Uncensored API

GLM api keys: uncensored LLM API alternative

Use the glm API keys with our 100,000 token uncensored LLM API for direct, filter-free responses via standard OpenAI SDK code.

Prepaid crypto billing only
No third-party training
$0.15 per 1M input tokens

Get API key View documentation

Test with one call

Uncensored LLM API. Pay per token. No filters.

curl https://api.glmapikeys.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "what is the current exchange rate for usd to jpy"}]
  }'

from openai import OpenAI

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

OpenAI Compatible

Drop-in replacement using standard chat completions endpoints.

Uncensored Model

Answers without refusals for lawful adult content.

Large Context

Supports 100,000 tokens for complex processing tasks.

Crypto Payments

Top up with USDT or USDC for bonus credits.

Function Calling

Full tool support with JSON mode capabilities.

No Subscription

Pay only for what you use with no fees.

Setup workflow

Create Account
Sign in with Google or email to get your key.
Add Crypto
Deposit USDT or USDC to receive bonus credits.
Start Coding
Point your SDK to our base URL and send requests.

Use cases

Content Generation

Produce unrestricted text for novels, scripts, or creative projects.

Data Extraction

Parse complex documents without model refusal or formatting errors.

Code Assistance

Get direct answers for coding tasks without content filters.

API Integration

Embed uncensored responses directly into your existing applications.

Common mistakes people make in this niche and how to avoid them

Stop paying for refusals

Many developers waste prepaid credit on blocked requests that should have been free. Our uncensored LLM API charges only for actual token usage, so errors and refusals cost nothing.

Configure max_tokens to prevent bill shock from runaway outputs.
Use temperature to control randomness without triggering extra retries.
Verify your base URL points to api.glmapikeys.com to ensure you are billed correctly.

glm API keys: the uncensored alternative for developers

Use our uncensored LLM API with standard OpenAI SDK code for unrestricted generation.

Direct Integration
Connect instantly by updating your base_url to https://api.glmapikeys.com/v1 and swapping your API key. No code rewrites required.
High Limits
Handle 100,000 token context windows efficiently. Perfect for long-form content generation without arbitrary cutoffs.
Crypto Billing
Top up with USDT or USDC. Enjoy bonus credits and never lose unused funds.

From signup to your first token

Get your key. Click "Get API key" and sign in with Google or email. Your credentials appear instantly.
Set your environment. Export GLM_API_KEY in your terminal.
Send a request. Point your SDK to https://api.glmapikeys.com/v1 and use model uncensored.
Receive text. Get immediate, uncensored outputs via standard OpenAI-compatible endpoints.

Worked cost examples with token arithmetic

Costs reflect strict token usage, not subscription tiers. Input runs $0.15 per million tokens, while output charges $0.50 per million. Errors incur zero fees. You only pay for actual consumption. Consider a 50k input prompt generating 10k output text. That totals 60k tokens. The calculation yields exactly $0.0385. No hidden base rates apply. Credit never expires. Pay via crypto top-ups starting at $20. Bonus credits increase your effective balance without changing unit costs.

What developers actually ask about this topic

Developers frequently ask how to configure the uncensored LLM in their existing tooling. The answer is straightforward: update your base URL to HTTPS://api.glmapikeys.com/v1 and set the model ID to "uncensored". This works with standard OpenAI SDKs. Users also wonder about context limits. The model supports 100,000 tokens total, with a maximum output of 16,000 tokens per request. Errors are free. Payment uses crypto only.

Who uses it, in which real situations; and plainly who it is NOT for

Developers use this uncensored LLM for unrestricted content generation and testing where standard models refuse lawful adult topics. It powers local setups via Docker with preconfigured keys, handling parallel model workflows without third-party training of prompts.

Use it for creative writing, security research, or NSFW chatbots needing 100k context windows.
Use it when you want predictable prepaid billing without subscription tiers.

It is NOT for users requiring image generation, audio processing, or embeddings. It also excludes those needing multi-model routing or high-availability SLAs, as this is a single-model API for direct integration.

Start with trial credit

Enter email and password to receive your key immediately.

Get API key

Common questions

What are glm API keys and how do they work?

They are prepaid tokens for our uncensored LLM API. You pay per request, with errors free. Streaming via SSE includes token usage in the last chunk. No subscriptions exist. 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.

How much does the uncensored model cost per token?

Input tokens cost $0.15 per million. Output tokens cost $0.50 per million. Errors and refusals incur no charge. You only pay for actual usage on our servers.

Can I top up my balance using cryptocurrency?

Yes, only USDT on TRC20 or USDC on Base are accepted. Minimum top-ups start at $20. Bonus credits apply automatically based on your contribution amount.

What is the context window limit for requests?

The model supports 100,000 tokens total. This includes both the prompt and the completion. Max output is 16,000 tokens unless you specify a lower limit.

Is there a rate limit on my API key?

You get 300 requests per minute. Only 8 requests can run simultaneously. The request body cannot exceed 8 MB. Exceeding these limits returns an error.

Get your key instantly