Integrate the uncensored LLM API

Base URL and Authentication

Start by pointing your SDK at our base URL. Replace the placeholder with your actual key.

• Base URL: https://api.pricingapillm.com/v1
• Model ID: uncensored

Copycurl https://api.pricingapillm.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "List the current prices for all models in your catalog"}]
  }'

Every request requires a valid Bearer token. The system rejects invalid keys immediately. You generate this key during signup via Google or email. Keep it secure.

Sending Your First Request

Send a standard chat completion payload to get text back. This works with any OpenAI-compatible client library.

Copyfrom openai import OpenAI

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

The model processes your prompt and returns a response. Input tokens cost $0.15 per million. Output tokens cost $0.50 per million. Errors do not consume credit. Refusals due to content policy are free. Check your balance after each call.

Streaming Responses

Enable real-time token generation by setting stream: true. This reduces perceived latency for users.

Copyimport OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.pricingapillm.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);

Token usage data appears in the final chunk. Monitor your prepaid balance closely. The API charges only for completed tokens. Streaming works with all standard parameters like temperature and top_p.

Function Calling Setup

Define tools in your request to enable structured output. The API supports tool_choice and JSON mode.

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)

Set response_format to {"type": "json_object"} for strict JSON. This ensures predictable parsing in your backend. Use this for data extraction or configuration generation. The uncensored model handles complex tool definitions well.

Context Window and Limits

Each request supports a 100,000 token context window. This includes both prompt and completion. Max output is 16,000 tokens. Set max_tokens to control output length.

Copycurl https://api.pricingapillm.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "List the current prices for all models in your catalog"}]
  }'

You get 300 requests per minute per key. Only 8 requests run simultaneously. The request body limit is 8 MB. Exceeding these limits triggers a 429 error. Plan your batch jobs accordingly.

Handling Errors and Limits

Check HTTP status codes to debug issues. 401 means invalid key. 402 indicates insufficient credit. 429 signals rate limit exhaustion.

Copyfrom openai import OpenAI

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

Credit never expires. You can top up with crypto anytime. Errors do not charge you. Use the support page for refund issues. Keep your API key safe to avoid 401s.