diff --git a/models/z-ai/glm-4.5-air-subscription.yaml b/models/z-ai/glm-4.5-air-subscription.yaml
new file mode 100644
index 0000000..39f70c5
--- /dev/null
+++ b/models/z-ai/glm-4.5-air-subscription.yaml
@@ -0,0 +1,41 @@
+# yaml-language-server: $schema=https://modelparams.dev/api/v1/schema.json
+provider: z-ai
+authType: subscription
+model: glm-4.5-air
+params:
+  - path: max_tokens
+    type: integer
+    label: Max tokens
+    description: Maximum number of tokens to generate in the response.
+    range:
+      min: 1
+    group: generation_length
+  - path: temperature
+    type: number
+    label: Temperature
+    description: Controls randomness. Lower values make outputs more focused; higher values make them more varied.
+    default: 0.6
+    range:
+      min: 0
+      max: 1
+      step: 0.1
+    group: sampling
+  - path: top_p
+    type: number
+    label: Top P
+    description: Controls nucleus sampling by limiting generation to tokens within the selected cumulative probability.
+    default: 0.95
+    range:
+      min: 0.01
+      max: 1
+      step: 0.01
+    group: sampling
+  - path: thinking.type
+    type: enum
+    label: Thinking mode
+    description: Toggles the model's extended reasoning before it produces the final answer.
+    default: enabled
+    values:
+      - enabled
+      - disabled
+    group: reasoning
diff --git a/models/z-ai/glm-4.5-air.yaml b/models/z-ai/glm-4.5-air.yaml
new file mode 100644
index 0000000..67bb627
--- /dev/null
+++ b/models/z-ai/glm-4.5-air.yaml
@@ -0,0 +1,62 @@
+# yaml-language-server: $schema=https://modelparams.dev/api/v1/schema.json
+provider: z-ai
+authType: api_key
+model: glm-4.5-air
+params:
+  - path: max_tokens
+    type: integer
+    label: Max tokens
+    description: Maximum number of tokens to generate in the response.
+    range:
+      min: 1
+    group: generation_length
+  - path: temperature
+    type: number
+    label: Temperature
+    description: Controls randomness. Lower values make outputs more focused; higher values make them more varied.
+    default: 0.6
+    range:
+      min: 0
+      max: 1
+      step: 0.1
+    group: sampling
+    applicability:
+      except:
+        do_sample: false
+  - path: top_p
+    type: number
+    label: Top P
+    description: Controls nucleus sampling by limiting generation to tokens within the selected cumulative probability.
+    default: 0.95
+    range:
+      min: 0.01
+      max: 1
+      step: 0.01
+    group: sampling
+    applicability:
+      except:
+        do_sample: false
+  - path: do_sample
+    type: boolean
+    label: Do sample
+    description: When false, the model uses greedy decoding and ignores temperature and top_p.
+    default: true
+    group: sampling
+  - path: thinking.type
+    type: enum
+    label: Thinking mode
+    description: Toggles the model's extended reasoning before it produces the final answer.
+    default: enabled
+    values:
+      - enabled
+      - disabled
+    group: reasoning
+  - path: response_format.type
+    type: enum
+    label: Response format
+    description: Forces the response into plain text or a JSON object.
+    default: text
+    values:
+      - text
+      - json_object
+    group: output_format
diff --git a/models/z-ai/glm-4.5-airx.yaml b/models/z-ai/glm-4.5-airx.yaml
new file mode 100644
index 0000000..3fa7d81
--- /dev/null
+++ b/models/z-ai/glm-4.5-airx.yaml
@@ -0,0 +1,62 @@
+# yaml-language-server: $schema=https://modelparams.dev/api/v1/schema.json
+provider: z-ai
+authType: api_key
+model: glm-4.5-airx
+params:
+  - path: max_tokens
+    type: integer
+    label: Max tokens
+    description: Maximum number of tokens to generate in the response.
+    range:
+      min: 1
+    group: generation_length
+  - path: temperature
+    type: number
+    label: Temperature
+    description: Controls randomness. Lower values make outputs more focused; higher values make them more varied.
+    default: 0.6
+    range:
+      min: 0
+      max: 1
+      step: 0.1
+    group: sampling
+    applicability:
+      except:
+        do_sample: false
+  - path: top_p
+    type: number
+    label: Top P
+    description: Controls nucleus sampling by limiting generation to tokens within the selected cumulative probability.
