API Documentation

Authentication and Base URL

Your API key authenticates every request. Send it in the Authorization header as a Bearer token. The base URL points directly to our endpoint.

Retrieve your key instantly from the dashboard after signing up with Google or email. No phone number verification is required.

The endpoint is https://api.unsupportedcodexauthmethodapikey.com/v1. Use this URL for all HTTP requests.

Copycurl https://api.unsupportedcodexauthmethodapikey.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Parse the JSON string in the request body"}]
  }'

POST /v1/chat/completions

Send your prompt to this endpoint. The model ID is always "uncensored". The API returns text completions based on your input.

Include your system prompt to define behavior. The model answers without content refusals for lawful adult use.

Configure parameters like temperature and top_p to control creativity. Use json_object for structured outputs.

Copyfrom openai import OpenAI

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

GET /v1/models

Query available models. This endpoint lists the single uncensored model ID. It confirms your API key is valid.

Use this to verify connectivity before sending heavy payloads. The response contains metadata about the model.

Only one model is available. It is an open-weight model tuned for freedom and privacy.

Copyimport OpenAI from "openai";

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

Parameters and Streaming

Enable streaming with stream: true. Receive tokens via Server-Sent Events (SSE). Token usage details appear in the final chunk.

Set max_tokens to limit output. Default is 2,048 tokens if unspecified. Max output is 16,000 tokens per request.

Use stop sequences to halt generation. The context window is 100,000 tokens total.

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)

Error Handling

Handle errors gracefully. A 401 status means your key is invalid. A 402 status indicates insufficient credit.

A 429 status signals rate limiting. You are limited to 300 requests per minute. Check the Retry-After header.

Refusals due to content limits return 400. Errors in request format return 400. No billing is charged for errors.

Limits and Context Window

The context window is 100,000 tokens. This includes both prompt and completion. Request body size is max 8 MB.

Concurrent requests are limited to 8 per key. Rate limit is 300 requests per minute. Exceeding these returns 429.

Credit never expires. Errors are free. Pay only for real token usage. Top up with crypto anytime.