chore(catalog): sync from gateway — 5 added, 0 corrected, 9 retired

models/fireworks/minimax-m3p1-flash.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: minimax-m3p1-flash
+wireId: accounts/fireworks/models/minimax-m3p1-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.
+    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/minimax/MiniMax-M2.1-highspeed.yaml

@@ -3,6 +3,7 @@ provider: minimax
 authType: api_key
 apiSurface: openai-chat-completions
 model: MiniMax-M2.1-highspeed
+status: retired
 params:
   - path: max_completion_tokens
     type: integer

models/minimax/MiniMax-M2.1.yaml

@@ -3,6 +3,7 @@ provider: minimax
 authType: api_key
 apiSurface: openai-chat-completions
 model: MiniMax-M2.1
+status: retired
 params:
   - path: max_completion_tokens
     type: integer

models/minimax/MiniMax-M2.5-highspeed.yaml

@@ -3,6 +3,7 @@ provider: minimax
 authType: api_key
 apiSurface: openai-chat-completions
 model: MiniMax-M2.5-highspeed
+status: retired
 params:
   - path: max_completion_tokens
     type: integer

models/minimax/MiniMax-M2.5.yaml

@@ -3,6 +3,7 @@ provider: minimax
 authType: api_key
 apiSurface: openai-chat-completions
 model: MiniMax-M2.5
+status: retired
 params:
   - path: max_completion_tokens
     type: integer

models/minimax/MiniMax-M2.7-highspeed.yaml

@@ -3,6 +3,7 @@ provider: minimax
 authType: api_key
 apiSurface: openai-chat-completions
 model: MiniMax-M2.7-highspeed
+status: retired
 params:
   - path: max_completion_tokens
     type: integer

models/minimax/MiniMax-M2.7.yaml

@@ -3,6 +3,7 @@ provider: minimax
 authType: api_key
 apiSurface: openai-chat-completions
 model: MiniMax-M2.7
+status: retired
 params:
   - path: max_completion_tokens
     type: integer

models/minimax/MiniMax-M2.yaml

@@ -3,6 +3,7 @@ provider: minimax
 authType: api_key
 apiSurface: openai-chat-completions
 model: MiniMax-M2
+status: retired
 params:
   - path: max_completion_tokens
     type: integer

models/mistral/zai-glm-5-3-flash.yaml

@@ -0,0 +1,72 @@
+# yaml-language-server: $schema=https://modelparams.dev/api/v1/schema.json
+provider: mistral
+authType: api_key
+apiSurface: openai-chat-completions
+model: zai-glm-5-3-flash
+params:
+  - path: max_tokens
+    type: integer
+    label: Max tokens
+    description: Maximum number of tokens to generate in the completion.
+    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: 1.5
+      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: 1
+    range:
+      min: 0.01
+      max: 1
+      step: 0.01
+    group: sampling
+  - path: random_seed
+    type: integer
+    label: Random seed
+    description: Seed used for deterministic sampling when reproducible outputs are desired.
+    range:
+      min: 0
+    group: sampling
+  - path: presence_penalty
+    type: number
+    label: Presence penalty
+    description: Penalizes repeated words or phrases to encourage a wider variety of generated content.
+    default: 0
+    range:
+      min: -2
+      max: 2
+      step: 0.1
+    group: sampling
+  - path: frequency_penalty
+    type: number
+    label: Frequency penalty
+    description: Penalizes words based on how often they already appear in the generated text.
+    default: 0
+    range:
+      min: -2
+      max: 2
+      step: 0.1
+    group: sampling
+  - path: prompt_mode
+    type: enum
+    label: Prompt mode
+    description: Enables Mistral's reasoning system prompt; leave unset to disable the default reasoning behavior.
+    values:
+      - reasoning
+    group: reasoning
+  - path: safe_prompt
+    type: boolean
+    label: Safe prompt
+    description: Controls whether Mistral injects its safety prompt before the conversation.
+    default: false
+    group: provider_metadata

