feat: add Gemma open weights, GLM-5.2, Qwen 3.7, Kimi K2.7

models/alibaba/qwen3.6-flash.yaml

@@ -0,0 +1,54 @@
+# yaml-language-server: $schema=https://modelparams.dev/api/v1/schema.json
+provider: alibaba
+authType: api_key
+model: qwen3.6-flash
+params:
+  - path: max_completion_tokens
+    type: integer
+    label: Max tokens
+    description: Maximum number of tokens to generate, including both reasoning and the final answer.
+    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.
+    range:
+      min: 0
+      max: 2
+      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.
+    range:
+      min: 0
+      max: 1
+      step: 0.01
+    group: sampling
+  - path: extra_body.top_k
+    type: integer
+    label: Top K
+    description: Limits generation to the selected number of highest-probability tokens. Values above 100 disable top-k sampling.
+    default: 20
+    range:
+      min: 0
+    group: sampling
+  - path: extra_body.enable_thinking
+    type: boolean
+    label: Enable thinking
+    description: Toggles the model's hybrid thinking mode, sent as a provider-specific extra body field on OpenAI-compatible clients.
+    default: true
+    group: reasoning
+  - path: extra_body.thinking_budget
+    type: integer
+    label: Thinking budget
+    description: Maximum number of tokens the model may spend on reasoning before it starts the final answer; defaults to the model's maximum reasoning length.
+    range:
+      min: 1
+    group: reasoning
+    applicability:
+      only:
+        extra_body.enable_thinking: true

models/alibaba/qwen3.7-max.yaml

@@ -0,0 +1,54 @@
+# yaml-language-server: $schema=https://modelparams.dev/api/v1/schema.json
+provider: alibaba
+authType: api_key
+model: qwen3.7-max
+params:
+  - path: max_completion_tokens
+    type: integer
+    label: Max tokens
+    description: Maximum number of tokens to generate, including both reasoning and the final answer.
+    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.
+    range:
+      min: 0
+      max: 2
+      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.
+    range:
+      min: 0
+      max: 1
+      step: 0.01
+    group: sampling
+  - path: extra_body.top_k
+    type: integer
+    label: Top K
+    description: Limits generation to the selected number of highest-probability tokens. Values above 100 disable top-k sampling.
+    default: 20
+    range:
+      min: 0
+    group: sampling
+  - path: extra_body.enable_thinking
+    type: boolean
+    label: Enable thinking
+    description: Toggles the model's hybrid thinking mode, sent as a provider-specific extra body field on OpenAI-compatible clients.
+    default: true
+    group: reasoning
+  - path: extra_body.thinking_budget
+    type: integer
+    label: Thinking budget
+    description: Maximum number of tokens the model may spend on reasoning before it starts the final answer; defaults to the model's maximum reasoning length.
+    range:
+      min: 1
+    group: reasoning
+    applicability:
+      only:
+        extra_body.enable_thinking: true

models/alibaba/qwen3.7-plus.yaml

@@ -0,0 +1,54 @@
+# yaml-language-server: $schema=https://modelparams.dev/api/v1/schema.json
+provider: alibaba
+authType: api_key
+model: qwen3.7-plus
+params:
+  - path: max_completion_tokens
+    type: integer
+    label: Max tokens
+    description: Maximum number of tokens to generate, including both reasoning and the final answer.
+    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.
+    range:
+      min: 0
+      max: 2
+      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.
+    range:
+      min: 0
+      max: 1
+      step: 0.01
+    group: sampling
+  - path: extra_body.top_k
+    type: integer
+    label: Top K
+    description: Limits generation to the selected number of highest-probability tokens. Values above 100 disable top-k sampling.
+    default: 20
+    range:
+      min: 0
+    group: sampling
+  - path: extra_body.enable_thinking
+    type: boolean
+    label: Enable thinking
+    description: Toggles the model's hybrid thinking mode, sent as a provider-specific extra body field on OpenAI-compatible clients.
+    default: true
+    group: reasoning
+  - path: extra_body.thinking_budget
+    type: integer
+    label: Thinking budget
+    description: Maximum number of tokens the model may spend on reasoning before it starts the final answer; defaults to the model's maximum reasoning length.
+    range:
+      min: 1
+    group: reasoning
+    applicability:
+      only:
+        extra_body.enable_thinking: true

models/google/gemini-3.1-flash-lite-subscription.yaml

@@ -48,7 +48,7 @@ params:
     type: enum
     label: Thinking level
     description: Controls Gemini 3.1 Flash-Lite reasoning effort.
-    default: high
+    default: minimal
     values:
       - minimal
       - low

