Uncensored LLM API

Codex api for uncensored generation

Get a dedicated uncensored LLM via our OpenAI-compatible codex API endpoint, featuring a 100k context window and transparent prepaid token billing for developers who need reliable text generation without refusals.

100k token context window
$0.15 per 1M input tokens
Crypto only billing

Claim trial key View documentation

per 1M input tokens: $0.15
Output tokens / 1M: $0.50
token context: 100,000
trial credit: $0.50
requests per minute: 300

Test with one call

curl https://api.apicodex.cc/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "fix syntax error in python loop"}]
  }'

from openai import OpenAI

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

import OpenAI from "openai";

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

Features included

Uncensored Model

We run one dedicated uncensored model tuned to answer without content refusals.

OpenAI Compatible

Use standard SDKs by changing the base URL and providing your API key.

Long Context

Process up to 100,000 tokens for prompt and completion combined in requests.

Streaming Support

Receive real-time tokens via SSE with usage metrics included in the final chunk.

JSON Mode

Force structured output using the response_format parameter for reliable data parsing.

No Subscription

Pay only for what you use with prepaid credit that never expires.

Setup process

Create Account

Top Up

Add crypto credit via USDT or USDC to start using the API.

Integrate

Point your OpenAI SDK to our base URL and send requests.

Use cases

Creative Writing

Generate adult or controversial fiction without unexpected content filters blocking your flow.

Code Analysis

Process large codebases within the 100k context window for deep analysis.

Data Extraction

Extract structured JSON from unstructured text using our reliable JSON mode.

Research Assistant

Ask uncensored questions about security or niche topics without standard refusals.

Who runs this API and when to skip it

The uncensored LLM runs on our dedicated servers, not via third-party routing or vendor aggregation.

Use it for NSFW chatbot content, creative writing, and security research where refusals matter.
Skip it if you need image generation, audio processing, or embedding vectors.

We do not offer SLA guarantees or HIPAA compliance. This is a direct API endpoint for developers who want raw, unfiltered model access without corporate tier restrictions.

6 checks to pick the right uncensored provider

Verify token pricing, context limits, and billing transparency immediately. Compare input rates against output costs to ensure realistic budgeting. Confirm the uncensored model handles adult content without hidden refusals. Check for prepaid credit expiry and minimum top-up amounts. Ensure the API key supports streaming and JSON modes. Avoid providers routing traffic through multiple vendors without clear latency guarantees.

codex API: concrete use cases for developers

The codex api delivers consistent uncensored generation via a standard POST /v1/chat/completions endpoint with 100k context windows.

NSFW Chatbot Backend

Deploy an nsfw chatbot without corporate refusal logic by setting the model ID to uncensored and passing user prompts directly to the dedicated server.

Deep Context Analysis

Process massive codebases using the 100,000-token limit for entire project reasoning without splitting files or losing earlier context.

Unhinged Creative Writing

Generate uncensored narratives with temperature adjustments for creative freedom, avoiding standard safety filters that block adult themes.

Worked token math: exactly what you pay

You pay precisely for tokens consumed. Input costs $0.15 per million tokens, while output runs $0.50 per million. A 50k token prompt with 2k output tokens totals $0.0075 in input fees and $1.00 in output fees. Errors incur zero charges. Billing uses prepaid crypto credit that never expires. You only fund what you actually use.

Migrate from OpenAI or Grok in 3 steps

Switch your base URL and API key to get started immediately.

Generate a new key on our signup page.
Update your base_url to https://api.apicodex.cc/v1.
Set model to uncensored in your client.

Our OpenAI-compatible endpoint handles streaming, JSON mode, and function calling exactly as you expect. Stop paying for refusals and start generating content without constraints today.

Developers ask: latency, limits, and logs

Is the codex API fast and reliable?

Yes. We run a single, dedicated uncensored LLM on our own servers, not a routed cluster. This guarantees stable 100k context windows without the erratic TTFT spikes common in shared enterprise models. You get straightforward limits: 300 requests per minute per key, with a strict 8 MB request body cap. No hidden throttling occurs when traffic spikes, ensuring your integration stays predictable during heavy usage cycles.

Common questions

What is the codex API uncensored model?

It is a single, hosted large language model designed to answer without content refusals for lawful adult use. It is not GPT, Claude, or any other vendor model. Text in, text out via standard endpoints.

Does it support function calling and JSON mode?

Yes, it supports function calling with tool_choice and JSON mode via response_format json_object. You can also use streaming via SSE, where token usage appears in the last chunk, ensuring precise tracking.

How much context can the uncensored LLM handle?

It handles a 100,000 token context window for prompt and completion combined. Max output is 16,000 tokens per request, or 2,048 if you do not set max_tokens explicitly in your API call.

Which payment methods do you accept?

Crypto only: USDT on TRC20 or USDC on Base, any whole amount from $20 to $500. Bonus credit applies from $50.

How do I top up my balance?

Top up with crypto only: USTRC20 or USDC on Base. Any whole amount from $20 to $500 works. You get +5% bonus from $50, +10% from $100, and +15% from $200 added to your balance.

What are the rate limits per key?

You get 300 requests per minute and 8 concurrent requests at the same time per key. The request body limit is 8 MB. One active key per account; a new key replaces the old one.

Get your API key

Claim trial key