API Documentation for uncensored model

Authentication and Base URL

Start by sending requests to https://api.bestllmapiprovider.com/v1 with your API key. The base URL replaces the standard OpenAI endpoint in your client configuration. Pass the key in the Authorization: Bearer <key> header for every call. This works with the official OpenAI SDKs and any OpenAI-compatible client.

Required Headers

• Content-Type: application/json
• Authorization: Bearer YOUR_API_KEY

Keep your key secure. If you lose it, generate a new one from the dashboard. The old key stops working immediately.

Copycurl https://api.bestllmapiprovider.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Calculate the total cost for 50k tokens"}]
  }'

Quickstart: Send your first uncensored request

Make a POST request to /v1/chat/completions to get text output. The model ID is always uncensored. Send your prompt in the messages array. The API returns a direct response without content filters for lawful adult use.

Example Payload

• model: "uncensored"
• messages: [{"role": "user", "content": "Explain quantum entanglement."}]

This endpoint handles text generation only. It does not support images or audio. Use the parameters below to control the output style.

Copyfrom openai import OpenAI

client = OpenAI(base_url="https://api.bestllmapiprovider.com/v1", api_key="YOUR_KEY")

resp = client.chat.completions.create(
    model="uncensored",
    messages=[{"role": "user", "content": "Summarise this thread without softening it."}],
)
print(resp.choices[0].message.content)

Parameters: Temperature, Top-P, and Seed

Control creativity with temperature and top_p. Set temperature to 0.7 for balanced output or 1.5 for more variation. Use top_p to limit the probability mass of sampled tokens. Set a seed integer for reproducible results. These parameters help you tune the model for specific tasks.

Key Parameters

• temperature: 0.0 to 2.0
• top_p: 0.1 to 1.0
• seed: any integer

Combine these with max_tokens to control length. The model respects the context window limits strictly.

Copyimport OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.bestllmapiprovider.com/v1", apiKey: process.env.API_KEY });

const resp = await client.chat.completions.create({
  model: "uncensored",
  messages: [{ role: "user", content: "Draft a villain monologue for my game." }],
});
console.log(resp.choices[0].message.content);

Streaming responses and token counting

Enable streaming by setting stream: true in your request. The API sends Server-Sent Events (SSE) for each generated token. This reduces perceived latency for long responses. Token usage is reported in the final chunk.

Stream Handling

• Read chunks as they arrive
• Parse the delta field
• Check usage in the last chunk

Streaming works with all parameters. It does not affect the per-token pricing. You pay for actual tokens generated.

Copystream = client.chat.completions.create(
    model="uncensored",
    messages=[{"role": "user", "content": "Tell the story in second person."}],
    stream=True,
)
for chunk in stream:
    if chunk.choices and chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="", flush=True)

Function Calling and JSON Mode

Use tools for function calling or response_format for JSON output. Set response_format to {"type": "json_object"} for strict JSON. The model returns structured data suitable for parsing. This is useful for building agents or data extraction pipelines.

Configuration

• tools: array of function definitions
• response_format: {"type": "json_object"}

Ensure your prompt instructions match the schema. The model may still require validation. Always handle potential parsing errors.

JSON Mode Example

Set response_format to enforce strict JSON output. This reduces the need for post-processing.

Limits, Errors, and Context Window

The context window is 100,000 tokens total. Max output is 16,000 tokens per request. You can send 300 requests per minute per key. Eight concurrent requests are allowed simultaneously. Errors return standard HTTP codes.

Common Errors

• 401: Invalid or missing API key
• 402: Insufficient credit
• 429: Rate limit exceeded

Refusals due to content limits do not charge credit. Errors do not charge credit either. Your prepaid credit never expires.

Request Limits

Max request body size is 8 MB. Exceeding this returns a 413 error. Manage your token usage carefully.