+    default: 0.95
+    range:
+      min: 0.01
+      max: 1
+      step: 0.01
+    group: sampling
+    applicability:
+      except:
+        do_sample: false
+  - path: do_sample
+    type: boolean
+    label: Do sample
+    description: When false, the model uses greedy decoding and ignores temperature and top_p.
+    default: true
+    group: sampling
+  - path: thinking.type
+    type: enum
+    label: Thinking mode
+    description: Toggles the model's extended reasoning before it produces the final answer.
+    default: enabled
+    values:
+      - enabled
+      - disabled
+    group: reasoning
+  - path: response_format.type
+    type: enum
+    label: Response format
+    description: Forces the response into plain text or a JSON object.
+    default: text
+    values:
+      - text
+      - json_object
+    group: output_format
diff --git a/models/z-ai/glm-4.5-flash.yaml b/models/z-ai/glm-4.5-flash.yaml
new file mode 100644
index 0000000..f7a0a0e
--- /dev/null
+++ b/models/z-ai/glm-4.5-flash.yaml
@@ -0,0 +1,62 @@
+# yaml-language-server: $schema=https://modelparams.dev/api/v1/schema.json
+provider: z-ai
+authType: api_key
+model: glm-4.5-flash
+params:
+  - path: max_tokens
+    type: integer
+    label: Max tokens
+    description: Maximum number of tokens to generate in the response.
+    range:
+      min: 1
+    group: generation_length
+  - path: temperature
+    type: number
+    label: Temperature
+    description: Controls randomness. Lower values make outputs more focused; higher values make them more varied.
+    default: 0.6
+    range:
+      min: 0
+      max: 1
+      step: 0.1
+    group: sampling
+    applicability:
+      except:
+        do_sample: false
+  - path: top_p
+    type: number
+    label: Top P
+    description: Controls nucleus sampling by limiting generation to tokens within the selected cumulative probability.
+    default: 0.95
+    range:
+      min: 0.01
+      max: 1
+      step: 0.01
+    group: sampling
+    applicability:
+      except:
+        do_sample: false
+  - path: do_sample
+    type: boolean
+    label: Do sample
+    description: When false, the model uses greedy decoding and ignores temperature and top_p.
+    default: true
+    group: sampling
+  - path: thinking.type
+    type: enum
+    label: Thinking mode
+    description: Toggles the model's extended reasoning before it produces the final answer.
+    default: enabled
+    values:
+      - enabled
+      - disabled
+    group: reasoning
+  - path: response_format.type
+    type: enum
+    label: Response format
+    description: Forces the response into plain text or a JSON object.
+    default: text
+    values:
+      - text
+      - json_object
+    group: output_format
diff --git a/models/z-ai/glm-4.5-x.yaml b/models/z-ai/glm-4.5-x.yaml
new file mode 100644
index 0000000..31a4c27
--- /dev/null
+++ b/models/z-ai/glm-4.5-x.yaml
@@ -0,0 +1,62 @@
+# yaml-language-server: $schema=https://modelparams.dev/api/v1/schema.json
+provider: z-ai
+authType: api_key
+model: glm-4.5-x
+params:
+  - path: max_tokens
+    type: integer
+    label: Max tokens
+    description: Maximum number of tokens to generate in the response.
+    range:
+      min: 1
+    group: generation_length
+  - path: temperature
+    type: number
+    label: Temperature
+    description: Controls randomness. Lower values make outputs more focused; higher values make them more varied.
+    default: 0.6
+    range:
+      min: 0
+      max: 1
+      step: 0.1
+    group: sampling
+    applicability:
+      except:
+        do_sample: false
+  - path: top_p
+    type: number
+    label: Top P
+    description: Controls nucleus sampling by limiting generation to tokens within the selected cumulative probability.
+    default: 0.95
+    range:
+      min: 0.01
+      max: 1
+      step: 0.01
+    group: sampling
+    applicability:
+      except:
+        do_sample: false
+  - path: do_sample
+    type: boolean
+    label: Do sample
+    description: When false, the model uses greedy decoding and ignores temperature and top_p.
+    default: true
+    group: sampling
+  - path: thinking.type
+    type: enum
+    label: Thinking mode
+    description: Toggles the model's extended reasoning before it produces the final answer.
