Help Center/ MaaS/ Model List
Updated on 2026-10-28 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.

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-5.3

Deep thinking (cannot be disabled)

Function calling

Prefix caching

Context length: 1M

Max input length: 1M

Max output length: 128K

Max CoT length: 128K

  • TPM: 2,000,000
  • RPM: 100

glm-5.2

Deep thinking (configurable)

Function calling

Context length: 1M

Max input length: 1M

Max output length: 128K

Max CoT 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 CoT length: 96K

  • TPM: 1,000,000
  • RPM: 100

deepseek-v4.1-flash-1017

Deep thinking (configurable)

Function calling

Prefix caching

Prefix completion

Image understanding

Context length: 1M

Max input length: 1M

Max output length: 384K

Max CoT length: 96K

Image limitations: A maximum of 600 images is supported. Each image referenced by a publicly accessible URL must be no larger than 32 MB. There are no resolution restrictions, but a resolution below 4096 × 2160 is recommended. Supported formats are JPEG, PNG, GIF, and WebP. When uploading images in Base64-encoded format, the entire request body must not exceed 5 MB. You are advised to use a publicly accessible image URL.

  • TPM: 2,000,000
  • RPM:100

deepseek-v4.1-flash

Deep thinking (configurable)

Function calling

Prefix caching

Image understanding

Context length: 1M

Max input length: 1M

Max output length: 384K

Max CoT length: 96K

Image limitations: A maximum of 600 images is supported. Each image referenced by a publicly accessible URL must be no larger than 32 MB. There are no resolution restrictions, but a resolution below 4096 × 2160 is recommended. Supported formats are JPEG, PNG, GIF, and WebP. When uploading images in Base64-encoded format, the entire request body must not exceed 5 MB. You are advised to use a publicly accessible image URL.

  • 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 CoT length: 96K

  • TPM: 60,000
  • RPM: 15

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-5.3

Deep thinking (cannot be disabled)

Function calling

Prefix caching

Context length: 1M

Max input length: 1M

Max output length: 128K

Max CoT length: 128K

  • TPM: 2,000,000
  • RPM: 100

glm-5.2

Deep thinking (configurable)

Function calling

Context length: 1M

Max input length: 1M

Max output length: 128K

Max CoT 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 CoT length: 96K

  • TPM: 1,000,000
  • RPM: 100

deepseek-v4.1-flash-1017

Deep thinking (configurable)

Function calling

Prefix caching

Prefix completion

Image understanding

Context length: 1M

Max input length: 1M

Max output length: 384K

Max CoT length: 96K

Image limitations: A maximum of 600 images is supported. Each image referenced by a publicly accessible URL must be no larger than 32 MB. There are no resolution restrictions, but a resolution below 4096 × 2160 is recommended. Supported formats are JPEG, PNG, GIF, and WebP. When uploading images in Base64-encoded format, the entire request body must not exceed 5 MB. You are advised to use a publicly accessible image URL.

  • TPM: 2,000,000
  • RPM:100

deepseek-v4.1-flash

Deep thinking (configurable)

Function calling

Prefix caching

Image understanding

Context length: 1M

Max input length: 1M

Max output length: 384K

Max CoT length: 96K

Image limitations: A maximum of 600 images is supported. Each image referenced by a publicly accessible URL must be no larger than 32 MB. There are no resolution restrictions, but a resolution below 4096 × 2160 is recommended. Supported formats are JPEG, PNG, GIF, and WebP. When uploading images in Base64-encoded format, the entire request body must not exceed 5 MB. You are advised to use a publicly accessible image URL.

  • 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 CoT length: 96K

  • TPM: 60,000
  • RPM: 15