Claude api proxy: quickstart and endpoints

Authentication and base URL

Connect by pointing your client to https://api.claudeapiproxy.com/v1 and sending your unique API key. You generate this key immediately after signing up with Google or an email address. The system issues one active key per account, so rotating keys is straightforward if needed. All requests require an Authorization: Bearer <key> header to verify your prepaid balance before processing tokens.

The chat-completions endpoint

Send your first message to the /v1/chat/completions endpoint using standard JSON formatting. This single endpoint handles all text generation tasks for our uncensored model. You must include the model field set to uncensored to ensure the correct inference path. The system charges only for the actual tokens processed in the prompt and completion.

Python SDK integration

Update the base URL in your existing OpenAI Python client to route requests through our infrastructure. This allows you to keep your current code structure while accessing unrestricted generation capabilities. Pass your API key via the environment variable or direct configuration. The client handles serialization and response parsing exactly like the standard provider.

Node SDK integration

Configure the Node.js SDK to point at our base URL while maintaining standard request structures. This ensures compatibility with libraries that expect specific OpenAI response schemas. You can pass parameters like temperature or top_p exactly as you would elsewhere. The response object contains the generated text and token usage details.

Streaming and token counts

Enable streaming by setting stream: true to receive real-time token chunks via Server-Sent Events. This reduces perceived latency for large responses and improves user experience in chat interfaces. The final chunk in the stream contains the total token usage for the request. You can parse these chunks incrementally without waiting for the full completion.

Limits, errors, and context window

The model supports a 100,000 token context window combining both input and output. You are limited to 300 requests per minute and 8 concurrent requests per key. Handle standard HTTP errors: 401 indicates an invalid key, 402 means you need more prepaid credit, and 429 signals rate limiting. Request bodies cannot exceed 8 MB, and max output is capped at 16,000 tokens unless specified otherwise.

cURL

Copycurl https://api.claudeapiproxy.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "get the current server time in ISO format"}]
  }'

Python

Copyfrom openai import OpenAI

client = OpenAI(base_url="https://api.claudeapiproxy.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

Copyimport OpenAI from "openai";

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

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)