codexapipricing.com

Uncensored LLM API

Codex api pricing for uncensored developers

Access a 100,000 token uncensored LLM via our openai compatible API with codex API pricing starting at just $0.15 per million input tokens.

$0.50 per million output tokens
No monthly fees or subscriptions
Crypto top-ups with bonus credit

Try with trial credit View documentation

Test with one call

curl https://api.codexapipricing.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "List the hourly rates for the large model."}]
  }'

from openai import OpenAI

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

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

Core features

Pay per token: Prepaid credits cover real usage; errors and refusals cost nothing.
Uncensored output: The model answers without filtering lawful adult or controversial topics.
Crypto payments only: Top up with USDT (TRC20) or USDC (Base) for privacy.
OpenAI compatible: Works with official SDKs by changing the base URL and key.
Streaming support: Receive tokens via SSE with usage data in the final chunk.
No data mining: Your prompts are not used for training or model improvement.

Setup guide

Create account
Sign up with Google or email to get your API key.
Top up credit
Add crypto funds to receive your prepaid balance instantly.
Make requests
Send POST requests to the chat completions endpoint immediately.

Common use cases

NSFW content generation

Produce uncensored stories and images without content filters blocking output.

Dev testing

Test prompts freely without worrying about temporary refusals or limits.

Data scraping

Aggregate large volumes of text without per-request subscription costs.

Privacy research

Analyze sensitive data with a model that does not track usage.

codex API pricing: The uncensored LLM for developers

Our uncensored LLM API charges $0.15 per 1M input tokens and $0.50 per 1M output tokens with no monthly fees.

NSFW Content Creators

Generate unlimited lawful adult text without hidden content filters or refusal penalties.

AI Developers

Use the standard POST /v1/chat/completions endpoint with our 100k context window.

Budget-Conscious Teams

Pay only for real usage with prepaid crypto credits that never expire.

Calculate your exact token costs

Your total bill equals input tokens multiplied by $0.15 per million, plus output tokens multiplied by $0.50 per million. Errors incur zero charges. Refusals cost nothing. Streaming tokens count only toward your final usage. Prepaid credit covers actual consumption without hidden monthly fees. No subscription locks you in. You pay strictly for what you send and receive. This transparency ensures you never overpay for unused capacity or failed requests during high-load periods.

How we differ from typical AI gateways

We strip away the subscription bloat and offer a truly uncensored LLM for developers who need direct, transparent access without content filters.

Feature	Typical Alternative	Our API
Pricing Model	Monthly subscription with tiered limits	Pay per token; no monthly fees
Content Policy	Aggressive filtering for adult content	Uncensored for lawful adult use
Payments	Credit cards and invoices	Crypto only (USDT/USDC)
Minimum Spend	Often requires minimum commitment	No minimum spend required
Privacy	Data used for model training	Prompts not used for training

Migrate from your current provider in three steps

Switch your LLM backend in minutes by updating your base URL and model ID. First, generate a new API key via our Google or email signup. Second, point your existing OpenAI SDK client to HTTPS://api.codexapipricing.com/v1. Third, set the model parameter to "uncensored". Your logic stays identical. You gain uncensored responses without rewriting your codebase.

Get a working key and send your first uncensored request in under two minutes.

Visit the Get API key page and sign up with Google or a simple email.
Retrieve your unique API key instantly; no phone number or credit card is required.
Configure your OpenAI-compatible SDK with the base URL and your key.
POST to /v1/chat/completions with model: "uncensored" to receive text output.

Who needs the uncensored API (and who doesn't)

Developers building NSFW apps or researchers needing raw model outputs without refusals should use this uncensored LLM. It serves any use case where standard filters block lawful adult content. The API lacks embeddings, images, and fine-tuning, so teams needing those features will find it insufficient. It is not a replacement for multi-model gateways or enterprise suites requiring SLAs. Use it for direct, unfiltered text generation.

Frequently asked questions

What is the codex API pricing structure for input and output tokens?

It costs $0.15 per million input tokens and $0.50 per million output tokens. You pay only for actual usage with no monthly subscriptions. Errors and refusals incur zero charges. This prepaid model ensures you never pay for wasted compute cycles during your development workflow.

Does the uncensored model filter lawful adult content?

No, it does not. The model is tuned to answer without content refusals for lawful adult use. The only hard limit that always applies is sexual content involving minors. You get true freedom for creative and adult writing without arbitrary gatekeeping mechanisms.

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 large is the context window for requests?

The context window supports 100,000 tokens for prompt and completion combined. Each request can output up to 16,000 tokens. If you do not set max_tokens, the limit defaults to 2,048 tokens. This handles long documents and complex multi-turn conversations effectively.

Can I use the standard OpenAI SDKs with this API?

Yes, it is fully OpenAI-compatible. You just need to change the base URL and API key in your client. The endpoints match standard chat-completions formats. Streaming, JSON mode, and function calling all work exactly as you expect from other major providers.

Is my prompt data used to train the model?

No, your prompts are not used for training. We prioritize privacy for developers and creators. An account needs only an email address. You retain full control over your data without worrying about your proprietary content being leaked into future model updates.

Get your API key in one step

Try with trial credit