Updated on 2026-09-10 GMT+08:00

Model List

MaaS provides multiple models for you to use. You can easily integrate model services into your business by following tutorials or API documentation.

Model Recommendation

GLM-5.2	GLM-5.1
GLM-5.2 is Zhipu AI's next-generation flagship model, officially launched and open-sourced on June 17, 2026. Its core features include: Enhanced long-horizon task capability: reduces context drift and goal forgetting in complex tasks. State-of-the-art coding and long-horizon task evaluation: achieves open-source SOTA performance, delivering greater stability in complex system engineering and deep debugging. Improved real-world development experience: more reliable project-level context handling, adherence to engineering standards, and multi-platform development. Support for 1M sequence length, with maximum input of 1M, maximum output of 128K, and maximum CoT length of 64K. It supports chain-of-thought and function calling.	GLM-5.1 is the latest flagship model from Zhipu. It provides enhanced coding capabilities and improved performance in long-horizon tasks. It can autonomously work for up to 8 hours in a single task, covering the entire process from planning and execution to iterative optimization and delivering engineering-level results. While GLM-5.1 matches Claude Opus 4.6 in general intelligence and raw coding proficiency, it significantly outperforms the global frontier in long-horizon sustained execution. It excels at autonomous, multi-stage tasks over extended periods, making it the ideal foundation for building highly resilient autonomous agents and long-horizon coding engines. It supports sequence lengths up to 198K, with a maximum input of 192K, a maximum output of 128K, and a maximum thought chain of 96K. It supports chain-of-thought and function calling.

GLM-5.2

GLM-5.1

GLM-5.2 is Zhipu AI's next-generation flagship model, officially launched and open-sourced on June 17, 2026. Its core features include:

Enhanced long-horizon task capability: reduces context drift and goal forgetting in complex tasks.

State-of-the-art coding and long-horizon task evaluation: achieves open-source SOTA performance, delivering greater stability in complex system engineering and deep debugging.

Improved real-world development experience: more reliable project-level context handling, adherence to engineering standards, and multi-platform development.

Support for 1M sequence length, with maximum input of 1M, maximum output of 128K, and maximum CoT length of 64K.

It supports chain-of-thought and function calling.

GLM-5.1 is the latest flagship model from Zhipu. It provides enhanced coding capabilities and improved performance in long-horizon tasks. It can autonomously work for up to 8 hours in a single task, covering the entire process from planning and execution to iterative optimization and delivering engineering-level results.

While GLM-5.1 matches Claude Opus 4.6 in general intelligence and raw coding proficiency, it significantly outperforms the global frontier in long-horizon sustained execution. It excels at autonomous, multi-stage tasks over extended periods, making it the ideal foundation for building highly resilient autonomous agents and long-horizon coding engines.

It supports sequence lengths up to 198K, with a maximum input of 192K, a maximum output of 128K, and a maximum thought chain of 96K.

It supports chain-of-thought and function calling.

Text Generation

Tutorial: Text Generation; API: Sending a Chat Request (Chat/Post); price: MaaS Text Generation Models.

**Table 1** Model list
Model Parameter (Model ID)	Supported Capabilities	Length Limit	Default Rate Limit
glm-5.2	Deep thinking (configurable) Function calling	Context length: 1M Max input length: 1M Max output length: 128K Max chain-of-thought length: 64K	TPM: 1,000,000 RPM: 100
glm-5.1	Deep thinking (configurable) Function calling	Context length: 198K Max input length: 192K Max output length: 128K Max chain-of-thought length: 96K	TPM: 1,000,000 RPM: 100
deepseek-v4-flash	Deep thinking (configurable) Function calling Prefix completion	Context length: 1M Max input length: 1M Max output length: 384K Max chain-of-thought length: 96K	TPM: 60,000 RPM: 15
deepseek-v4-pro	Deep thinking (configurable) Function calling Prefix completion	Context length: 1M Max input length: 1M Max output length: 128K Max chain-of-thought length: 96K	TPM: 30,000 RPM: 3

Deep Thinking

Tutorial: Deep Thinking; API: Sending a Chat Request (Chat/Post); price: MaaS Text Generation Models.

**Table 2** Model list
Model Parameter (Model ID)	Supported Capabilities	Length Limit	Default Rate Limit
glm-5.2	Deep thinking (configurable) Function calling	Context length: 1M Max input length: 1M Max output length: 128K Max chain-of-thought length: 64K	TPM: 1,000,000 RPM: 100
glm-5.1	Deep thinking (configurable) Function calling	Context length: 198K Max input length: 192K Max output length: 128K Max chain-of-thought length: 96K	TPM: 1,000,000 RPM: 100
deepseek-v4-flash	Deep thinking (configurable) Function calling Prefix completion	Context length: 1M Max input length: 1M Max output length: 384K Max chain-of-thought length: 96K	TPM: 60,000 RPM: 15
deepseek-v4-pro	Deep thinking (configurable) Function calling Prefix completion	Context length: 1M Max input length: 1M Max output length: 128K Max chain-of-thought length: 96K	TPM: 30,000 RPM: 3

Model List

Model Recommendation

Text Generation

Deep Thinking

What is your overall rating for this page?