ruby_llm 1.7.0 → 1.8.0

data/lib/ruby_llm/models.json

@@ -3,7 +3,7 @@
     "id": "claude-3-5-haiku-20241022",
     "name": "Claude Haiku 3.5",
     "provider": "anthropic",
-    "family": "claude-3-5-haiku-latest",
+    "family": "claude-3-5-haiku",
     "created_at": null,
     "context_window": 200000,
     "max_output_tokens": 8192,
@@ -14,10 +14,12 @@
         "text"
       ],
       "output": [
+        "embeddings",
         "text"
       ]
     },
     "capabilities": [
+      "batch",
       "function_calling"
     ],
     "pricing": {
@@ -26,6 +28,10 @@
           "input_per_million": 0.8,
           "cached_input_per_million": 1.0,
           "output_per_million": 4.0
+        },
+        "batch": {
+          "input_per_million": 0.4,
+          "output_per_million": 2.0
         }
       }
     },
@@ -111,7 +117,7 @@
     "id": "claude-3-7-sonnet-20250219",
     "name": "Claude Sonnet 3.7",
     "provider": "anthropic",
-    "family": "claude-3-7-sonnet-latest",
+    "family": "claude-3-7-sonnet",
     "created_at": null,
     "context_window": 200000,
     "max_output_tokens": 64000,
@@ -122,10 +128,12 @@
         "text"
       ],
       "output": [
+        "embeddings",
         "text"
       ]
     },
     "capabilities": [
+      "batch",
       "function_calling"
     ],
     "pricing": {
@@ -134,6 +142,10 @@
           "input_per_million": 3.0,
           "cached_input_per_million": 3.75,
           "output_per_million": 15.0
+        },
+        "batch": {
+          "input_per_million": 1.5,
+          "output_per_million": 7.5
         }
       }
     },
@@ -154,10 +166,12 @@
         "text"
       ],
       "output": [
+        "embeddings",
         "text"
       ]
     },
     "capabilities": [
+      "batch",
       "function_calling"
     ],
     "pricing": {
@@ -166,6 +180,10 @@
           "input_per_million": 0.25,
           "cached_input_per_million": 0.3,
           "output_per_million": 1.25
+        },
+        "batch": {
+          "input_per_million": 0.125,
+          "output_per_million": 0.625
         }
       }
     },
@@ -224,10 +242,12 @@
         "text"
       ],
       "output": [
+        "embeddings",
         "text"
       ]
     },
     "capabilities": [
+      "batch",
       "function_calling"
     ],
     "pricing": {
@@ -236,6 +256,10 @@
           "input_per_million": 15.0,
           "cached_input_per_million": 18.75,
           "output_per_million": 75.0
+        },
+        "batch": {
+          "input_per_million": 7.5,
+          "output_per_million": 37.5
         }
       }
     },
@@ -245,7 +269,7 @@
     "id": "claude-opus-4-20250514",
     "name": "Claude Opus 4",
     "provider": "anthropic",
-    "family": "claude-opus-4-0",
+    "family": "claude-opus-4",
     "created_at": null,
     "context_window": 200000,
     "max_output_tokens": 32000,
@@ -256,10 +280,12 @@
         "text"
       ],
       "output": [
+        "embeddings",
         "text"
       ]
     },
     "capabilities": [
+      "batch",
       "function_calling"
     ],
     "pricing": {
@@ -268,6 +294,10 @@
           "input_per_million": 15.0,
           "cached_input_per_million": 18.75,
           "output_per_million": 75.0
+        },
+        "batch": {
+          "input_per_million": 7.5,
+          "output_per_million": 37.5
         }
       }
     },
@@ -277,7 +307,7 @@
     "id": "claude-sonnet-4-20250514",
     "name": "Claude Sonnet 4",
     "provider": "anthropic",
-    "family": "claude-sonnet-4-0",
+    "family": "claude-sonnet-4",
     "created_at": null,
     "context_window": 200000,
     "max_output_tokens": 64000,
@@ -288,10 +318,12 @@
         "text"
       ],
       "output": [
+        "embeddings",
         "text"
       ]
     },
     "capabilities": [
+      "batch",
       "function_calling"
     ],
     "pricing": {
@@ -300,6 +332,10 @@
           "input_per_million": 3.0,
           "cached_input_per_million": 3.75,
           "output_per_million": 15.0
+        },
+        "batch": {
+          "input_per_million": 1.5,
+          "output_per_million": 7.5
         }
       }
     },
@@ -1249,55 +1285,6 @@
       ]
     }
   },
-  {
-    "id": "anthropic.claude-instant-v1",
-    "name": "Claude Instant",
-    "provider": "bedrock",
-    "family": "claude_instant",
-    "created_at": null,
-    "context_window": 200000,
-    "max_output_tokens": 4096,
-    "knowledge_cutoff": null,
-    "modalities": {
-      "input": [
-        "text",
-        "image",
-        "pdf"
-      ],
-      "output": [
-        "text"
-      ]
-    },
-    "capabilities": [
-      "streaming",
-      "function_calling"
-    ],
-    "pricing": {
-      "text_tokens": {
-        "standard": {
-          "input_per_million": 0.8,
-          "output_per_million": 2.4
-        },
-        "batch": {
-          "input_per_million": 0.4,
-          "output_per_million": 1.2
-        }
-      }
-    },
-    "metadata": {
-      "provider_name": "Anthropic",
-      "inference_types": [
-        "ON_DEMAND"
-      ],
-      "streaming_supported": true,
-      "input_modalities": [
-        "TEXT"
-      ],
-      "output_modalities": [
-        "TEXT"
-      ]
-    }
-  },
   {
     "id": "anthropic.claude-instant-v1:2:100k",
     "name": "Claude Instant",
@@ -1347,55 +1334,6 @@
       ]
     }
   },
-  {
-    "id": "anthropic.claude-v2",
-    "name": "Claude",
-    "provider": "bedrock",
-    "family": "claude2",
-    "created_at": null,
-    "context_window": 200000,
-    "max_output_tokens": 4096,
-    "knowledge_cutoff": null,
-    "modalities": {
-      "input": [
-        "text",
-        "image",
-        "pdf"
-      ],
-      "output": [
-        "text"
-      ]
-    },
-    "capabilities": [
-      "streaming",
-      "function_calling"
-    ],
-    "pricing": {
-      "text_tokens": {
-        "standard": {
-          "input_per_million": 8.0,
-          "output_per_million": 24.0
-        },
-        "batch": {
-          "input_per_million": 4.0,
-          "output_per_million": 12.0
-        }
-      }
-    },
-    "metadata": {
-      "provider_name": "Anthropic",
-      "inference_types": [
-        "ON_DEMAND"
-      ],
-      "streaming_supported": true,
-      "input_modalities": [
-        "TEXT"
-      ],
-      "output_modalities": [
-        "TEXT"
-      ]
-    }
-  },
   {
     "id": "anthropic.claude-v2:0:100k",
     "name": "Claude",
@@ -1494,55 +1432,6 @@
       ]
     }
   },
-  {
-    "id": "anthropic.claude-v2:1",
-    "name": "Claude",
-    "provider": "bedrock",
-    "family": "claude2",
-    "created_at": null,
-    "context_window": 200000,
-    "max_output_tokens": 4096,
-    "knowledge_cutoff": null,
-    "modalities": {
-      "input": [
-        "text",
-        "image",
-        "pdf"
-      ],
-      "output": [
-        "text"
-      ]
-    },
-    "capabilities": [
-      "streaming",
-      "function_calling"
