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

Uncensored LLM API

Codex api token for uncensored generation

Get a single uncensored LLM via our OpenAI compatible API with a 100,000 token context window and transparent codex API token pricing starting at $0.15 per million input tokens.

No credit card required for trial
Crypto top-ups only, no monthly fees
Prompts never used for training data

Start now View documentation

Test with one call

curl https://api.codexapitoken.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Summit the tax form for Q3 2024"}]
  }'

from openai import OpenAI

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

import OpenAI from "openai";

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

Key features

OpenAI Compatible

Drop-in replacement using standard endpoints and official SDKs for immediate integration.

100k Context Window

Process large documents with a combined prompt and completion limit of 100,000 tokens.

Streaming Support

Receive real-time token usage and content via Server-Sent Events with final chunk details.

Tool Use Ready

Enable function calling and structured JSON outputs for reliable programmatic interactions.

Privacy Focused

Simple email signup ensures your prompt data remains private and unused for training.

Simple Pricing

Pay only for real usage with prepaid crypto credit that never expires.

Setup guide

Create Account

Top Up Crypto

Add USDT or USDC to your balance with no minimum card requirement.

Send Requests

Point your client to our base URL and start generating uncensored text.

Common use cases

Roleplay Bots

Deploy consistent characters without unexpected content refusals for immersive storytelling experiences.

Creative Writing

Generate mature narratives and fiction with a model tuned for fewer restrictions.

Developer Testing

Test prompt efficiency and token usage with a straightforward, predictable pricing model.

API Integration

Connect existing applications to an uncensored backend using standard HTTP clients.

Cost examples: 100k tokens input + 16k output

Generating 16,000 output tokens from a 100,000-token prompt costs exactly $0.02. We charge $0.15 per million input tokens and $0.50 per million output tokens. This transparent per-token pricing ensures you pay only for actual usage. Errors and refusals incur zero charges, so your prepaid credit remains intact. There are no hidden subscription fees or monthly commitments to drain your account. Your budget stays predictable with every request.

Who uses it: roleplay bots, creative writers, developers; who it is not for: enterprises needing SLAs

This uncensored LLM API serves roleplay bots, creative writers, and developers who need raw, unfiltered text generation without content refusals.

Roleplay bots: Users get consistent character responses with no sudden topic changes.
Creative writers: Generate mature themes freely using the uncensored model.
Developers: Integrate via OpenAI-compatible endpoints for NSFW chatbot projects.

It is not for enterprises needing SLAs, as we lack guarantees on uptime or support response times.

Integrating the codex API token into your stack

Send requests to our OpenAI-compatible endpoint using standard libraries.

Direct SDK integration

Change the base URL to HTTPS://api.codexapitoken.com/v1 and inject your key. The model ID is "uncensored". Streaming via SSE returns usage data in the final chunk.

CLI and scripts

Use curl or Python scripts to pipe text in and out. No configuration files needed. Just set environment variables for the key and base URL.

Rate limits

You get 300 requests per minute. Keep payloads under 8 MB. Errors are free, so retry logic costs nothing.

Checklist for choosing an uncensored API provider

Verify strict input/output pricing to avoid hidden fees. Confirm a 100k token context window supports your data needs. Ensure the provider does not train on your prompts. Check for streaming support and function calling compatibility. Confirm crypto-only top-ups match your payment preferences.

Developers ask: token limits and usage tracking

Our uncensored LLM enforces a 100,000-token context window and a strict 16,000-token output limit per request. You can easily track usage via SessionWatcher or by inspecting the final streaming chunk for token counts. The codex API token supports function calling and JSON mode for precise billing. We do not charge for errors or refusals, ensuring you only pay for actual generation. This transparency helps developers manage costs without hidden fees or subscription traps.

From signup to first response in 5 steps

Click Get API key and sign in with Google or email.
Your unique key appears immediately; no phone number required.
Activate your $0.50 trial credit, valid for 7 days.
Point your SDK to our base URL with your key.
Send a POST request to /v1/chat/completions and receive uncensored text.

Frequently asked questions

What is the codex API token and how does it work?

It is an authentication string for our uncensored LLM. We charge per token usage. Prepaid credit covers requests. Errors are free. Use the standard OpenAI SDKs with our base URL to start sending text requests immediately.

Is the uncensored model free to use?

No. It costs $0.15 per million input tokens and $0.50 per million output tokens. You only pay for real usage. Errors do not cost credits. Credit never expires.

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.

Can I use the API for NSFW chatbot applications?

Yes. The model answers without filtering adult content. We only refuse sexual content involving minors. This makes it ideal for NSFW chatbot deployments and creative writing applications.

How do I top up my account balance?

Use USDT on TRC20 or USDC on Base. Minimum top-ups start at $20. You get bonus credit for larger amounts.

What is the maximum context window size?

The window is 100,000 tokens. This includes both prompt and completion. You can request up to 16,000 tokens per response. Set max_tokens to control output length.

Get your key instantly

Start now