# OpenRouter

> ZopNight registers 6 OpenRouter models through the AI Gateway, spanning several vendors: GPT-4o, Claude Sonnet and Haiku, Llama 3.1 70B and DeepSeek. OpenRouter is the multi-vendor path, so a single credential reaches several model families with spend still metered per team.

Source: https://zop.dev/integrations/ai-gateway/openrouter
Updated: 2026-08-20

---

## Common questions

### Why route through OpenRouter instead of each vendor directly?

One credential reaches several model families, which makes it the cheapest way to compare a routing posture across vendors without provisioning an account with each. The tradeoff is an extra hop and OpenRouter's own margin, worth it for breadth and less so once a workload has settled on one vendor.

### Which vendors does ZopNight reach through OpenRouter?

Six models spanning four vendors: OpenAI gpt-4o and gpt-4o-mini, Anthropic claude-sonnet-4.5 and claude-haiku-4.5, Meta llama-3.1-70b-instruct, and DeepSeek deepseek-chat.

### Do newly available OpenRouter models appear automatically?

Yes. Live model discovery runs against OpenRouter's /models endpoint, so a new model shows up without a ZopNight release.

## OpenAI, Anthropic, Llama and DeepSeek in one list

Six, deliberately spanning vendors:

- `or-gpt-4o`, `or-gpt-4o-mini`: OpenAI via OpenRouter
- `or-claude-sonnet` → claude-sonnet-4.5, `or-claude-haiku` → claude-haiku-4.5
- `or-llama-70b` → llama-3.1-70b-instruct
- `or-deepseek` → deepseek-chat

## Why route through OpenRouter at all

One credential reaches several model families, which makes it the cheapest way to A/B a routing
posture across vendors without provisioning accounts with each. The tradeoff is an extra hop
and OpenRouter's own margin, worth it for breadth, less so for a workload that has settled on
one vendor.

Live model discovery runs against OpenRouter's `/models` endpoint, so newly available models
appear without a ZopNight release.

## OpenRouter traffic bypasses ZopNight infrastructure

ZopNight never sits in your request path. The gateway runs on hosted LiteLLM; ZopNight
configures it, meters it and enforces the budget, but your prompts and completions do not
traverse our infrastructure. That distinction is why per-request cost attribution is possible
without us reading request bodies.

## One OpenRouter key per team, with a hard budget

Each team gets a virtual key with a hard USD budget and its own model allow-list. When a key
hits its cap it stops working. This is a limit, not an alert. Keys rotate and revoke
independently, so a leaked key is contained to one team's budget rather than the org's.

## Routing postures across OpenRouter vendors

Three postures decide which model serves a request: **Cost-saver**, **Balanced** and
**Quality-first**. Requests are classified into four semantic categories (coding, analysis and
reasoning, extraction and classification, chit-chat) and routed accordingly, so cheap models
take the traffic that does not need an expensive one.

A semantic cache sits in front, with strictness settings from strict (0.98 similarity) to loose
(0.90). On repetitive workloads the cache is usually a larger saving than the routing itself.