Uncensored LLM API
Codex llm API for uncensored development
Get direct access to an uncensored LLM with a 100k context window, paying strictly for real usage with no monthly subscriptions or hidden tiers.
- 100,000 token context window
- $0.15 per 1M input tokens
- Crypto only, no card needed
curl https://api.codexllm.cc/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "uncensored",
"messages": [{"role": "user", "content": "Convert this JSON object to a YAML file."}]
}'from openai import OpenAI
client = OpenAI(base_url="https://api.codexllm.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.codexllm.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);- per 1M input tokens
- $0.15
- Output tokens / 1M
- $0.50
- token context
- 100,000
- trial credit
- $0.50
- requests per minute
- 300
Capabilities
Massive Context
Process long documents with a 100,000 token context window for deep analysis.
OpenAI Compatible
Drop-in replacement using standard endpoints, requiring only base URL and key changes.
True Uncensored
Answers without refusals for lawful adult, fiction, or security research topics.
Simple Pricing
Pay $0.15 per million input tokens and $0.50 per million output tokens.
Crypto Payments
Top up with USDT or USDC; credit never expires and bonuses apply.
Developer First
Get your key instantly via Google or email; no phone number required.
Setup guide
Create Account
Sign up with Google or email to receive your API key instantly.
Add Crypto
Top up with USDT or USDC to activate your prepaid credit balance.
Send Request
Point your SDK to our base URL and start generating uncensored text.
Built with Codex
Long-Form Coding
Pass entire codebases into the context window for accurate refactoring and analysis.
NSFW Story Gen
Generate adult content without unexpected filters blocking lawful creative writing outputs.
Agentic Workflows
Run complex multi-step agents that require long memory and low refusal rates.
Sensitive Research
Analyze controversial topics or security data without content policy interruptions.
What is the codex LLM?
Codex LLM is an uncensored large language model accessible via an OpenAI-compatible API, designed for developers who need direct access without content filters.
Large Context Handling
Process up to 100,000 tokens in a single request to maintain context across complex codebases.
Uncensored Output
Receive raw responses for lawful adult content, avoiding unnecessary refusals that disrupt creative or technical workflows.
Developer Integration
Connect your existing tools by pointing them to our base URL and using the standard chat-completions endpoint.
Migrate from OpenAI in three steps
Migrate from OpenAI in three steps
Update your base URL to HTTPS://api.codexllm.cc/v1 and swap in your new uncensored API key. The endpoint structure matches standard OpenAI protocols, so existing code works without refactoring.
- Generate a key via Google or email signup.
- Update your SDK configuration.
- Test with a simple chat request.
Switch to a 100k context window instantly.
From signup to first token
Get your first uncensored response in under two minutes using standard OpenAI tools.
- Sign up with Google or email; receive your API key instantly with no phone number required.
- Top up prepaid credit via USDT or USDC to begin usage.
- Configure your SDK with base_url HTTPS://api.codexllm.cc/v1 and the model id "uncensored".
- Send requests to /v1/chat/completions and receive streaming tokens directly.
The uncensored developer checklist
Verify your provider’s actual refusal behavior before committing.
- Confirm a 100k context window supports your long-running tasks.
- Ensure the base URL is OpenAI-compatible for easy SDK migration.
- Check that pricing is strictly usage-based without hidden tiers.
- Confirm no subscription fees lock you into unused capacity.
- Verify streaming support via SSE for real-time agent responses.
- Ensure the model allows lawful adult content without extra fees.
How we differ from aggregators
Direct access, zero routing overhead
We serve a single uncensored model. Aggregators route requests through multiple vendors, adding latency and variability to your outputs. Our architecture guarantees deterministic responses from one tuned model, not a patchwork of third-party endpoints.
| Feature | Typical Aggregator | Our API |
|---|---|---|
| Model Selection | Automatic routing | Single uncensored model |
| Pricing | Hidden markups | $0.15/$0.50 per 1M tokens |
| Context Window | Varies by vendor | 100,000 tokens guaranteed |
| Content Filter | Inconsistent refusals | Lawful NSFW allowed |
Developers ask about integration
Hooking Codex LLM into Claude Code works by pointing the CLI’s system prompt to our OpenAI-compatible base URL. This lets you leverage the CC framework with our unfiltered model. You can also integrate the API into existing agents by passing context through standard parameters like messages. Streaming via SSE provides real-time token updates, while JSON mode ensures reliable structure. The 100k context window handles large codebases without truncation. Use our SDKs to send requests directly to our endpoints for immediate, uncensored results.
Common questions
What is the codex LLM model?
It is an open-weight, uncensored large language model served via standard OpenAI-compatible endpoints. You access it through the /v1/chat/completions route with model id "uncensored". It is distinct from GPT, Claude, or other vendor offerings.
How much does the API cost per token?
Input tokens cost $0.15 per million, while output tokens are $0.50 per million. Errors do not consume credit. You pay strictly for real usage with prepaid credit that never expires.
Can I use this NSFW API with the official OpenAI SDK?
Yes. The API is fully compatible with official OpenAI SDKs. You only need to update the base_url to HTTPS://api.codexllm.cc/v1 and provide your API key. Streaming, tools, and JSON modes work identically.
Does the API support function calling?
Yes, it supports tools and tool_choice parameters. You can also enforce JSON mode using response_format. The API handles streaming via SSE, including token usage details in the final chunk.
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.
What is the maximum context window size?
The model supports a 100,000 token context window for combined prompt and completion. Maximum output per request is 16,000 tokens. If you omit max_tokens, the limit defaults to 2,048 tokens.
Get your API key
Sign up, copy the key, update the base URL. That is all.
