← Back to Skills Marketplace
One API key for 70+ AI models. Route to GPT, Claude, Gemini, Qwen, Deepseek, Grok and more
by
0xjordansg-yolo
· GitHub ↗
· v1.0.0
1520
Downloads
5
Stars
4
Active Installs
1
Versions
Install in OpenClaw
/install openclaw-aisa-llm-gateway
Description
Unified LLM Gateway - One API for 70+ AI models. Route to GPT, Claude, Gemini, Qwen, Deepseek, Grok and more with a single API key.
Usage Guidance
This skill appears to do what it says: route requests to the AIsa / aisa.one gateway using a single API key. Before installing, confirm you trust the AIsa provider (https://api.aisa.one / marketplace.aisa.one) because any prompt, file, or image you send will be visible to that service and may consume billing. Use a key with appropriate billing limits or a dedicated account, avoid sending sensitive secrets or private data, and monitor usage after enabling the skill. If you need stronger controls, ask for more info about the provider's privacy, retention, and billing policies or test with a low-privilege key first.
Capability Analysis
Type: OpenClaw Skill
Name: openclaw-aisa-llm-gateway
Version: 1.0.0
The skill bundle provides a client for an LLM gateway, `api.aisa.one`. The Python script `scripts/llm_router_client.py` uses standard libraries, retrieves the `AISA_API_KEY` from environment variables, and makes authenticated HTTP requests exclusively to `api.aisa.one`. The `SKILL.md` and `README.md` files contain only documentation and usage examples, with no evidence of prompt injection attempts or instructions for the agent to perform malicious actions. All observed behaviors are aligned with the stated purpose of an LLM router client.
Capability Assessment
Purpose & Capability
Name/description, SKILL.md examples, and the included Python client all target the same API host (https://api.aisa.one) and require a single API key (AISA_API_KEY). Required binaries (curl, python3) are appropriate for a CLI/client skill. No unrelated credentials or binaries are requested.
Instruction Scope
SKILL.md and README instruct the agent to send user prompts, images, and other data to the remote AIsa endpoints. That is expected for a gateway, but it means any data you pass (including images or secrets) is transmitted to a third-party service. The instructions do not request reading local files or unrelated environment variables, nor do they instruct exfiltration beyond the intended API.
Install Mechanism
There is no install spec (instruction-only), and the shipped Python script uses only stdlib modules (urllib, json, argparse). Nothing is downloaded or written to disk by an installer here, so install-time risk is low.
Credentials
The skill requires a single API credential (AISA_API_KEY) which is proportional to a gateway client. That key grants access to the provider and may be able to consume billing/quota and see all request payloads — this is expected but sensitive. No other unrelated secrets are requested.
Persistence & Privilege
always:false and no install-time changes or modifications to other skills are requested. The skill is user-invocable and allows normal autonomous invocation (platform default) but does not request elevated or permanent platform privileges.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install openclaw-aisa-llm-gateway - After installation, invoke the skill by name or use
/openclaw-aisa-llm-gateway - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial release of unified LLM Gateway.
- Provides a single API key to access 70+ LLMs (e.g., GPT-4, Claude-3, Gemini, Qwen, Deepseek, Grok) via a unified, OpenAI-compatible API.
- Enables multi-model chat, side-by-side comparisons, and automatic fallback between models.
- Supports advanced features: streaming, vision/image analysis, and function calling.
- Includes a CLI tool and minimal Python SDK for easy integration and usage.
- Centralized billing, model switching, and usage tracking across all supported providers.
Metadata
Frequently Asked Questions
What is One API key for 70+ AI models. Route to GPT, Claude, Gemini, Qwen, Deepseek, Grok and more?
Unified LLM Gateway - One API for 70+ AI models. Route to GPT, Claude, Gemini, Qwen, Deepseek, Grok and more with a single API key. It is an AI Agent Skill for Claude Code / OpenClaw, with 1520 downloads so far.
How do I install One API key for 70+ AI models. Route to GPT, Claude, Gemini, Qwen, Deepseek, Grok and more?
Run "/install openclaw-aisa-llm-gateway" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is One API key for 70+ AI models. Route to GPT, Claude, Gemini, Qwen, Deepseek, Grok and more free?
Yes, One API key for 70+ AI models. Route to GPT, Claude, Gemini, Qwen, Deepseek, Grok and more is completely free (open-source). You can download, install and use it at no cost.
Which platforms does One API key for 70+ AI models. Route to GPT, Claude, Gemini, Qwen, Deepseek, Grok and more support?
One API key for 70+ AI models. Route to GPT, Claude, Gemini, Qwen, Deepseek, Grok and more is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created One API key for 70+ AI models. Route to GPT, Claude, Gemini, Qwen, Deepseek, Grok and more?
It is built and maintained by 0xjordansg-yolo (@0xjordansg-yolo); the current version is v1.0.0.
More Skills