From 27961530cd7d8a67bed578b2da129b6189bae2af Mon Sep 17 00:00:00 2001 From: Bruno Perez Date: Sat, 23 May 2026 03:46:57 -0700 Subject: [PATCH 1/4] feat: add z.ai GLM models to the catalog Add the z.ai (GLM) provider with both classic API-key access and the GLM Coding Plan subscription. Covers the current lineup: GLM-5.1, GLM-5, GLM-5-Turbo, the GLM-4.7 family, GLM-4.6, and the GLM-4.5 family. Adds the provider label, model display names, and logo. --- models/z-ai/glm-4.5-air-subscription.yaml | 41 +++++++++++++++ models/z-ai/glm-4.5-air.yaml | 62 +++++++++++++++++++++++ models/z-ai/glm-4.5-airx.yaml | 62 +++++++++++++++++++++++ models/z-ai/glm-4.5-flash.yaml | 62 +++++++++++++++++++++++ models/z-ai/glm-4.5-x.yaml | 62 +++++++++++++++++++++++ models/z-ai/glm-4.5.yaml | 62 +++++++++++++++++++++++ models/z-ai/glm-4.6.yaml | 62 +++++++++++++++++++++++ models/z-ai/glm-4.7-flash.yaml | 62 +++++++++++++++++++++++ models/z-ai/glm-4.7-flashx.yaml | 62 +++++++++++++++++++++++ models/z-ai/glm-4.7-subscription.yaml | 41 +++++++++++++++ models/z-ai/glm-4.7.yaml | 62 +++++++++++++++++++++++ models/z-ai/glm-5-turbo-subscription.yaml | 41 +++++++++++++++ models/z-ai/glm-5-turbo.yaml | 62 +++++++++++++++++++++++ models/z-ai/glm-5.1-subscription.yaml | 41 +++++++++++++++ models/z-ai/glm-5.1.yaml | 62 +++++++++++++++++++++++ models/z-ai/glm-5.yaml | 62 +++++++++++++++++++++++ src/client/logos/z-ai.svg | 3 ++ src/data/display.ts | 13 +++++ 18 files changed, 924 insertions(+) create mode 100644 models/z-ai/glm-4.5-air-subscription.yaml create mode 100644 models/z-ai/glm-4.5-air.yaml create mode 100644 models/z-ai/glm-4.5-airx.yaml create mode 100644 models/z-ai/glm-4.5-flash.yaml create mode 100644 models/z-ai/glm-4.5-x.yaml create mode 100644 models/z-ai/glm-4.5.yaml create mode 100644 models/z-ai/glm-4.6.yaml create mode 100644 models/z-ai/glm-4.7-flash.yaml create mode 100644 models/z-ai/glm-4.7-flashx.yaml create mode 100644 models/z-ai/glm-4.7-subscription.yaml create mode 100644 models/z-ai/glm-4.7.yaml create mode 100644 models/z-ai/glm-5-turbo-subscription.yaml create mode 100644 models/z-ai/glm-5-turbo.yaml create mode 100644 models/z-ai/glm-5.1-subscription.yaml create mode 100644 models/z-ai/glm-5.1.yaml create mode 100644 models/z-ai/glm-5.yaml create mode 100644 src/client/logos/z-ai.svg 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 @@ + + + diff --git a/src/data/display.ts b/src/data/display.ts index e4e2b2c..c767b7c 100644 --- a/src/data/display.ts +++ b/src/data/display.ts @@ -10,6 +10,7 @@ const PROVIDER_LABELS: Record = { deepseek: "DeepSeek", cohere: "Cohere", perplexity: "Perplexity", + "z-ai": "Z.ai", }; const MODEL_LABEL_OVERRIDES: Record = { @@ -20,6 +21,18 @@ const MODEL_LABEL_OVERRIDES: Record = { "openai/o3": "o3", "openai/o3-mini": "o3-mini", "openai/o4-mini": "o4-mini", + "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", }; const AUTH_LABELS: Record = { From 7a2e76a1f0a66695ef50dc501b74066397b4e7ee Mon Sep 17 00:00:00 2001 From: Bruno Perez Date: Sat, 23 May 2026 04:08:26 -0700 Subject: [PATCH 2/4] feat: add stop sequences and tool_choice to z.ai API models Both are documented z.ai chat-completions parameters that were missing. stop is modeled as a single string (matching the catalog's Mistral convention), and tool_choice is an enum noting auto is the only value z.ai supports. Left off the GLM Coding Plan subscription files, which don't expose these. --- models/z-ai/glm-4.5-air.yaml | 13 +++++++++++++ models/z-ai/glm-4.5-airx.yaml | 13 +++++++++++++ models/z-ai/glm-4.5-flash.yaml | 13 +++++++++++++ models/z-ai/glm-4.5-x.yaml | 13 +++++++++++++ models/z-ai/glm-4.5.yaml | 13 +++++++++++++ models/z-ai/glm-4.6.yaml | 13 +++++++++++++ models/z-ai/glm-4.7-flash.yaml | 13 +++++++++++++ models/z-ai/glm-4.7-flashx.yaml | 13 +++++++++++++ models/z-ai/glm-4.7.yaml | 13 +++++++++++++ models/z-ai/glm-5-turbo.yaml | 13 +++++++++++++ models/z-ai/glm-5.1.yaml | 13 +++++++++++++ models/z-ai/glm-5.yaml | 13 +++++++++++++ 12 files changed, 156 insertions(+) diff --git a/models/z-ai/glm-4.5-air.yaml b/models/z-ai/glm-4.5-air.yaml index 67bb627..e7ebbf0 100644 --- a/models/z-ai/glm-4.5-air.yaml +++ b/models/z-ai/glm-4.5-air.yaml @@ -10,6 +10,11 @@ params: range: min: 1 group: generation_length + - path: stop + type: string + label: Stop sequence + description: Stops generation when this string is produced; the API accepts up to four stop sequences. + group: generation_length - path: temperature type: number label: Temperature @@ -51,6 +56,14 @@ params: - enabled - disabled group: reasoning + - path: tool_choice + type: enum + label: Tool choice + description: Controls how the model selects tools; z.ai documents auto as the only supported value. + default: auto + values: + - auto + group: tooling - path: response_format.type type: enum label: Response format diff --git a/models/z-ai/glm-4.5-airx.yaml b/models/z-ai/glm-4.5-airx.yaml index 3fa7d81..e7e75df 100644 --- a/models/z-ai/glm-4.5-airx.yaml +++ b/models/z-ai/glm-4.5-airx.yaml @@ -10,6 +10,11 @@ params: range: min: 1 group: generation_length + - path: stop + type: string + label: Stop sequence + description: Stops generation when this string is produced; the API accepts up to four stop sequences. + group: generation_length - path: temperature type: number label: Temperature @@ -51,6 +56,14 @@ params: - enabled - disabled group: reasoning + - path: tool_choice + type: enum + label: Tool choice + description: Controls how the model selects tools; z.ai documents auto as the only supported value. + default: auto + values: + - auto + group: tooling - path: response_format.type type: enum label: Response format diff --git a/models/z-ai/glm-4.5-flash.yaml b/models/z-ai/glm-4.5-flash.yaml index f7a0a0e..b55dd3b 100644 --- a/models/z-ai/glm-4.5-flash.yaml +++ b/models/z-ai/glm-4.5-flash.yaml @@ -10,6 +10,11 @@ params: range: min: 1 group: generation_length + - path: stop + type: string + label: Stop sequence + description: Stops generation when this string is produced; the API accepts up to four stop sequences. + group: generation_length - path: temperature type: number label: Temperature @@ -51,6 +56,14 @@ params: - enabled - disabled group: reasoning + - path: tool_choice + type: enum + label: Tool choice + description: Controls how the model selects tools; z.ai documents auto as the only supported value. + default: auto + values: + - auto + group: tooling - path: response_format.type type: enum label: Response format diff --git a/models/z-ai/glm-4.5-x.yaml b/models/z-ai/glm-4.5-x.yaml index 31a4c27..7099252 100644 --- a/models/z-ai/glm-4.5-x.yaml +++ b/models/z-ai/glm-4.5-x.yaml @@ -10,6 +10,11 @@ params: range: min: 1 group: generation_length + - path: stop + type: string + label: Stop sequence + description: Stops generation when this string is produced; the API accepts up to four stop sequences. + group: generation_length - path: temperature type: number label: Temperature @@ -51,6 +56,14 @@ params: - enabled - disabled group: reasoning + - path: tool_choice + type: enum + label: Tool choice + description: Controls how the model selects tools; z.ai documents auto as the only supported value. + default: auto + values: + - auto + group: tooling - path: response_format.type type: enum label: Response format diff --git a/models/z-ai/glm-4.5.yaml b/models/z-ai/glm-4.5.yaml index b93d2ef..7663744 100644 --- a/models/z-ai/glm-4.5.yaml +++ b/models/z-ai/glm-4.5.yaml @@ -10,6 +10,11 @@ params: range: min: 1 group: generation_length + - path: stop + type: string + label: Stop sequence + description: Stops generation when this string is produced; the API accepts up to four stop sequences. + group: generation_length - path: temperature type: number label: Temperature @@ -51,6 +56,14 @@ params: - enabled - disabled group: reasoning + - path: tool_choice + type: enum + label: Tool choice + description: Controls how the