feat: add z.ai GLM models to the catalog

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

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

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

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

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

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