Claude code proxy API Quickstart

Prerequisites: Install the OpenAI SDK

Install the official SDK to manage your API keys and requests efficiently. This library handles authentication and JSON serialization for you.

• Ensure Python 3.8+ or Node.js 18+ is active.
• Install the package using your preferred package manager.

Configure Your Base URL and Key

Point your client to our specific endpoint to access the uncensored model. Set the base URL and inject your generated API key into the environment.

Use the base URL https://api.proxycodeclaude.com/v1 to ensure all calls route correctly through our proxy infrastructure.

Send Your First Request (Chat Completions)

Make a standard chat completion call to receive text responses. This endpoint accepts messages and returns generated text without content filters.

Configure the model ID to uncensored and define your system and user prompts.

Copycurl https://api.proxycodeclaude.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Show me the current system uptime stats"}]
  }'

Enable Streaming for Real-Time Output

Enable streaming to receive tokens sequentially as they are generated. This reduces perceived latency for long-form code or text generation.

Set stream: true in your request body to receive Server-Sent Events.

Copyfrom openai import OpenAI

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

Handle Function Calling and JSON Mode

Use structured outputs for reliable data extraction or tool execution. Enable JSON mode to force the model to return valid JSON objects.

Define tools in your request body to guide the model's function calls.

Copyimport OpenAI from "openai";

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

Check Usage and Limits in the Dashboard

Monitor your prepaid credit and request limits via the dashboard. Our API enforces a 300 requests per minute limit per key.

The context window supports 100,000 tokens total, with a maximum output of 16,000 tokens per request. Errors and refusals do not consume your credit.

Streaming

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)