feat(minimax): add MiniMax-M3.1-Flash with reasoning effort

models/minimax/MiniMax-M3.1-Flash-subscription.yaml

@@ -0,0 +1,26 @@
+# yaml-language-server: $schema=https://modelparams.dev/api/v1/schema.json
+provider: minimax
+authType: subscription
+apiSurface: openai-chat-completions
+model: MiniMax-M3.1-Flash
+status: active
+params:
+  - path: max_tokens
+    type: integer
+    label: Max tokens
+    description: Maximum number of tokens to generate in the response. Thinking tokens count toward it.
+    range:
+      min: 1
+    group: generation_length
+  - path: reasoning_effort
+    type: enum
+    label: Reasoning effort
+    description: Sets how deeply the model thinks. Higher levels produce more thinking tokens at higher latency.
+    default: max
+    values:
+      - low
+      - medium
+      - high
+      - xhigh
+      - max
+    group: reasoning

models/minimax/MiniMax-M3.1-Flash.yaml

@@ -0,0 +1,26 @@
+# yaml-language-server: $schema=https://modelparams.dev/api/v1/schema.json
+provider: minimax
+authType: api_key
+apiSurface: openai-chat-completions
+model: MiniMax-M3.1-Flash
+status: active
+params:
+  - path: max_completion_tokens
+    type: integer
+    label: Max completion tokens
+    description: Maximum number of tokens to generate in the completion. Thinking tokens count toward it.
+    range:
+      min: 1
+    group: generation_length
+  - path: reasoning_effort
+    type: enum
+    label: Reasoning effort
+    description: Sets how deeply the model thinks. Higher levels produce more thinking tokens at higher latency.
+    default: max
+    values:
+      - low
+      - medium
+      - high
+      - xhigh
+      - max
+    group: reasoning

packages/modelparams-python/src/modelparams/_generated/catalog.json

@@ -22046,6 +22046,74 @@
       }
     ]
   },
+  {
+    "provider": "minimax",
+    "authType": "api_key",
+    "apiSurface": "openai-chat-completions",
+    "model": "MiniMax-M3.1-Flash",
+    "status": "active",
+    "params": [
+      {
+        "path": "max_completion_tokens",
+        "label": "Max completion tokens",
+        "description": "Maximum number of tokens to generate in the completion. Thinking tokens count toward it.",
+        "group": "generation_length",
+        "type": "integer",
+        "range": {
+          "min": 1
+        }
+      },
+      {
+        "path": "reasoning_effort",
+        "label": "Reasoning effort",
+        "description": "Sets how deeply the model thinks. Higher levels produce more thinking tokens at higher latency.",
+        "group": "reasoning",
+        "type": "enum",
+        "default": "max",
+        "values": [
+          "low",
+          "medium",
+          "high",
+          "xhigh",
+          "max"
+        ]
+      }
+    ]
+  },
+  {
+    "provider": "minimax",
+    "authType": "subscription",
+    "apiSurface": "openai-chat-completions",
+    "model": "MiniMax-M3.1-Flash",
+    "status": "active",
+    "params": [
+      {
+        "path": "max_tokens",
+        "label": "Max tokens",
+        "description": "Maximum number of tokens to generate in the response. Thinking tokens count toward it.",
+        "group": "generation_length",
+        "type": "integer",
+        "range": {
+          "min": 1
+        }
+      },
+      {
+        "path": "reasoning_effort",
+        "label": "Reasoning effort",
+        "description": "Sets how deeply the model thinks. Higher levels produce more thinking tokens at higher latency.",
+        "group": "reasoning",
+        "type": "enum",
+        "default": "max",
+        "values": [
+          "low",
+          "medium",
+          "high",
+          "xhigh",
+          "max"
+        ]
+      }
+    ]
+  },
   {
     "provider": "mistral",
     "authType": "api_key",

packages/modelparams-python/src/modelparams/_generated/model_ids.py

@@ -287,6 +287,8 @@
     "minimax/MiniMax-M2.7-subscription",
     "minimax/MiniMax-M3",
     "minimax/MiniMax-M3-subscription",
+    "minimax/MiniMax-M3.1-Flash",
+    "minimax/MiniMax-M3.1-Flash-subscription",
     "mistral/codestral-2508",
     "mistral/codestral-latest",
     "mistral/devstral-2512",
@@ -787,6 +789,8 @@
     "minimax/MiniMax-M2.7-subscription",
     "minimax/MiniMax-M3",
     "minimax/MiniMax-M3-subscription",
+    "minimax/MiniMax-M3.1-Flash",
+    "minimax/MiniMax-M3.1-Flash-subscription",
     "mistral/codestral-2508",
     "mistral/codestral-latest",
     "mistral/devstral-2512",

packages/modelparams-python/src/modelparams/_generated/registry.py

@@ -312,6 +312,8 @@
     "minimax/MiniMax-M2.7-subscription": minimax.Minimax_M2_7_SubscriptionParams,
     "minimax/MiniMax-M3": minimax.Minimax_M3Params,
     "minimax/MiniMax-M3-subscription": minimax.Minimax_M3_SubscriptionParams,
+    "minimax/MiniMax-M3.1-Flash": minimax.Minimax_M3_1_FlashParams,
+    "minimax/MiniMax-M3.1-Flash-subscription": minimax.Minimax_M3_1_Flash_SubscriptionParams,
     "mistral/codestral-2508": mistral.Codestral_2508Params,
     "mistral/codestral-latest": mistral.Codestral_LatestParams,
     "mistral/devstral-2512": mistral.Devstral_2512Params,

packages/modelparams-python/src/modelparams/types/minimax.py

@@ -194,6 +194,26 @@
 )
 setattr(Minimax_M3_SubscriptionParams, "__pydantic_config__", _PARAMS_CONFIG)
 
