API documentation for developers

Base URL and authentication

The base URL is HTTPS://api.ollamaapiurl.com/v1. You authenticate by passing your unique API key in the Authorization header. This key acts as your credential for all requests. Retrieve it from your dashboard immediately after signup.

• Keep your key secure. It grants full access to your prepaid credit.
• Generate a new key anytime from the settings page.

Our API key system is simple. One active key per account ensures clear tracking. If you lose access, regenerate it instantly. No phone number verification blocks your entry.

First request

Send your first prompt using standard HTTP. The endpoint accepts text input and returns text output. This method works with any HTTP client library you prefer.

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

The response includes token usage. You pay only for tokens processed. Errors do not consume your prepaid balance. This transparency lets you control your spend exactly.

Python SDK integration

Use the official OpenAI Python library. Point it to our base URL. Set the model id to uncensored. This ensures you get the uncensored behavior without local setup hassles.

Copyfrom openai import OpenAI

client = OpenAI(base_url="https://api.ollamaapiurl.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 library handles retries and formatting. You get structured JSON or raw text. Streaming is supported too. This approach keeps your code clean and maintainable.

Node SDK setup

Install the openai package. Configure the base URL to point to our service. Set the API key from your environment. This setup mirrors the Python configuration closely.

Copyimport OpenAI from "openai";

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

Node developers get consistent behavior. The model responds to prompts instantly. You can integrate this into any web server or background worker. No complex routing logic needed.

Streaming responses

Enable streaming by setting stream to true. The API returns chunks as they generate. This improves perceived latency for users. You can display tokens as they appear.

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)

The final chunk contains the total token count. Use this for billing verification. Streaming works with all parameters. It supports function calls too. Your users see progress in real time.

Limits, errors, and context

Your context window spans 100,000 tokens total. This includes both prompt and completion. You can output up to 16,000 tokens per request. The rate limit allows 300 requests per minute. Concurrent requests cap at eight per key.

Common errors include 401 for invalid keys. A 402 error means your prepaid credit is exhausted. A 429 response signals you hit the rate limit. Check your dashboard to top up via crypto. Credits never expire. Mistakes like double charges are fixed via support.