Updated
Abliterated model in OpenCode
OpenCode takes any OpenAI-compatible provider in opencode.json, so an abliterated model needs one config block. Effort levels become variants you switch with ctrl+t.
- 1
Install OpenCode
macOS and Linuxcurl -fsSL https://opencode.ai/install | bashnpmnpm install -g opencode-ai - 2
Set your key
Create a key on Silk Compute's API keys page and add credits from $5. Keep it in an environment variable.
Shellexport SILK_API_KEY="sk-..." - 3
Add the provider
Save the file below as
~/.config/opencode/opencode.json, or asopencode.jsonin one project. Add one entry per model undermodels. - 4
Run it
Switch the model with
/modelsand the effort withctrl+t.Runopencode
opencode.json
opencode.json{
"$schema": "https://opencode.ai/config.json",
"model": "silkcompute/deepseek-v4.1-flash-1017-uncensored",
"provider": {
"silkcompute": {
"npm": "@ai-sdk/openai-compatible",
"name": "Silk Compute",
"options": { "baseURL": "https://api.silkcompute.com", "apiKey": "{env:SILK_API_KEY}" },
"models": {
"deepseek-v4.1-flash-1017-uncensored": {
"name": "DeepSeek V4.1 Flash 1017",
"tool_call": true,
"interleaved": { "field": "reasoning_content" },
"modalities": { "input": ["text", "image"], "output": ["text"] },
"limit": { "context": 1048576, "output": 131072 },
"cost": { "input": 0.24, "output": 0.9, "cache_read": 0.038 },
"variants": {
"none": { "reasoningEffort": "none" },
"low": { "reasoningEffort": "low" },
"high": { "reasoningEffort": "high" },
"max": { "reasoningEffort": "max" }
}
}
}
}
}
}Example output
/models
Silk Compute
DeepSeek V4.1 Flash 1017
ctrl+t
none, low, high, max