+    default: enabled
+    values:
+      - enabled
+      - disabled
+    group: reasoning
+  - path: response_format.type
+    type: enum
+    label: Response format
+    description: Forces the response into plain text or a JSON object.
+    default: text
+    values:
+      - text
+      - json_object
+    group: output_format
diff --git a/models/z-ai/glm-4.5.yaml b/models/z-ai/glm-4.5.yaml
new file mode 100644
index 0000000..b93d2ef
--- /dev/null
+++ b/models/z-ai/glm-4.5.yaml
@@ -0,0 +1,62 @@
+# yaml-language-server: $schema=https://modelparams.dev/api/v1/schema.json
+provider: z-ai
+authType: api_key
+model: glm-4.5
+params:
+  - path: max_tokens
+    type: integer
+    label: Max tokens
+    description: Maximum number of tokens to generate in the response.
+    range:
+      min: 1
+    group: generation_length
+  - path: temperature
+    type: number
+    label: Temperature
+    description: Controls randomness. Lower values make outputs more focused; higher values make them more varied.
+    default: 0.6
+    range:
+      min: 0
+      max: 1
+      step: 0.1
+    group: sampling
+    applicability:
+      except:
+        do_sample: false
+  - path: top_p
+    type: number
+    label: Top P
+    description: Controls nucleus sampling by limiting generation to tokens within the selected cumulative probability.
+    default: 0.95
+    range:
+      min: 0.01
+      max: 1
+      step: 0.01
+    group: sampling
+    applicability:
+      except:
+        do_sample: false
+  - path: do_sample
+    type: boolean
+    label: Do sample
+    description: When false, the model uses greedy decoding and ignores temperature and top_p.
+    default: true
+    group: sampling
+  - path: thinking.type
+    type: enum
+    label: Thinking mode
+    description: Toggles the model's extended reasoning before it produces the final answer.
+    default: enabled
+    values:
+      - enabled
+      - disabled
+    group: reasoning
+  - path: response_format.type
+    type: enum
+    label: Response format
+    description: Forces the response into plain text or a JSON object.
+    default: text
+    values:
+      - text
+      - json_object
+    group: output_format
diff --git a/models/z-ai/glm-4.6.yaml b/models/z-ai/glm-4.6.yaml
new file mode 100644
index 0000000..99ff0a0
--- /dev/null
+++ b/models/z-ai/glm-4.6.yaml
@@ -0,0 +1,62 @@
+# yaml-language-server: $schema=https://modelparams.dev/api/v1/schema.json
+provider: z-ai
+authType: api_key
+model: glm-4.6
+params:
+  - path: max_tokens
+    type: integer
+    label: Max tokens
+    description: Maximum number of tokens to generate in the response.
+    range:
+      min: 1
+    group: generation_length
+  - path: temperature
+    type: number
+    label: Temperature
+    description: Controls randomness. Lower values make outputs more focused; higher values make them more varied.
+    default: 1
+    range:
+      min: 0
+      max: 1
+      step: 0.1
+    group: sampling
+    applicability:
+      except:
+        do_sample: false
+  - path: top_p
+    type: number
+    label: Top P
+    description: Controls nucleus sampling by limiting generation to tokens within the selected cumulative probability.
+    default: 0.95
+    range:
+      min: 0.01
+      max: 1
+      step: 0.01
+    group: sampling
+    applicability:
+      except:
+        do_sample: false
+  - path: do_sample
+    type: boolean
+    label: Do sample
+    description: When false, the model uses greedy decoding and ignores temperature and top_p.
+    default: true
+    group: sampling
+  - path: thinking.type
+    type: enum
+    label: Thinking mode
+    description: Toggles the model's extended reasoning before it produces the final answer.
+    default: enabled
+    values:
+      - enabled
+      - disabled
+    group: reasoning
+  - path: response_format.type
+    type: enum
+    label: Response format
+    description: Forces the response into plain text or a JSON object.
+    default: text
+    values:
+      - text
+      - json_object
+    group: output_format
diff --git a/models/z-ai/glm-4.7-flash.yaml b/models/z-ai/glm-4.7-flash.yaml
new file mode 100644
index 0000000..5275eef
--- /dev/null
+++ b/models/z-ai/glm-4.7-flash.yaml
@@ -0,0 +1,62 @@
+# yaml-language-server: $schema=https://modelparams.dev/api/v1/schema.json
+provider: z-ai
+authType: api_key
+model: glm-4.7-flash
+params:
+  - path: max_tokens
+    type: integer
+    label: Max tokens
+    description: Maximum number of tokens to generate in the response.
