LLM-api-key-proxy API Reference

Authentication and Base URL

The llm-api-key-proxy uses standard API key authentication. You pass your key in the Authorization header. Sign up with Google or email to get your key instantly. No phone number is required for the trial. Use this base URL for all requests: https://api.llmapikeyproxy.com/v1. Your key is tied to one account. A new key replaces the old one immediately.

First Request

Send a POST request to /v1/chat/completions. The model ID is always uncensored. This is a text-only API. You get text in and text out. No embeddings or images are supported. The model answers without refusals for lawful adult content. Check the limits before sending bulk requests.

Copycurl https://api.llmapikeyproxy.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "What is the current date?"}]
  }'

Python SDK Integration

Use the official OpenAI Python library. Set the base URL to our endpoint. Pass your API key. The client handles serialization automatically. You can stream results or get full responses. The model ID remains uncensored in all calls. This ensures compatibility with existing codebases. You only change the URL and key.

Copyfrom openai import OpenAI

client = OpenAI(base_url="https://api.llmapikeyproxy.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 SDK Usage

Initialize the OpenAI client with your custom base URL. Pass the API key. The request format matches the standard OpenAI schema. You can use the async/await pattern for clean code. The response includes the generated text and token usage. This works with any Node.js environment. It is a simple drop-in replacement.

Copyimport OpenAI from "openai";

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

Enable streaming by setting stream: true. The API returns data chunks via Server-Sent Events (SSE). Each chunk contains part of the response. The final chunk includes the total token usage. This reduces perceived latency for long outputs. You can process tokens in real-time. This is useful for interactive applications.

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 Error Handling

Rate limits are 300 requests per minute per key. Concurrent requests are capped at 8. The request body must be under 8 MB. A 401 error means your key is invalid. A 402 error indicates insufficient credit. A 429 error signals rate limiting. The context window is 100,000 tokens. Output maxes at 16,000 tokens. Errors and refusals do not consume credit.