chore(catalog): sync from gateway — 4 added, 1 corrected, 0 retired

models/alibaba/pre-mock_new_gateway_session_affinity.yaml

@@ -0,0 +1,55 @@
+# yaml-language-server: $schema=https://modelparams.dev/api/v1/schema.json
+provider: alibaba
+authType: api_key
+apiSurface: openai-chat-completions
+model: pre-mock_new_gateway_session_affinity
+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: 1.9
+      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/fireworks/muse-spark-open.yaml

@@ -0,0 +1,66 @@
+# yaml-language-server: $schema=https://modelparams.dev/api/v1/schema.json
+provider: fireworks
+authType: api_key
+apiSurface: openai-chat-completions
+model: muse-spark-open
+wireId: accounts/fireworks/models/muse-spark-open
+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.
+    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: top_k
+    type: integer
+    label: Top K
+    description: Limits token sampling to the top K most likely next tokens.
+    range:
+      min: 1
+      max: 100
+    group: sampling
+  - path: presence_penalty
+    type: number
+    label: Presence penalty
+    description: Penalizes tokens that have already appeared to encourage a wider variety of content.
+    range:
+      min: -2
+      max: 2
+      step: 0.1
+    group: sampling
+  - path: frequency_penalty
+    type: number
+    label: Frequency penalty
+    description: Penalizes tokens in proportion to how often they have already appeared.
+    range:
+      min: -2
+      max: 2
+      step: 0.1
+    group: sampling
+  - path: response_format.type
+    type: enum
+    label: Response format
+    description: Choose plain text or force valid JSON output.
+    values:
+      - text
+      - json_object
+    group: output_format

models/nvidia/nemotron-3.5-super-vl-120b-a12b.yaml

@@ -0,0 +1,51 @@
+# yaml-language-server: $schema=https://modelparams.dev/api/v1/schema.json
+provider: nvidia
+authType: api_key
+apiSurface: openai-chat-completions
+model: nemotron-3.5-super-vl-120b-a12b
+wireId: nvidia/nemotron-3.5-super-vl-120b-a12b
+params:
+  - path: temperature
+    type: number
+    label: Temperature
+    description: Controls randomness. Lower values make outputs more focused; higher values make them more varied. Not recommended to modify both temperature and top_p in the same call.
+    default: 1
+    range:
+      max: 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. Not recommended to modify both temperature and top_p in the same call.
+    default: 0.95
+    range:
+      max: 1
+    group: sampling
+  - path: max_tokens
+    type: integer
+    label: Max tokens
+    description: Maximum number of tokens to generate. Generation stops when this limit is reached.
+    default: 16384
+    range:
+      min: 1
+      max: 32768
+    group: generation_length
+  - path: reasoning_effort
+    type: enum
+    label: Reasoning effort
+    description: Controls the reasoning mode. 'none' disables reasoning tokens, 'low' enables low-effort reasoning, and 'high' enables full reasoning.
+    default: high
+    values:
+      - none
+      - low
+      - high
+    group: reasoning
+  - path: reasoning_budget
+    type: integer
+    label: Reasoning budget
+    description: Maximum number of tokens the model may use for internal reasoning before being forced to end the reasoning trace. Use -1 to disable budget enforcement.
+    default: 16384
+    range:
+      min: -1
+      max: 32768
+    group: reasoning

models/nvidia/step-5-preview.yaml

@@ -0,0 +1,51 @@
+# yaml-language-server: $schema=https://modelparams.dev/api/v1/schema.json
+provider: nvidia
+authType: api_key
+apiSurface: openai-chat-completions
+model: step-5-preview
+wireId: stepfun-ai/step-5-preview
+params:
+  - path: temperature
+    type: number
+    label: Temperature
+    description: Controls randomness. Lower values make outputs more focused; higher values make them more varied. Not recommended to modify both temperature and top_p in the same call.
+    default: 0.6
+    range:
+      min: 0
+      max: 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. Not recommended to modify both temperature and top_p in the same call.
+    default: 0.95
+    range:
+      max: 1
+    group: sampling
+  - path: max_tokens
+    type: integer
+    label: Max tokens
+    description: Maximum number of tokens to generate. Generation stops when this limit is reached.
+    default: 4096
+    range:
+      min: 1
+      max: 16384
+    group: generation_length
+  - path: frequency_penalty
+    type: number
+    label: Frequency penalty
+    description: Penalizes new tokens based on their existing frequency in the text so far, decreasing the model's likelihood to repeat the same line verbatim.
+    default: 0
+    range:
+      min: -2
+      max: 2
+    group: sampling
+  - path: presence_penalty
+    type: number
+    label: Presence penalty
+    description: Positive values penalize new tokens based on whether they appear in the text so far, increasing the model's likelihood to talk about new topics.
+    default: 0
+    range:
+      min: -2
+      max: 2
+    group: sampling

models/xai/grok-4.7.yaml

@@ -28,7 +28,7 @@ params:
     description: Controls nucleus sampling by limiting generation to tokens within the selected cumulative probability.
     default: 1
     range:
-      min: 0
+      min: 0.01
       max: 1
       step: 0.01
     group: sampling