Adultgpt API Quickstart

Base URL and Authentication

Start requests immediately by pointing your client to our base URL and injecting your unique API key.

Use https://api.adultgpt.cc/v1 as the server address. Authentication relies on a single bearer token generated during signup via Google or email. You receive one active key per account; issuing a new key invalidates the previous one. This approach keeps your integration simple and eliminates the need for complex OAuth flows or session management.

The system charges only for real token usage, so errors do not drain your balance. You can top up using USDT on TRC20 or USDC on Base, with amounts ranging from $20 to $500.

Chat Completions Endpoint

Send text inputs and receive generated responses via the standard chat completions endpoint.

Use the POST /v1/chat/completions route with the model identifier set to uncensored. This endpoint handles all text generation tasks without requiring additional configuration for routing or model selection. You can define the conversation history using the messages array, which supports both user and assistant roles.

The model processes prompts up to a 100,000-token context window. Outputs are limited to 16,000 tokens per request, or 2,048 tokens if you do not specify a maximum.

Copycurl https://api.adultgpt.cc/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "List my current usage stats"}]
  }'

Model Listing and Parameters

Query available models and configure generation behavior using standard parameters.

Call GET /v1/models to verify the service status and view available identifiers. You can fine-tune responses using temperature, top_p, stop, and seed. These settings allow you to control creativity and reproducibility. The API also supports JSON mode via response_format and function calling for tool integration.

All parameters follow the standard OpenAI schema, ensuring your existing code works without modification. You can enforce strict JSON structures for programmatic applications or allow more flexible creative writing.

Copyfrom openai import OpenAI

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

Streaming and Function Calling

Receive token-by-token updates and integrate external tools efficiently.

Enable streaming by setting the stream flag to true. The API returns Server-Sent Events (SSE) containing partial responses. The final chunk includes the total token usage, allowing you to track costs in real-time. Function calling works seamlessly with the tools and tool_choice parameters.

This setup is ideal for chat interfaces requiring low latency. You can process user input, call external functions, and append results to the conversation history dynamically.

Copyimport OpenAI from "openai";

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

Error Handling and Limits

Manage errors and rate limits programmatically to ensure robust application performance.

Handle HTTP status codes appropriately. A 401 error indicates an invalid or expired API key. A 402 error signals insufficient prepaid credit; you must top up via crypto to resume service. A 429 error means you have exceeded the 300 requests per minute limit.

Each key allows eight concurrent requests. The request body size is capped at 8 MB. Errors and refusals do not consume tokens, so failed requests are free. This structure ensures predictable billing even during high-traffic periods.

Context Window and Constraints

Optimize your prompts within the 100,000-token context window and 16,000-token output limit.

The model processes the entire conversation history within the context window. Efficient prompt engineering maximizes the available space for new inputs. You can adjust the max_tokens parameter to control output length, defaulting to 2,048 tokens if unspecified.

The system refuses content involving minors but allows lawful adult, fictional, and controversial topics. This constraint applies consistently across all requests. Use the seed parameter for reproducible outputs during testing.

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)