Updated
Abliterated LLM API quickstart
You can call an abliterated LLM API in three steps with the SDK you already use. The code runs as written against Silk Compute, the worked example on this site.
- 1
Create a 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-..." - 2
Install an SDK
Any OpenAI or Anthropic SDK works, and cURL needs nothing.
Pythonpip install openaiNodenpm install openaiGogo get -u 'github.com/openai/openai-go/v3'Anthropicpip install anthropic - 3
Send a request
Set the base URL to
https://api.silkcompute.comand the model to an id from the model list. The program below is the whole request.
https://api.silkcompute.com
import os
from openai import OpenAI
client = OpenAI(
base_url="https://api.silkcompute.com",
api_key=os.environ["SILK_API_KEY"],
)
reply = client.chat.completions.create(
model="deepseek-v4.1-flash-1017-uncensored",
messages=[{"role": "user", "content": "What is a mutex?"}],
)
print(reply.choices[0].message.content)Example response
{
"object": "chat.completion",
"model": "deepseek-v4.1-flash-1017-uncensored",
"choices": [{
"index": 0,
"message": {
"role": "assistant",
"reasoning_content": "Define it in one line.",
"content": "A lock only one thread can hold at a time."
},
"finish_reason": "stop"
}],
"usage": {
"prompt_tokens": 16,
"completion_tokens": 48,
"prompt_tokens_details": {"cached_tokens": 0}
}
}import OpenAI from 'openai'
const client = new OpenAI({
baseURL: 'https://api.silkcompute.com',
apiKey: process.env.SILK_API_KEY,
})
const reply = await client.chat.completions.create({
model: 'deepseek-v4.1-flash-1017-uncensored',
messages: [{ role: 'user', content: 'What is a mutex?' }],
})
console.log(reply.choices[0].message.content)Example response
{
"object": "chat.completion",
"model": "deepseek-v4.1-flash-1017-uncensored",
"choices": [{
"index": 0,
"message": {
"role": "assistant",
"reasoning_content": "Define it in one line.",
"content": "A lock only one thread can hold at a time."
},
"finish_reason": "stop"
}],
"usage": {
"prompt_tokens": 16,
"completion_tokens": 48,
"prompt_tokens_details": {"cached_tokens": 0}
}
}curl https://api.silkcompute.com/chat/completions \
-H "Authorization: Bearer $SILK_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "deepseek-v4.1-flash-1017-uncensored",
"messages": [
{"role": "user", "content": "What is a mutex?"}
]
}'Example response
{
"object": "chat.completion",
"model": "deepseek-v4.1-flash-1017-uncensored",
"choices": [{
"index": 0,
"message": {
"role": "assistant",
"reasoning_content": "Define it in one line.",
"content": "A lock only one thread can hold at a time."
},
"finish_reason": "stop"
}],
"usage": {
"prompt_tokens": 16,
"completion_tokens": 48,
"prompt_tokens_details": {"cached_tokens": 0}
}
}package main
import (
"context"
"fmt"
"os"
"github.com/openai/openai-go/v3"
"github.com/openai/openai-go/v3/option"
)
func main() {
client := openai.NewClient(
option.WithBaseURL("https://api.silkcompute.com"),
option.WithAPIKey(os.Getenv("SILK_API_KEY")),
)
reply, err := client.Chat.Completions.New(context.TODO(), openai.ChatCompletionNewParams{
Model: "deepseek-v4.1-flash-1017-uncensored",
Messages: []openai.ChatCompletionMessageParamUnion{
openai.UserMessage("What is a mutex?"),
},
})
if err != nil {
panic(err)
}
fmt.Println(reply.Choices[0].Message.Content)
}Example response
{
"object": "chat.completion",
"model": "deepseek-v4.1-flash-1017-uncensored",
"choices": [{
"index": 0,
"message": {
"role": "assistant",
"reasoning_content": "Define it in one line.",
"content": "A lock only one thread can hold at a time."
},
"finish_reason": "stop"
}],
"usage": {
"prompt_tokens": 16,
"completion_tokens": 48,
"prompt_tokens_details": {"cached_tokens": 0}
}
}Pick your stack
PythonThe openai package, streaming and retries.JavaScript and TypeScriptNode, Bun or Deno with the openai package.cURLAll three formats as raw HTTP.GoThe official openai-go package.Anthropic SDKPOST /v1/messages from Python or TypeScript.Claude CodeOne settings file, every model in /model.CodexA provider block in config.toml.OpenCodeA provider block in opencode.json.