Suno API: Prompts and scripts over one endpoint

Authentication & Base URL

Our API uses standard OpenAI authentication. You only need an API key, which you generate on the Get API key page. No phone number or credit card is required to start; every new account receives $0.50 in trial credit valid for 7 days.

Set the base URL to https://api.sunoapis.com/v1 in your client configuration. The model identifier you must send in every request is uncensored. This is an open-weight model hosted on our own GPU servers, tuned for lawful adult and creative use without the refusals typical of major providers.

• Base URL: https://api.sunoapis.com/v1
• Model ID: uncensored
• Auth Header: Authorization: Bearer YOUR_API_KEY

First Request

Get started immediately with a standard chat completion request. The endpoint accepts JSON payloads containing your system prompt, user instructions, and any metadata needed for your text-to-video or AI music pipeline.

This is a text-only API. It does not generate audio, video, or images; it generates the text instructions that drive those tools. Use this endpoint to script scenes, write lyrics, or extract structured data from your creative assets.

Copycurl https://api.sunoapis.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Write a blunt product review of a cheap VPN."}]
  }'

Python SDK

Integrate the API into your Python applications using the official OpenAI SDK. Since we are OpenAI-compatible, you can reuse your existing code by simply changing the base URL and API key.

This approach works for generating scripts for video generation tools or writing metadata for music APIs. Ensure your SDK version is up to date to support the streaming and function calling features described in the next sections.

Copyfrom openai import OpenAI

client = OpenAI(base_url="https://api.sunoapis.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 SDK

For JavaScript/TypeScript developers, the @anthropic-ai/sdk or official openai package works with minor configuration adjustments. Point your client to our base URL and use the uncensored model ID.

This allows you to build server-side text generation for your creative apps. You can use this to preprocess user inputs or post-process generated scripts before sending them to your audio or video generation endpoints. The API returns standard JSON responses compatible with modern web frameworks.

Copyimport OpenAI from "openai";

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

For long scripts or detailed metadata, use Server-Sent Events (SSE) to receive tokens in real-time. Set stream: true in your request body. The API will send a series of chunks, allowing you to display text as it is generated.

This is particularly useful for interactive creative tools where users want to see the prompt evolving as it is written. Each chunk contains only the delta text, so you must concatenate the fragments to reconstruct the full response.

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)

Limits, Errors & Context

Each account is limited to one API key, which can be regenerated at any time (revoking the old one). You are allowed 300 requests per minute per key, with a maximum request body size of 8 MB.

Common errors include 401 for invalid keys, 402 if you have insufficient prepaid credit, and 429 for rate limits. The model supports a 100,000-token context window for both input and output combined.

Content Note: The model does not refuse controversial or adult topics, but it strictly blocks sexual content involving minors in all requests.