model selects tools; z.ai documents auto as the only supported value. + default: auto + values: + - auto + group: tooling - path: response_format.type type: enum label: Response format diff --git a/models/z-ai/glm-4.6.yaml b/models/z-ai/glm-4.6.yaml index 99ff0a0..514f2f8 100644 --- a/models/z-ai/glm-4.6.yaml +++ b/models/z-ai/glm-4.6.yaml @@ -10,6 +10,11 @@ params: range: min: 1 group: generation_length + - path: stop + type: string + label: Stop sequence + description: Stops generation when this string is produced; the API accepts up to four stop sequences. + group: generation_length - path: temperature type: number label: Temperature @@ -51,6 +56,14 @@ params: - enabled - disabled group: reasoning + - path: tool_choice + type: enum + label: Tool choice + description: Controls how the model selects tools; z.ai documents auto as the only supported value. + default: auto + values: + - auto + group: tooling - path: response_format.type type: enum label: Response format diff --git a/models/z-ai/glm-4.7-flash.yaml b/models/z-ai/glm-4.7-flash.yaml index 5275eef..884ddfc 100644 --- a/models/z-ai/glm-4.7-flash.yaml +++ b/models/z-ai/glm-4.7-flash.yaml @@ -10,6 +10,11 @@ params: range: min: 1 group: generation_length + - path: stop + type: string + label: Stop sequence + description: Stops generation when this string is produced; the API accepts up to four stop sequences. + group: generation_length - path: temperature type: number label: Temperature @@ -51,6 +56,14 @@ params: - enabled - disabled group: reasoning + - path: tool_choice + type: enum + label: Tool choice + description: Controls how the model selects tools; z.ai documents auto as the only supported value. + default: auto + values: + - auto + group: tooling - path: response_format.type type: enum label: Response format diff --git a/models/z-ai/glm-4.7-flashx.yaml b/models/z-ai/glm-4.7-flashx.yaml index cb473fe..5b0ec8d 100644 --- a/models/z-ai/glm-4.7-flashx.yaml +++ b/models/z-ai/glm-4.7-flashx.yaml @@ -10,6 +10,11 @@ params: range: min: 1 group: generation_length + - path: stop + type: string + label: Stop sequence + description: Stops generation when this string is produced; the API accepts up to four stop sequences. + group: generation_length - path: temperature type: number label: Temperature @@ -51,6 +56,14 @@ params: - enabled - disabled group: reasoning + - path: tool_choice + type: enum + label: Tool choice + description: Controls how the model selects tools; z.ai documents auto as the only supported value. + default: auto + values: + - auto + group: tooling - path: response_format.type type: enum label: Response format diff --git a/models/z-ai/glm-4.7.yaml b/models/z-ai/glm-4.7.yaml index dc96331..c7c9e6d 100644 --- a/models/z-ai/glm-4.7.yaml +++ b/models/z-ai/glm-4.7.yaml @@ -10,6 +10,11 @@ params: range: min: 1 group: generation_length + - path: stop + type: string + label: Stop sequence + description: Stops generation when this string is produced; the API accepts up to four stop sequences. + group: generation_length - path: temperature type: number label: Temperature @@ -51,6 +56,14 @@ params: - enabled - disabled group: reasoning + - path: tool_choice + type: enum + label: Tool choice + description: Controls how the model selects tools; z.ai documents auto as the only supported value. + default: auto + values: + - auto + group: tooling - path: response_format.type type: enum label: Response format diff --git a/models/z-ai/glm-5-turbo.yaml b/models/z-ai/glm-5-turbo.yaml index 0e82642..d77f5c7 100644 --- a/models/z-ai/glm-5-turbo.yaml +++ b/models/z-ai/glm-5-turbo.yaml @@ -10,6 +10,11 @@ params: range: min: 1 group: generation_length + - path: stop + type: string + label: Stop sequence + description: Stops generation when this string is produced; the API accepts up to four stop sequences. + group: generation_length - path: temperature type: number label: Temperature @@ -51,6 +56,14 @@ params: - enabled - disabled