-    ],
-    "pricing": {
-      "text_tokens": {
-        "standard": {
-          "input_per_million": 8.0,
-          "output_per_million": 24.0
-        },
-        "batch": {
-          "input_per_million": 4.0,
-          "output_per_million": 12.0
-        }
-      }
-    },
-    "metadata": {
-      "provider_name": "Anthropic",
-      "inference_types": [
-        "ON_DEMAND"
-      ],
-      "streaming_supported": true,
-      "input_modalities": [
-        "TEXT"
-      ],
-      "output_modalities": [
-        "TEXT"
-      ]
-    }
-  },
   {
     "id": "anthropic.claude-v2:1:18k",
     "name": "Claude",
@@ -2014,7 +1903,7 @@
     "id": "gemini-1.5-flash",
     "name": "Gemini 1.5 Flash",
     "provider": "gemini",
-    "family": "gemini-1.5-flash",
+    "family": "models/gemini-1.5-flash",
     "created_at": null,
     "context_window": 1048576,
     "max_output_tokens": 8192,
@@ -2055,7 +1944,7 @@
     "id": "gemini-1.5-flash-001",
     "name": "Gemini 1.5 Flash",
     "provider": "gemini",
-    "family": "gemini-1.5-flash",
+    "family": "models/gemini-1.5-flash",
     "created_at": null,
     "context_window": 1048576,
     "max_output_tokens": 8192,
@@ -2089,7 +1978,7 @@
     "id": "gemini-1.5-flash-002",
     "name": "Gemini 1.5 Flash",
     "provider": "gemini",
-    "family": "gemini-1.5-flash",
+    "family": "models/gemini-1.5-flash",
     "created_at": null,
     "context_window": 1048576,
     "max_output_tokens": 8192,
@@ -2131,7 +2020,7 @@
     "id": "gemini-1.5-flash-8b",
     "name": "Gemini 1.5 Flash-8B",
     "provider": "gemini",
-    "family": "gemini-1.5-flash-8b",
+    "family": "models/gemini-1.5-flash-8b",
     "created_at": null,
     "context_window": 1048576,
     "max_output_tokens": 8192,
@@ -2173,7 +2062,7 @@
     "id": "gemini-1.5-flash-8b-001",
     "name": "Gemini 1.5 Flash-8B",
     "provider": "gemini",
-    "family": "gemini-1.5-flash-8b",
+    "family": "models/gemini-1.5-flash-8b",
     "created_at": null,
     "context_window": 1048576,
     "max_output_tokens": 8192,
@@ -2215,7 +2104,7 @@
     "id": "gemini-1.5-flash-8b-latest",
     "name": "Gemini 1.5 Flash-8B",
     "provider": "gemini",
-    "family": "gemini-1.5-flash-8b",
+    "family": "models/gemini-1.5-flash-8b",
     "created_at": null,
     "context_window": 1048576,
     "max_output_tokens": 8192,
@@ -2257,7 +2146,7 @@
     "id": "gemini-1.5-flash-latest",
     "name": "Gemini 1.5 Flash",
     "provider": "gemini",
-    "family": "gemini-1.5-flash",
+    "family": "models/gemini-1.5-flash",
     "created_at": null,
     "context_window": 1048576,
     "max_output_tokens": 8192,
@@ -2298,7 +2187,7 @@
     "id": "gemini-1.5-pro",
     "name": "Gemini 1.5 Pro",
     "provider": "gemini",
-    "family": "gemini-1.5-pro",
+    "family": "models/gemini-1.5-pro",
     "created_at": null,
     "context_window": 2097152,
     "max_output_tokens": 8192,
@@ -2339,7 +2228,7 @@
     "id": "gemini-1.5-pro-001",
     "name": "Gemini 1.5 Pro",
     "provider": "gemini",
-    "family": "gemini-1.5-pro",
+    "family": "models/gemini-1.5-pro",
     "created_at": null,
     "context_window": 2097152,
     "max_output_tokens": 8192,
@@ -2373,7 +2262,7 @@
     "id": "gemini-1.5-pro-002",
     "name": "Gemini 1.5 Pro",
     "provider": "gemini",
-    "family": "gemini-1.5-pro",
+    "family": "models/gemini-1.5-pro",
     "created_at": null,
     "context_window": 2097152,
     "max_output_tokens": 8192,
@@ -2415,7 +2304,7 @@
     "id": "gemini-1.5-pro-latest",
     "name": "Gemini 1.5 Pro",
     "provider": "gemini",
-    "family": "gemini-1.5-pro",
+    "family": "models/gemini-1.5-pro",
     "created_at": null,
     "context_window": 2097152,
     "max_output_tokens": 8192,
@@ -2456,7 +2345,7 @@
     "id": "gemini-2.0-flash",
     "name": "Gemini 2.0 Flash",
     "provider": "gemini",
-    "family": "gemini-2.0-flash",
+    "family": "models/gemini-2.0-flash",
     "created_at": null,
     "context_window": 1048576,
     "max_output_tokens": 8192,
@@ -2504,7 +2393,7 @@
     "id": "gemini-2.0-flash-001",
     "name": "Gemini 2.0 Flash",
     "provider": "gemini",
-    "family": "gemini-2.0-flash",
+    "family": "models/gemini-2.0-flash",
     "created_at": null,
     "context_window": 1048576,
     "max_output_tokens": 8192,
@@ -2552,7 +2441,7 @@
     "id": "gemini-2.0-flash-exp",
     "name": "Gemini 2.0 Flash",
     "provider": "gemini",
-    "family": "gemini-2.0-flash",
+    "family": "models/gemini-2.0-flash",
     "created_at": null,
     "context_window": 1048576,
     "max_output_tokens": 8192,
@@ -2599,7 +2488,7 @@
     "id": "gemini-2.0-flash-lite",
     "name": "Gemini 2.0 Flash-Lite",
     "provider": "gemini",
-    "family": "gemini-2.0-flash-lite",
+    "family": "models/gemini-2.0-flash-lite",
     "created_at": null,
     "context_window": 1048576,
     "max_output_tokens": 8192,
@@ -2647,7 +2536,7 @@
     "id": "gemini-2.0-flash-lite-001",
     "name": "Gemini 2.0 Flash-Lite",
     "provider": "gemini",
-    "family": "gemini-2.0-flash-lite",
+    "family": "models/gemini-2.0-flash-lite",
     "created_at": null,
     "context_window": 1048576,
     "max_output_tokens": 8192,
@@ -2704,7 +2593,8 @@
       "input": [
         "text",
         "image",
-        "pdf"
+        "pdf",
+        "video"
       ],
       "output": [
         "text"
@@ -2750,7 +2640,8 @@
       "input": [
         "text",
         "image",
-        "pdf"
+        "pdf",
+        "video"
       ],
       "output": [
         "text"
@@ -2787,7 +2678,7 @@
     "id": "gemini-2.0-flash-live-001",
     "name": "Gemini 2.0 Flash Live",
     "provider": "gemini",
-    "family": "gemini-2.0-flash-live-001",
+    "family": "models/gemini-2.0-flash-live-001",
     "created_at": null,
     "context_window": 1048576,
     "max_output_tokens": 8192,
@@ -2821,7 +2712,7 @@
     "id": "gemini-2.0-flash-preview-image-generation",
     "name": "Gemini 2.0 Flash Preview Image Generation",
     "provider": "gemini",
-    "family": "gemini-2.0-flash-preview-image-generation",
+    "family": "models/gemini-2.0-flash-preview-image-generation",
     "created_at": null,
     "context_window": 32000,
     "max_output_tokens": 8192,
@@ -2869,7 +2760,8 @@
       "input": [
         "text",
         "image",
-        "pdf"
+        "pdf",
+        "video"
       ],
       "output": [
         "text"
@@ -2918,7 +2810,8 @@
       "input": [
         "text",
         "image",
-        "pdf"
+        "pdf",
+        "video"
       ],
       "output": [
         "text"
@@ -2967,7 +2860,8 @@
       "input": [
         "text",
         "image",
-        "pdf"
+        "pdf",
+        "video"
       ],
       "output": [
         "text"
@@ -3016,7 +2910,8 @@
       "input": [
         "text",
         "image",
-        "pdf"
+        "pdf",
+        "video"
       ],
       "output": [
         "text"
@@ -3064,7 +2959,8 @@
