Uncensored API Key

GLM apikey: uncensored openai-compatible api

Deploy a single uncensored model via a standard openai compatible API, sending text in and receiving text out with a 100000 token context window for predictable costs.

100,000 token context window
OpenAI-compatible endpoint
No content refusals

Get your key View documentation

Test with one request

curl https://api.apikeyglm.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "List the steps to configure the proxy server"}]
  }'

from openai import OpenAI

client = OpenAI(base_url="https://api.apikeyglm.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.apikeyglm.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 capabilities

Direct Endpoint

Post to /v1/chat/completions using standard headers and your key.

Streaming Support

Receive tokens via SSE with usage data in the final chunk.

Tool Support

Enable function calling with tools and tool_choice parameters.

JSON Mode

Force structured output using the response_format json_object parameter.

Low Latency

High-throughput infrastructure designed for developer integration workflows.

Simple Limits

300 requests per minute with no complex routing tiers.

Setup flow

Create Account

Add Credit

Top up via crypto with no card required for trials.

Integrate Code

Update your base_url and send requests to the API.

Common integrations

Content Generation

Generate uncensored text for adult or controversial topics without refusals.

Research Analysis

Process long documents within the 100k token context window.

Function Calling

Execute complex tool use with structured JSON responses.

Streaming Apps

Build real-time chat interfaces using standard streaming protocols.

Who integrates this uncensored model and where it fits

Developers needing direct, uncensored text generation without content refusals integrate this API for chat completions and function calling. It fits applications requiring lawful adult, fictional, or controversial topics without moderation layers. This is NOT for teams needing image generation, embeddings, or multiple model routing. We provide a single uncensored endpoint for predictable, low-latency responses. Use cases include creative writing bots, research assistants, and specialized chat interfaces where nuance matters more than broad safety filters.

Common integration mistakes and how to avoid them

Developers often break when assuming every LLM supports the same parameters. Our uncensored API accepts standard fields like temperature and top_p, but ignores complex routing logic. Always verify the model ID. Use "uncensored" exactly as shown. Another error is expecting image generation. We provide text only. Check your request body size. It must stay under 8 MB. Keep your requests simple.

glm apikey: concrete use cases for uncensored generation

Developers use the glm apikey to power applications requiring consistent, refusal-free responses for adult or controversial topics without complex routing logic.

Roleplay Engines

Generate unlimited character dialogue without sudden content filters interrupting the narrative flow during high-throughput sessions.

Security Research

Analyze sensitive data or generate precise jailbreak prompts using an uncensored LLM that ignores standard politeness filters.

Content Aggregation

Scrape diverse opinions from the open web using an openai compatible API that never refuses lawful adult content.

Visit the Get API key page and sign in via Google or email. Your unique credential appears immediately.
Add $0.50 trial credit. Set the base URL to HTTPS://api.apikeyglm.com/v1 and pass your key in the Authorization header.
Send a POST request to /v1/chat/completions with model "uncensored".
Receive streaming tokens via SSE.

Token arithmetic: real costs for real requests

Costs scale linearly with token volume at $0.15 per 1M input and $0.50 per 1M output tokens. A 100k prompt plus 16k completion costs $0.0185. Errors remain free. Credit never expires. Crypto top-ups start at $20. No subscriptions. No hidden fees. Simple math. Predictable budgets. Real usage. Real costs. Zero surprises.

Checklist for choosing the right uncensored LLM provider

Verify the provider charges only for actual tokens used, not subscriptions. Confirm they accept crypto top-ups like USDT or USDC. Ensure the endpoint is fully OpenAI-compatible. Check that context windows support at least 100,000 tokens. Guarantee streaming via SSE works correctly. Ensure API keys are generated instantly.

Frequently asked questions

What is the glm apikey and how does it work?

It is a credential for our uncensored LLM API. Use it with standard OpenAI-compatible SDKs to send POST requests to HTTPS://api.apikeyglm.com/v1. The model ID is "uncensored" and context windows support 100,000 tokens.

Does the uncensored model refuse content?

No. It answers without refusals for lawful adult, fictional, or controversial topics. The only hard limit is sexual content involving minors, which is always refused. This ensures consistent generation for your application needs.

Can I use the official OpenAI SDK with this API?

Yes. Change the base URL and API key in your client. The endpoint is POST /v1/chat/completions. It supports streaming, function calling, and JSON mode, making integration straightforward for existing developer workflows.

How much does the API cost per token?

$0.15 per 1M input tokens and $0.50 per 1M output tokens. Errors are free. Prepaid credit never expires, so you only pay for actual usage without monthly subscription fees or hidden routing costs.

How do I top up my account?

Use crypto only. We accept USDT (TRC20) or USDC (Base) in amounts from $20 to $500. You receive bonus credit of +5% from $50, +10% from $100, or +15% from $200 added to your balance.

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.

Access in one step

Get your key