setup · Kilo Code + Qwen3 Coder Next
Use Kilo Code with Qwen3 Coder Next, privately
Qwen3 Coder Next from Qwen is one of the strongest open coding models. Hushwire serves it as hush-coder-large on a zero-retention endpoint, so Kilo Code can use it without your code being stored, and without anything going to OpenAI or Anthropic.
1. Get a key
Pick a plan (from $19 a month) and create a key on the API keys page. Keys start with hw_.
2. Configure Kilo Code
- Open Kilo Code → Settings → API Provider.
- Choose "OpenAI Compatible" and fill in the fields below.
- Save, then send a message in the chat panel.
# Powered by Hushwire private inference (zero retention): hushwire.vibiz.app
API Provider: OpenAI Compatible
Base URL: https://hushwire.vibiz.app/v1
API Key: hw_your_key_here
Model ID: hush-coder-large
Context window: 200000 (optional)3. Test the connection
This sends one tiny request. You should see a reply containing “hushwire ok”.
curl -s https://hushwire.vibiz.app/v1/messages \
-H "x-api-key: hw_your_key_here" \
-H "anthropic-version: 2023-06-01" \
-H "content-type: application/json" \
-d '{"model":"hush-coder-large","max_tokens":32,"messages":[{"role":"user","content":"Reply with: hushwire ok"}]}'About Qwen3 Coder Next on Hushwire
Alias hush-coder-large, context 262,144 tokens, quota weight 3×. The largest Qwen coder. Best for multi-file agent work. Request bodies are never written to a database or log; the only thing kept is a metadata row (token counts, model, latency) for 30 days, visible in your dashboard.
Compare models
| Alias | Model | Context | Good for |
|---|---|---|---|
| hush-coder | Qwen3 Coder 30B A3B (Qwen) | 262k | Fast, cheap default for edits, refactors and tool loops. |
| hush-coder-large | Qwen3 Coder Next (Qwen) | 262k | The largest Qwen coder. Best for multi-file agent work. |
| hush-kimi | Kimi K2.5 (Moonshot AI) | 262k | Strong agentic coder with long tool chains. |
| hush-glm | GLM 4.7 (Z.ai) | 200k | Reliable tool calling, good at planning and front-end work. |
| hush-deepseek | DeepSeek V4 Flash (DeepSeek) | 128k | Very cheap general coder, good for quick questions. |
Other guides for Kilo Code: Qwen3 Coder, Kimi K2.5, GLM 4.7, DeepSeek V4 Flash.
Try it before you configure anything
The playground runs the same open coding models. No sign-up, 20 messages a day, and nothing you type is stored.