EN ▾
Get API key

OpenAI-compatible GLM API, uncensored & private.

GLM API: an independent guide and a drop-in alternative

A direct, open-weight GLM API alternative that accepts standard OpenAI client code. Get uncensored text generation with transparent prepaid credits and no prompt training.

  • 100k token context window
  • No prompt training used
  • Prepaid credit never expires

Get API keyRead the docs

Try it in one request

curl https://api.glmapikey.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Write a blunt product review of a cheap VPN."}]
  }'
per 1M input tokens
$0.15
Output tokens / 1M
$0.50
token context
100,000
trial credit
$0.50
requests per minute
300

What you get

OpenAI-Compatible Endpoint

Use the official OpenAI SDKs or any compatible client. Change the base URL to https://api.glmapikey.com/v1 and your API key to start sending requests immediately.

Uncensored Text Generation

The model answers without ideological filtering for lawful adult, fictional, or controversial topics. It is an open-weight model run on our own servers, not a copy of GPT or Claude.

Transparent Pricing

Pay $0.15 per 1M input tokens and $0.50 per 1M output tokens. Prepaid credit never expires, and there are no hidden fees or subscription traps.

Privacy First

Your prompts are not used to train the model. We require only an email and password to start, keeping your data usage simple and private.

Streaming & Tools

Supports streaming via Server-Sent Events (SSE) and standard tool/function calling. The API handles text input and output efficiently for complex workflows.

Simple Limits

300 requests per minute per key with an 8 MB request body limit. Keys are easily regenerated if compromised, ensuring secure access.

How it works

Sign Up

Create an account with just an email and password to receive your immediate API key and $0.50 trial credit. Claim this credit with one click on your API key page.

Configure Client

Update your OpenAI-compatible client configuration to point to https://api.glmapikey.com/v1 using your new key.

Start Generating

Send your first POST request to /v1/chat/completions with the model id 'uncensored' and see the results.

What people build with it

Creative Writing

Generate stories and scripts without content filters blocking mature themes or controversial narratives. The uncensored model allows for full creative freedom in fiction.

Security Research

Analyze sensitive data or prompt the model to reveal internal biases without fear of standard refusals. Ideal for red-teaming and edge-case testing.

Data Extraction

Process large volumes of text through the 100k context window for consistent extraction. The open-weight model handles diverse input formats reliably.

Custom Chatbots

Build chat applications that respond naturally to adult or niche topics. Use function calling to integrate the API into your existing software stack.

Why Switch to an Uncensored GLM API?

Many developers find standard LLM APIs too restrictive for creative or niche use cases. Our API serves an open-weight model tuned to answer without content refusals for lawful adult use. This means you get direct responses to controversial, sexual, or political topics without the model refusing to engage. It is not GPT, Claude, or Gemini; it is a distinct open-weight model running on our own GPU servers.

We strip away the complexity of multi-model aggregators. You get a single, reliable endpoint for text generation. Unlike generic gateways, we provide transparent prepaid credit with no expiration. Your prompts are not used for training, ensuring your data remains yours. This is a straightforward text-in, text-out API for developers who want control.

OpenAI-Compatible Compatibility

Our API follows the standard OpenAI chat completions structure. You can use the official OpenAI SDKs or any library that supports the OpenAI protocol. Simply update the base URL to https://api.glmapikey.com/v1 and provide your API key. The model id you must send is 'uncensored'.

The endpoint supports streaming via Server-Sent Events (SSE) and standard tool/function calling. You can POST to /v1/chat/completions for text generation. The context window is 100,000 tokens, covering both the prompt and the completion. This allows you to process long documents or maintain extensive conversation history in a single request.

Transparent Pay-As-You-Go Pricing

We charge $0.15 per 1 million input tokens and $0.50 per 1 million output tokens. There is no monthly subscription fee. You pay for what you use with prepaid credit. If you top up from $50, you receive a 5% bonus. Top up $100 or more for a 10% bonus. Credit never expires, so you can pause usage without losing funds.

Who this is NOT for: If you need image generation, audio, video, embeddings, or fine-tuning, this API is not for you. We only serve text completions. If you require strict SLA guarantees or SOC2 certifications, look elsewhere. We are a simple, direct API for text generation without enterprise overhead.

Privacy First: No Prompt Training

Your data privacy is straightforward. We do not use your prompts to train the model. An account requires only an email and a password; no phone number or credit card is needed for the trial. You get $0.50 of trial credit valid for 7 days to test the API before committing. Claim this credit with one click on your API key page.

We maintain one key per account, which can be regenerated at any time. Old keys are revoked immediately upon regeneration. The hard content limit is minimal: we only block sexual content involving minors. All other lawful content, including adult themes, is allowed. This ensures a private, uncensored environment for your development and production needs.

Questions and answers

Is this model the same as DeepSeek or Mistral?

No. Our model is an open-weight model run on our own servers. It is not GPT, Claude, Gemini, Grok, DeepSeek, or Mistral. It is a distinct model tuned for uncensored responses. If you are looking for the official DeepSeek or Mistral API, you should check their respective vendor documentation for current prices and limits.

What is the context window limit?

The context window is 100,000 tokens. This limit applies to the combined total of the prompt and the completion. You cannot send more than 100k tokens in a single request.

Do you use my prompts for training?

No. We do not use your prompts to train the model. Your data remains private and is not used to improve our weights. This is a key privacy feature for developers who want to keep their data usage internal.

What are the rate limits?

You are limited to 300 requests per minute per key. The maximum request body size is 8 MB. If you exceed these limits, your requests will be rejected until the window resets.

How does the trial credit work?

New users get $0.50 of trial credit, one per person. It is valid for 7 days and requires no credit card. Claim this credit with one click on your API key page. You can use this to test the API before buying prepaid credit. The credit does not expire during the 7-day window.

Your key is one form away

Create an account, copy the key, change the base URL. That is the whole setup.

Get API key