Developer Quickstart Guide

Installation and environment setup

Start by installing the standard OpenAI SDK for your language. Our API behaves exactly like the OpenAI API, so you do not need a custom library or complex routing layer. Just set your environment variable with the key you generated on our Get API key page. No phone number is required for signup, and you can start immediately with a free trial credit.

Configuring the base URL and headers

Point your SDK client to our specific base URL. This small change redirects traffic to our uncensored model instead of the standard provider. You only need to update the base URL and inject your API key into the headers. Everything else remains identical to your existing configuration.

Copyfrom openai import OpenAI

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

Copyimport OpenAI from "openai";

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

Making your first POST /v1/chat/completions request

Send a simple message to verify connectivity and response quality. The model ID is set to "uncensored" to ensure no content refusals for lawful adult use. You will receive a direct text response without the usual corporate filters. This endpoint handles both short queries and complex instructions efficiently.

Copycurl https://api.claudecodeprix.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Show me the pricing tiers for the standard plan."}]
  }'

Enabling streaming for real-time token output

Enable streaming by setting the stream parameter to true. You receive chunks of text as they are generated, which reduces perceived latency significantly. The final chunk contains the total token usage for accurate billing tracking. This approach works seamlessly with the official SDKs and standard SSE parsers.

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)

Using function calling and JSON mode

Define tools in your request to enable structured data extraction or automated actions. The model supports function calling and JSON mode for reliable parsing. You can specify parameters like temperature and top_p to control randomness. This flexibility allows you to build complex agents without leaving the OpenAI-compatible ecosystem.

Handling rate limits and errors

Monitor your usage to avoid hitting the 300 requests per minute limit. A 401 error indicates an invalid key, while 402 means your prepaid credit is exhausted. The context window allows up to 100,000 tokens for prompt and completion combined. Errors during generation are free, so you only pay for successful output tokens.