API Documentation

Base URL and Authentication

Use https://api.botchataiunfiltered.com/v1 as your base URL. Pass your API key in the Authorization header as a bearer token. This works with any standard OpenAI SDK or client by updating the base_url configuration. No phone number is required for signup, and keys are issued immediately after Google or email authentication.

Copycurl https://api.botchataiunfiltered.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "set max tokens to fifty"}]
  }'

Each account supports one active key. If you generate a new key, the old one becomes invalid instantly. The system charges only for real token usage, so errors and refusals do not consume your prepaid credit.

First Request: Chat Completions

Send a POST request to /v1/chat/completions with the model ID set to uncensored. This endpoint handles text-in, text-out interactions without content refusals for lawful adult use. The model is an open-weight variant tuned for unrestricted responses, distinct from GPT or Claude.

Copyfrom openai import OpenAI

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

Request bodies are limited to 8 MB. The system supports function calling and JSON mode for structured outputs. You can adjust parameters like temperature and top_p to control creativity. Every request is billed based on actual input and output tokens processed.

List Available Models

Query GET /v1/models to retrieve metadata about the serving environment. This endpoint confirms the available model IDs, such as uncensored, and their basic properties. It helps verify connectivity before sending heavy payloads.

Copyimport OpenAI from "openai";

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

Unlike multi-vendor gateways, we serve a single model. This ensures consistent behavior across all requests. There is no model routing or fallback logic to complicate your debugging process. The response includes standard fields compatible with OpenAI client libraries.

Streaming and SSE

Enable streaming by setting stream: true in your request. The API returns Server-Sent Events (SSE) for real-time token delivery. Token usage statistics appear in the final chunk of the stream, allowing you to track costs dynamically.

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)

Streaming reduces perceived latency for long responses. You can parse partial tokens to display text incrementally. This approach works well for chat interfaces or real-time data visualization. The stream ends when the model completes or the context window fills.

Parameters: Temperature, Top P, and JSON Mode

Control generation behavior using temperature, top_p, and stop sequences. Set response_format to {"type": "json_object"} for strict JSON output. These parameters allow fine-tuning of the uncensored model's creativity and structure.

Copycurl https://api.botchataiunfiltered.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "set max tokens to fifty"}]
  }'

The model supports tool use via tool_choice and tools. You can also set a seed for reproducible outputs. Presence and frequency penalties help reduce repetition. Adjust these values to match your specific use case, from creative writing to structured data extraction.

Rate Limits, Errors, and Context Window

The context window supports 100,000 tokens for prompt and completion combined. Max output is 16,000 tokens per request, or 2,048 if unspecified. Rate limits allow 300 requests per minute and 8 concurrent requests per key.

Handle errors by checking HTTP status codes. A 401 indicates an invalid key. A 402 means your prepaid credit is exhausted. A 429 signals that you have hit the rate limit. Refunds are not issued for credit, but billing errors are resolved via the Support page. Credit never expires.