GPT models in Taskade reward detailed requests. They follow a specific, well-described instruction closely, and they deliver quickly.
GPT models available today
| Model | Good at | Speed | Intelligence | Cost | Availability |
|---|---|---|---|---|---|
| GPT-6.1 Sol | Frontier reasoning for hard problems | Slow | Frontier | Medium | Every paid plan |
| GPT-6 Luna | Everyday building | Fast | High | Low | Every paid plan |
| GPT-5.6 Sol | Deepest reasoning for hard problems | Slow | Frontier | High | Max and Enterprise |
| GPT-5.6 Terra | Fast frontier all-rounder | Fast | Frontier | Medium | Max and Enterprise |
| GPT-5.6 Luna | Fast, economical quick tasks | Fast | High | Low | Every paid plan |
How to pick within GPT
- GPT-6.1 Sol for a hard problem where you can wait for the answer. It is the newest deep-reasoning GPT model, and it costs less than GPT-5.6 Sol.
- GPT-5.6 Sol for the deepest reasoning in the family, at the highest cost band.
- GPT-5.6 Terra when you want frontier quality without the wait. It is the fast all-rounder of the family.
- GPT-6 Luna or GPT-5.6 Luna for everyday building. Both are fast, and both are in the low cost band. GPT-6 Luna is the newer model.
GPT-6.1 Sol replaced GPT-6 Sol. A chat, agent, or automation step that saved GPT-6 Sol now runs on GPT-6.1 Sol, at a credit rate no higher than before. The step shows no error, and it needs no edit from you.
This family repays specificity. Describe the screens, the fields, and the behavior you want, and the result tracks the description closely.
Set it on an agent or a chat
Open the model menu in the builder chat or on an agent. In the builder chat, open More models and choose from the provider groups. In the agent editor, choose from All Models. The choice applies only to that surface. An AI step in an automation offers TSK-Auto and the rungs only.
If you do not want to pin a model, a rung sets a speed-to-depth trade-off and follows the catalog forward as models change.
How GPT performs
We build the same apps on every family and publish what happened. See the GPT build results for the test-by-test record.
Next steps
- Compare every family in the full catalog.
- Read how Taskade picks a model for Auto and the rungs.
- Open each GPT model from the OpenAI models page to see its plans and test results.