       "input": [
         "text",
         "image",
-        "pdf"
+        "pdf",
+        "video"
       ],
       "output": [
         "text"
@@ -3103,7 +2999,7 @@
     "id": "gemini-2.5-flash",
     "name": "Gemini 2.5 Flash",
     "provider": "gemini",
-    "family": "gemini-2.5-flash",
+    "family": "models/gemini-2.5-flash",
     "created_at": null,
     "context_window": 1048576,
     "max_output_tokens": 65536,
@@ -3151,7 +3047,7 @@
     "id": "gemini-2.5-flash-exp-native-audio-thinking-dialog",
     "name": "Gemini 2.5 Flash Native Audio",
     "provider": "gemini",
-    "family": "gemini-2.5-flash-preview-native-audio-dialog",
+    "family": "models/gemini-2.5-flash-preview-native-audio-dialog",
     "created_at": null,
     "context_window": 128000,
     "max_output_tokens": 8000,
@@ -3184,7 +3080,7 @@
     "id": "gemini-2.5-flash-image-preview",
     "name": "Gemini 2.5 Flash Image Preview",
     "provider": "gemini",
-    "family": "gemini-2.5-flash-image-preview",
+    "family": "models/gemini-2.5-flash-image-preview",
     "created_at": null,
     "context_window": 32768,
     "max_output_tokens": 32768,
@@ -3229,7 +3125,7 @@
     "id": "gemini-2.5-flash-lite",
     "name": "Gemini 2.5 Flash-Lite",
     "provider": "gemini",
-    "family": "gemini-2.5-flash-lite",
+    "family": "models/gemini-2.5-flash-lite",
     "created_at": null,
     "context_window": 1048576,
     "max_output_tokens": 65536,
@@ -3277,7 +3173,7 @@
     "id": "gemini-2.5-flash-lite-06-17",
     "name": "Gemini 2.5 Flash-Lite",
     "provider": "gemini",
-    "family": "gemini-2.5-flash-lite",
+    "family": "models/gemini-2.5-flash-lite",
     "created_at": null,
     "context_window": 1048576,
     "max_output_tokens": 65536,
@@ -3325,7 +3221,8 @@
       "input": [
         "text",
         "image",
-        "pdf"
+        "pdf",
+        "video"
       ],
       "output": [
         "text"
@@ -3363,7 +3260,7 @@
     "id": "gemini-2.5-flash-preview-05-20",
     "name": "Gemini 2.5 Flash",
     "provider": "gemini",
-    "family": "gemini-2.5-flash",
+    "family": "models/gemini-2.5-flash",
     "created_at": null,
     "context_window": 1048576,
     "max_output_tokens": 65536,
@@ -3411,7 +3308,7 @@
     "id": "gemini-2.5-flash-preview-native-audio-dialog",
     "name": "Gemini 2.5 Flash Native Audio",
     "provider": "gemini",
-    "family": "gemini-2.5-flash-preview-native-audio-dialog",
+    "family": "models/gemini-2.5-flash-preview-native-audio-dialog",
     "created_at": null,
     "context_window": 128000,
     "max_output_tokens": 8000,
@@ -3444,7 +3341,7 @@
     "id": "gemini-2.5-flash-preview-tts",
     "name": "Gemini 2.5 Flash Preview TTS",
     "provider": "gemini",
-    "family": "gemini-2.5-flash-preview-tts",
+    "family": "models/gemini-2.5-flash-preview-tts",
     "created_at": null,
     "context_window": 8000,
     "max_output_tokens": 16000,
@@ -3486,7 +3383,7 @@
     "id": "gemini-2.5-pro",
     "name": "Gemini 2.5 Pro",
     "provider": "gemini",
-    "family": "gemini-2.5-pro",
+    "family": "models/gemini-2.5-pro",
     "created_at": null,
     "context_window": 1048576,
     "max_output_tokens": 65536,
@@ -3543,7 +3440,8 @@
       "input": [
         "text",
         "image",
-        "pdf"
+        "pdf",
+        "video"
       ],
       "output": [
         "text"
@@ -3591,7 +3489,8 @@
       "input": [
         "text",
         "image",
-        "pdf"
+        "pdf",
+        "video"
       ],
       "output": [
         "text"
@@ -3639,7 +3538,8 @@
       "input": [
         "text",
         "image",
-        "pdf"
+        "pdf",
+        "video"
       ],
       "output": [
         "text"
@@ -3678,7 +3578,7 @@
     "id": "gemini-2.5-pro-preview-tts",
     "name": "Gemini 2.5 Pro Preview TTS",
     "provider": "gemini",
-    "family": "gemini-2.5-pro-preview-tts",
+    "family": "models/gemini-2.5-pro-preview-tts",
     "created_at": null,
     "context_window": 8000,
     "max_output_tokens": 16000,
@@ -3727,7 +3627,8 @@
     "knowledge_cutoff": null,
     "modalities": {
       "input": [
-        "text"
+        "text",
+        "video"
       ],
       "output": [
         "text",
@@ -3769,7 +3670,8 @@
       "input": [
         "text",
         "image",
-        "pdf"
+        "pdf",
+        "video"
       ],
       "output": [
         "text",
@@ -3823,7 +3725,8 @@
       "input": [
         "text",
         "image",
-        "pdf"
+        "pdf",
+        "video"
       ],
       "output": [
         "text",
@@ -3877,7 +3780,8 @@
       "input": [
         "text",
         "image",
-        "pdf"
+        "pdf",
+        "video"
       ],
       "output": [
         "text"
@@ -3916,7 +3820,7 @@
     "id": "gemini-live-2.5-flash-preview",
     "name": "Gemini 2.5 Flash Live",
     "provider": "gemini",
-    "family": "gemini-live-2.5-flash-preview",
+    "family": "models/gemini-live-2.5-flash-preview",
     "created_at": null,
     "context_window": 1048576,
     "max_output_tokens": 8192,
@@ -5045,6 +4949,30 @@
       "owned_by": "mistralai"
     }
   },
+  {
+    "id": "mistral-embed-2312",
+    "name": "Mistral Embed",
+    "provider": "mistral",
+    "family": "mistral-embed",
+    "created_at": null,
+    "context_window": 32768,
+    "max_output_tokens": 8192,
+    "knowledge_cutoff": null,
+    "modalities": {
+      "input": [
+        "text"
+      ],
+      "output": [
+        "embeddings"
+      ]
+    },
+    "capabilities": [],
+    "pricing": {},
+    "metadata": {
+      "object": "model",
+      "owned_by": "mistralai"
+    }
+  },
   {
     "id": "mistral-large-2407",
     "name": "Mistral Large",
@@ -9815,8 +9743,8 @@
     "provider": "openrouter",
     "family": "alfredpros",
     "created_at": "2025-04-14 16:44:34 +0200",
-    "context_window": 8192,
-    "max_output_tokens": 8192,
+    "context_window": 4096,
+    "max_output_tokens": 4096,
     "knowledge_cutoff": null,
     "modalities": {
       "input": [
@@ -9827,14 +9755,13 @@
       ]
     },
     "capabilities": [
-      "streaming",
-      "predicted_outputs"
+      "streaming"
     ],
     "pricing": {
       "text_tokens": {
         "standard": {
-          "input_per_million": 0.7,
-          "output_per_million": 1.1
+          "input_per_million": 0.7999999999999999,
+          "output_per_million": 1.2
         }
       }
     },
@@ -9852,14 +9779,13 @@
         "instruct_type": "alpaca"
       },
       "top_provider": {
-        "context_length": 8192,
-        "max_completion_tokens": 8192,
+        "context_length": 4096,
+        "max_completion_tokens": 4096,
         "is_moderated": false
       },
       "per_request_limits": null,
       "supported_parameters": [
         "frequency_penalty",
-        "logit_bias",
         "max_tokens",
         "min_p",
         "presence_penalty",
@@ -9873,17 +9799,18 @@
     }
   },
   {
-    "id": "alpindale/goliath-120b",
