OpenAI-compatible API
GLM docs: The Uncensored API Guide
Integrate our uncensored LLM API using standard OpenAI SDKs with a 100,000 token context window for direct, transparent coding and content generation.
- POST /v1/chat/completions standard
- $0.15 per 1M input tokens
- 300 requests per minute limit
Test with a single call
curl https://api.glmdocs.com/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "uncensored",
"messages": [{"role": "user", "content": "Explain how to parse JSON in Python"}]
}'from openai import OpenAI
client = OpenAI(base_url="https://api.glmdocs.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.glmdocs.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
Key features
Standard Integration
Use existing OpenAI SDKs by simply changing the base URL to our endpoint.
Long Context Window
Process up to 100,000 tokens total for complex coding and data tasks.
Streaming Support
Receive real-time token usage and content via Server-Sent Events (SSE).
JSON Mode
Enforce structured output with response_format set to json_object for reliability.
Tool Calling
Pass functions directly as arguments for native multi-step agentic workflows.
No Training Usage
Prompts remain private and are not used to train our base models.
Setup guide
Create Account
Sign up with Google or email to get your API key instantly.
Add Credit
Top up with USDT or USDC to start sending requests immediately.
Start Coding
Update your SDK base URL and begin streaming responses to your app.
Common use cases
Agentic Coding
Run local-style agentic workflows with high context limits for code generation.
Creative Writing
Generate uncensored narratives without standard content filters blocking adult or edgy topics.
Data Processing
Parse large JSON structures efficiently using structured output modes and tools.
Security Research
Test model vulnerabilities without refusals blocking controversial or technical security topics.
glm docs: Your Guide to Uncensored API Integration
Our glm docs guide delivers the uncensored LLM API you need for direct integration. This openai compatible API serves a single model via standard endpoints.
Direct Code Integration
Swap your base URL and inject the key. The SDK handles streaming and JSON mode automatically.
Transparent Pricing
Pay only for tokens. Errors are free. Prepaid credit never expires.
Local Flexibility
Access high-performance models locally or via our hosted endpoint. No subscriptions required.
What Developers Ask About Uncensored LLM APIs
Uncensored APIs remove default refusals for adult or controversial topics while maintaining standard OpenAI compatibility. Developers frequently ask about context limits. Our endpoint supports 100,000 tokens for prompts and completions combined, with a 16,000 token output ceiling. Pricing is transparent: $0.15 per million input tokens and $0.50 per million output tokens. You top up using USDT or USDC only. Errors cost nothing.
Real-World Cost Examples for This API
Predictable Token Billing
Our uncensored LLM charges $0.15 per 1M input tokens and $0.50 per 1M output tokens. A typical 10,000 token prompt costs $0.0015. Adding 2,000 output tokens adds $0.001. Errors remain free. This transparent LLM API pricing ensures you pay only for actual usage. No hidden fees. Crypto top-ups apply bonuses. The openai compatible API delivers precise, auditable costs for every request.
Who Uses This API and Who Should Skip It
Who Uses This API and Who Should Skip It
Developers needing uncensored text generation for creative writing, coding, and data processing use this API. It serves teams wanting an OpenAI-compatible endpoint with a 100,000 token context window and function calling support. Skip it if you require image, audio, or video generation, as this service handles text only. It is also unsuitable for projects demanding a custom model selection or fine-tuning capabilities, since we host a single uncensored model.
How This API Differs from Standard Alternatives
We strip away marketing fluff to offer a direct, code-first integration path using standard OpenAI SDKs for an uncensored model, focusing on transparent token pricing and immediate utility.
Checklist for Choosing an Uncensored LLM Provider
Checklist for Choosing an Uncensored LLM Provider
Verify your provider’s technical constraints before committing code. First, confirm strict OpenAI compatibility for your SDK. Second, check the context window size and max output tokens. Third, ensure the pricing model charges only for real usage without monthly fees. Fourth, verify payment options like crypto top-ups. Fifth, review rate limits per key. Finally, confirm the uncensored policy excludes only specific content types.
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.
Does the uncensored LLM support streaming responses?
Yes. You can enable streaming by setting the stream parameter to true in your request. The API sends Server-Sent Events, allowing you to receive tokens as they are generated, which significantly improves the perceived latency for your users.
What is the context window size for this API?
It supports 100,000 tokens for the combined prompt and completion. This allows you to process large documents or long conversation histories efficiently without losing earlier context, making it suitable for complex agentic workflows and extensive codebases.
Can I use function calling tools with this model?
Yes. The API supports tool definitions and tool_choice parameters just like the OpenAI standard. You can pass structured function definitions to guide the model, enabling reliable integration with external systems and automated data processing pipelines.
How much does input token processing cost?
Input tokens cost $0.15 per 1 million tokens. Output tokens are $0.50 per 1 million. You pay only for what you use, with no monthly subscription fees. Errors and refusals do not incur charges, keeping costs predictable.
Are prompts used to train the model?
No. Your prompt data is not used for training. The service requires only an email address for account creation. This ensures your proprietary data remains private and is not reused to improve the base model for other users.
Access starts with a form
Sign up, grab the token, update your base URL. Simple.
