OpenRouter

Route your OpenRouter API calls through AI SpendOps for automatic usage tracking and cost attribution.

Configuration

Setting	Value
Route	/v1/openrouter/*
Upstream	https://openrouter.ai/api
Auth header	Authorization: Bearer sk-or-...
Streaming usage	Always included

SDK base URL

https://proxy.aispendops.com/v1/openrouter/v1

Example

curl https://proxy.aispendops.com/v1/openrouter/v1/chat/completions \
  -H "Authorization: Bearer sk-or-your-openrouter-key" \
  -H "X-ASO-API-Key: aso_k_yourkey.secret" \
  -H "Content-Type: application/json" \
  -d '{"model":"anthropic/claude-sonnet-4-20250514","messages":[{"role":"user","content":"Hello"}]}'

Python SDK

from openai import OpenAI

client = OpenAI(
    api_key="sk-or-your-openrouter-key",
    base_url="https://proxy.aispendops.com/v1/openrouter/v1",
    default_headers={"X-ASO-API-Key": "aso_k_yourkey.secret"},
)

response = client.chat.completions.create(
    model="anthropic/claude-sonnet-4-20250514",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Usage fields

Field	Description
prompt_tokens	Input tokens
completion_tokens	Output tokens
total_tokens	Sum of prompt + completion tokens
cost	Actual cost charged by OpenRouter (provider_cost)

Notes

• OpenRouter is a multi-provider routing service. The provider_cost field is the actual amount charged and takes precedence over token-based cost calculations.
• OpenRouter always includes usage data in responses, including streaming.
• Model names use the format provider/model (e.g. anthropic/claude-sonnet-4-20250514).