diff --git a/models/nvidia/laguna-xs-2.1.yaml b/models/nvidia/laguna-xs-2.1.yaml
new file mode 100644
index 00000000..af6f6efa
--- /dev/null
+++ b/models/nvidia/laguna-xs-2.1.yaml
@@ -0,0 +1,65 @@
+# yaml-language-server: $schema=https://modelparams.dev/api/v1/schema.json
+provider: nvidia
+authType: api_key
+apiSurface: openai-chat-completions
+model: laguna-xs-2.1
+wireId: poolside/laguna-xs-2.1
+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
+  - path: seed
+    type: integer
+    label: Seed
+    description: Best-effort deterministic sampling seed. Changing the seed produces a different response with similar characteristics. Fix the seed to reproduce results.
+    default: 0
+    range:
+      min: 0
+      max: 18446744073709552000
+    group: sampling
+  - path: stop
+    type: string
+    label: Stop
+    description: A string or list of strings where the API will stop generating further tokens. The returned text will not contain the stop sequence.
+    group: generation_length
diff --git a/packages/modelparams-python/src/modelparams/_generated/catalog.json b/packages/modelparams-python/src/modelparams/_generated/catalog.json
index 08adcb73..92051eed 100644
--- a/packages/modelparams-python/src/modelparams/_generated/catalog.json
+++ b/packages/modelparams-python/src/modelparams/_generated/catalog.json
@@ -22557,6 +22557,93 @@
       }
     ]
   },
+  {
+    "provider": "nvidia",
+    "authType": "api_key",
+    "apiSurface": "openai-chat-completions",
+    "model": "laguna-xs-2.1",
+    "wireId": "poolside/laguna-xs-2.1",
+    "params": [
+      {
+        "path": "temperature",
+        "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.",
+        "group": "sampling",
+        "type": "number",
+        "default": 0.6,
+        "range": {
+          "min": 0,
+          "max": 1
+        }
+      },
+      {
+        "path": "top_p",
+        "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.",
+        "group": "sampling",
+        "type": "number",
+        "default": 0.95,
+        "range": {
+          "max": 1
+        }
+      },
+      {
+        "path": "max_tokens",
+        "label": "Max tokens",
+        "description": "Maximum number of tokens to generate. Generation stops when this limit is reached.",
+        "group": "generation_length",
+        "type": "integer",
+        "default": 4096,
+        "range": {
+          "min": 1,
+          "max": 16384
+        }
+      },
+      {
+        "path": "frequency_penalty",
+        "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.",
+        "group": "sampling",
+        "type": "number",
+        "default": 0,
+        "range": {
+          "min": -2,
+          "max": 2
+        }
+      },
+      {
+        "path": "presence_penalty",
+        "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.",
+        "group": "sampling",
+        "type": "number",
+        "default": 0,
+        "range": {
+          "min": -2,
+          "max": 2
+        }
+      },
+      {
+        "path": "seed",
+        "label": "Seed",
+        "description": "Best-effort deterministic sampling seed. Changing the seed produces a different response with similar characteristics. Fix the seed to reproduce results.",
+        "group": "sampling",
+        "type": "integer",
+        "default": 0,
+        "range": {
+          "min": 0,
+          "max": 18446744073709552000
+        }
+      },
+      {
+        "path": "stop",
+        "label": "Stop",
+        "description": "A string or list of strings where the API will stop generating further tokens. The returned text will not contain the stop sequence.",
+        "group": "generation_length",
+        "type": "string"
+      }
+    ]
+  },
   {
     "provider": "nvidia",
     "authType": "api_key",
