Claude openai compatible api: quickstart guide

Supported endpoints: chat and models

We provide two standard endpoints. Use POST /v1/chat/completions for text generation. Use GET /v1/models to verify the model ID.

Our service does not support embeddings, image generation, or fine-tuning. We focus strictly on chat completions. This keeps the infrastructure simple and cost-effective.

You can send text prompts and receive text responses. The system supports streaming via Server-Sent Events. You can also use function calling and JSON mode.

Authentication and base URL setup

Point your client at our base URL and provide your API key. The base URL is https://api.claudeopenaicompatibleapi.com/v1.

You get one key per account. If you need a new key, generate one and the old one stops working. No phone number is required for signup.

Set your API key in the environment variable or SDK config. The key grants access to your prepaid credit.

cURL

Copycurl https://api.claudeopenaicompatibleapi.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Convert this Python function to Rust"}]
  }'

Python

Copyfrom openai import OpenAI

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