+    range:
+      min: 1
+    group: generation_length
+  - path: temperature
+    type: number
+    label: Temperature
+    description: Controls randomness. Lower values make outputs more focused; higher values make them more varied.
+    default: 1
+    range:
+      min: 0
+      max: 1
+      step: 0.1
+    group: sampling
+    applicability:
+      except:
+        do_sample: false
+  - path: top_p
+    type: number
+    label: Top P
+    description: Controls nucleus sampling by limiting generation to tokens within the selected cumulative probability.
+    default: 0.95
+    range:
+      min: 0.01
+      max: 1
+      step: 0.01
+    group: sampling
+    applicability:
+      except:
+        do_sample: false
+  - path: do_sample
+    type: boolean
+    label: Do sample
+    description: When false, the model uses greedy decoding and ignores temperature and top_p.
+    default: true
+    group: sampling
+  - path: thinking.type
+    type: enum
+    label: Thinking mode
+    description: Toggles the model's extended reasoning before it produces the final answer.
+    default: enabled
+    values:
+      - enabled
+      - disabled
+    group: reasoning
+  - path: response_format.type
+    type: enum
+    label: Response format
+    description: Forces the response into plain text or a JSON object.
+    default: text
+    values:
+      - text
+      - json_object
+    group: output_format
diff --git a/models/z-ai/glm-4.7-flashx.yaml b/models/z-ai/glm-4.7-flashx.yaml
new file mode 100644
index 0000000..cb473fe
--- /dev/null
+++ b/models/z-ai/glm-4.7-flashx.yaml
@@ -0,0 +1,62 @@
+# yaml-language-server: $schema=https://modelparams.dev/api/v1/schema.json
+provider: z-ai
+authType: api_key
+model: glm-4.7-flashx
+params:
+  - path: max_tokens
+    type: integer
+    label: Max tokens
+    description: Maximum number of tokens to generate in the response.
+    range:
+      min: 1
+    group: generation_length
+  - path: temperature
+    type: number
+    label: Temperature
+    description: Controls randomness. Lower values make outputs more focused; higher values make them more varied.
+    default: 1
+    range:
+      min: 0
+      max: 1
+      step: 0.1
+    group: sampling
+    applicability:
+      except:
+        do_sample: false
+  - path: top_p
+    type: number
+    label: Top P
+    description: Controls nucleus sampling by limiting generation to tokens within the selected cumulative probability.
+    default: 0.95
+    range:
+      min: 0.01
+      max: 1
+      step: 0.01
+    group: sampling
+    applicability:
+      except:
+        do_sample: false
+  - path: do_sample
+    type: boolean
+    label: Do sample
+    description: When false, the model uses greedy decoding and ignores temperature and top_p.
+    default: true
+    group: sampling
+  - path: thinking.type
+    type: enum
+    label: Thinking mode
+    description: Toggles the model's extended reasoning before it produces the final answer.
+    default: enabled
+    values:
+      - enabled
+      - disabled
+    group: reasoning
+  - path: response_format.type
+    type: enum
+    label: Response format
+    description: Forces the response into plain text or a JSON object.
+    default: text
+    values:
+      - text
+      - json_object
+    group: output_format
diff --git a/models/z-ai/glm-4.7-subscription.yaml b/models/z-ai/glm-4.7-subscription.yaml
new file mode 100644
index 0000000..eb5280f
--- /dev/null
+++ b/models/z-ai/glm-4.7-subscription.yaml
@@ -0,0 +1,41 @@
+# yaml-language-server: $schema=https://modelparams.dev/api/v1/schema.json
+provider: z-ai
+authType: subscription
+model: glm-4.7
+params:
+  - path: max_tokens
+    type: integer
+    label: Max tokens
+    description: Maximum number of tokens to generate in the response.
+    range:
+      min: 1
+    group: generation_length
+  - path: temperature
+    type: number
+    label: Temperature
+    description: Controls randomness. Lower values make outputs more focused; higher values make them more varied.
+    default: 1
+    range:
+      min: 0
+      max: 1
+      step: 0.1
+    group: sampling
+  - path: top_p
+    type: number
+    label: Top P
+    description: Controls nucleus sampling by limiting generation to tokens within the selected cumulative probability.
