Documentation - Noob Keys API

Getting Started

Noob Keys provides OpenAI-compatible API endpoints for Claude models. Use it as a drop-in replacement with any OpenAI-compatible client.

Base URL: https://noobkeys.onrender.com/v1

Quick Start

Generate an API key from the homepage
Use https://noobkeys.onrender.com/v1 as your base URL
Make requests to /v1/chat/completions

Authentication

All API requests require a Bearer token:

Authorization: Bearer nk-your-api-key-here

Available Models

All models accessible through OpenAI-compatible endpoints:

Claude Models

claude-opus-4-5-20251101 $5 / $25 per 1M Best for complex reasoning

claude-sonnet-4-5-20250929 $6 / $22.50 per 1M Balanced (recommended)

claude-haiku-4-5-20251001 $1 / $5 per 1M Fast responses

claude-sonnet-4-20250514 $3 / $15 per 1M Coding tasks

claude-3-7-sonnet-20250219 $3 / $15 per 1M General purpose

claude-3-5-haiku-latest $0.80 / $4 per 1M Cheapest Claude

Open Source Models

moonshotai/kimi-k2-instruct-0905 $0.15 / $2.50 per 1M Kimi K2 Instruct

openai/gpt-oss-120b $0.15 / $0.60 per 1M GPT-OSS 120B

qwen/qwen3-32b $0.29 / $0.59 per 1M Qwen3-32B

API Endpoints

POST /v1/chat/completions

Main endpoint - Create a chat completion

GET /v1/models

List available models

GET /v1/test

Test connectivity (no auth required)

Request Parameters

Parameter	Type	Required	Description
`model`	string	Required	Model ID (e.g., claude-3-5-haiku-latest)
`messages`	array	Required	Array of {role, content} objects
`stream`	boolean	Optional	Enable SSE streaming
`max_tokens`	integer	Optional	Maximum tokens to generate
`temperature`	number	Optional	Sampling temperature (0-2)

Streaming

Enable streaming with stream: true. Responses use Server-Sent Events (SSE):

                curl -N "https://noobkeys.onrender.com/v1/chat/completions" \
  -H "Authorization: Bearer nk-YOUR_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"claude-3-5-haiku-latest","messages":[{"role":"user","content":"Hello"}],"stream":true}'
            

Stream Response Format

                data: {"id":"chatcmpl-123","object":"chat.completion.chunk","choices":[{"delta":{"content":"Hello"}}]}

data: {"id":"chatcmpl-123","object":"chat.completion.chunk","choices":[{"delta":{"content":"!"}}]}

data: [DONE]

IDE & Tool Setup

Universal Settings:

Base URL:	`https://noobkeys.onrender.com/v1`
API Key:	`nk-xxxxxxxx`
Model:	`claude-3-5-haiku-latest` (cheapest)

🖥️ Cursor

Open Settings (Ctrl/Cmd + ,) → Models
Click "Add Model" or "OpenAI API"
Enter Base URL: https://noobkeys.onrender.com/v1
Enter your nk- API key
Set model: claude-3-5-haiku-latest

🔮 Cline (VS Code)

Open Cline settings in VS Code
Select "OpenAI Compatible" provider
Base URL: https://noobkeys.onrender.com/v1
API Key: Your nk- key
Model ID: claude-3-5-haiku-latest

🦘 RooCode / Roo Cline

Open RooCode settings
Select "OpenAI Compatible" or "Custom" provider
Base URL: https://noobkeys.onrender.com/v1
API Key: Your nk- key
Model: claude-3-5-haiku-latest

⚡ Kilocode

Open Kilocode settings
Choose "OpenAI Compatible" provider
API Endpoint: https://noobkeys.onrender.com/v1
API Key: Your nk- key
Model: claude-3-5-haiku-latest

🔗 Dyad.sh

Open Dyad settings
Select "OpenAI Compatible" as provider
Base URL: https://noobkeys.onrender.com/v1
API Key: Your nk- key
Model: claude-3-5-haiku-latest

🐍 Python (OpenAI SDK)

                    from openai import OpenAI

client = OpenAI(
    base_url="https://noobkeys.onrender.com/v1",
    api_key="nk-your-api-key"
)

response = client.chat.completions.create(
    model="claude-3-5-haiku-latest",
    messages=[{"role": "user", "content": "Hello!"}]
)
print(response.choices[0].message.content)
                

📜 JavaScript (OpenAI SDK)

                    import OpenAI from 'openai';

const client = new OpenAI({
  baseURL: 'https://noobkeys.onrender.com/v1',
  apiKey: 'nk-your-api-key'
});

const response = await client.chat.completions.create({
  model: 'claude-3-5-haiku-latest',
  messages: [{ role: 'user', content: 'Hello!' }]
});
console.log(response.choices[0].message.content);
                

Rate Limits & Quotas

Limit Type	Value	Description
Rate Limit	10 requests/minute	Per API key
User Quota	$20.00 USD	Per API key lifetime
Global Quota	$600.00 USD	Total service limit

Rate Limit Headers

                X-RateLimit-Limit: 10
X-RateLimit-Remaining: 9
X-RateLimit-Reset: 1733500060
            

Error Handling

Errors are returned in OpenAI-compatible format:

                {
  "error": {
    "message": "Invalid API key provided",
    "type": "invalid_request_error",
    "code": "invalid_api_key"
  }
}
            

Common Error Codes

Status	Type	Description
400	invalid_request_error	Missing/invalid parameters
401	invalid_request_error	Invalid API key
403	insufficient_quota	Quota exceeded
429	rate_limit_error	Rate limit exceeded
500	api_error	Server error

Troubleshooting:

Verify base URL is exactly: https://noobkeys.onrender.com/v1
Check your API key starts with nk-
Ensure you haven't exceeded your $20 quota
Test with: https://noobkeys.onrender.com/v1/test

API Documentation

Quick Navigation