# GLM in Taskade

> Which GLM models you can use in Taskade, what each one is good at, and how to pick between them.

- Source: https://www.taskade.com/docs/models/glm
- Section: Models
- Updated: 2026-10-17
- Index of all pages: https://www.taskade.com/docs/llms.txt

GLM in Taskade is the model to reach for when your instruction is incomplete. It exercises good judgment where details are unclear.

## GLM models available today

| Model | Good at | Speed | Intelligence | Cost | Availability |
| --- | --- | --- | --- | --- | --- |
| GLM 5.3 | Latest GLM for autonomous coding | Slow | Frontier | Medium | Max and Enterprise |
| GLM 5.2 | Autonomous coding | Slow | Frontier | Medium | Max and Enterprise |

## How to pick within GLM

- **GLM 5.3 or GLM 5.2** for autonomous coding runs, and for requests where you have deliberately left the details open. GLM 5.3 is the newer model, and both are in the medium cost band.

## 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](https://www.taskade.com/docs/models#tsk-rungs) sets a speed-to-depth trade-off and follows the catalog forward as models change.

## How GLM performs

We build the same apps on every family and publish what happened. See the [GLM build results](https://www.taskade.com/tsk/glm) for the test-by-test record.

## Next steps

- Compare every family in the [full catalog](https://www.taskade.com/docs/models/custom-engine).
- Read [how Taskade picks a model](https://www.taskade.com/docs/models) for Auto and the rungs.
- Open each GLM model from the [Zhipu models page](https://www.taskade.com/models/zai) to see its plans and test results.