Integrate the Uncensored Qwen API in Minutes

Base URL and Authentication

Start sending requests by pointing your client at https://api.qwenapiprice.com/v1 and passing your key in the Authorization header.

Get your key instantly by clicking Get API key on our site; you can sign in with Google or use a simple email and password without providing a phone number.

Each account supports only one active key at a time, so generating a new one immediately invalidates the previous key for security.

Our service is strictly OpenAI-compatible, meaning you do not need to rewrite your integration logic just to switch to our uncensored model.

Keep your key secure, as it is the sole identifier for your prepaid credit and usage limits.

Chat Completions Endpoint

Send text to the POST /v1/chat/completions endpoint to receive instant, unfiltered responses from our model.

This endpoint handles standard text-in, text-out interactions without requiring complex configurations or additional setup steps.

You can define your conversation history using the messages array, just like you would with any other OpenAI-compatible service.

The model runs on our own servers and does not use your prompts for training, ensuring your data stays private.

Use this endpoint for everything from creative writing to technical debugging without worrying about content filters blocking your requests.

Model Information Endpoint

Query the GET /v1/models endpoint to verify your connection and see the available model ID.

This simple request confirms that your authentication is working correctly before you start sending heavy payloads.

You will see the model ID listed as uncensored, which you must use in your subsequent chat requests.

This endpoint returns metadata about the model, helping you ensure your client library is correctly configured.

It is a lightweight call that consumes minimal tokens, making it perfect for integration tests.

Streaming and Tool Usage

Enable streaming by setting stream: true to receive tokens via Server-Sent Events (SSE) for lower perceived latency.

The final chunk of the stream includes the complete token usage statistics, allowing you to track costs accurately in real-time.

You can also use function calling by providing a tools array and specifying tool_choice to let the model decide when to execute functions.

This flexibility makes our API suitable for building complex agents that need to interact with external systems or APIs.

Streaming is particularly useful for long-form content generation where users prefer to see output as it is being generated.

JSON Mode and Parameters

Force structured output by setting response_format to {"type": "json_object"} for reliable data extraction.

You can tune the model's behavior using parameters like temperature, top_p, stop sequences, and seed for reproducibility.

Adjust presence_penalty and frequency_penalty to control how often the model repeats itself or introduces new topics.

These parameters give you fine-grained control over the model's output style and consistency without needing to retrain anything.

Use JSON mode to ensure your downstream applications receive perfectly formatted data every time.

Token Limits and Context Window

The model supports a total context window of 100,000 tokens, encompassing both the prompt and the completion.

You can generate up to 16,000 tokens per request, or default to 2,048 tokens if you do not specify max_tokens.

Requests are limited to 300 per minute per key, with a concurrency limit of 8 simultaneous requests to ensure stability.

The maximum request body size is 8 MB, which is sufficient for most large-context use cases without hitting network limits.

Paid credit never expires, so you can accumulate tokens for large projects without worrying about monthly renewal dates.

cURL

Copycurl https://api.qwenapiprice.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "List the current pricing tiers for the API"}]
  }'

Python

Copyfrom openai import OpenAI

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