Skip to content
Back to skills

Openrouter Install Auth

BSecurity

'Set up OpenRouter API authentication and configure API keys. Use when

  • 2,719 stars
  • 0 votes
  • 0 copies
  • 1 view
  • Added September 21, 2026
ai-agentstypescriptpythongobashnodeawsgcptestinggitapi

Works with

  • claude code
  • cli
  • api

Security analysis

B84/100
  • mediumInstalls packages at runtime which could introduce malicious dependencies
  • mediumInstalls packages at runtime which could introduce malicious dependencies

Pro scans all 4 files and shows the line behind each finding

Scanned September 21, 2026

npx -y skills add jeremylongshore/claude-code-plugins-plus --skill openrouter-install-auth --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Openrouter Install Auth?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Openrouter Install Auth
[![Security: B — Skills Directory](https://www.skillsdirectory.com/api/skills/jeremylongshore-openrouter-install-auth-19a5fec5/badge)](https://www.skillsdirectory.com/skills/jeremylongshore-openrouter-install-auth-19a5fec5)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: openrouter-install-auth
description: 'Set up OpenRouter API authentication and configure API keys. Use when
  starting a new OpenRouter integration, rotating keys, or troubleshooting auth issues.
  Triggers: ''openrouter setup'', ''openrouter api key'', ''configure openrouter auth'',
  ''sk-or key''.

  '
allowed-tools: Read, Write, Edit, Grep, Bash(python3:*), Bash(node:*), Bash(pip:*), Bash(npm:*)
version: 1.20.0
license: MIT
author: Jeremy Longshore <jeremy@intentsolutions.io>
tags:
- saas
- openrouter
- api
- authentication
- setup
compatibility: Designed for Claude Code
---
# OpenRouter Install & Auth

## Overview

Set up OpenRouter API credentials, configure the OpenAI-compatible client, verify authentication, and check credit balance. OpenRouter keys start with `sk-or-v1-` and authenticate against `https://openrouter.ai/api/v1`.

## Prerequisites

- OpenRouter account (free at [openrouter.ai](https://openrouter.ai))
- Python 3.8+ or Node.js 18+
- OpenAI SDK (`pip install openai` or `npm install openai`)

## Instructions

### 1. Generate an API Key

1. Go to [openrouter.ai/keys](https://openrouter.ai/keys)
2. Click **Create Key**, name it (e.g., `my-app-dev`)
3. Copy the `sk-or-v1-...` value immediately (shown only once)
4. Optionally set a credit limit on the key for spend control

### 2. Configure Environment

```bash
# .env file (add .env to .gitignore!)
OPENROUTER_API_KEY=sk-or-v1-your-key-here

# Or export directly
export OPENROUTER_API_KEY="sk-or-v1-your-key-here"
```

### 3. Initialize the Client

**Python:**

```python
from openai import OpenAI

client = OpenAI(
    base_url="https://openrouter.ai/api/v1",
    api_key=os.environ["OPENROUTER_API_KEY"],
    default_headers={
        "HTTP-Referer": "https://your-app.com",  # For analytics attribution
        "X-Title": "Your App Name",               # Shows in dashboard
    },
)
```

**TypeScript:**

```typescript
import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://openrouter.ai/api/v1",
  apiKey: process.env.OPENROUTER_API_KEY,
  defaultHeaders: {
    "HTTP-Referer": "https://your-app.com",
    "X-Title": "Your App Name",
  },
});
```

### 4. Verify Authentication

```python
# Quick auth + credit check
import requests

resp = requests.get(
    "https://openrouter.ai/api/v1/auth/key",
    headers={"Authorization": f"Bearer {os.environ['OPENROUTER_API_KEY']}"},
)
data = resp.json()["data"]
print(f"Key: {data['label']}")
print(f"Credits used: ${data['usage']:.4f}")
print(f"Credit limit: ${data.get('limit', 'unlimited')}")
print(f"Free tier: {data['is_free_tier']}")
print(f"Rate limit: {data['rate_limit']['requests']} req / {data['rate_limit']['interval']}")
```