+    default: 0.95
+    range:
+      min: 0.01
+      max: 1
+      step: 0.01
+    group: sampling
+  - path: thinking.type
+    type: enum
+    label: Thinking mode
+    description: Toggles the model's extended reasoning before it produces the final answer.
+    default: enabled
+    values:
+      - enabled
+      - disabled
+    group: reasoning
diff --git a/models/z-ai/glm-4.7.yaml b/models/z-ai/glm-4.7.yaml
new file mode 100644
index 0000000..dc96331
--- /dev/null
+++ b/models/z-ai/glm-4.7.yaml
@@ -0,0 +1,62 @@
+# yaml-language-server: $schema=https://modelparams.dev/api/v1/schema.json
+provider: z-ai
+authType: api_key
+model: glm-4.7
+params:
+  - path: max_tokens
+    type: integer
+    label: Max tokens
+    description: Maximum number of tokens to generate in the response.
+    range:
+      min: 1
+    group: generation_length
+  - path: temperature
+    type: number
+    label: Temperature
+    description: Controls randomness. Lower values make outputs more focused; higher values make them more varied.
+    default: 1
+    range:
+      min: 0
+      max: 1
+      step: 0.1
+    group: sampling
+    applicability:
+      except:
+        do_sample: false
+  - path: top_p
+    type: number
+    label: Top P
+    description: Controls nucleus sampling by limiting generation to tokens within the selected cumulative probability.
+    default: 0.95
+    range:
+      min: 0.01
+      max: 1
+      step: 0.01
+    group: sampling
+    applicability:
+      except:
+        do_sample: false
+  - path: do_sample
+    type: boolean
+    label: Do sample
+    description: When false, the model uses greedy decoding and ignores temperature and top_p.
+    default: true
+    group: sampling
+  - path: thinking.type
+    type: enum
+    label: Thinking mode
+    description: Toggles the model's extended reasoning before it produces the final answer.
+    default: enabled
+    values:
+      - enabled
+      - disabled
+    group: reasoning
+  - path: response_format.type
+    type: enum
+    label: Response format
+    description: Forces the response into plain text or a JSON object.
+    default: text
+    values:
+      - text
+      - json_object
+    group: output_format
diff --git a/models/z-ai/glm-5-turbo-subscription.yaml b/models/z-ai/glm-5-turbo-subscription.yaml
new file mode 100644
index 0000000..7b02ec6
--- /dev/null
+++ b/models/z-ai/glm-5-turbo-subscription.yaml
@@ -0,0 +1,41 @@
+# yaml-language-server: $schema=https://modelparams.dev/api/v1/schema.json
+provider: z-ai
+authType: subscription
+model: glm-5-turbo
+params:
+  - path: max_tokens
+    type: integer
+    label: Max tokens
+    description: Maximum number of tokens to generate in the response.
+    range:
+      min: 1
+    group: generation_length
+  - path: temperature
+    type: number
+    label: Temperature
+    description: Controls randomness. Lower values make outputs more focused; higher values make them more varied.
+    default: 1
+    range:
+      min: 0
+      max: 1
+      step: 0.1
+    group: sampling
+  - path: top_p
+    type: number
+    label: Top P
+    description: Controls nucleus sampling by limiting generation to tokens within the selected cumulative probability.
+    default: 0.95
+    range:
+      min: 0.01
+      max: 1
+      step: 0.01
+    group: sampling
+  - path: thinking.type
+    type: enum
+    label: Thinking mode
+    description: Toggles the model's extended reasoning before it produces the final answer.
+    default: enabled
+    values:
+      - enabled
+      - disabled
+    group: reasoning
diff --git a/models/z-ai/glm-5-turbo.yaml b/models/z-ai/glm-5-turbo.yaml
new file mode 100644
index 0000000..0e82642
--- /dev/null
+++ b/models/z-ai/glm-5-turbo.yaml
@@ -0,0 +1,62 @@
+# yaml-language-server: $schema=https://modelparams.dev/api/v1/schema.json
+provider: z-ai
+authType: api_key
+model: glm-5-turbo
+params:
+  - path: max_tokens
+    type: integer
+    label: Max tokens
+    description: Maximum number of tokens to generate in the response.
+    range:
+      min: 1
+    group: generation_length
+  - path: temperature
+    type: number
+    label: Temperature
+    description: Controls randomness. Lower values make outputs more focused; higher values make them more varied.
