Claude token pricing: openai compatible docs

Authentication and base URL setup

Start by pointing your SDK to our base URL and passing your API key in the authorization header. We require simple header-based authentication, so you do not need complex OAuth flows or SDK-specific initialization logic. Create an account via Google or email, then retrieve your key instantly from the dashboard. This key grants access to the single uncensored model identified as 'uncensored'. You can rotate keys if needed, but only one active key exists per account at any time. Ensure your client library is configured to send the Bearer token correctly before making your first request.

Chat completions endpoint structure

Send POST requests to /v1/chat/completions with a messages array containing your prompt and system instructions. The endpoint accepts standard OpenAI-compatible JSON payloads, allowing you to swap our service into Cursor, Windsurf, or custom scripts without rewriting your code. Specify the model as 'uncensored' to ensure you receive our specific uncensored LLM output. You can control creativity via temperature and top_p, or force deterministic results by setting temperature to 0. Requests are processed immediately, and you are billed only for actual token usage. Errors and refusals do not consume your prepaid credit.

Streaming responses and token usage

Enable streaming by setting stream to true in your request body. This returns Server-Sent Events (SSE) that update your UI in real time as tokens are generated. The final chunk of the stream contains the total token usage for the request, allowing you to track costs accurately without polling a separate usage endpoint. Streaming is ideal for long context windows up to 100,000 tokens. You can parse the delta content chunks to display text as it appears. This approach reduces perceived latency for users waiting for complex reasoning or long-form outputs.

Function calling and JSON mode

Use the tools parameter to define function schemas for function calling, or set response_format to json_object for strict JSON outputs. The model supports both structured data extraction and dynamic tool execution within the same context window. You can define multiple tools in a single request, and the model will return tool calls or direct text responses as needed. This flexibility makes the API suitable for building agents or automating workflows. Ensure your function definitions follow the OpenAI format to ensure compatibility with standard clients.

Rate limits and concurrency rules

Each API key allows 300 requests per minute and up to 8 concurrent requests simultaneously. The maximum request body size is 8 MB, which restricts the amount of data you can send in a single prompt. If you exceed these limits, you will receive a 429 status code indicating that you have hit the rate limit. You can monitor your usage via the streaming response or the /v1/models endpoint. These limits ensure stable performance for all users. Plan your batch processing accordingly to avoid throttling during peak usage times.

Error handling and refunds

Handle HTTP 401 errors by verifying your API key is correct and active. A 402 error indicates insufficient prepaid credit, requiring you to top up before further requests. Refunds are not issued for consumed credit, but mistakes like double charges are resolved via the Support page. Errors during processing do not deduct tokens from your balance. The model refuses content involving minors but allows other lawful adult themes. Check your account balance regularly to avoid unexpected interruptions in your workflow.

cURL

Copycurl https://api.claudetokenpricing.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "calculate the cost for 100k tokens"}]
  }'

Python

Copyfrom openai import OpenAI

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