Uncensored LLM API

GLM key: Uncensored LLM API

Get your glm key for an uncensored LLM with a 100,000 token context window, paying only for actual token usage with no monthly fees.

100,000 token context window
Pay per token, no subscription
$0.50 trial credit, no card

Start now View documentation

Test with one request

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

from openai import OpenAI

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

$0.15per 1M input tokens

$0.50Output tokens / 1M

100,000token context

$0.50trial credit

300requests per minute

Core features

OpenAI Compatible

Works with official SDKs by changing base_url and API key.

Uncensored Model

Answers without refusals for lawful adult content and controversial topics.

Streaming Support

SSE streaming with token usage included in the final chunk.

Function Calling

Full support for tools, tool_choice, and JSON mode responses.

Prepaid Billing

Credit never expires; errors and refusals do not consume balance.

Crypto Top-up

Top up with USDT or USDC; bonuses available for larger amounts.

Setup process

Create Account
Sign up with Google or email to get your key instantly.
Add Credits
Top up with crypto or start with the free trial credit.
Start Coding
Use the model id "uncensored" with your preferred OpenAI-compatible client.

Use cases

NSFW Content Generation

Generate adult content without the typical refusals found in other models.

Long Context Analysis

Process large documents with a 100,000 token context window limit.

Coding Assistants

Integrate into coding tools like Cursor or Windsurf via API key.

Cost Effective Scaling

Pay only for tokens used, avoiding expensive monthly subscription tiers.

Why developers choose our glm key

We provide a low-cost, uncensored LLM API that accepts lawful adult content without subscription constraints or hidden model routing.

Unrestricted generation

Our model answers without refusals for standard adult themes, making it ideal for creative writing or adult-themed applications.

Predictable prepaid billing

You only pay for actual token usage with no monthly fees. Errors and refusals are free, ensuring transparent cost control.

Easy integration

Use the standard OpenAI-compatible endpoints to integrate our uncensored AI API key into your existing client code quickly.

How to get your API key in 60 seconds

Start using the uncensored LLM immediately by following these three steps to obtain your key and make your first request.

Sign up via Google or email to receive an instant API key with $0.50 trial credit.
Configure your OpenAI-compatible SDK by setting the base URL to our endpoint.
Send your first chat completion request to the uncensored model.

The system charges only for actual tokens used, with no hidden fees.

Pricing, limits, and billing transparency

Pay per token, no hidden routing

We charge only for actual usage, not subscriptions. Your prepaid credit never expires, and errors cost nothing. Unlike proxy services that add markup, we route directly to one uncensored model. You control context length and temperature without extra fees. This approach ensures total cost visibility. No monthly commitments block your budget. You get exactly what you need for development.

Feature	Our Service
Billing Model	Prepaid per token
Expiry	Never
Model Routing	Direct, single uncensored model
Errors Cost	$0.00

Migrating from other openai-compatible providers

Switching is simple because our endpoint follows the standard OpenAI schema. Most clients like Cursor or Windsurf require only a base URL and key update. Change the base URL to HTTPS://api.glmkey.com/v1 and enter your new credential. The model identifier changes to "uncensored". Your existing code runs without modification. This approach avoids proxy overhead while retaining full tool support.

Frequently asked questions from developers

Is the glm key free?

No. You pay per token with prepaid credit. Subsequent top-ups start at $20 and accept only USDT (TRC20) or USDC (Base).

Can I use this for NSFW content?

Yes. The uncensored model answers without refusals for lawful adult content. The single hard exception is sexual content involving minors, which is always blocked.

Does it support long contexts?

The model supports a 100,000-token context window, with a maximum output of 16,000 tokens per request.

Who should and should not use this API

Developers needing uncensored text generation for NSFW, coding, or research tasks should use this API. Our uncensored model handles adult content without refusals, making it ideal for creative writing or unrestricted AI applications. You should not use this service if you require image, audio, or video generation, as we only serve text. Additionally, teams needing multiple model choices or fine-tuning capabilities will find this single-model approach limiting for their specific workflows.

FAQ

What is the glm key and how does it work?

It is your unique authentication token for our uncensored API. You send requests to our OpenAI-compatible endpoint. Credit deducts only for actual token usage. Errors remain free. No monthly subscription applies to your account.

Is this the official GLM model from the original vendor?

No. We host an open-weight uncensored model on our own servers. It is not GPT, Claude, or Gemini. You use standard client code. Check the original vendor for their specific model details.

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 context window supports 100,000 tokens for prompt and completion combined. You can generate up to 16,000 output tokens per request. Streaming via SSE works seamlessly with this limit.

Does the uncensored model allow adult content?

Yes, it answers without refusals for lawful adult topics. One hard exception always applies: sexual content involving minors is refused. All other content remains accessible. This applies to all requests.

How many requests can I make per minute?

You may send 300 requests per minute per key. The system allows 8 concurrent requests. The request body limit is 8 MB. These limits ensure stable performance for your applications.

Generate your key now

Start now