-    "name": "Goliath 120B",
+    "id": "allenai/molmo-7b-d",
+    "name": "AllenAI: Molmo 7B D",
     "provider": "openrouter",
-    "family": "alpindale",
-    "created_at": "2023-11-10 01:00:00 +0100",
-    "context_window": 6144,
-    "max_output_tokens": 512,
+    "family": "allenai",
+    "created_at": "2025-03-26 22:07:27 +0100",
+    "context_window": 4096,
+    "max_output_tokens": 4096,
     "knowledge_cutoff": null,
     "modalities": {
       "input": [
-        "text"
+        "text",
+        "image"
       ],
       "output": [
         "text"
@@ -9891,32 +9818,159 @@
     },
     "capabilities": [
       "streaming",
-      "structured_output",
       "predicted_outputs"
     ],
     "pricing": {
       "text_tokens": {
         "standard": {
-          "input_per_million": 4.0,
-          "output_per_million": 5.5
+          "input_per_million": 0.09999999999999999,
+          "output_per_million": 0.19999999999999998
         }
       }
     },
     "metadata": {
-      "description": "A large LLM created by combining two fine-tuned Llama 70B models into one 120B model. Combines Xwin and Euryale.\n\nCredits to\n- [@chargoddard](https://huggingface.co/chargoddard) for developing the framework used to merge the model - [mergekit](https://github.com/cg123/mergekit).\n- [@Undi95](https://huggingface.co/Undi95) for helping with the merge ratios.\n\n#merge",
+      "description": "Molmo is a family of open vision-language models developed by the Allen Institute for AI. Molmo models are trained on PixMo, a dataset of 1 million, highly-curated image-text pairs. It has state-of-the-art performance among multimodal models with a similar size while being fully open-source. You can find all models in the Molmo family [here](https://huggingface.co/collections/allenai/molmo-66f379e6fe3b8ef090a8ca19). Learn more about the Molmo family [in the announcement blog post](https://molmo.allenai.org/blog) or the [paper](https://huggingface.co/papers/2409.17146).\n\nMolmo 7B-D is based on [Qwen2-7B](https://huggingface.co/Qwen/Qwen2-7B) and uses [OpenAI CLIP](https://huggingface.co/openai/clip-vit-large-patch14-336) as vision backbone. It performs comfortably between GPT-4V and GPT-4o on both academic benchmarks and human evaluation.\n\nThis checkpoint is a preview of the Molmo release. All artifacts used in creating Molmo (PixMo dataset, training code, evaluations, intermediate checkpoints) will be made available at a later date, furthering our commitment to open-source AI development and reproducibility.",
       "architecture": {
-        "modality": "text->text",
+        "modality": "text+image->text",
         "input_modalities": [
-          "text"
+          "text",
+          "image"
         ],
         "output_modalities": [
           "text"
         ],
-        "tokenizer": "Llama2",
-        "instruct_type": "airoboros"
+        "tokenizer": "Other",
+        "instruct_type": null
       },
       "top_provider": {
-        "context_length": 6144,
+        "context_length": 4096,
+        "max_completion_tokens": 4096,
+        "is_moderated": false
+      },
+      "per_request_limits": null,
+      "supported_parameters": [
+        "frequency_penalty",
+        "logit_bias",
+        "max_tokens",
+        "min_p",
+        "presence_penalty",
+        "repetition_penalty",
+        "seed",
+        "stop",
+        "temperature",
+        "top_k",
+        "top_p"
+      ]
+    }
+  },
+  {
+    "id": "allenai/olmo-2-0325-32b-instruct",
+    "name": "AllenAI: Olmo 2 32B Instruct",
+    "provider": "openrouter",
+    "family": "allenai",
+    "created_at": "2025-03-14 22:42:36 +0100",
+    "context_window": 4096,
+    "max_output_tokens": 4096,
+    "knowledge_cutoff": null,
+    "modalities": {
+      "input": [
+        "text"
+      ],
+      "output": [
+        "text"
+      ]
+    },
+    "capabilities": [
+      "streaming",
+      "predicted_outputs"
+    ],
+    "pricing": {
+      "text_tokens": {
+        "standard": {
+          "input_per_million": 1.0,
+          "output_per_million": 1.5
+        }
+      }
+    },
+    "metadata": {
+      "description": "OLMo-2 32B Instruct is a supervised instruction-finetuned variant of the OLMo-2 32B March 2025 base model. It excels in complex reasoning and instruction-following tasks across diverse benchmarks such as GSM8K, MATH, IFEval, and general NLP evaluation. Developed by AI2, OLMo-2 32B is part of an open, research-oriented initiative, trained primarily on English-language datasets to advance the understanding and development of open-source language models.",
+      "architecture": {
+        "modality": "text->text",
+        "input_modalities": [
+          "text"
+        ],
+        "output_modalities": [
+          "text"
+        ],
+        "tokenizer": "Other",
+        "instruct_type": null
+      },
+      "top_provider": {
+        "context_length": 4096,
+        "max_completion_tokens": 4096,
+        "is_moderated": false
+      },
+      "per_request_limits": null,
+      "supported_parameters": [
+        "frequency_penalty",
+        "logit_bias",
+        "max_tokens",
+        "min_p",
+        "presence_penalty",
+        "repetition_penalty",
+        "seed",
+        "stop",
+        "temperature",
+        "top_k",
+        "top_p"
+      ]
+    }
+  },
+  {
+    "id": "alpindale/goliath-120b",
+    "name": "Goliath 120B",
+    "provider": "openrouter",
+    "family": "alpindale",
+    "created_at": "2023-11-10 01:00:00 +0100",
+    "context_window": 6144,
+    "max_output_tokens": 512,
+    "knowledge_cutoff": null,
+    "modalities": {
+      "input": [
+        "text"
+      ],
+      "output": [
+        "text"
+      ]
+    },
+    "capabilities": [
+      "streaming",
+      "structured_output",
+      "predicted_outputs"
+    ],
+    "pricing": {
+      "text_tokens": {
+        "standard": {
+          "input_per_million": 4.0,
+          "output_per_million": 5.5
+        }
+      }
+    },
+    "metadata": {
+      "description": "A large LLM created by combining two fine-tuned Llama 70B models into one 120B model. Combines Xwin and Euryale.\n\nCredits to\n- [@chargoddard](https://huggingface.co/chargoddard) for developing the framework used to merge the model - [mergekit](https://github.com/cg123/mergekit).\n- [@Undi95](https://huggingface.co/Undi95) for helping with the merge ratios.\n\n#merge",
+      "architecture": {
+        "modality": "text->text",
+        "input_modalities": [
+          "text"
+        ],
+        "output_modalities": [
+          "text"
+        ],
+        "tokenizer": "Llama2",
+        "instruct_type": "airoboros"
+      },
+      "top_provider": {
+        "context_length": 6144,
         "max_completion_tokens": 512,
         "is_moderated": false
       },
@@ -10802,7 +10856,7 @@
       "top_provider": {
