Zhipu · models in Taskade

Zhipu models in Taskade

GLM 5.2 and GLM 5.3 from Zhipu are in the model menu now. We tested GLM 5 and GLM 4.7 in TSK-1, but they are not in Taskade. Their test results stay here. GLM 5.3 Flash is not in the Taskade model menu. We ran it in preview tests, which the TSK-1 ranking does not count.

In Taskade now
2In the model menu or on your own key
TSK Score
63/ 100GLM family, our app-building test
Newest release
GLM 5.3 Flash

Available now

Zhipu models in Taskade: Available now
ModelResult
GLM 5.2AvailableReleased 1M contextYour key: OpenRouter, Together AI, Cloudflare Workers AITested
GLM 5.3AvailableReleased 1M contextYour key: Fireworks, Z.ai, Cloudflare Workers AITested

Tested, not in Taskade

We tested these models in TSK-1 or in unranked preview runs, and Taskade does not offer them. Their results stay here.

Zhipu models in Taskade: Tested, not in Taskade
ModelResult
GLM 5Not in TaskadeReleased 205K contextWorks 1/1From 1 build
GLM 4.7Not in TaskadeReleased 205K contextGapsFrom 1 build
GLM 5.3 FlashNot in TaskadeReleased 1M contextPreview

Context is how much a model can read at once, counted in tokens. A token is about three quarters of a word.
Published specs from the model maker, via models.dev (MIT).

TSK-1 scorecard for the GLM family

TSK Score

GLM family, every version tested in TSK-1, our app-building test

TSK Score 63 out of 100
Interfaceready to share
Emerging
Taskcompletes your task
Strong
Memorykeeps your data
Emerging
Adapthandles follow-up edits
Strong

The model that said no.

More

It considered adding a sign-in screen, decided the brief had not asked for one, and offered it as a suggestion instead. The only model to push back rather than quietly add something. Its apps have saved real data since an August test.

Where GLM ranks

TSK Score out of 100.

  1. 1GPT88 out of 100
  2. 2Claude75 out of 100
  3. 2DeepSeek75 out of 100
  4. 2Kimi75 out of 100
  5. 2Grok75 out of 100
  6. 6GLM63 out of 100
  7. 7Qwen50 out of 100
  8. 8Gemini44 out of 100

The whole Zhipu lineup

Every Zhipu model that models.dev lists, newest first. A model that runs in Taskade links its page here. Every other name opens models.dev in a new tab.

Every Zhipu model, newest first, and its status in Taskade
ModelIn Taskade
GLM 5.3 Flash1M contextNot in Taskade
GLM 5.31M contextAvailable
GLM 5.21M contextAvailable
GLM 5.1200K contextNot in Taskade
GLM 5V Turbo200K contextNot in Taskade
GLM 5 Turbo200K contextNot in Taskade
GLM 5205K contextNot in Taskade
GLM 4.7 Flash200K contextNot in Taskade
GLM 4.7 FlashX200K contextNot in Taskade
GLM ImageImage10K contextNot in Taskade
Show 9 more
Every Zhipu model, newest first, continued
ModelIn Taskade
GLM 4.7205K contextNot in Taskade
AutoGLM Phone 9B Multilingual66K contextNot in Taskade
GLM 4.6V128K contextNot in Taskade
GLM 4.6V Flash128K contextNot in Taskade
GLM 4.6205K contextNot in Taskade
GLM 4.5V64K contextNot in Taskade
GLM 4.5131K contextNot in Taskade
GLM 4.5 Air131K contextNot in Taskade
GLM 4.5 Flash131K contextNot in Taskade

Published specs from the model maker, via models.dev (MIT).

FAQ

Which Zhipu models can I use in Taskade?

GLM 5.2 and GLM 5.3 are in the Taskade model menu now. Each model page names the plan it needs.

Which Zhipu model builds apps best in TSK-1?

GLM 5 works on 1 of 1 request in the TSK-1 Build arena, the best result of the Zhipu models we tested.

Can I use my own API key for Zhipu models?

Yes. In a custom agent, a key from OpenRouter, Fireworks, Together AI, Z.ai or Cloudflare Workers AI can pick Zhipu models. Each provider page names the plan it needs and the models its key can pick.