Stable Diffusion API: Prompts and scripts over one endpoint

Access the API using the base URL https://api.sdxlapi.com/v1. This endpoint is fully compatible with standard OpenAI SDKs and clients. To authenticate, pass your API key in the Authorization header of every request.

How to get a key: Sign up at the Get API key page with just an email and password. Your key is displayed immediately. No credit card is required for the trial. Keep your key secure; you can regenerate it anytime, which invalidates the old one.

Send a standard chat-completions request to generate text. The model ID is uncensored. This model is tuned to answer without content refusals for lawful adult use, making it ideal for creative prompt generation.

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

The API accepts JSON payloads with a messages array. It returns a text completion. You can pass system prompts to define the persona, such as a professional prompt engineer for image generation.

Use the official openai Python package. Configure the client with the base URL and your API key. This approach works for any OpenAI-compatible client.

Copyfrom openai import OpenAI

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

The response contains the generated text in response.choices[0].message.content. You can parse this output directly into your pipeline for captions or metadata extraction. The SDK handles JSON serialization and HTTP details automatically.

For JavaScript or TypeScript projects, use the openai npm package. Set the baseURL and apiKey in the configuration object. This ensures compatibility with existing OpenAI codebases.

Copyimport OpenAI from "openai";

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

The response structure mirrors the standard OpenAI format. Access the generated text via response.data.choices[0].message.content. This is useful for server-side prompt generation before sending images to a Stable Diffusion instance.

Support for Server-Sent Events (SSE) allows you to receive tokens as they are generated. This reduces perceived latency for long prompt scripts or detailed descriptions.

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)

Stream the response in your client application. Each chunk contains a partial message. Aggregate these chunks to reconstruct the final text. This is especially useful for real-time preview of generated prompts in a web interface.

Rate Limits: 300 requests per minute per key. Body Size: Max 8 MB. Context Window: 100,000 tokens total (input + output). This allows for long scripts or extensive prompt engineering.

Common Errors:

• 401 Unauthorized: Invalid or missing API key.
• 402 Payment Required: Insufficient prepaid credit.
• 429 Too Many Requests: Rate limit exceeded.

If you exceed limits, wait briefly or regenerate your key. All requests are text-only; no images, audio, or video are generated by this API.