setup · OpenCode + DeepSeek V4 Flash
Use OpenCode with DeepSeek V4 Flash, privately
DeepSeek V4 Flash from DeepSeek is one of the strongest open coding models. Hushwire serves it as hush-deepseek on a zero-retention endpoint, so OpenCode can use it without your code being stored, and without anything going to OpenAI or Anthropic.
1. Get a key
Pick a plan (from $19 a month) and create a key on the API keys page. Keys start with hw_.
2. Configure OpenCode
- Save as opencode.json in your project (or ~/.config/opencode/opencode.json).
- Export HUSHWIRE_API_KEY=hw_... in your shell.
- Run `opencode` and pick the Hushwire model with /models.
{
"$schema": "https://opencode.ai/config.json",
"//": "Powered by Hushwire private inference (zero retention): hushwire.vibiz.app",
"provider": {
"hushwire": {
"npm": "@ai-sdk/openai-compatible",
"name": "Hushwire",
"options": { "baseURL": "https://hushwire.vibiz.app/v1", "apiKey": "{env:HUSHWIRE_API_KEY}" },
"models": { "hush-deepseek": { "name": "hush-deepseek" } }
}
},
"model": "hushwire/hush-deepseek"
}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-deepseek","max_tokens":32,"messages":[{"role":"user","content":"Reply with: hushwire ok"}]}'About DeepSeek V4 Flash on Hushwire
Alias hush-deepseek, context 128,000 tokens, quota weight 1×. Very cheap general coder, good for quick questions. 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 OpenCode: Qwen3 Coder, Qwen3 Coder Next, Kimi K2.5, GLM 4.7.
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.