Concierge + OpenAI.
Run Concierge on your own OpenAI account. Your digital employees work the same way, and you pay OpenAI directly.
- integration type
- AI model
- integration type
- to connect
- Minutes
- to connect
- approvals still apply
- Your rules
- approvals still apply
The problem
Some teams already have an OpenAI agreement, credits or data terms they want every AI call to fall under. With your own key, Concierge's agents run on your OpenAI account.
What it does.
Your key, your account
Add an OpenAI API key, plus your organization and project IDs if you use them.
Pick the model
Choose GPT-5.1, GPT-5 Mini or GPT-6 Luna for your agents.
Never charged twice
Calls on your own key are not taken from your Chargezen credits. OpenAI bills you.
Open models too
Prefer open models? A Fireworks key runs DeepSeek, Kimi, Qwen and GPT-OSS models.
How it works.
- 1
Create a key in OpenAI
In the project you want billed.
- 2
Add it to Chargezen
With organization and project IDs if you use them.
- 3
Pick GPT models
GPT-5.1, GPT-5 Mini or GPT-6 Luna.
- 4
Calls bill to OpenAI
Under your OpenAI terms.
What you get.
Answers in seconds
Customers get help right away, day or night.
Your team freed up
People focus on the conversations that need them.
Within your rules
Every action follows your policies and approvals.
Put a digital employee to work.
Concierge answers your customers, runs back-office work on its own computer and gets better every week. See it on your own store.
Common questions
Add your OpenAI API key.
Not for model calls on your key. Chargezen never charges credits for a workspace's own provider key.
No. This chooses the model behind Concierge. Connecting ChatGPT to your workspace is a separate connector.
Concierge Starter is $20 a month with 20,000 credits. Pro is $199 a month with 199,000 credits, or $1,990 a year. Phone and text charges are billed as used, and you can connect your own OpenAI or Anthropic account.