         "context_length": 200000,
         "max_completion_tokens": 32000,
-        "is_moderated": false
+        "is_moderated": true
       },
       "per_request_limits": null,
       "supported_parameters": [
@@ -10868,7 +10922,7 @@
       "top_provider": {
         "context_length": 200000,
         "max_completion_tokens": 32000,
-        "is_moderated": false
+        "is_moderated": true
       },
       "per_request_limits": null,
       "supported_parameters": [
@@ -11225,8 +11279,8 @@
     "pricing": {
       "text_tokens": {
         "standard": {
-          "input_per_million": 0.01,
-          "output_per_million": 0.0400032
+          "input_per_million": 0.017934774,
+          "output_per_million": 0.07173912240000001
         }
       }
     },
@@ -11614,8 +11668,8 @@
     "pricing": {
       "text_tokens": {
         "standard": {
-          "input_per_million": 0.10366159999999999,
-          "output_per_million": 0.414848
+          "input_per_million": 0.2006688,
+          "output_per_million": 0.80267549538462
         }
       }
     },
@@ -11863,8 +11917,8 @@
     "pricing": {
       "text_tokens": {
         "standard": {
-          "input_per_million": 0.037022,
-          "output_per_million": 0.14816
+          "input_per_million": 0.0271739,
+          "output_per_million": 0.10869564
         }
       }
     },
@@ -11986,8 +12040,8 @@
     "pricing": {
       "text_tokens": {
         "standard": {
-          "input_per_million": 0.01,
-          "output_per_million": 0.0340768
+          "input_per_million": 0.01333333333333,
+          "output_per_million": 0.0347826048
         }
       }
     },
@@ -12818,8 +12872,8 @@
     "pricing": {
       "text_tokens": {
         "standard": {
-          "input_per_million": 0.1999188,
-          "output_per_million": 0.800064
+          "input_per_million": 0.24999987999999998,
+          "output_per_million": 0.999999888
         }
       }
     },
@@ -12889,8 +12943,8 @@
     "pricing": {
       "text_tokens": {
         "standard": {
-          "input_per_million": 0.1999188,
-          "output_per_million": 0.800064
+          "input_per_million": 0.24999987999999998,
+          "output_per_million": 0.999999888
         }
       }
     },
@@ -13021,8 +13075,8 @@
     "pricing": {
       "text_tokens": {
         "standard": {
-          "input_per_million": 0.19999999999999998,
-          "output_per_million": 0.7999999999999999
+          "input_per_million": 0.24999987999999998,
+          "output_per_million": 0.999999888
         }
       }
     },
@@ -13291,8 +13345,8 @@
     "pricing": {
       "text_tokens": {
         "standard": {
-          "input_per_million": 0.1999188,
-          "output_per_million": 0.800064
+          "input_per_million": 0.24999987999999998,
+          "output_per_million": 0.999999888
         }
       }
     },
@@ -13362,8 +13416,8 @@
     "pricing": {
       "text_tokens": {
         "standard": {
-          "input_per_million": 0.01703012,
-          "output_per_million": 0.0681536
+          "input_per_million": 0.013043472,
+          "output_per_million": 0.0521739072
         }
       }
     },
@@ -13551,8 +13605,8 @@
     "pricing": {
       "text_tokens": {
         "standard": {
-          "input_per_million": 0.025915399999999998,
-          "output_per_million": 0.103712
+          "input_per_million": 0.03260868,
+          "output_per_million": 0.130434768
         }
       }
     },
@@ -13872,8 +13926,8 @@
     "pricing": {
       "text_tokens": {
         "standard": {
-          "input_per_million": 0.075,
-          "output_per_million": 0.15
+          "input_per_million": 0.27,
+          "output_per_million": 0.27
         }
       }
     },
@@ -13986,8 +14040,8 @@
     "pricing": {
       "text_tokens": {
         "standard": {
-          "input_per_million": 0.19999999999999998,
-          "output_per_million": 0.7999999999999999
+          "input_per_million": 0.24999987999999998,
+          "output_per_million": 0.999999888
         }
       }
     },
@@ -14384,7 +14438,7 @@
       }
     },
     "metadata": {
-      "description": "Gemini 2.5 Flash Image Preview is a state of the art image generation model with contextual understanding. It is capable of image generation, edits, and multi-turn conversations.",
+      "description": "Gemini 2.5 Flash Image Preview, AKA Nano Banana is a state of the art image generation model with contextual understanding. It is capable of image generation, edits, and multi-turn conversations.",
       "architecture": {
         "modality": "text+image->text+image",
         "input_modalities": [
@@ -15054,8 +15108,8 @@
     "pricing": {
       "text_tokens": {
         "standard": {
-          "input_per_million": 0.01,
-          "output_per_million": 0.0100008
+          "input_per_million": 0.02,
+          "output_per_million": 0.035869561200000004
         }
       }
     },
@@ -15180,8 +15234,8 @@
     "pricing": {
       "text_tokens": {
         "standard": {
-          "input_per_million": 0.0481286,
-          "output_per_million": 0.192608
+          "input_per_million": 0.035326069999999994,
+          "output_per_million": 0.141304332
         }
       }
     },
@@ -15309,8 +15363,8 @@
     "pricing": {
       "text_tokens": {
         "standard": {
-          "input_per_million": 0.0666396,
-          "output_per_million": 0.26668800000000004
+          "input_per_million": 0.06521736,
+          "output_per_million": 0.260869536
         }
       }
     },
@@ -15897,69 +15951,6 @@
       ]
     }
   },
-  {
-    "id": "infermatic/mn-inferor-12b",
-    "name": "Infermatic: Mistral Nemo Inferor 12B",
-    "provider": "openrouter",
-    "family": "infermatic",
-    "created_at": "2024-11-13 03:20:28 +0100",
-    "context_window": 8192,
-    "max_output_tokens": 8192,
-    "knowledge_cutoff": null,
-    "modalities": {
-      "input": [
-        "text"
-      ],
-      "output": [
-        "text"
-      ]
-    },
-    "capabilities": [
-      "streaming",
-      "predicted_outputs"
-    ],
-    "pricing": {
-      "text_tokens": {
-        "standard": {
-          "input_per_million": 0.6,
-          "output_per_million": 1.0
-        }
-      }
-    },
-    "metadata": {
-      "description": "Inferor 12B is a merge of top roleplay models, expert on immersive narratives and storytelling.\n\nThis model was merged using the [Model Stock](https://arxiv.org/abs/2403.19522) merge method using [anthracite-org/magnum-v4-12b](https://openrouter.ai/anthracite-org/magnum-v4-72b) as a base.\n",
-      "architecture": {
-        "modality": "text->text",
-        "input_modalities": [
-          "text"
-        ],
-        "output_modalities": [
-          "text"
-        ],
-        "tokenizer": "Mistral",
-        "instruct_type": "mistral"
-      },
-      "top_provider": {
-        "context_length": 8192,
