AI Coding API Quickstart Guide

Authentication Setup

Start by creating an account at Get API key. You only need an email and password; no card is required to start. Upon signup, you receive a single API key immediately. This key authenticates all requests to the base URL: https://api.codingllmapi.com/v1.

Keep your key secure. You can regenerate it at any time from your dashboard, which instantly invalidates the previous key. The model identifier to send in your requests is uncensored. This is an open-weight model running on our own servers, not a proxy for GPT, Claude, or Gemini.

First Request

Send a standard chat completion request using the OpenAI-compatible format. The API accepts messages with a role (user/assistant/system) and content. It returns text output optimized for code generation without filtering lawful adult or controversial topics (except for minors).

• Base URL: https://api.codingllmapi.com/v1
• Endpoint: POST /v1/chat/completions
• Model: uncensored

Copycurl https://api.codingllmapi.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Write a blunt product review of a cheap VPN."}]
  }'

Python SDK Integration

Use the official OpenAI Python SDK. Point the client to our base URL and supply your API key. The SDK handles the request format automatically. This approach works for simple text generation or building more complex agent loops.

Ensure you are using a recent version of the openai package. The client will handle JSON serialization and HTTP headers correctly for our endpoint.

Copyfrom openai import OpenAI

client = OpenAI(base_url="https://api.codingllmapi.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 SDK Integration

Use the official openai Node.js package, not the Anthropic or Google-specific SDKs. Configure the base URL to point to our service. This ensures compatibility with the OpenAI-compatible request structure we serve.

Install the package via npm install openai. Initialize the client with your key and the custom base URL. This method is reliable for server-side coding agents that need to generate code snippets or analyze repositories.

Copyimport OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.codingllmapi.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 Code Responses

For real-time feedback, enable streaming by setting stream: true. The API returns Server-Sent Events (SSE). Each chunk contains partial token outputs, allowing your agent to display code as it is generated. This reduces perceived latency for long code blocks.

Handle the stream events to accumulate the final response. The model continues generating until it reaches the context limit or the max_tokens parameter.

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)

Limits and Errors

Watch these limits to avoid interruptions. You get 300 requests per minute per key. The maximum request body size is 8 MB. If you exceed the rate limit, you receive a 429 error. If your prepaid credit runs out, you get a 402 error. An invalid or revoked key returns 401.

The context window is 100,000 tokens total (prompt + completion). If your prompt plus generated code exceeds this, the model stops. Plan your input tokens carefully to leave room for the output.