GPT sem filtro API Documentation

Base URL and Authentication

Point your client to https://api.gptsemfiltro.com/v1 and send your key in the Authorization header. This base URL works with the official OpenAI SDKs and any OpenAI-compatible client. You get one active key per account, which you can replace if needed. Errors and refusals do not consume your balance, so you can test freely. The model ID to send is uncensored, an open-weight model tuned for unrestricted answers.

Copycurl https://api.gptsemfiltro.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "List the steps to compile a C program"}]
  }'

Chat Completions Endpoint

Send messages to POST /v1/chat/completions and receive text responses. This endpoint supports temperature, top_p, stop, seed, presence_penalty, and frequency_penalty. The model handles a 100,000 token context window, combining prompt and completion. Max output is 16,000 tokens per request, or 2,048 if you omit max_tokens. You can enable JSON mode with response_format set to json_object for structured data. Function calling is also supported via the tools parameter.

Copyfrom openai import OpenAI

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

Streaming with Server-Sent Events

Enable streaming by setting stream: true in your request. The API returns Server-Sent Events (SSE) for real-time token delivery. The final chunk includes the complete token usage statistics for the request. This method reduces perceived latency for long responses, which is useful when generating extended narratives or code. You can stop the stream early if the client disconnects. The model does not refuse content based on standard filters, so expect consistent output even for edge cases.

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)

Function Calling and JSON Mode

Use the tools parameter to define functions the model can call. This allows for structured interactions where the model outputs arguments for your backend logic. You can also force JSON output using response_format for strict parsing. Both features work with the uncensored model without extra cost. Define your tool schema in the request body, and the model will respond with function calls when appropriate. This is ideal for building agents or automating workflows that require precise data extraction.

Rate Limits and Quotas

Each API key is limited to 300 requests per minute and 8 concurrent requests. The maximum request body size is 8 MB. If you exceed these limits, you will receive a 429 status code. Authentication failures return 401, and insufficient credit returns 402. Your prepaid credit is charged by real token usage, and errors are free. The 100,000 token context window allows for extensive conversation history without immediate truncation. Monitor your usage via the dashboard to manage your budget effectively.

Pricing and Top-Up

Input tokens cost $0.15 per 1M, and output tokens cost $0.50 per 1M. You can top up with USDT (TRC20) or USDC (Base) in whole amounts from $20 to $500. Bonus credit applies: +5% from $50, +10% from $100, and +15% from $200. Credit never expires, and you can add funds whenever needed. The trial credit of $0.50 is available for new accounts. No subscriptions or monthly fees are required, making it a transparent option for developers.

Node.js

Copyimport OpenAI from "openai";

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