-        "max_completion_tokens": 8192,
-        "is_moderated": false
-      },
-      "per_request_limits": null,
-      "supported_parameters": [
-        "frequency_penalty",
-        "logit_bias",
-        "max_tokens",
-        "min_p",
-        "presence_penalty",
-        "repetition_penalty",
-        "seed",
-        "stop",
-        "temperature",
-        "top_k",
-        "top_p"
-      ]
-    }
-  },
   {
     "id": "inflection/inflection-3-pi",
     "name": "Inflection: Inflection 3 Pi",
@@ -16263,13 +16254,13 @@
     }
   },
   {
-    "id": "meta-llama/llama-3-70b-instruct",
-    "name": "Meta: Llama 3 70B Instruct",
+    "id": "meituan/longcat-flash-chat",
+    "name": "Meituan: LongCat Flash Chat",
     "provider": "openrouter",
-    "family": "meta-llama",
-    "created_at": "2024-04-18 02:00:00 +0200",
-    "context_window": 8192,
-    "max_output_tokens": 16384,
+    "family": "meituan",
+    "created_at": "2025-09-09 16:20:58 +0200",
+    "context_window": 131072,
+    "max_output_tokens": 131072,
     "knowledge_cutoff": null,
     "modalities": {
       "input": [
@@ -16282,19 +16273,18 @@
     "capabilities": [
       "streaming",
       "function_calling",
-      "structured_output",
       "predicted_outputs"
     ],
     "pricing": {
       "text_tokens": {
         "standard": {
-          "input_per_million": 0.3,
-          "output_per_million": 0.39999999999999997
+          "input_per_million": 0.15,
+          "output_per_million": 0.75
         }
       }
     },
     "metadata": {
-      "description": "Meta's latest class of model (Llama 3) launched with a variety of sizes & flavors. This 70B instruct-tuned version was optimized for high quality dialogue usecases.\n\nIt has demonstrated strong performance compared to leading closed-source models in human evaluations.\n\nTo read more about the model release, [click here](https://ai.meta.com/blog/meta-llama-3/). Usage of this model is subject to [Meta's Acceptable Use Policy](https://llama.meta.com/llama3/use-policy/).",
+      "description": "LongCat-Flash-Chat is a large-scale Mixture-of-Experts (MoE) model with 560B total parameters, of which 18.6B–31.3B (≈27B on average) are dynamically activated per input. It introduces a shortcut-connected MoE design to reduce communication overhead and achieve high throughput while maintaining training stability through advanced scaling strategies such as hyperparameter transfer, deterministic computation, and multi-stage optimization.\n\nThis release, LongCat-Flash-Chat, is a non-thinking foundation model optimized for conversational and agentic tasks. It supports long context windows up to 128K tokens and shows competitive performance across reasoning, coding, instruction following, and domain benchmarks, with particular strengths in tool use and complex multi-step interactions.",
       "architecture": {
         "modality": "text->text",
         "input_modalities": [
@@ -16303,12 +16293,12 @@
         "output_modalities": [
           "text"
         ],
-        "tokenizer": "Llama3",
-        "instruct_type": "llama3"
+        "tokenizer": "Other",
+        "instruct_type": null
       },
       "top_provider": {
-        "context_length": 8192,
-        "max_completion_tokens": 16384,
+        "context_length": 131072,
+        "max_completion_tokens": 131072,
         "is_moderated": false
       },
       "per_request_limits": null,
@@ -16320,7 +16310,6 @@
         "min_p",
         "presence_penalty",
         "repetition_penalty",
-        "response_format",
         "seed",
         "stop",
         "temperature",
@@ -16333,8 +16322,8 @@
     }
   },
   {
-    "id": "meta-llama/llama-3-8b-instruct",
-    "name": "Meta: Llama 3 8B Instruct",
+    "id": "meta-llama/llama-3-70b-instruct",
+    "name": "Meta: Llama 3 70B Instruct",
     "provider": "openrouter",
     "family": "meta-llama",
     "created_at": "2024-04-18 02:00:00 +0200",
@@ -16358,13 +16347,13 @@
     "pricing": {
       "text_tokens": {
         "standard": {
-          "input_per_million": 0.03,
-          "output_per_million": 0.06
+          "input_per_million": 0.3,
+          "output_per_million": 0.39999999999999997
         }
       }
     },
     "metadata": {
-      "description": "Meta's latest class of model (Llama 3) launched with a variety of sizes & flavors. This 8B instruct-tuned version was optimized for high quality dialogue usecases.\n\nIt has demonstrated strong performance compared to leading closed-source models in human evaluations.\n\nTo read more about the model release, [click here](https://ai.meta.com/blog/meta-llama-3/). Usage of this model is subject to [Meta's Acceptable Use Policy](https://llama.meta.com/llama3/use-policy/).",
+      "description": "Meta's latest class of model (Llama 3) launched with a variety of sizes & flavors. This 70B instruct-tuned version was optimized for high quality dialogue usecases.\n\nIt has demonstrated strong performance compared to leading closed-source models in human evaluations.\n\nTo read more about the model release, [click here](https://ai.meta.com/blog/meta-llama-3/). Usage of this model is subject to [Meta's Acceptable Use Policy](https://llama.meta.com/llama3/use-policy/).",
       "architecture": {
         "modality": "text->text",
         "input_modalities": [
@@ -16385,6 +16374,7 @@
       "supported_parameters": [
         "frequency_penalty",
         "logit_bias",
+        "logprobs",
         "max_tokens",
         "min_p",
         "presence_penalty",
@@ -16396,18 +16386,19 @@
         "tool_choice",
         "tools",
         "top_k",
+        "top_logprobs",
         "top_p"
       ]
     }
   },
   {
-    "id": "meta-llama/llama-3.1-405b",
-    "name": "Meta: Llama 3.1 405B (base)",
+    "id": "meta-llama/llama-3-8b-instruct",
+    "name": "Meta: Llama 3 8B Instruct",
     "provider": "openrouter",
     "family": "meta-llama",
-    "created_at": "2024-08-02 02:00:00 +0200",
-    "context_window": 32768,
-    "max_output_tokens": null,
+    "created_at": "2024-04-18 02:00:00 +0200",
+    "context_window": 8192,
+    "max_output_tokens": 16384,
     "knowledge_cutoff": null,
     "modalities": {
       "input": [
@@ -16419,18 +16410,20 @@
     },
     "capabilities": [
       "streaming",
+      "function_calling",
+      "structured_output",
       "predicted_outputs"
     ],
     "pricing": {
       "text_tokens": {
         "standard": {
-          "input_per_million": 2.0,
-          "output_per_million": 2.0
+          "input_per_million": 0.03,
+          "output_per_million": 0.06
         }
       }
     },
     "metadata": {
-      "description": "Meta's latest class of model (Llama 3.1) launched with a variety of sizes & flavors. This is the base 405B pre-trained version.\n\nIt has demonstrated strong performance compared to leading closed-source models in human evaluations.\n\nTo read more about the model release, [click here](https://ai.meta.com/blog/meta-llama-3/). Usage of this model is subject to [Meta's Acceptable Use Policy](https://llama.meta.com/llama3/use-policy/).",