+    default: 1
+    range:
+      min: 0
+      max: 1
+      step: 0.1
+    group: sampling
+    applicability:
+      except:
+        do_sample: false
+  - path: top_p
+    type: number
+    label: Top P
+    description: Controls nucleus sampling by limiting generation to tokens within the selected cumulative probability.
+    default: 0.95
+    range:
+      min: 0.01
+      max: 1
+      step: 0.01
+    group: sampling
+    applicability:
+      except:
+        do_sample: false
+  - path: do_sample
+    type: boolean
+    label: Do sample
+    description: When false, the model uses greedy decoding and ignores temperature and top_p.
+    default: true
+    group: sampling
+  - path: thinking.type
+    type: enum
+    label: Thinking mode
+    description: Toggles the model's extended reasoning before it produces the final answer.
+    default: enabled
+    values:
+      - enabled
+      - disabled
+    group: reasoning
+  - path: response_format.type
+    type: enum
+    label: Response format
+    description: Forces the response into plain text or a JSON object.
+    default: text
+    values:
+      - text
+      - json_object
+    group: output_format
diff --git a/models/z-ai/glm-5.1-subscription.yaml b/models/z-ai/glm-5.1-subscription.yaml
new file mode 100644
index 0000000..cf6b8d5
--- /dev/null
+++ b/models/z-ai/glm-5.1-subscription.yaml
@@ -0,0 +1,41 @@
+# yaml-language-server: $schema=https://modelparams.dev/api/v1/schema.json
+provider: z-ai
+authType: subscription
+model: glm-5.1
+params:
+  - path: max_tokens
+    type: integer
+    label: Max tokens
+    description: Maximum number of tokens to generate in the response.
+    range:
+      min: 1
+    group: generation_length
+  - path: temperature
+    type: number
+    label: Temperature
+    description: Controls randomness. Lower values make outputs more focused; higher values make them more varied.
+    default: 1
+    range:
+      min: 0
+      max: 1
+      step: 0.1
+    group: sampling
+  - path: top_p
+    type: number
+    label: Top P
+    description: Controls nucleus sampling by limiting generation to tokens within the selected cumulative probability.
+    default: 0.95
+    range:
+      min: 0.01
+      max: 1
+      step: 0.01
+    group: sampling
+  - path: thinking.type
+    type: enum
+    label: Thinking mode
+    description: Toggles the model's extended reasoning before it produces the final answer.
+    default: enabled
+    values:
+      - enabled
+      - disabled
+    group: reasoning
diff --git a/models/z-ai/glm-5.1.yaml b/models/z-ai/glm-5.1.yaml
new file mode 100644
index 0000000..716fee7
--- /dev/null
+++ b/models/z-ai/glm-5.1.yaml
@@ -0,0 +1,62 @@
+# yaml-language-server: $schema=https://modelparams.dev/api/v1/schema.json
+provider: z-ai
+authType: api_key
+model: glm-5.1
+params:
+  - path: max_tokens
+    type: integer
+    label: Max tokens
+    description: Maximum number of tokens to generate in the response.
+    range:
+      min: 1
+    group: generation_length
+  - path: temperature
+    type: number
+    label: Temperature
+    description: Controls randomness. Lower values make outputs more focused; higher values make them more varied.
+    default: 1
+    range:
+      min: 0
+      max: 1
+      step: 0.1
+    group: sampling
+    applicability:
+      except:
+        do_sample: false
+  - path: top_p
+    type: number
+    label: Top P
+    description: Controls nucleus sampling by limiting generation to tokens within the selected cumulative probability.
+    default: 0.95
+    range:
+      min: 0.01
+      max: 1
+      step: 0.01
+    group: sampling
+    applicability:
+      except:
+        do_sample: false
+  - path: do_sample
+    type: boolean
+    label: Do sample
+    description: When false, the model uses greedy decoding and ignores temperature and top_p.
+    default: true
+    group: sampling
+  - path: thinking.type
+    type: enum
+    label: Thinking mode
+    description: Toggles the model's extended reasoning before it produces the final answer.
+    default: enabled
+    values:
+      - enabled
+      - disabled
+    group: reasoning
+  - path: response_format.type
+    type: enum
+    label: Response format
+    description: Forces the response into plain text or a JSON object.
