OpenAI Compatible API Documentation

Prerequisites: SDK and Base URL

Start by installing your preferred library and pointing it to our endpoint. The base_url is https://api.apicompatible.com/v1. This openai compatible API documentation confirms that standard libraries work immediately. You do not need a router or complex gateway setup. Change the URL and key, then run your existing code.

Authentication: Header and Key Format

Send your key in the Authorization header. Use the format Bearer your_api_key. Our API uses the standard openai compatible API key structure. Keys are generated instantly via Google or email login. Keep your key secure, as it grants access to your prepaid credit.

Chat Completions Endpoint

Post requests to /v1/chat/completions. Specify the model as uncensored. The API returns text responses directly. Use the following curl command to verify connectivity:

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

This openai SDK compatible approach ensures you get unrestricted text generation. The model handles complex prompts without unnecessary refusals for lawful content.

Streaming Responses with SSE

Enable streaming by setting stream: true. Responses arrive via Server-Sent Events (SSE). Token usage details appear in the final chunk. This openai compatible API documentation supports standard streaming protocols. Use this for real-time user experiences:

Copyfrom openai import OpenAI

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

Streaming reduces perceived latency significantly. It works seamlessly with standard client-side libraries.

Parameters: Temperature, Top-P, and Tools

Control generation with standard parameters. Set temperature for randomness or top_p for nucleus sampling. Enable tools for function calling. JSON mode is available via response_format. The uncensored model respects these constraints effectively:

Copyimport OpenAI from "openai";

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

These parameters allow fine-tuned control over output style. You can enforce strict JSON structures for programmatic use cases.

Limits: Rate Limits and Body Size

Each key allows 300 requests per minute. Concurrent requests are limited to 8 per key. The maximum request body size is 8 MB. The context window supports 100,000 tokens total. Handle 401 errors by checking your key. Resolve 402 errors by topping up credit. Manage 429 errors by implementing backoff logic.

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)