diff --git a/packages/modelparams-python/src/modelparams/_generated/model_ids.py b/packages/modelparams-python/src/modelparams/_generated/model_ids.py
index 6053d3df..6e53e3be 100644
--- a/packages/modelparams-python/src/modelparams/_generated/model_ids.py
+++ b/packages/modelparams-python/src/modelparams/_generated/model_ids.py
@@ -277,6 +277,7 @@
     "nvidia/gliner-pii",
     "nvidia/gpt-oss-120b",
     "nvidia/gpt-oss-20b",
+    "nvidia/laguna-xs-2.1",
     "nvidia/llama-3.1-nemoguard-8b-topic-control",
     "nvidia/llama-3.1-nemotron-nano-8b-v1",
     "nvidia/llama-3.1-nemotron-safety-guard-8b-v3",
@@ -689,6 +690,7 @@
     "nvidia/gliner-pii",
     "nvidia/gpt-oss-120b",
     "nvidia/gpt-oss-20b",
+    "nvidia/laguna-xs-2.1",
     "nvidia/llama-3.1-nemoguard-8b-topic-control",
     "nvidia/llama-3.1-nemotron-nano-8b-v1",
     "nvidia/llama-3.1-nemotron-safety-guard-8b-v3",
diff --git a/packages/modelparams-python/src/modelparams/_generated/registry.py b/packages/modelparams-python/src/modelparams/_generated/registry.py
index 183ce3e8..6a8590f0 100644
--- a/packages/modelparams-python/src/modelparams/_generated/registry.py
+++ b/packages/modelparams-python/src/modelparams/_generated/registry.py
@@ -302,6 +302,7 @@
     "nvidia/gliner-pii": nvidia.Gliner_PiiParams,
     "nvidia/gpt-oss-120b": nvidia.Gpt_Oss_120bParams,
     "nvidia/gpt-oss-20b": nvidia.Gpt_Oss_20bParams,
+    "nvidia/laguna-xs-2.1": nvidia.Laguna_Xs_2_1Params,
     "nvidia/llama-3.1-nemoguard-8b-topic-control": nvidia.Llama_3_1_Nemoguard_8b_Topic_ControlParams,
     "nvidia/llama-3.1-nemotron-nano-8b-v1": nvidia.Llama_3_1_Nemotron_Nano_8b_V1Params,
     "nvidia/llama-3.1-nemotron-safety-guard-8b-v3": nvidia.Llama_3_1_Nemotron_Safety_Guard_8b_V3Params,
diff --git a/packages/modelparams-python/src/modelparams/types/nvidia.py b/packages/modelparams-python/src/modelparams/types/nvidia.py
index af213cb1..71777e92 100644
--- a/packages/modelparams-python/src/modelparams/types/nvidia.py
+++ b/packages/modelparams-python/src/modelparams/types/nvidia.py
@@ -97,6 +97,21 @@
 )
 setattr(Gpt_Oss_20bParams, "__pydantic_config__", _PARAMS_CONFIG)
 
+Laguna_Xs_2_1Params = TypedDict(
+    "Laguna_Xs_2_1Params",
+    {
+        "temperature": Annotated[float, Field(ge=0, le=1)],
+        "top_p": Annotated[float, Field(le=1)],
+        "max_tokens": Annotated[int, Field(ge=1, le=16384)],
+        "frequency_penalty": Annotated[float, Field(ge=-2, le=2)],
+        "presence_penalty": Annotated[float, Field(ge=-2, le=2)],
+        "seed": Annotated[int, Field(ge=0, le=18446744073709552000)],
+        "stop": str,
+    },
+    total=False,
+)
+setattr(Laguna_Xs_2_1Params, "__pydantic_config__", _PARAMS_CONFIG)
+
 Llama_3_1_Nemoguard_8b_Topic_ControlParams = TypedDict(
     "Llama_3_1_Nemoguard_8b_Topic_ControlParams",
     {
@@ -336,6 +351,7 @@
     "Gliner_PiiParams",
     "Gpt_Oss_120bParams",
     "Gpt_Oss_20bParams",
+    "Laguna_Xs_2_1Params",
     "Llama_3_1_Nemoguard_8b_Topic_ControlParams",
     "Llama_3_1_Nemotron_Nano_8b_V1Params",
     "Llama_3_1_Nemotron_Safety_Guard_8b_V3Params",
diff --git a/packages/modelparams/src/generated/data.ts b/packages/modelparams/src/generated/data.ts
index da46b249..56f5b8df 100644
--- a/packages/modelparams/src/generated/data.ts
+++ b/packages/modelparams/src/generated/data.ts
@@ -22562,6 +22562,93 @@ const GENERATED_CATALOG = [
       }
     ]
   },
+  {
+    "provider": "nvidia",
+    "authType": "api_key",
+    "apiSurface": "openai-chat-completions",
+    "model": "laguna-xs-2.1",
+    "wireId": "poolside/laguna-xs-2.1",
+    "params": [
+      {
+        "path": "temperature",
+        "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.",
+        "group": "sampling",
+        "type": "number",
+        "default": 0.6,
+        "range": {