+    default: text
+    values:
+      - text
+      - json_object
+    group: output_format
diff --git a/models/z-ai/glm-5.yaml b/models/z-ai/glm-5.yaml
new file mode 100644
index 0000000..5788943
--- /dev/null
+++ b/models/z-ai/glm-5.yaml
@@ -0,0 +1,62 @@
+# yaml-language-server: $schema=https://modelparams.dev/api/v1/schema.json
+provider: z-ai
+authType: api_key
+model: glm-5
+params:
+  - path: max_tokens
+    type: integer
+    label: Max tokens
+    description: Maximum number of tokens to generate in the response.
+    range:
+      min: 1
+    group: generation_length
+  - path: temperature
+    type: number
+    label: Temperature
+    description: Controls randomness. Lower values make outputs more focused; higher values make them more varied.
+    default: 1
+    range:
+      min: 0
+      max: 1
+      step: 0.1
+    group: sampling
+    applicability:
+      except:
+        do_sample: false
+  - path: top_p
+    type: number
+    label: Top P
+    description: Controls nucleus sampling by limiting generation to tokens within the selected cumulative probability.
+    default: 0.95
+    range:
+      min: 0.01
+      max: 1
+      step: 0.01
+    group: sampling
+    applicability:
+      except:
+        do_sample: false
+  - path: do_sample
+    type: boolean
+    label: Do sample
+    description: When false, the model uses greedy decoding and ignores temperature and top_p.
+    default: true
+    group: sampling
+  - path: thinking.type
+    type: enum
+    label: Thinking mode
+    description: Toggles the model's extended reasoning before it produces the final answer.
+    default: enabled
+    values:
+      - enabled
+      - disabled
+    group: reasoning
+  - path: response_format.type
+    type: enum
+    label: Response format
+    description: Forces the response into plain text or a JSON object.
+    default: text
+    values:
+      - text
+      - json_object
+    group: output_format
diff --git a/src/client/logos/z-ai.svg b/src/client/logos/z-ai.svg
new file mode 100644
index 0000000..87a8b77
--- /dev/null
+++ b/src/client/logos/z-ai.svg
@@ -0,0 +1,3 @@
+<svg width="24" height="24" viewBox="0 0 24 24" fill="none" xmlns="http://www.w3.org/2000/svg">
+  <path d="M4.5 4H19.5V7.5L9.8 16.5H19.5V20H4.5V16.5L14.2 7.5H4.5V4Z" fill="currentColor"/>
+</svg>
diff --git a/src/data/display.ts b/src/data/display.ts
index bbf2e55..e1a1edf 100644
--- a/src/data/display.ts
+++ b/src/data/display.ts
@@ -12,6 +12,7 @@ const PROVIDER_LABELS: Record<string, string> = {
   minimax: "MiniMax",
   cohere: "Cohere",
   perplexity: "Perplexity",
+  "z-ai": "Z.ai",
   moonshot: "Moonshot AI",
 };
 
@@ -30,6 +31,18 @@ const MODEL_LABEL_OVERRIDES: Record<string, string> = {
   "minimax/minimax-m2.5-highspeed": "MiniMax M2.5 Highspeed",
   "minimax/minimax-m2.7": "MiniMax M2.7",
   "minimax/minimax-m2.7-highspeed": "MiniMax M2.7 Highspeed",
+  "z-ai/glm-5.1": "GLM-5.1",
+  "z-ai/glm-5": "GLM-5",
+  "z-ai/glm-5-turbo": "GLM-5-Turbo",
+  "z-ai/glm-4.7": "GLM-4.7",
+  "z-ai/glm-4.7-flash": "GLM-4.7-Flash",
+  "z-ai/glm-4.7-flashx": "GLM-4.7-FlashX",
+  "z-ai/glm-4.6": "GLM-4.6",
+  "z-ai/glm-4.5": "GLM-4.5",
+  "z-ai/glm-4.5-air": "GLM-4.5-Air",
+  "z-ai/glm-4.5-x": "GLM-4.5-X",
+  "z-ai/glm-4.5-airx": "GLM-4.5-AirX",
+  "z-ai/glm-4.5-flash": "GLM-4.5-Flash",
   "moonshot/kimi-k2.6": "Kimi K2.6",
   "moonshot/kimi-k2.5": "Kimi K2.5",
   "moonshot/moonshot-v1-8k": "Moonshot v1 8K",