group: reasoning + - path: tool_choice + type: enum + label: Tool choice + description: Controls how the model selects tools; z.ai documents auto as the only supported value. + default: auto + values: + - auto + group: tooling - path: response_format.type type: enum label: Response format diff --git a/models/z-ai/glm-5.1.yaml b/models/z-ai/glm-5.1.yaml index 716fee7..bca96c1 100644 --- a/models/z-ai/glm-5.1.yaml +++ b/models/z-ai/glm-5.1.yaml @@ -10,6 +10,11 @@ params: range: min: 1 group: generation_length + - path: stop + type: string + label: Stop sequence + description: Stops generation when this string is produced; the API accepts up to four stop sequences. + group: generation_length - path: temperature type: number label: Temperature @@ -51,6 +56,14 @@ params: - enabled - disabled group: reasoning + - path: tool_choice + type: enum + label: Tool choice + description: Controls how the model selects tools; z.ai documents auto as the only supported value. + default: auto + values: + - auto + group: tooling - path: response_format.type type: enum label: Response format diff --git a/models/z-ai/glm-5.yaml b/models/z-ai/glm-5.yaml index 5788943..bf26521 100644 --- a/models/z-ai/glm-5.yaml +++ b/models/z-ai/glm-5.yaml @@ -10,6 +10,11 @@ params: range: min: 1 group: generation_length + - path: stop + type: string + label: Stop sequence + description: Stops generation when this string is produced; the API accepts up to four stop sequences. + group: generation_length - path: temperature type: number label: Temperature @@ -51,6 +56,14 @@ params: - enabled - disabled group: reasoning + - path: tool_choice + type: enum + label: Tool choice + description: Controls how the model selects tools; z.ai documents auto as the only supported value. + default: auto + values: + - auto + group: tooling - path: response_format.type type: enum label: Response format From 12379d1ac1a65e341831687366fc160d7a969019 Mon Sep 17 00:00:00 2001 From: Guillaume Gay Date: Sun, 24 May 2026 09:24:49 +0200 Subject: [PATCH 3/4] fix(z-ai): align tool and stop parameters --- models/z-ai/glm-4.5-air.yaml | 9 +++------ models/z-ai/glm-4.5-airx.yaml | 9 +++------ models/z-ai/glm-4.5-flash.yaml | 9 +++------ models/z-ai/glm-4.5-x.yaml | 9 +++------ models/z-ai/glm-4.5.yaml | 9 +++------ models/z-ai/glm-4.6.yaml | 9 +++------ models/z-ai/glm-4.7-flash.yaml | 9 +++------ models/z-ai/glm-4.7-flashx.yaml | 9 +++------ models/z-ai/glm-4.7.yaml | 9 +++------ models/z-ai/glm-5-turbo.yaml | 9 +++------ models/z-ai/glm-5.1.yaml | 9 +++------ models/z-ai/glm-5.yaml | 9 +++------ 12 files changed, 36 insertions(+), 72 deletions(-) diff --git a/models/z-ai/glm-4.5-air.yaml b/models/z-ai/glm-4.5-air.yaml index e7ebbf0..1249595 100644 --- a/models/z-ai/glm-4.5-air.yaml +++ b/models/z-ai/glm-4.5-air.yaml @@ -10,11 +10,6 @@ params: range: min: 1 group: generation_length - - path: stop - type: string - label: Stop sequence - description: Stops generation when this string is produced; the API accepts up to four stop sequences. - group: generation_length - path: temperature type: number label: Temperature @@ -59,10 +54,12 @@ params: - path: tool_choice type: enum label: Tool choice - description: Controls how the model selects tools; z.ai documents auto as the only supported value. + description: Controls how the model selects tools. z.ai accepts auto, none, and required. default: auto values: - auto + - none + - required group: tooling - path: response_format.type type: enum diff --git a/models/z-ai/glm-4.5-airx.yaml b/models/z-ai/glm-4.5-airx.yaml index e7e75df..ed85f0d 100644 --- a/models/z-ai/glm-4.5-airx.yaml +++ b/models/z-ai/glm-4.5-airx.yaml @@ -10,11 +10,6 @@ params: range: min: 1 group: generation_length - - path: stop - type: string - label: Stop sequence - description: Stops generation when this string is produced; the API accepts up to four stop sequences. - group: generation_length - path: temperature type: number label: Temperature @@ -59,10 +54,12 @@ params: - path: tool_choice type: enum label: Tool choice - description: Controls how the model selects tools; z.ai documents auto as the only supported value. + description: Controls how the model selects tools. z.ai accepts auto, none, and required. default: auto values: - auto + - none + - required group: tooling - path: response_format.type type: enum diff --git a/models/z-ai/glm-4.5-flash.yaml b/models/z-ai/glm-4.5-flash.yaml index b55dd3b..0d20f21 100644 --- a/models/z-ai/glm-4.5-flash.yaml +++ b/models/z-ai/glm-4.5-flash.yaml @@ -10,11 +10,6 @@ params: range: min: 1 group: generation_length - - path: stop - type: string - label: Stop sequence - description: Stops generation when this string is produced; the API accepts up to four stop sequences. - group: generation_length - path: temperature type: number label: Temperature @@ -59,10 +54,12 @@ params: - path: tool_choice type: enum label: Tool choice - description: Controls how the model selects tools; z.ai documents auto as the only supported value. + description: Controls how the model selects tools. z.ai accepts auto, none, and required. default: auto values: - auto + - none + - required group: tooling - path: response_format.type type: enum diff --git a/models/z-ai/glm-4.5-x.yaml b/models/z-ai/glm-4.5-x.yaml index 7099252..4848803 100644 --- a/models/z-ai/glm-4.5-x.yaml +++ b/models/z-ai/glm-4.5-x.yaml @@ -10,11 +10,6 @@ params: range: min: 1 group: generation_length - - path: stop - type: string - label: Stop sequence - description: Stops generation when this string is produced; the API accepts up to four stop sequences. - group: generation_length - path: temperature type: number label: Temperature @@ -59,10 +54,12 @@ params: - path: tool_choice type: enum label: Tool choice - description: Controls how the model selects tools; z.ai documents auto as the only supported value. + description: Controls how the model selects tools. z.ai accepts auto, none, and required. default: auto values: - auto + - none + - required group: tooling - path: response_format.type type: enum diff --git a/models/z-ai/glm-4.5.yaml b/models/z-ai/glm-4.5.yaml index 7663744..9659242 100644 --- a/models/z-ai/glm-4.5.yaml +++ b/models/z-ai/glm-4.5.yaml @@ -10,11 +10,6 @@ params: range: min: 1 group: generation_length - - path: stop - type: string - label: Stop sequence - description: Stops generation when this string is produced; the API accepts up to four stop sequences. - group: generation_length - path: temperature type: number label: Temperature @@ -59,10 +54,12 @@ params: - path: tool_choice type: enum label: Tool choice - description: Controls how the model selects tools; z.ai documents auto as the only supported value. + description: Controls how the model selects tools. z.ai accepts auto, none, and required. default: auto values: - auto + - none + - required group: tooling - path: response_format.type type: enum diff --git a/models/z-ai/glm-4.6.yaml b/models/z-ai/glm-4.6.yaml index 514f2f8..ae70beb 100644 --- a/models/z-ai/glm-4.6.yaml +++ b/models/z-ai/glm-4.6.yaml @@ -10,11 +10,6 @@ params: range: min: 1 group: generation_length - - path: stop - type: string - label: Stop sequence - description: Stops generation when this string is produced; the API accepts up to four stop sequences. - group: generation_length - path: temperature type: number label: Temperature @@ -59,10 +54,12 @@ params: - path: tool_choice type: enum label: Tool choice - description: Controls how the model selects tools; z.ai documents auto as the only supported value. + description: Controls how the model selects tools. z.ai accepts auto, none, and required. default: auto values: - auto + - none + - required group: tooling - path: response_format.type type: enum diff --git a/models/z-ai/glm-4.7-flash.yaml b/models/z-ai/glm-4.7-flash.yaml index 884ddfc..c2cf3fd 100644 --- a/models/z-ai/glm-4.7-flash.yaml +++ b/models/z-ai/glm-4.7-flash.yaml @@ -10,11 +10,6 @@ params: range: min: 1 group: generation_length - - path: stop - type: string - label: Stop sequence - description: Stops generation when this string is produced; the API accepts up to four stop sequences. - group: generation_length - path: temperature type: number label: Temperature @@ -59,10 +54,12 @@ params: - path: tool_choice type: enum label: Tool choice - description: Controls how the model selects tools; z.ai documents auto as the only supported value. + description: Controls how the model selects tools. z.ai accepts auto, none, and required. default: auto values: - auto + - none + - required group: tooling - path: response_format.type type: enum diff --git a/models/z-ai/glm-4.7-flashx.yaml b/models/z-ai/glm-4.7-flashx.yaml index 5b0ec8d..1b60e9e 100644 --- a/models/z-ai/glm-4.7-flashx.yaml +++ b/models/z-ai/glm-4.7-flashx.yaml @@ -10,11 +10,6 @@ params: range: min: 1 group: generation_length - - path: stop - type: string - label: Stop sequence - description: Stops generation when this string is produced; the API accepts up to four stop sequences. - group: generation_length - path: temperature type: number label: Temperature @@ -59,10 +54,12 @@ params: - path: tool_choice type: enum label: Tool choice - description: Controls how the model selects tools; z.ai documents auto as the only supported value. + description: Controls how the model selects tools. z.ai accepts auto, none, and required. default: auto values: - auto + - none + - required group: tooling - path: response_format.type type: enum diff --git a/models/z-ai/glm-4.7.yaml b/models/z-ai/glm-4.7.yaml index c7c9e6d..2c73107 100644 --- a/models/z-ai/glm-4.7.yaml +++ b/models/z-ai/glm-4.7.yaml @@ -10,11 +10,6 @@ params: range: min: 1 group: generation_length - - path: stop - type: string - label: Stop sequence - description: Stops generation when this string is produced; the API accepts up to four stop sequences. - group: generation_length - path: temperature type: number label: Temperature @@ -59,10 +54,12 @@ params: - path: tool_choice type: enum label: Tool choice - description: Controls how the model selects tools; z.ai documents auto as the only supported value. + description: Controls how the model selects tools. z.ai accepts auto, none, and required. default: auto values: - auto + - none + - required group: tooling - path: response_format.type type: enum diff --git a/models/z-ai/glm-5-turbo.yaml b/models/z-ai/glm-5-turbo.yaml index d77f5c7..af42362 100644 --- a/models/z-ai/glm-5-turbo.yaml +++ b/models/z-ai/glm-5-turbo.yaml @@ -10,11 +10,6 @@ params: range: min: 1 group: generation_length - - path: stop - type: string - label: Stop sequence - description: Stops generation when this string is produced; the API accepts up to four stop sequences. - group: generation_length - path: temperature type: number label: Temperature @@ -59,10 +54,12 @@ params: - path: tool_choice type: enum label: Tool choice - description: Controls how the model selects tools; z.ai documents auto as the only supported value. + description: Controls how the model selects tools. z.ai accepts auto, none, and required. default: auto values: - auto + - none + - required group: tooling - path: response_format.type type: enum diff --git a/models/z-ai/glm-5.1.yaml b/models/z-ai/glm-5.1.yaml index bca96c1..1ec60b6 100644 --- a/models/z-ai/glm-5.1.yaml +++ b/models/z-ai/glm-5.1.yaml @@ -10,11 +10,6 @@ params: range: min: 1 group: generation_length - - path: stop - type: string - label: Stop sequence - description: Stops generation when this string is produced; the API accepts up to four stop sequences. - group: generation_length - path: temperature type: number label: Temperature @@ -59,10 +54,12 @@ params: - path: tool_choice type: enum label: Tool choice - description: Controls how the model selects tools; z.ai documents auto as the only supported value. + description: Controls how the model selects tools. z.ai accepts auto, none, and