+Minimax_M3_1_FlashParams = TypedDict(
+    "Minimax_M3_1_FlashParams",
+    {
+        "max_completion_tokens": Annotated[int, Field(ge=1)],
+        "reasoning_effort": Literal["low", "medium", "high", "xhigh", "max"],
+    },
+    total=False,
+)
+setattr(Minimax_M3_1_FlashParams, "__pydantic_config__", _PARAMS_CONFIG)
+
+Minimax_M3_1_Flash_SubscriptionParams = TypedDict(
+    "Minimax_M3_1_Flash_SubscriptionParams",
+    {
+        "max_tokens": Annotated[int, Field(ge=1)],
+        "reasoning_effort": Literal["low", "medium", "high", "xhigh", "max"],
+    },
+    total=False,
+)
+setattr(Minimax_M3_1_Flash_SubscriptionParams, "__pydantic_config__", _PARAMS_CONFIG)
+
 __all__ = [
     "Minimax_M2Params",
     "Minimax_M2_SubscriptionParams",
@@ -211,4 +231,6 @@
     "Minimax_M2_7_SubscriptionParams",
     "Minimax_M3Params",
     "Minimax_M3_SubscriptionParams",
+    "Minimax_M3_1_FlashParams",
+    "Minimax_M3_1_Flash_SubscriptionParams",
 ]

packages/modelparams/src/generated/data.ts

@@ -22051,6 +22051,74 @@ const GENERATED_CATALOG = [
       }
     ]
   },
+  {
+    "provider": "minimax",
+    "authType": "api_key",
+    "apiSurface": "openai-chat-completions",
+    "model": "MiniMax-M3.1-Flash",
+    "status": "active",
+    "params": [
+      {
+        "path": "max_completion_tokens",
+        "label": "Max completion tokens",
+        "description": "Maximum number of tokens to generate in the completion. Thinking tokens count toward it.",
+        "group": "generation_length",
+        "type": "integer",
+        "range": {
+          "min": 1
+        }
+      },
+      {
+        "path": "reasoning_effort",
+        "label": "Reasoning effort",
+        "description": "Sets how deeply the model thinks. Higher levels produce more thinking tokens at higher latency.",
+        "group": "reasoning",
+        "type": "enum",
+        "default": "max",
+        "values": [
+          "low",
+          "medium",
+          "high",
+          "xhigh",
+          "max"
+        ]
+      }
+    ]
+  },
+  {
+    "provider": "minimax",
+    "authType": "subscription",
+    "apiSurface": "openai-chat-completions",
+    "model": "MiniMax-M3.1-Flash",
+    "status": "active",
+    "params": [
+      {
+        "path": "max_tokens",
+        "label": "Max tokens",
+        "description": "Maximum number of tokens to generate in the response. Thinking tokens count toward it.",
+        "group": "generation_length",
+        "type": "integer",
+        "range": {
+          "min": 1
+        }
+      },
+      {
+        "path": "reasoning_effort",
+        "label": "Reasoning effort",
+        "description": "Sets how deeply the model thinks. Higher levels produce more thinking tokens at higher latency.",
+        "group": "reasoning",
+        "type": "enum",
+        "default": "max",
+        "values": [
+          "low",
+          "medium",
+          "high",
+          "xhigh",
+          "max"
+        ]
+      }
+    ]
+  },
   {
     "provider": "mistral",
     "authType": "api_key",

packages/modelparams/src/generated/defaults.ts

@@ -1261,6 +1261,12 @@ export const DEFAULTS = {
     temperature: 1,
     top_p: 0.95,
   },
+  "minimax/MiniMax-M3.1-Flash": {
+    reasoning_effort: "max",
+  },
+  "minimax/MiniMax-M3.1-Flash-subscription": {
+    reasoning_effort: "max",
+  },
   "mistral/codestral-2508": {
     top_p: 1,
     presence_penalty: 0,

packages/modelparams/src/generated/model-ids.ts

@@ -285,6 +285,8 @@ export const MODEL_IDS = [
   "minimax/MiniMax-M2.7-subscription",
   "minimax/MiniMax-M3",
   "minimax/MiniMax-M3-subscription",
+  "minimax/MiniMax-M3.1-Flash",
+  "minimax/MiniMax-M3.1-Flash-subscription",
   "mistral/codestral-2508",
   "mistral/codestral-latest",
   "mistral/devstral-2512",

packages/modelparams/src/generated/params-by-id.ts

@@ -2205,6 +2205,14 @@ export type ParamsById = {
     temperature: number;
     top_p: number;
   };
+  "minimax/MiniMax-M3.1-Flash": {
+    max_completion_tokens: number;
+    reasoning_effort: "low" | "medium" | "high" | "xhigh" | "max";
+  };
+  "minimax/MiniMax-M3.1-Flash-subscription": {
+    max_tokens: number;
+    reasoning_effort: "low" | "medium" | "high" | "xhigh" | "max";
+  };
   "mistral/codestral-2508": {
     max_tokens: number;
     stop: string;