+      "description": "Meta's latest class of model (Llama 3) launched with a variety of sizes & flavors. This 8B instruct-tuned version was optimized for high quality dialogue usecases.\n\nIt has demonstrated strong performance compared to leading closed-source models in human evaluations.\n\nTo read more about the model release, [click here](https://ai.meta.com/blog/meta-llama-3/). Usage of this model is subject to [Meta's Acceptable Use Policy](https://llama.meta.com/llama3/use-policy/).",
       "architecture": {
         "modality": "text->text",
         "input_modalities": [
@@ -16440,18 +16433,84 @@
           "text"
         ],
         "tokenizer": "Llama3",
-        "instruct_type": "none"
+        "instruct_type": "llama3"
       },
       "top_provider": {
-        "context_length": 32768,
-        "max_completion_tokens": null,
+        "context_length": 8192,
+        "max_completion_tokens": 16384,
         "is_moderated": false
       },
       "per_request_limits": null,
       "supported_parameters": [
         "frequency_penalty",
         "logit_bias",
-        "logprobs",
+        "max_tokens",
+        "min_p",
+        "presence_penalty",
+        "repetition_penalty",
+        "response_format",
+        "seed",
+        "stop",
+        "temperature",
+        "tool_choice",
+        "tools",
+        "top_k",
+        "top_p"
+      ]
+    }
+  },
+  {
+    "id": "meta-llama/llama-3.1-405b",
+    "name": "Meta: Llama 3.1 405B (base)",
+    "provider": "openrouter",
+    "family": "meta-llama",
+    "created_at": "2024-08-02 02:00:00 +0200",
+    "context_window": 32768,
+    "max_output_tokens": null,
+    "knowledge_cutoff": null,
+    "modalities": {
+      "input": [
+        "text"
+      ],
+      "output": [
+        "text"
+      ]
+    },
+    "capabilities": [
+      "streaming",
+      "predicted_outputs"
+    ],
+    "pricing": {
+      "text_tokens": {
+        "standard": {
+          "input_per_million": 2.0,
+          "output_per_million": 2.0
+        }
+      }
+    },
+    "metadata": {
+      "description": "Meta's latest class of model (Llama 3.1) launched with a variety of sizes & flavors. This is the base 405B pre-trained version.\n\nIt has demonstrated strong performance compared to leading closed-source models in human evaluations.\n\nTo read more about the model release, [click here](https://ai.meta.com/blog/meta-llama-3/). Usage of this model is subject to [Meta's Acceptable Use Policy](https://llama.meta.com/llama3/use-policy/).",
+      "architecture": {
+        "modality": "text->text",
+        "input_modalities": [
+          "text"
+        ],
+        "output_modalities": [
+          "text"
+        ],
+        "tokenizer": "Llama3",
+        "instruct_type": "none"
+      },
+      "top_provider": {
+        "context_length": 32768,
+        "max_completion_tokens": null,
+        "is_moderated": false
+      },
+      "per_request_limits": null,
+      "supported_parameters": [
+        "frequency_penalty",
+        "logit_bias",
+        "logprobs",
         "max_tokens",
         "min_p",
         "presence_penalty",
@@ -17719,8 +17778,8 @@
     "pricing": {
       "text_tokens": {
         "standard": {
-          "input_per_million": 0.1999188,
-          "output_per_million": 0.800064
+          "input_per_million": 0.24999987999999998,
+          "output_per_million": 0.999999888
         }
       }
     },
@@ -18012,8 +18071,7 @@
     },
     "capabilities": [
       "streaming",
-      "structured_output",
-      "predicted_outputs"
+      "structured_output"
     ],
     "pricing": {
       "text_tokens": {
@@ -18044,8 +18102,6 @@
       "per_request_limits": null,
       "supported_parameters": [
         "frequency_penalty",
-        "logit_bias",
-        "logprobs",
         "max_tokens",
         "min_p",
         "presence_penalty",
@@ -18056,7 +18112,6 @@
         "structured_outputs",
         "temperature",
         "top_k",
-        "top_logprobs",
         "top_p"
       ]
     }
@@ -18666,8 +18721,8 @@
     "pricing": {
       "text_tokens": {
         "standard": {
-          "input_per_million": 0.01999188,
-          "output_per_million": 0.0800064
+          "input_per_million": 0.035869548,
+          "output_per_million": 0.14347824480000002
         }
       }
     },
@@ -19706,8 +19761,8 @@
     "pricing": {
       "text_tokens": {
         "standard": {
-          "input_per_million": 0.01,
-          "output_per_million": 0.0400032
+          "input_per_million": 0.017934774,
+          "output_per_million": 0.07173912240000001
         }
       }
     },
@@ -19963,8 +20018,8 @@
     "pricing": {
       "text_tokens": {
         "standard": {
-          "input_per_million": 0.01999188,
-          "output_per_million": 0.0800064
+          "input_per_million": 0.03804346,
+          "output_per_million": 0.152173896
         }
       }
     },
@@ -20093,8 +20148,8 @@
     "pricing": {
       "text_tokens": {
         "standard": {
-          "input_per_million": 0.01999188,
-          "output_per_million": 0.0800064
+          "input_per_million": 0.03804346,
+          "output_per_million": 0.152173896
         }
       }
     },
@@ -20899,8 +20954,8 @@
     "pricing": {
       "text_tokens": {
         "standard": {
-          "input_per_million": 0.2962,
-          "output_per_million": 1.1852999999999998
+          "input_per_million": 0.38043459999999996,
+          "output_per_million": 1.52173896
         }
       }
     },
@@ -21030,8 +21085,8 @@
     "pricing": {
       "text_tokens": {
         "standard": {
-          "input_per_million": 0.02498985,
-          "output_per_million": 0.100008
+          "input_per_million": 0.062499969999999995,
+          "output_per_million": 0.249999972
         }
       }
     },
@@ -21521,8 +21576,8 @@
     "pricing": {
       "text_tokens": {
         "standard": {
-          "input_per_million": 0.09329544,
-          "output_per_million": 0.3733632
+          "input_per_million": 0.127173852,
+          "output_per_million": 0.5086955952000001
         }
       }
     },
@@ -21639,7 +21694,7 @@
     "family": "nousresearch",
     "created_at": "2024-08-16 02:00:00 +0200",
     "context_window": 131072,
-    "max_output_tokens": 16384,
+    "max_output_tokens": 131072,
     "knowledge_cutoff": null,
     "modalities": {
       "input": [
@@ -21657,7 +21712,7 @@
     "pricing": {
       "text_tokens": {
         "standard": {
-          "input_per_million": 0.7,
+          "input_per_million": 0.7999999999999999,
           "output_per_million": 0.7999999999999999
         }
       }
@@ -21677,7 +21732,7 @@
       },
       "top_provider": {
