Last updated: 2026-04-20

OpenRouter Integration

Route OpenRouter API calls through SpendLil.

SpendLil proxies OpenRouter's API. Swap openrouter.ai/api for openrouter.gateway.spendlil.ai and add X-SpendLil-Key. OpenRouter is OpenAI-compatible — use the OpenAI SDK with the OpenRouter gateway.

URL Pattern

diff Before → After 
- POST https://openrouter.ai/api/v1/chat/completions
+ POST https://openrouter.gateway.spendlil.ai/v1/chat/completions

OpenAI SDK (Python)

python Use the OpenAI SDK with the OpenRouter gateway 
import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ['OPENROUTER_API_KEY'],
    base_url='https://openrouter.gateway.spendlil.ai/v1',
    default_headers={'X-SpendLil-Key': os.environ['SPENDLIL_KEY']},
)

response = client.chat.completions.create(
    model='anthropic/claude-sonnet-4-5',
    messages=[{'role': 'user', 'content': 'Hello'}],
)
print(response.choices[0].message.content)

cURL

bash Direct HTTP request 
curl https://openrouter.gateway.spendlil.ai/v1/chat/completions \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  -H "X-SpendLil-Key: $SPENDLIL_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "anthropic/claude-sonnet-4-5",
    "messages": [{"role": "user", "content": "Hello"}]
  }'
ℹ One gateway, many models

OpenRouter routes to hundreds of models under a single OpenAI-compatible API. SpendLil tracks each model's usage and cost individually, letting you see exactly which OpenRouter-backed models are costing what.