Uncensored api documentation

Quick Start: Install and Configure the SDK

Start by pointing your client at our base URL and passing your API key. The endpoint is https://api.claudeapitokencosts.com/v1 and requires no complex routing logic.

Authentication uses a standard bearer token in the Authorization header. You can generate your key instantly via Google or email.

Our service is fully OpenAI-compatible. You can use the official SDKs without modifying your core logic. Just update the base URL and inject your key.

Use curl to verify connectivity immediately.

Basic Chat Completion Request

Send a POST request to /v1/chat/completions to get text output. This endpoint handles all standard chat interactions.

Define your system prompt and user message in the JSON body. The model ID is always uncensored.

The API returns a direct text response. You do not need to parse complex streaming objects for simple use cases.

This approach works for simple scripts or batch processing jobs. Use curl to test your first call.

Streaming Responses with Server-Sent Events

Enable streaming by setting stream: true in your request. The server returns chunks as they are generated.

This method reduces perceived latency for long outputs. It also allows your application to display tokens in real time.

Each chunk contains partial data and usage statistics in the final payload.

Handle the SSE stream in your client code to process tokens as they arrive. This is critical for interactive applications.

Function Calling and JSON Mode

Support structured output using the response_format parameter. Set it to {"type": "json_object"} for strict JSON replies.

You can also define tools for function calling. The model respects the tool definitions provided in the request.

This ensures reliable data extraction for your pipelines. Combine JSON mode with tools for complex workflows.

Our model handles structured data generation efficiently.

Parameters: Temperature, Top P, and Seed

Control creativity with temperature and top_p. Higher values increase randomness. Lower values make outputs more deterministic.

Use the seed parameter for reproducible results. This is useful for debugging or testing specific prompts.

Set max_tokens to limit output length. The default is 2,048 tokens per request.

Adjust these settings to fit your specific use case. Balance consistency with variety as needed.

Understanding Token Usage and Costs

You pay only for tokens consumed. Input tokens cost $0.15 per million. Output tokens cost $0.50 per million.

Errors and refusals do not consume credit. You only pay for successful completions.

Use the token calculator to estimate costs before sending large batches. Our pricing is transparent and usage-based.

No monthly fees or subscription locks apply. Credit never expires. You can top up with crypto anytime.

Monitor your usage via the final chunk in streaming responses.

cURL

Copycurl https://api.claudeapitokencosts.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Run the unit tests and show me the output"}]
  }'

Python

Copyfrom openai import OpenAI

client = OpenAI(base_url="https://api.claudeapitokencosts.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)

Node.js

Copyimport OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.claudeapitokencosts.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

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)