+          "min": 0,
+          "max": 1
+        }
+      },
+      {
+        "path": "top_p",
+        "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.",
+        "group": "sampling",
+        "type": "number",
+        "default": 0.95,
+        "range": {
+          "max": 1
+        }
+      },
+      {
+        "path": "max_tokens",
+        "label": "Max tokens",
+        "description": "Maximum number of tokens to generate. Generation stops when this limit is reached.",
+        "group": "generation_length",
+        "type": "integer",
+        "default": 4096,
+        "range": {
+          "min": 1,
+          "max": 16384
+        }
+      },
+      {
+        "path": "frequency_penalty",
+        "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.",
+        "group": "sampling",
+        "type": "number",
+        "default": 0,
+        "range": {
+          "min": -2,
+          "max": 2
+        }
+      },
+      {
+        "path": "presence_penalty",
+        "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.",
+        "group": "sampling",
+        "type": "number",
+        "default": 0,
+        "range": {
+          "min": -2,
+          "max": 2
+        }
+      },
+      {
+        "path": "seed",
+        "label": "Seed",
+        "description": "Best-effort deterministic sampling seed. Changing the seed produces a different response with similar characteristics. Fix the seed to reproduce results.",
+        "group": "sampling",
+        "type": "integer",
+        "default": 0,
+        "range": {
+          "min": 0,
+          "max": 18446744073709552000
+        }
+      },
+      {
+        "path": "stop",
+        "label": "Stop",
+        "description": "A string or list of strings where the API will stop generating further tokens. The returned text will not contain the stop sequence.",
+        "group": "generation_length",
+        "type": "string"
+      }
+    ]
+  },
   {
     "provider": "nvidia",
     "authType": "api_key",
diff --git a/packages/modelparams/src/generated/defaults.ts b/packages/modelparams/src/generated/defaults.ts
index b4b691e5..ddaed193 100644
--- a/packages/modelparams/src/generated/defaults.ts
+++ b/packages/modelparams/src/generated/defaults.ts
@@ -1346,6 +1346,14 @@ export const DEFAULTS = {
     presence_penalty: 0,
     seed: 0,
   },
+  "nvidia/laguna-xs-2.1": {
+    temperature: 0.6,
+    top_p: 0.95,
+    max_tokens: 4096,
+    frequency_penalty: 0,
+    presence_penalty: 0,
+    seed: 0,
+  },
   "nvidia/llama-3.1-nemoguard-8b-topic-control": {
     temperature: 0.5,
     top_p: 1,
diff --git a/packages/modelparams/src/generated/model-ids.ts b/packages/modelparams/src/generated/model-ids.ts
index 8a6a2bab..8f6e3f6c 100644
--- a/packages/modelparams/src/generated/model-ids.ts
+++ b/packages/modelparams/src/generated/model-ids.ts
@@ -275,6 +275,7 @@ export const MODEL_IDS = [
   "nvidia/gliner-pii",
   "nvidia/gpt-oss-120b",
   "nvidia/gpt-oss-20b",
+  "nvidia/laguna-xs-2.1",
   "nvidia/llama-3.1-nemoguard-8b-topic-control",
   "nvidia/llama-3.1-nemotron-nano-8b-v1",
   "nvidia/llama-3.1-nemotron-safety-guard-8b-v3",
diff --git a/packages/modelparams/src/generated/params-by-id.ts b/packages/modelparams/src/generated/params-by-id.ts
index c338a8b9..e89e1244 100644
--- a/packages/modelparams/src/generated/params-by-id.ts
+++ b/packages/modelparams/src/generated/params-by-id.ts
@@ -2237,6 +2237,15 @@ export type ParamsById = {
     seed: number;
     stop: string;
   };
+  "nvidia/laguna-xs-2.1": {
+    temperature: number;
+    top_p: number;
+    max_tokens: number;
+    frequency_penalty: number;
+    presence_penalty: number;
+    seed: number;
+    stop: string;
+  };
   "nvidia/llama-3.1-nemoguard-8b-topic-control": {
     temperature: number;
     top_p: number;