen/DashScope API key (set as DASHSCOPE_API_KEY in .env — a free-tier quota exists, check the qianwen-usage skill); never paste the key in chat
- Install
- Copy the installer prompt below into your Muse — your agent does the rest.
Curated by Skill Harbor — @qianwen-ai's Qwen text skill: generate text, hold conversations, write code, reason and call functions through the OpenAI-compatible chat/completions API with a bundled stdlib-only Python script (`scripts/text.py` — streaming, `--output` save, `--print-response`), three fallback paths (curl, Python SDK, autonomous resolution), function calling, structured JSON output, web search, thinking mode, batch inference with a 50% discount, plus API-key type detection (PAYG vs Token Plan — Token Plan keys only allow listed models) and strict key hygiene (never output API keys in plaintext; guide the user to set DASHSCOPE_API_KEY in `.env` instead of asking for the key directly). Requires Python 3.9+ and a QianWen/DashScope API key — free-tier quota exists (check the qianwen-usage skill). Includes a diagnostic table for common failures (401, 429, SSL, proxy), mandatory post-execution stderr signal checks (`[ACTION_REQUIRED]`, `[UPDATE_AVAILABLE]`) that surface update notices, and detailed references (execution, API, prompt engineering, sources). Honest caveats: the model catalogs are point-in-time snapshots — verify the model ID against the official list before committing; output files always go to `./output/` under the working directory, never into the skill's own folder; Apache-2.0 licensed. Skill Harbor never reviews the code, review it yourself before use. Discovered via skills.sh.
Version:
Install
Prerequisites: Python 3.9+; a QianWen/DashScope API key (set as DASHSCOPE_API_KEY in .env — a free-tier quota exists, check the qianwen-usage skill); never paste the key in chat Install "Qwen text chat: OpenAI-compatible API skill" for me. Generate text, converse, write code, reason and call functions with Qwen models through the OpenAI-compatible chat/completions API: bundled stdlib-only Python script (streaming, --output save, --print-response), three fallback paths (curl, Python SDK, autonomous), function calling, structured JSON output, web search, thinking mode, batch inference, API-key type detection (PAYG vs Token Plan), strict key hygiene (never output keys in plaintext), a diagnostic table for common failures (401, 429, SSL, proxy) and mandatory post-execution stderr signal checks ([ACTION_REQUIRED], [UPDATE_AVAILABLE]). Repository: https://github.com/qianwen-ai/qianwen-ai/blob/main/skills/text/qianwen-text/SKILL.md 1. Fetch the SKILL.md file (and any helper files) from the repository path into a temporary folder and summarize what it does in one or two sentences. 2. Safety check: review the SKILL.md and scripts for anything suspicious (unexpected network calls, shell commands, credential harvesting). This repo should contain zero secrets in code, credentials only via the secure vault, allowed hosts declared in the SKILL.md. Verify that holds here; STOP on any red flag and tell me. 3. Install it as a skill: copy SKILL.md and its helper files into the agent's skills directory, in a folder named "qianwen-text". 4. Verify with no network calls: frontmatter valid, files in place. 5. Report what was installed, where, and what I still need to do myself (e.g. obtain a key from the QianWen console, set DASHSCOPE_API_KEY in my .env file, keep outputs under ./output/ in the working directory). GitHub is optional: if I have a GitHub account or the gh CLI, you may use it; otherwise public access is fine. Never require it unless it's in the prerequisites above. Rules: don't touch anything outside the temp folder and the install target. If anything looks off, stop and ask me.
Questions
How do I install a build?
Every product page includes a copy-paste install prompt. Paste it into your Muse and it sets the build up for you — no manual configuration.
Where does my money go?
Straight to the seller. Skill Harbor never processes payments: checkout happens on the seller’s own page, usually Stripe.
What does the ✓ next to a creator’s name mean?
It means we confirmed the identity of the person behind the listing. It says nothing about the code itself — always check a build before installing it.