models/moonshot/kimi-k3.1-pro-highspeed.yaml

@@ -0,0 +1,73 @@
+# yaml-language-server: $schema=https://modelparams.dev/api/v1/schema.json
+provider: moonshot
+authType: api_key
+apiSurface: openai-chat-completions
+model: kimi-k3.1-pro-highspeed
+status: active
+params:
+  - path: max_completion_tokens
+    type: integer
+    label: Max tokens
+    description: Maximum number of tokens to generate in the chat completion.
+    range:
+      min: 1
+    group: generation_length
+  - path: thinking.type
+    type: enum
+    label: Thinking mode
+    description: >-
+      Controls whether Kimi reasons step by step before answering. Thinking is enabled by default;
+      set disabled to respond directly.
+    default: enabled
+    values:
+      - enabled
+      - disabled
+    group: reasoning
+  - path: thinking.keep
+    type: enum
+    label: Keep prior reasoning
+    description: >-
+      Set to all to carry reasoning content from earlier assistant turns into the request; leave
+      null to send only the final answers.
+    default: null
+    values:
+      - all
+      - null
+    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
+  - path: tool_choice
+    type: enum
+    label: Tool choice
+    description: >-
+      Controls tool calling: auto lets the model decide and none blocks tool calls. Moonshot rejects
+      required while thinking is enabled, which is the default on this model.
+    default: auto
+    values:
+      - auto
+      - none
+    group: tooling
+  - path: logprobs
+    type: boolean
+    label: Log probabilities
+    description: Controls whether the response includes log probabilities for the generated tokens.
+    default: false
+    group: observability
+  - path: top_logprobs
+    type: integer
+    label: Top log probabilities
+    description: Number of most likely tokens to return a log probability for at each position.
+    range:
+      min: 0
+      max: 20
+    group: observability
+    applicability:
+      only:
+        logprobs: true

models/moonshot/kimi-k3.1-pro.yaml

@@ -0,0 +1,73 @@
+# yaml-language-server: $schema=https://modelparams.dev/api/v1/schema.json
+provider: moonshot
+authType: api_key
+apiSurface: openai-chat-completions
+model: kimi-k3.1-pro
+status: active
+params:
+  - path: max_completion_tokens
+    type: integer
+    label: Max tokens
+    description: Maximum number of tokens to generate in the chat completion.
+    range:
+      min: 1
+    group: generation_length
+  - path: thinking.type
+    type: enum
+    label: Thinking mode
+    description: >-
+      Controls whether Kimi reasons step by step before answering. Thinking is enabled by default;
+      set disabled to respond directly.
+    default: enabled
+    values:
+      - enabled
+      - disabled
+    group: reasoning
+  - path: thinking.keep
+    type: enum
+    label: Keep prior reasoning
+    description: >-
+      Set to all to carry reasoning content from earlier assistant turns into the request; leave
+      null to send only the final answers.
+    default: null
+    values:
+      - all
+      - null
+    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
+  - path: tool_choice
+    type: enum
+    label: Tool choice
+    description: >-
+      Controls tool calling: auto lets the model decide and none blocks tool calls. Moonshot rejects
+      required while thinking is enabled, which is the default on this model.
+    default: auto
+    values:
+      - auto
+      - none
+    group: tooling
+  - path: logprobs
+    type: boolean
+    label: Log probabilities
+    description: Controls whether the response includes log probabilities for the generated tokens.
+    default: false
+    group: observability
+  - path: top_logprobs
+    type: integer
+    label: Top log probabilities
+    description: Number of most likely tokens to return a log probability for at each position.
+    range:
+      min: 0
+      max: 20
+    group: observability
+    applicability:
+      only:
+        logprobs: true

models/nvidia/kimi-k3.yaml

@@ -4,6 +4,7 @@ authType: api_key
 apiSurface: openai-chat-completions
 model: kimi-k3
 wireId: moonshotai/kimi-k3
+status: retired
 params:
   - path: temperature
     type: number