Seedance API: Prompts and scripts over one endpoint

Prerequisites: Install the SDK

Before sending your first request, ensure you have the official OpenAI SDK for your preferred language installed. This API uses the standard chat/completions protocol, so any OpenAI-compatible client works. For Python, install the package via pip. For Node.js, use npm. You only need the client library; no extra dependencies are required for basic text generation or tool calling.

Authentication: Setting Your API Key

Authentication is handled via a simple Bearer token. Create an account on the Get API key page to receive your unique key. No credit card is required for the trial. Store this key in an environment variable or your application's config file. The key grants access to the uncensored model and is tied to your prepaid credit balance. Regenerate the key anytime from your dashboard if needed.

Sending a Chat Completion Request

Make a POST request to the base URL. The model field must be set to uncensored. Include your system prompt to define the role, and user messages for the content generation. This endpoint handles scriptwriting, captioning, and post-processing text tasks efficiently.

Copycurl https://api.seedanceapis.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."}]
  }'

Streaming Responses for Real-Time Output

For long scripts or real-time captioning, enable streaming by setting stream: true. The API returns a Server-Sent Events (SSE) stream of partial completions. This allows your application to display text as it is generated, improving perceived latency. Handle the stream chunks in your SDK to update the UI incrementally.

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)

Using Tool Calling for Structured Data

The API supports function calling to extract structured data from text or generate JSON output. Define your tool schemas in the request. The model will respond with structured arguments that your code can execute. This is ideal for post-processing steps where you need specific fields from generated scripts or metadata.

Copyfrom openai import OpenAI

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

Understanding Limits and Quotas

Watch for standard HTTP status codes. A 401 error means your API key is invalid or expired. A 402 error indicates insufficient prepaid credit; top up to continue. A 429 error signals rate limiting, capped at 300 requests per minute per key. The context window is 100,000 tokens total. Requests exceeding 8 MB will be rejected.

Copyimport OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.seedanceapis.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);