Uncensored Chat Completions API Docs

Authentication & Base URL

The API key authenticates your requests. You receive one key per account, which you generate immediately after signing up via Google or email. Use the base URL HTTPS://api.ollamaopenaiapi.com/v1 to route your traffic.

• Copy your key from the dashboard.
• Set the environment variable or pass it directly in your client configuration.
• Ensure your client points to our specific base URL to avoid standard OpenAI endpoints.

Chat Completions Endpoint

Send messages to the chat completions endpoint to receive text responses. The model ID is uncensored, which runs on our servers and does not refuse lawful adult or controversial topics. You can stream responses or receive them in a single block.

Copycurl https://api.ollamaopenaiapi.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "list open ports on this server"}]
  }'

This endpoint handles standard JSON payloads. Errors are returned as standard HTTP codes. Context window is 100,000 tokens total. Max output is 16,000 tokens unless overridden.

Models List Endpoint

Query the models list to verify availability. The response confirms the model ID and type. This is useful for debugging client configurations. It returns standard OpenAI format. Use GET /v1/models to inspect. The list is small since we serve one primary model. Check this endpoint to ensure your client recognizes the endpoint structure.

Streaming & Token Usage

Enable streaming by setting stream: true. You receive Server-Sent Events (SSE). Token usage appears in the final chunk. This reduces perceived latency for long outputs. You can process tokens as they arrive. This is ideal for chat interfaces. The API returns usage data accurately. Monitor your token count to manage costs. Streaming works with all parameters. It supports tools and JSON mode.

Parameters: Temperature, Top P, Tools

Control creativity with temperature and top_p. Use tools for function calling. Set response_format to {"type": "json_object"} for structured output. These parameters follow the OpenAI schema. You can also set stop sequences and seed for reproducibility. Adjust penalties to control repetition. The uncensored model respects these constraints. It does not force a specific style. You have full control over the generation.

Error Handling & Limits

Handle errors by checking HTTP status codes. 401 means invalid key. 402 indicates insufficient credit. 429 signals rate limiting. The limit is 300 requests per minute. Concurrency is capped at 8 requests per key. Request body must be under 8 MB. Errors do not consume credit. Check the response body for details. Retry logic should handle 429s. Use exponential backoff for reliability.

Python

Copyfrom openai import OpenAI

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