Quickstart: Uncensored LLM API

Install and Configure the SDK

Start by installing the official OpenAI SDK for your language. Our API works with any standard OpenAI-compatible client, so you do not need a custom library. Set your base_url to HTTPS://api.ollamaapipricing.com/v1 and provide the API key from your account dashboard. The model identifier is uncensored. This single model handles all your text generation needs without routing logic.

Authentication requires a valid key. If you see a 401 error, your key is invalid. If you see a 402 error, you have no credit. Top up with USDT or USDC to continue. The base URL ensures your requests reach our servers directly.

Send Your First Request

Make a POST request to /v1/chat/completions with your prompt. The model responds with text only. You can control the response length using max_tokens. The default max output is 2,048 tokens unless you specify otherwise. The context window supports up to 100,000 tokens for both prompt and completion combined.

Use the following example to verify connectivity and response quality. Adjust the messages array to fit your use case.

Copycurl https://api.ollamaapipricing.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "calculate total cost for 100m tokens"}]
  }'

Enable Streaming and Tools

Streaming returns tokens via Server-Sent Events (SSE). The final chunk contains the total token usage statistics. This allows you to display responses in real-time while tracking costs accurately. Function calling is also supported. You can define tools in your request and let the model choose which to use.

Set stream to true in your SDK configuration. The response will arrive as a series of chunks. Handle each chunk appropriately in your application logic. This approach reduces perceived latency for users waiting for long responses.

Copyfrom openai import OpenAI

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

Handle JSON Mode Responses

Use response_format set to {"type": "json_object"} to enforce structured output. This is useful for parsing data or generating code. The model adheres to the JSON schema provided in the prompt. If the output is invalid, the request may fail or return malformed JSON.

Combine JSON mode with function calling for robust tool integration. Ensure your prompts clearly define the expected structure. This reduces the need for post-processing errors. The API does not validate the JSON structure itself, so rely on the model's training.

Copyimport OpenAI from "openai";

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

Understand Token Usage

Pricing is $0.15 per 1M input tokens and $0.50 per 1M output tokens. Errors and refusals are free. Credit is charged only for successful token generation. Prepaid credit never expires. This model is uncensored for lawful adult use, meaning fewer refusals for standard topics.

Monitor your usage via the final SSE chunk or the API response headers. Keep track of your balance to avoid service interruption. You can top up anytime with crypto. The system is transparent about costs per request. No hidden fees apply.

Limits and Errors

Rate limits are 300 requests per minute and 8 concurrent requests per key. The request body size limit is 8 MB. If you exceed these limits, you will receive a 429 error. Use exponential backoff to handle retries. Each account has one active key. Generating a new key replaces the old one immediately.

Handle errors gracefully. A 401 error means the key is invalid. A 402 error means insufficient credit. A 429 error means you are rate-limited. The API does not offer SLAs or uptime guarantees. Plan your retries accordingly.

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)