provider

Use OpenRouter with Empryo with Empryo

OpenRouter is a built-in Empryo provider: one API key unlocks 200+ models from every major lab behind a single OpenAI-compatible endpoint. Set `openrouter` once and switch between Claude, GPT, Gemini, Grok, and open-weight models from inside Empryo without juggling separate accounts or keys.

Popular models

anthropic/claude-opus-4.5anthropic/claude-sonnet-4.5anthropic/claude-haiku-4.5openai/gpt-5.1openai/gpt-5.1-miniopenai/o4-minigoogle/gemini-2.5-progoogle/gemini-2.5-flashx-ai/grok-4deepseek/deepseek-v3.2deepseek/deepseek-r1qwen/qwen3-codermoonshotai/kimi-k2z-ai/glm-4.6meta-llama/llama-4-maverick

Setup

OpenRouter ships as one of Empryo's 21 built-in providers, so there is no custom config block to write.

1. Get a key

Create an API key at openrouter.ai/keys. OpenRouter keys are prefixed sk-or-.

2. Save it

empryo --set-key openrouter sk-or-...

The key is stored in your OS keychain (Login Keychain on macOS, libsecret on Linux, DPAPI on Windows), with an encrypted file fallback. See configuration for backends and lookup order.

3. Pick a model

Launch Empryo, press Ctrl+L, and choose any OpenRouter model. Or set it as your default in ~/.empryo/config.json:

{
  "defaultModel": "openrouter/anthropic/claude-sonnet-4.5"
}

Empryo's OpenRouter model strings are openrouter/<vendor>/<model> — e.g. openrouter/openai/gpt-5.1, openrouter/google/gemini-2.5-pro, openrouter/x-ai/grok-4.

4. (Optional) Route different jobs to different models

The single OpenRouter key powers every slot in Empryo's task router, so you can run a cheap model for research and a strong one for code edits — no extra keys:

{
  "taskRouter": {
    "ember":   "openrouter/anthropic/claude-sonnet-4.5",
    "spark":   "openrouter/deepseek/deepseek-v3.2",
    "compact": "openrouter/google/gemini-2.5-flash"
  }
}

Per-launch key

For one-off sessions or CI you can pass the key via env var instead of storing it:

OPENROUTER_API_KEY=sk-or-... empryo

Inspect what's configured with empryo --list-providers and empryo --list-models openrouter.

When to use it

Pick OpenRouter when you want breadth and flexibility from a single key. It fronts 200+ models from Anthropic, OpenAI, Google, xAI, DeepSeek, Qwen, Moonshot, Z.ai, Meta and more behind one OpenAI-compatible endpoint, with normalized billing, automatic provider failover, and the ability to A/B different models against the same task without opening new accounts. That makes it a natural fit for Empryo's per-slot task router — assign a frontier model to code edits and a cheap fast model to research and compaction, all funded by one balance. It is also handy for reaching open-weight models (Qwen3-Coder, GLM-4.6, Kimi K2, Llama 4) that you might not have direct accounts for. The trade-offs to weigh: routing through OpenRouter adds a small markup over going direct to a lab, you depend on a third party sitting between you and the model, and latency can vary with the upstream provider OpenRouter selects. If you only ever use one lab's models, a direct provider key (Anthropic, OpenAI, Google) is simpler and slightly cheaper; if you want minimum-cost frontier access across labs, compare against Empryo's other gateway options like LLM Gateway. But for sheer model coverage from one key, OpenRouter is hard to beat — and Empryo treats it as a first-class built-in, no custom provider block required.

Get Empryo All providers