models/google/gemini-3.1-flash-lite.yaml

@@ -0,0 +1,72 @@
+# yaml-language-server: $schema=https://modelparams.dev/api/v1/schema.json
+provider: google
+authType: api_key
+model: gemini-3.1-flash-lite
+params:
+  - path: generationConfig.maxOutputTokens
+    type: integer
+    label: Max output tokens
+    description: Maximum number of tokens to include in a response candidate.
+    range:
+      min: 1
+      max: 65536
+    group: generation_length
+  - path: generationConfig.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: 2
+      step: 0.1
+    group: sampling
+  - path: generationConfig.topP
+    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
+      max: 1
+      step: 0.01
+    group: sampling
+  - path: generationConfig.topK
+    type: integer
+    label: Top K
+    description: Limits token sampling to the top K most likely next tokens.
+    default: 64
+    range:
+      min: 0
+    group: sampling
+  - path: generationConfig.seed
+    type: integer
+    label: Seed
+    description: Optional seed used for decoding when reproducible sampling is desired.
+    group: sampling
+  - path: generationConfig.thinkingConfig.thinkingLevel
+    type: enum
+    label: Thinking level
+    description: Controls Gemini 3.1 Flash-Lite reasoning effort.
+    default: minimal
+    values:
+      - minimal
+      - low
+      - medium
+      - high
+    group: reasoning
+  - path: generationConfig.thinkingConfig.includeThoughts
+    type: boolean
+    label: Include thoughts
+    description: Controls whether Gemini returns available thought summaries in the response parts.
+    default: false
+    group: reasoning
+  - path: generationConfig.responseMimeType
+    type: enum
+    label: Response MIME type
+    description: MIME type for generated text candidates.
+    default: text/plain
+    values:
+      - text/plain
+      - application/json
+    group: output_format

models/google/gemma-3-12b-it.yaml

@@ -0,0 +1,36 @@
+# yaml-language-server: $schema=https://modelparams.dev/api/v1/schema.json
+provider: google
+authType: api_key
+model: gemma-3-12b-it
+params:
+  - path: max_completion_tokens
+    type: integer
+    label: Max tokens
+    description: Maximum number of output tokens the model may generate; output shares the 128K context window with the input.
+    range:
+      min: 1
+      max: 131072
+    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
+    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
+      max: 1
+    group: sampling
+  - path: top_k
+    type: integer
+    label: Top K
+    description: Limits generation to the selected number of highest-probability tokens.
+    default: 64
+    range:
+      min: 0
+    group: sampling

models/google/gemma-3-1b-it.yaml

@@ -0,0 +1,36 @@
+# yaml-language-server: $schema=https://modelparams.dev/api/v1/schema.json
+provider: google
+authType: api_key
+model: gemma-3-1b-it
+params:
+  - path: max_completion_tokens
+    type: integer
+    label: Max tokens
+    description: Maximum number of output tokens the model may generate; output shares the 32K context window with the input.
+    range:
+      min: 1
+      max: 32768
+    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
+    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
+      max: 1
+    group: sampling
+  - path: top_k
+    type: integer
+    label: Top K
+    description: Limits generation to the selected number of highest-probability tokens.
+    default: 64
+    range:
+      min: 0
+    group: sampling

models/google/gemma-3-27b-it.yaml

@@ -0,0 +1,36 @@
+# yaml-language-server: $schema=https://modelparams.dev/api/v1/schema.json
+provider: google
+authType: api_key
+model: gemma-3-27b-it
+params:
+  - path: max_completion_tokens
+    type: integer
+    label: Max tokens
+    description: Maximum number of output tokens the model may generate; output shares the 128K context window with the input.
+    range:
+      min: 1
+      max: 131072
+    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
+    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
+      max: 1
+    group: sampling
+  - path: top_k
+    type: integer
+    label: Top K
+    description: Limits generation to the selected number of highest-probability tokens.
+    default: 64
+    range:
+      min: 0
+    group: sampling

models/google/gemma-3-4b-it.yaml

@@ -0,0 +1,36 @@
+# yaml-language-server: $schema=https://modelparams.dev/api/v1/schema.json
+provider: google
+authType: api_key
+model: gemma-3-4b-it
+params:
+  - path: max_completion_tokens
+    type: integer
+    label: Max tokens
+    description: Maximum number of output tokens the model may generate; output shares the 128K context window with the input.
+    range:
+      min: 1
+      max: 131072
+    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
+    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
+      max: 1
+    group: sampling
+  - path: top_k
+    type: integer
+    label: Top K
+    description: Limits generation to the selected number of highest-probability tokens.
+    default: 64
+    range:
+      min: 0
+    group: sampling