### 5. Send a Test Request

```python
response = client.chat.completions.create(
    model="google/gemma-2-9b-it:free",  # Free model for testing
    messages=[{"role": "user", "content": "Say hello"}],
    max_tokens=50,
)
print(response.choices[0].message.content)
print(f"Tokens: {response.usage.prompt_tokens} in / {response.usage.completion_tokens} out")
```

## Required Headers

| Header | Purpose | Required |
|--------|---------|----------|
| `Authorization` | `Bearer sk-or-v1-...` | Yes |
| `HTTP-Referer` | Your app URL for dashboard attribution | Recommended |
| `X-Title` | App name shown in OpenRouter dashboard | Recommended |
| `Content-Type` | `application/json` | Yes (POST) |

## Key Formats

| Type | Pattern | Purpose |
|------|---------|---------|
| Standard key | `sk-or-v1-...` | API access (chat completions, models) |
| Management key | `sk-or-v1-...` | Key provisioning only (cannot call completions) |
| BYOK provider key | Varies by provider | Bring-your-own-key for direct provider access |

## Output

A completed setup leaves you with:

- `OPENROUTER_API_KEY` set in your environment (or a gitignored `.env` file), holding the `sk-or-v1-...` key from [openrouter.ai/keys](https://openrouter.ai/keys)
- A configured OpenAI-SDK client pointed at `https://openrouter.ai/api/v1` with `HTTP-Referer` and `X-Title` headers for dashboard attribution
- An auth-verification printout from `/api/v1/auth/key`: key label, credits used, credit limit, free-tier flag, and rate limit
- A test completion from the free model (`google/gemma-2-9b-it:free`) with its reply text and prompt/completion token counts

## Examples

Running the step-4 verification against a fresh key prints something like:

```text
Key: my-app-dev
Credits used: $0.0000
Credit limit: unlimited
Free tier: True
Rate limit: 10 req / 10s
```

Then the step-5 test request returns a greeting plus `Tokens: 9 in / 12 out`, confirming the key can call completions end-to-end. More worked examples: `references/examples.md`.

## Error Handling

| HTTP | Error Code | Cause | Fix |
|------|-----------|-------|-----|
| 401 | `invalid_api_key` | Key malformed, revoked, or wrong | Regenerate at [openrouter.ai/keys](https://openrouter.ai/keys) |
| 401 | `missing_api_key` | No `Authorization` header | Add `Authorization: Bearer sk-or-v1-...` |
| 403 | `insufficient_credits` | Zero balance on paid model | Add credits at [openrouter.ai/credits](https://openrouter.ai/credits) or use `:free` model |
| 403 | `key_disabled` | Key was disabled by admin | Re-enable in dashboard or create new key |

## Key Rotation

```python
# Programmatic key management via Management API
import requests

MGMT_KEY = os.environ["OPENROUTER_MGMT_KEY"]  # Management key, not API key

# Create a new key
resp = requests.post(
    "https://openrouter.ai/api/v1/keys",
    headers={"Authorization": f"Bearer {MGMT_KEY}"},
    json={"name": "my-app-prod-v2", "limit": 100.0},
)
new_key = resp.json()["data"]["key"]  # sk-or-v1-...

# List existing keys
keys = requests.get(
    "https://openrouter.ai/api/v1/keys",
    headers={"Authorization": f"Bearer {MGMT_KEY}"},
).json()
```

## Enterprise Considerations

- Store keys in a secrets manager (AWS Secrets Manager, GCP Secret Manager, Vault)
- Use management keys to provision per-service API keys programmatically
- Set credit limits per key to isolate blast radius
- Rotate keys on a schedule (90 days recommended)
- Add secret scanning to CI pipelines (e.g., `gitleaks`, `trufflehog`)
- Use BYOK for direct provider billing when volume justifies it

## References

- Examples | Errors
- [OpenRouter Quickstart](https://openrouter.ai/docs/quickstart) | [Auth Docs](https://openrouter.ai/docs/api/reference/authentication) | [Key Provisioning](https://openrouter.ai/docs/guides/overview/auth/provisioning-api-keys)

Files in this skill

  • SKILL.md6.4 KB
  • references/environment-setup.md714 B
  • references/errors.md478 B
  • references/examples.md3 KB

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.