Uncensored API

GLM api key: The Uncensored Alternative

Get your glm API key for an uncensored LLM with 100,000 token context, streaming support, and crypto-only prepaid pricing that never expires.

Open account View documentation

100,000 token context window
Crypto payments only
No training data use

Test with one call

curl https://api.keyapiglm.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Verify endpoint latency for high traffic loads"}]
  }'

from openai import OpenAI

client = OpenAI(base_url="https://api.keyapiglm.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.keyapiglm.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

Features

Uncensored Completions

No refusals for lawful adult content or controversial topics.

OpenAI Compatible

Works with standard SDKs by changing the base URL.

Streaming Support

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

Function Calling

Native tools support with flexible choice configurations.

JSON Mode

Force structured output using the response_format parameter.

Privacy First

Only email needed; prompts are not used for training.

Getting started

Sign Up

Create an account with Google or email password.

Add Key

Copy your key and update your client base URL.

Send Request

Make a POST request to chat/completions with your model.

Use cases

NSFW Chatbots

Run adult-oriented conversational agents without content blocks.

Dev Workflows

Integrate uncensored models into IDEs like Cursor or Windsurf.

Code Generation

Generate code without style or topic restrictions.

Research Testing

Test models for jailbreaks or controversial outputs freely.

Migrate to our uncensored API in three steps

Switch your base URL and update your API key to start using our endpoint immediately.

Sign up with Google or email to receive your unique key instantly.
Update your client configuration to point to https://api.keyapiglm.com/v1 and set the model ID to uncensored.
Send requests as usual; you will get transparent token billing with no hidden fees.

What developers actually ask about this topic

Can I use my existing key? Yes, but you must update the base URL to HTTPS://api.keyapiglm.com/v1 in your client configuration. How does pricing work? We charge $0.15 per 1M input tokens and $0.50 per 1M output tokens. Errors are free. Is it uncensored? The model refuses no lawful adult content, except for minors. You get a single open-weight model, not a routed proxy. Setup takes seconds via Google or email.

glm API key: uncensored completions for dev workflows

Stop wrestling with restrictive filters when you need raw generation. Our uncensored LLM endpoint accepts standard OpenAI requests without blocking lawful adult content, ensuring your dev workflows run uninterrupted.

NSFW Chatbot Integration

Deploy character-driven apps that skip moralizing. Send text, get text, and handle adult themes without extra flags.

Uncensored AI Research

Run security tests on controversial topics. The model answers directly, giving you clean data for analysis.

Unfiltered Chatbot Scaling

Use the 100k context window for long conversations. Stream tokens via SSE for real-time user experiences.

Worked cost examples with token arithmetic

Our prepaid credit charges strictly by real usage. Input costs $0.15 per million tokens, while output runs $0.50 per million tokens. Consider a 20k prompt combined with a 2k completion: the input consumes 0.003 dollars and the output consumes 0.001 dollars. Errors incur zero charges. Prepaid credit never expires, so unused funds roll over indefinitely. You only pay for what the model actually generates, ensuring precise budget control without hidden subscription fees.

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

Developers build uncensored chatbots, NSFW roleplay engines, and character AI agents using this endpoint.

Local LLM users seeking uncensored alternatives for local deployment.
Creators needing reliable uncensored API access for adult content.
Researchers testing boundaries without standard refusals.

It is NOT for teams requiring image generation, embeddings, or fine-tuning capabilities, as we offer only text completions.

A checklist for choosing a provider in this niche

Start by verifying true OpenAI compatibility. Ensure the endpoint accepts standard headers without custom wrappers. Check that input and output token counts match your billing expectations. Confirm whether refusals incur charges. Verify that privacy policies exclude prompt training. Test streaming support for real-time UX. Validate crypto payment options if you prefer discretion. Compare latency against your application’s needs.

Frequently asked questions

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.

Is this a full OpenAI compatible API?

Yes. It supports POST /v1/chat/completions. You can use official OpenAI SDKs by changing the base_url. It handles streaming, JSON mode, and function calling tools effectively.

Does it use my prompts for training?

No. We keep a minimal privacy footprint. We only need your email to create the account. Your data stays separate from our training sets.

Can I add this key to Windsurf or Zed?

Yes. Configure your editor to point to our base URL. Paste your key as the auth token. It works with any OpenAI-compatible client tool.

What is the context window size?

It is 100,000 tokens total. You can output up to 16,000 tokens per request. This allows deep context for complex coding tasks.

How do I top up my credit?

Use crypto only. We accept USDT on TRC20 or USDC on Base. Minimum top-ups start at $20. Credits never expire.

Get your API key

Open account