Claude tokens: Quickstart Guide

Authentication and Base URL

Your API key authenticates every request. Use the base URL HTTPS://api.tokensclaude.com/v1 and set the model to "uncensored". This works with any OpenAI-compatible client by changing the base_url.

Sending Your First Request

Send a POST request to /v1/chat/completions to generate text. The API returns JSON with the model's response. Use the following example to test your key immediately.

Copycurl https://api.tokensclaude.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "List the current token pricing tiers for this model"}]
  }'

SDK Examples for Python and JavaScript

Use the official OpenAI SDKs for Python or Node.js. Set the base URL to our endpoint and the model to "uncensored". This ensures your existing code works without major changes. Use the Python example to start generating text in your scripts.

Copyfrom openai import OpenAI

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

Use the Node.js example for web applications or server-side rendering.

Copyimport OpenAI from "openai";

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

Enable streaming by setting stream=true. The API returns Server-Sent Events (SSE) for real-time token delivery. Token usage details appear in the final chunk. This reduces perceived latency for long outputs.

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)

Function Calling and JSON Mode

Use function calling for structured tool integration. Set response_format to json_object for strict JSON output. Support parameters like temperature, top_p, and stop sequences. These features allow precise control over model behavior.

Understanding Token Usage and Limits

Each key allows 300 requests per minute and 8 concurrent requests. The context window is 100,000 tokens total. Errors and refusals incur no charge. Credit never expires, so you can pause usage without losing funds. Check your balance via the dashboard.