required. default: auto values: - auto + - none + - required group: tooling - path: response_format.type type: enum diff --git a/models/z-ai/glm-5.yaml b/models/z-ai/glm-5.yaml index bf26521..9fb6062 100644 --- a/models/z-ai/glm-5.yaml +++ b/models/z-ai/glm-5.yaml @@ -10,11 +10,6 @@ params: range: min: 1 group: generation_length - - path: stop - type: string - label: Stop sequence - description: Stops generation when this string is produced; the API accepts up to four stop sequences. - group: generation_length - path: temperature type: number label: Temperature @@ -59,10 +54,12 @@ params: - path: tool_choice type: enum label: Tool choice - description: Controls how the model selects tools; z.ai documents auto as the only supported value. + description: Controls how the model selects tools. z.ai accepts auto, none, and required. default: auto values: - auto + - none + - required group: tooling - path: response_format.type type: enum From 651d1868c019906575f96e55a37478f0eb166116 Mon Sep 17 00:00:00 2001 From: Guillaume Gay Date: Sun, 24 May 2026 09:28:55 +0200 Subject: [PATCH 4/4] fix(z-ai): omit tool selection capability --- models/z-ai/glm-4.5-air.yaml | 10 ---------- models/z-ai/glm-4.5-airx.yaml | 10 ---------- models/z-ai/glm-4.5-flash.yaml | 10 ---------- models/z-ai/glm-4.5-x.yaml | 10 ---------- models/z-ai/glm-4.5.yaml | 10 ---------- models/z-ai/glm-4.6.yaml | 10 ---------- models/z-ai/glm-4.7-flash.yaml | 10 ---------- models/z-ai/glm-4.7-flashx.yaml | 10 ---------- models/z-ai/glm-4.7.yaml | 10 ---------- models/z-ai/glm-5-turbo.yaml | 10 ---------- models/z-ai/glm-5.1.yaml | 10 ---------- models/z-ai/glm-5.yaml | 10 ---------- 12 files changed, 120 deletions(-) diff --git a/models/z-ai/glm-4.5-air.yaml b/models/z-ai/glm-4.5-air.yaml index 1249595..67bb627 100644 --- a/models/z-ai/glm-4.5-air.yaml +++ b/models/z-ai/glm-4.5-air.yaml @@ -51,16 +51,6 @@ params: - enabled - disabled group: reasoning - - path: tool_choice - type: enum - label: Tool choice - description: Controls how the model selects tools. z.ai accepts auto, none, and required. - default: auto - values: - - auto - - none - - required - group: tooling - path: response_format.type type: enum label: Response format diff --git a/models/z-ai/glm-4.5-airx.yaml b/models/z-ai/glm-4.5-airx.yaml index ed85f0d..3fa7d81 100644 --- a/models/z-ai/glm-4.5-airx.yaml +++ b/models/z-ai/glm-4.5-airx.yaml @@ -51,16 +51,6 @@ params: - enabled - disabled group: reasoning - - path: tool_choice - type: enum - label: Tool choice - description: Controls how the model selects tools. z.ai accepts auto, none, and required. - default: auto - values: - - auto - - none - - required - group: tooling - path: response_format.type type: enum label: Response format diff --git a/models/z-ai/glm-4.5-flash.yaml b/models/z-ai/glm-4.5-flash.yaml index 0d20f21..f7a0a0e 100644 --- a/models/z-ai/glm-4.5-flash.yaml +++ b/models/z-ai/glm-4.5-flash.yaml @@ -51,16 +51,6 @@ params: - enabled - disabled group: reasoning - - path: tool_choice - type: enum - label: Tool choice - description: Controls how the model selects tools. z.ai accepts auto, none, and required. - default: auto - values: - - auto - - none - - required - group: tooling - path: response_format.type type: enum label: Response format diff --git a/models/z-ai/glm-4.5-x.yaml b/models/z-ai/glm-4.5-x.yaml index 4848803..31a4c27 100644 --- a/models/z-ai/glm-4.5-x.yaml +++ b/models/z-ai/glm-4.5-x.yaml @@ -51,16 +51,6 @@ params: - enabled - disabled group: reasoning - - path: tool_choice - type: enum - label: Tool choice - description: Controls how the model selects tools. z.ai accepts auto, none, and required. - default: auto - values: - - auto - - none - - required - group: tooling - path: response_format.type type: enum label: Response format diff --git a/models/z-ai/glm-4.5.yaml b/models/z-ai/glm-4.5.yaml index 9659242..b93d2ef 100644 --- a/models/z-ai/glm-4.5.yaml +++ b/models/z-ai/glm-4.5.yaml @@ -51,16 +51,6 @@ params: - enabled - disabled group: reasoning - - path: tool_choice - type: enum - label: Tool choice - description: Controls how the model selects tools. z.ai accepts auto, none, and required. - default: auto - values: - - auto - - none - - required - group: tooling - path: response_format.type type: enum label: Response format diff --git a/models/z-ai/glm-4.6.yaml b/models/z-ai/glm-4.6.yaml index ae70beb..99ff0a0 100644 --- a/models/z-ai/glm-4.6.yaml +++ b/models/z-ai/glm-4.6.yaml @@ -51,16 +51,6 @@ params: - enabled - disabled group: reasoning - - path: tool_choice - type: enum - label: Tool choice - description: Controls how the model selects tools. z.ai accepts auto, none, and required. - default: auto - values: - - auto - - none - - required - group: tooling - path: response_format.type type: enum label: Response format diff --git a/models/z-ai/glm-4.7-flash.yaml b/models/z-ai/glm-4.7-flash.yaml index c2cf3fd..5275eef 100644 --- a/models/z-ai/glm-4.7-flash.yaml +++ b/models/z-ai/glm-4.7-flash.yaml @@ -51,16 +51,6 @@ params: - enabled - disabled group: reasoning - - path: tool_choice - type: enum - label: Tool choice - description: Controls how the model selects tools. z.ai accepts auto, none, and required. - default: auto - values: - - auto - - none - - required - group: tooling - path: response_format.type type: enum label: Response format diff --git a/models/z-ai/glm-4.7-flashx.yaml b/models/z-ai/glm-4.7-flashx.yaml index 1b60e9e..cb473fe 100644 --- a/models/z-ai/glm-4.7-flashx.yaml +++ b/models/z-ai/glm-4.7-flashx.yaml @@ -51,16 +51,6 @@ params: - enabled - disabled group: reasoning - - path: tool_choice - type: enum - label: Tool choice - description: Controls how the model selects tools. z.ai accepts auto, none, and required. - default: auto - values: - - auto - - none - - required - group: tooling - path: response_format.type type: enum label: Response format diff --git a/models/z-ai/glm-4.7.yaml b/models/z-ai/glm-4.7.yaml index 2c73107..dc96331 100644 --- a/models/z-ai/glm-4.7.yaml +++ b/models/z-ai/glm-4.7.yaml @@ -51,16 +51,6 @@ params: - enabled - disabled group: reasoning - - path: tool_choice - type: enum - label: Tool choice - description: Controls how the model selects tools. z.ai accepts auto, none, and required. - default: auto - values: - - auto - - none - - required - group: tooling - path: response_format.type type: enum label: Response format diff --git a/models/z-ai/glm-5-turbo.yaml b/models/z-ai/glm-5-turbo.yaml index af42362..0e82642 100644 --- a/models/z-ai/glm-5-turbo.yaml +++ b/models/z-ai/glm-5-turbo.yaml @@ -51,16 +51,6 @@ params: - enabled - disabled group: reasoning - - path: tool_choice - type: enum - label: Tool choice - description: Controls how the model selects tools. z.ai accepts auto, none, and required. - default: auto - values: - - auto - - none - - required - group: tooling - path: response_format.type type: enum label: Response format diff --git a/models/z-ai/glm-5.1.yaml b/models/z-ai/glm-5.1.yaml index 1ec60b6..716fee7 100644 --- a/models/z-ai/glm-5.1.yaml +++ b/models/z-ai/glm-5.1.yaml @@ -51,16 +51,6 @@ params: - enabled - disabled group: reasoning - - path: tool_choice - type: enum - label: Tool choice - description: Controls how the model selects tools. z.ai accepts auto, none, and required. - default: auto - values: - - auto - - none - - required - group: tooling - path: response_format.type type: enum label: Response format diff --git a/models/z-ai/glm-5.yaml b/models/z-ai/glm-5.yaml index 9fb6062..5788943 100644 --- a/models/z-ai/glm-5.yaml +++ b/models/z-ai/glm-5.yaml @@ -51,16 +51,6 @@ params: - enabled - disabled group: reasoning - - path: tool_choice - type: enum - label: Tool choice - description: Controls how the model selects tools. z.ai accepts auto, none, and required. - default: auto - values: - - auto - - none - - required - group: tooling - path: response_format.type type: enum label: Response format