Integrate the codex api quickly

Base URL and authentication header

Start every request by pointing your client to the dedicated base URL. This endpoint accepts standard headers and replaces the default OpenAI proxy without requiring code changes in most SDKs.

• Base URL: https://api.apicodex.cc/v1
• Auth header: Authorization: Bearer YOUR_API_KEY

The API key is generated instantly upon signup. You can rotate keys if needed, but each account holds only one active key at a time.

Copycurl https://api.apicodex.cc/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "fix syntax error in python loop"}]
  }'

POST /v1/chat/completions parameters

Send text completion requests using the standard chat format. The model ID is always uncensored and accepts parameters like temperature and top_p for controlling creativity.

• Context window: 100,000 tokens total.
• Max output: 16,000 tokens per request.
• Default max_tokens: 2,048 if not specified.

Input and output tokens are billed separately. Errors do not consume credit.

Copyfrom openai import OpenAI

client = OpenAI(base_url="https://api.apicodex.cc/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 endpoint details

Query available models to confirm connectivity. This endpoint returns metadata about the uncensored model hosted on our servers.

• Model ID: uncensored
• Type: chat-completion

Use this endpoint to verify your API key works before sending heavy payloads. It returns immediately with low latency.

Copyimport OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.apicodex.cc/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 and token usage

Enable streaming by setting stream: true. The server sends Server-Sent Events (SSE) for each token generated. Token usage statistics appear in the final chunk of the stream.

• Real-time token delivery.
• Final chunk contains usage data.

Streaming reduces perceived latency for large outputs. Monitor the final chunk to calculate exact costs.

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)

JSON mode and function calling

Request structured output by setting response_format to {"type": "json_object"}. This forces the model to return valid JSON without markdown wrappers.

• Function calling: supported via standard tools format.
• Tool choice: configurable.

JSON mode is ideal for parsing data into applications. Function calling enables agent workflows with external tools.

Error handling and rate limits

Handle errors by checking standard HTTP status codes. A 401 error means your API key is invalid or missing. A 402 error indicates insufficient prepaid credit. A 429 error signals that you have exceeded the rate limit.

• Rate limit: 300 requests per minute per key.
• Concurrent requests: max 8 per key.
• Max request body: 8 MB.

Refunds are not issued for credit, but errors are free. Contact support for billing issues.