A broad bench of models
OpenAI's GPT range covers chat, reasoning, and tool-calling work, so agents can match the model to the job.
The lane your agents think on when the job calls for a GPT model — your key, OpenAI's prices.
model lane · your key, OpenAI's prices
Missions
OpenAI's GPT range covers chat, reasoning, and tool-calling work, so agents can match the model to the job.
OpenAI bills the key you connect directly; Ahel adds nothing on top of it.
Once connected, the model picker fills with the GPT models your key can reach; you pick per agent.
The catalog
A model provider gives an agent a lane to think on, not actions to call — so there is no action catalogue here. Tool actions come from the other integrations.
Connect
Your own OpenAI key, created in their dashboard and pasted once into the Ahel desktop app.
FAQ
From OpenAI's own platform dashboard; paste it once in the Ahel desktop app and it stays in your runtime. Ahel is invite-only right now, with access opened in batches.
Whatever OpenAI charges your key — Ahel adds no markup and sells no usage tier of its own. Model usage appears on your OpenAI invoice, at OpenAI's prices.
The picker lists the models your key can actually reach — access depends on your OpenAI account, not on us. You pick the model per agent from that list.