Integration Guide

Quickstart: Your first request

The API is an openai compatible API that mirrors the Chat Completions structure. You send text, receive text. No extra endpoints for embeddings or audio clutter your workflow. Start by pointing your client to our base URL.

• Base URL: HTTPS://api.filtrosemia.com/v1
• Model ID: "uncensored"

Replace your existing base URL in your SDK configuration. The endpoint handles everything from roleplay to translation without the usual filters.

Copycurl https://api.filtrosemia.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "check balance"}]
  }'

Authentication and Headers

Pass your API key in the standard Authorization header. We use a single active key per account for simplicity. If you need a new one, generate it from your dashboard.

• Header: Authorization: Bearer YOUR_API_KEY
• No OAuth flows or refresh tokens to manage.

Keep your key secure. It grants direct access to your prepaid credits. Errors like 401 Unauthorized mean the key is missing or invalid.

Copyfrom openai import OpenAI

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

Chat Completions Endpoint

Send messages to POST /v1/chat/completions. The model supports standard parameters like temperature, top_p, and stop sequences. It is an uncensored model tuned for adult and creative content.

• Supports json_object response format.
• Accepts tool definitions for function calling.

Requests are processed sequentially within your rate limits. Ensure your payload stays under 8 MB.

Copyimport OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.filtrosemia.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 (SSE)

Use Server-Sent Events for real-time token delivery. This reduces perceived latency for long outputs. The final chunk contains the complete token usage statistics.

• Set stream: true in your request.
• Parse the SSE stream in your client.

Streaming works identically to the standard OpenAI SDK behavior. You handle the chunks as they arrive.

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)

Context Window and Limits

The model supports a 100,000 token context window. This allows heavy workloads with long histories. Max output is 16,000 tokens per request.

• Default max output: 2,048 tokens.
• Rate limit: 300 requests per minute.

Exceeding limits triggers a 429 Too Many Requests error. Adjust your concurrency to stay within bounds. 8 concurrent requests per key are allowed.

Error Handling and Tokens

Handle standard HTTP errors. 402 Payment Required means your prepaid credit is exhausted. 429 indicates rate limiting. 401 signals authentication issues.

• Errors are free. You only pay for successful token usage.
• Refusals due to content policy are also free.

Check the response body for detailed error messages. Use these to adjust your retry logic or credit top-up frequency.