OpenAI with Empryo

OpenAI is built into Empryo. Save one API key and you can use OpenAI's GPT models for chat, code and any task-router slot. You can also set how much reasoning each model does.

What you get

Example models

gpt-5.5
gpt-5.4
gpt-5.4-mini
gpt-5.4-nano

When to use it

Pick OpenAI when you want to use GPT models directly. A common setup puts the largest GPT model on the ember (code-writing) slot and the smaller mini or nano models on research, web search and compaction. You pay more for the model that edits code and less for the models that read and summarize. If you want the lowest cost per task, compare against a gateway (LLM Gateway, OpenRouter). If you want everything to run on your own machine, use a local option (Ollama, LM Studio).

Set it up

1. Get an API keyLink to this section

Create a key at platform.openai.com. OpenAI keys start with sk-.

2. Save it to EmpryoLink to this section

bash

empryo --set-key openai sk-...

The key goes to your OS keychain when available (macOS Login Keychain, libsecret on Linux, DPAPI on Windows), with a file fallback otherwise. Confirm it was saved:

bash

empryo --list-providers

Or pass it per-launchLink to this section

Built-in providers also read environment variables, useful for CI or one-off sessions. Nothing is persisted:

bash

OPENAI_API_KEY=sk-... empryo

If a shell-exported key keeps overriding a stored one, flip the lookup order in ~/.empryo/config.json:

json

{ "keyPriority": "app" }

"app" resolves keychain → file → env. The default "env" checks env first.

3. Pick a modelLink to this section

Inside Empryo, press Ctrl+L and choose OpenAI, then a model. Or set it as the default in ~/.empryo/config.json:

json

{ "defaultModel": "openai/gpt-5.5" }

From the command line:

bash

empryo --list-models openai
empryo --model openai/gpt-5.4

Model strings are always openai/<model-id>, e.g. openai/gpt-5.5, openai/gpt-5.4-mini.

4. Tune reasoningLink to this section

GPT-5 series models reason. Control the depth in config:

json

{
  "thinking": { "mode": "adaptive" }
}

mode is "off", "adaptive", or "enabled". With "enabled", set an explicit thinking.budgetTokens (1024, 2048, 5000, 10000, 20000). "adaptive" lets Empryo scale effort to the task.

5. Route models per task (optional)Link to this section

You don't have to run one model for everything. The task router assigns models per job, so a cheap model handles search and cleanup while a strong one writes code:

json

{
  "taskRouter": {
    "ember":      "openai/gpt-5.5",
    "spark":      "openai/gpt-5.4-mini",
    "webSearch":  "openai/gpt-5.4-nano",
    "compact":    "openai/gpt-5.4-mini"
  }
}

ember runs code-writing agents, spark runs read-only research agents, webSearch runs the search agent, and compact handles context compaction. Anything unset falls back to taskRouter.default, then your active model.

Keys or subscriptions

OpenAI connects the way marked below. You can mix ways across task-router slots.

API keyOpenAIPaste a key once. Empryo keeps it in your system keychain, and you pay the provider for what you use.
Sign inApprove Empryo in your browser and use a plan or credits you already have. There is no key to copy.
On your machineRun open models on your own computer. No key, no per-token bill, and nothing has to leave your machine.
Any compatible APIOne block of JSON config turns any OpenAI-compatible endpoint into a provider, including your own server.

Keep going

Download Empryo All providers