Documentation
Developer hub
OneToolz Documentation
Everything you need to plug premium AI models into your app, IDE, or CLI in minutes.
Getting Started
Welcome to OneToolz — a unified gateway for premium AI models at developer-friendly prices. To get started:
- Pick a package from All Packages.
- Complete checkout — delivery is instant.
- Log in to the API Portal to grab your API key.
- Point your OpenAI-compatible client at our base URL and start shipping.
Portal & Key Management
All API keys are provisioned and managed through the API portal. Log in with the credentials sent to your email after purchase.
Open portal- View, rotate, and revoke API keys
- Track real-time token usage and remaining quota
- Extend or upgrade active packages
- Download invoices and receipts
Unified API Endpoints
The marketplace exposes two OpenAI-compatible base URLs depending on your package:
https://api.nghimmo.com/v1Used by Codex and Claude short-duration packages.
https://api.codexhub.click/v1Used by DeepSeek and multi-provider packages.
Both endpoints follow the OpenAI Chat Completions spec — you can swap between them by changing base_url.
Compatibility
Your API keys work anywhere the OpenAI SDK is supported:
- Official OpenAI SDKs (Python, Node.js, Go, Java, .NET)
- Anthropic SDK — for Claude-family packages via the nghimmo gateway
- OpenAI Codex CLI
- Cursor, VS Code + Continue, Zed, Aider, Cline
- LangChain, LlamaIndex, LiteLLM, Vercel AI SDK
- Anything that accepts a custom
base_url
Integration Guides
Python — OpenAI SDK
from openai import OpenAI
client = OpenAI(
api_key="YOUR_API_KEY",
base_url="https://api.codexhub.click/v1",
)
resp = client.chat.completions.create(
model="deepseek-v4-pro",
messages=[{"role": "user", "content": "Write a haiku about caching."}],
)
print(resp.choices[0].message.content)JavaScript — fetch
const res = await fetch("https://api.codexhub.click/v1/chat/completions", {
method: "POST",
headers: {
"Content-Type": "application/json",
Authorization: `Bearer ${process.env.API_KEY}`,
},
body: JSON.stringify({
model: "gpt-5.5",
messages: [{ role: "user", content: "Ping" }],
}),
});
const data = await res.json();
console.log(data.choices[0].message.content);cURL
curl https://api.nghimmo.com/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "claude-sonnet-4",
"messages": [{"role": "user", "content": "Say hi in one line."}]
}'Model-Specific Guides
DeepSeek V4 Pro / Flash
Flash is unlimited on eligible packages. Pro consumes tokens from your quota. Both are OpenAI-compatible.
Claude family (Opus, Sonnet, Haiku)
Use with the Anthropic SDK or through the OpenAI-compatible layer on the nghimmo gateway.
Codex / GPT variants
gpt-5.5, gpt-5.4, gpt-5.3-codex-spark and siblings — great for IDE completions and agent loops.
Unified multi-provider
One key across gateways — route by model name, no per-provider setup.
Checking Usage & Keys
Verify a key or inspect remaining tokens at the key-check pages below:
Troubleshooting & FAQ
I'm getting 401 Unauthorized.+
Authorization: Bearer … header matches the key from the portal, and that the base URL matches your package's gateway.