Run your agents on OpenAI GPT models

Choose a GPT model for each Runbear agent and deploy it to Slack or Microsoft Teams. On the default runtime you can also pick Claude or Gemini for an agent when another model suits the job.
Or, book a demo

Teams already running Runbear

  • Matillion
  • Fireflies.ai
  • BCG
  • Minted
  • Mercor
  • Tabs
  • TaxDome
  • Peak Ace
  • Storykit
  • SYPartners

How to run a Runbear agent on GPT

  1. 01

    Create an agent

    New agents usually run on the Claude Agent SDK runtime, which offers Claude, GPT, and Gemini models. Describe the job and connect the knowledge and tools it needs.

  2. 02

    Pick a GPT model

    In the agent's Model Selection section, choose a GPT model, from the strongest reasoning tier to fast, inexpensive ones for high-volume questions.

  3. 03

    Deploy it

    Add the agent to Slack or Microsoft Teams. Usage runs on Runbear credits. On the Business and Enterprise plans you can use your own OpenAI API key instead, and credits then cover only a processing fee.

The model is a per-agent setting, so different agents in the same organization can run on different models. See how to build a no-code AI agent for Slack, or how shared AI agents for teams work across a whole company.

Hear from our Customers

“Runbear completely changed how we onboard external consultants. They get answers in seconds instead of waiting for me to come back from meetings. I got my calendar back.”
Project Leaderat Management Consultancy
“Really satisfied with Runbear—its seamless Slack integration for our tasks and documentation has boosted our team's efficiency and met our specific needs perfectly.”
Anthony Pitassiat Merchant Centric
“Runbear simplifies integrating Assistants and seamlessly connects webhooks/APIs to Teams, eliminating no-code challenges.”Read the case study
Julien Lopatoat PeakAce
“It’s saved us a lot of time. Before, we had people scouring the Slack channels for answers. Now they can just ask these questions directly to the docs and get the answers they need without human intervention.”
Todd Heckmannat LaserAway
“Runbear has made it very accessible to play around with OpenAI without needing a developer’s help. The ease of use and quick integration with platforms like Slack have been invaluable.”
Tej Tandonat Copilot AI
“Runbear worked seamlessly and was very easy to use, helping our TAs create custom AI assistants for each course.”
Ruddy Simonpourat the University of San Diego
“Discovering Runbear was a life saver for our project. It enabled us to swiftly integrate our AI assistant with Slack, enhancing team collaboration and speeding up our testing process.”
James Everestat Flock
“Runbear’s simplicity and customer support is second to none. We explored all sorts of application providers, but Runbear stood out for its innovation and support. Runbear allowed us to integrate seamlessly and provided prompt customer support throughout the entire process.”
Jed Kramat Got Game
“Looks like Runbear can solve a lot of our headaches and help automate our law firm!”
Milo Poplarat Fellow

OpenAI models FAQ

Yes. On the Claude Agent SDK runtime, the usual default, each agent can run on Claude, GPT, or Gemini models, and you pick the model per agent.

No. You build the agent in Runbear: write its instructions, connect its knowledge and tools, and choose the model. Runbear runs the model calls for you.

Yes, on the Business and Enterprise plans. Turn on Use my own OpenAI API key in the agent's API Key section and paste the key. OpenAI then bills your account directly for the model calls, and Runbear credits cover only a processing fee.

Yes. OpenAI Responses agents, created with Create manually and then OpenAI, run on GPT models and add a Reasoning section for effort and verbosity. They can deploy to every channel your plan includes.

Runbear charges by usage, not by seat. One subscription covers every teammate who uses your agents in Slack or Microsoft Teams. Plans include a set number of builders, the members of your Runbear organization who create and manage agents in the dashboard: 5 on Team and 10 on Business. Usage is metered in credits, based on the tokens each model call uses and the model you choose for each agent. Team is $99 per month with 20,000 credits, and Business is $399 per month with 100,000 credits.

Stop being the bottleneck. Start being the leader.

Your team needs your judgment, not your availability. Let Runbear handle the first pass so you can focus on the work that actually matters.

Want a walkthrough first? Book 20 minutes with our CEO