         "context_length": 131072,
-        "max_completion_tokens": 16384,
+        "max_completion_tokens": 131072,
         "is_moderated": false
       },
       "per_request_limits": null,
@@ -21725,8 +21780,8 @@
     "pricing": {
       "text_tokens": {
         "standard": {
-          "input_per_million": 0.09999999999999999,
-          "output_per_million": 0.28
+          "input_per_million": 0.12,
+          "output_per_million": 0.3
         }
       }
     },
@@ -21795,8 +21850,8 @@
     "pricing": {
       "text_tokens": {
         "standard": {
-          "input_per_million": 0.1999188,
-          "output_per_million": 0.800064
+          "input_per_million": 0.24999987999999998,
+          "output_per_million": 0.999999888
         }
       }
     },
@@ -21865,8 +21920,8 @@
     "pricing": {
       "text_tokens": {
         "standard": {
-          "input_per_million": 0.09329544,
-          "output_per_million": 0.3733632
+          "input_per_million": 0.127173852,
+          "output_per_million": 0.5086955952000001
         }
       }
     },
@@ -22102,11 +22157,11 @@
     }
   },
   {
-    "id": "nvidia/llama-3.3-nemotron-super-49b-v1",
-    "name": "NVIDIA: Llama 3.3 Nemotron Super 49B v1",
+    "id": "nvidia/nemotron-nano-9b-v2",
+    "name": "NVIDIA: Nemotron Nano 9B V2",
     "provider": "openrouter",
     "family": "nvidia",
-    "created_at": "2025-04-08 15:38:14 +0200",
+    "created_at": "2025-09-05 23:13:27 +0200",
     "context_window": 131072,
     "max_output_tokens": null,
     "knowledge_cutoff": null,
@@ -22120,18 +22175,19 @@
     },
     "capabilities": [
       "streaming",
-      "predicted_outputs"
+      "function_calling",
+      "structured_output"
     ],
     "pricing": {
       "text_tokens": {
         "standard": {
-          "input_per_million": 0.13,
-          "output_per_million": 0.39999999999999997
+          "input_per_million": 0.04,
+          "output_per_million": 0.16
         }
       }
     },
     "metadata": {
-      "description": "Llama-3.3-Nemotron-Super-49B-v1 is a large language model (LLM) optimized for advanced reasoning, conversational interactions, retrieval-augmented generation (RAG), and tool-calling tasks. Derived from Meta's Llama-3.3-70B-Instruct, it employs a Neural Architecture Search (NAS) approach, significantly enhancing efficiency and reducing memory requirements. This allows the model to support a context length of up to 128K tokens and fit efficiently on single high-performance GPUs, such as NVIDIA H200.\n\nNote: you must include `detailed thinking on` in the system prompt to enable reasoning. Please see [Usage Recommendations](https://huggingface.co/nvidia/Llama-3_1-Nemotron-Ultra-253B-v1#quick-start-and-usage-recommendations) for more.",
+      "description": "NVIDIA-Nemotron-Nano-9B-v2 is a large language model (LLM) trained from scratch by NVIDIA, and designed as a unified model for both reasoning and non-reasoning tasks. It responds to user queries and tasks by first generating a reasoning trace and then concluding with a final response. \n\nThe model's reasoning capabilities can be controlled via a system prompt. If the user prefers the model to provide its final answer without intermediate reasoning traces, it can be configured to do so.",
       "architecture": {
         "modality": "text->text",
         "input_modalities": [
@@ -22151,22 +22207,26 @@
       "per_request_limits": null,
       "supported_parameters": [
         "frequency_penalty",
-        "logit_bias",
-        "logprobs",
+        "include_reasoning",
         "max_tokens",
+        "min_p",
         "presence_penalty",
+        "reasoning",
+        "repetition_penalty",
+        "response_format",
         "seed",
         "stop",
         "temperature",
+        "tool_choice",
+        "tools",
         "top_k",
-        "top_logprobs",
         "top_p"
       ]
     }
   },
   {
-    "id": "nvidia/nemotron-nano-9b-v2",
-    "name": "NVIDIA: Nemotron Nano 9B V2",
+    "id": "nvidia/nemotron-nano-9b-v2:free",
+    "name": "NVIDIA: Nemotron Nano 9B V2 (free)",
     "provider": "openrouter",
     "family": "nvidia",
     "created_at": "2025-09-05 23:13:27 +0200",
@@ -24674,7 +24734,8 @@
     "knowledge_cutoff": null,
     "modalities": {
       "input": [
-        "text"
+        "text",
+        "file"
       ],
       "output": [
         "text"
@@ -24699,7 +24760,8 @@
       "architecture": {
         "modality": "text->text",
         "input_modalities": [
-          "text"
+          "text",
+          "file"
         ],
         "output_modalities": [
           "text"
@@ -24734,7 +24796,8 @@
     "knowledge_cutoff": null,
     "modalities": {
       "input": [
-        "text"
+        "text",
+        "file"
       ],
       "output": [
         "text"
@@ -24759,12 +24822,13 @@
       "architecture": {
         "modality": "text->text",
         "input_modalities": [
-          "text"
+          "text",
+          "file"
         ],
         "output_modalities": [
           "text"
         ],
-        "tokenizer": "Other",
+        "tokenizer": "GPT",
         "instruct_type": null
       },
       "top_provider": {
@@ -25493,69 +25557,6 @@
       ]
     }
   },
-  {
-    "id": "pygmalionai/mythalion-13b",
-    "name": "Pygmalion: Mythalion 13B",
-    "provider": "openrouter",
-    "family": "pygmalionai",
-    "created_at": "2023-09-02 02:00:00 +0200",
-    "context_window": 4096,
-    "max_output_tokens": 4096,
-    "knowledge_cutoff": null,
-    "modalities": {
-      "input": [
-        "text"
-      ],
-      "output": [
-        "text"
-      ]
-    },
-    "capabilities": [
-      "streaming",
-      "predicted_outputs"
-    ],
-    "pricing": {
-      "text_tokens": {
-        "standard": {
-          "input_per_million": 0.7,
-          "output_per_million": 1.1
-        }
-      }
-    },
-    "metadata": {
-      "description": "A blend of the new Pygmalion-13b and MythoMax. #merge",
-      "architecture": {
-        "modality": "text->text",
-        "input_modalities": [
-          "text"
-        ],
-        "output_modalities": [
-          "text"
-        ],
-        "tokenizer": "Llama2",
-        "instruct_type": "alpaca"
-      },
-      "top_provider": {
-        "context_length": 4096,
-        "max_completion_tokens": 4096,
-        "is_moderated": false
-      },
-      "per_request_limits": null,
-      "supported_parameters": [
-        "frequency_penalty",
-        "logit_bias",
-        "max_tokens",
-        "min_p",
-        "presence_penalty",
-        "repetition_penalty",
-        "seed",
-        "stop",
-        "temperature",
-        "top_k",
-        "top_p"
-      ]
-    }
-  },
   {
     "id": "qwen/qwen-2.5-72b-instruct",
     "name": "Qwen2.5 72B Instruct",
@@ -25582,8 +25583,8 @@
     "pricing": {
       "text_tokens": {
         "standard": {
-          "input_per_million": 0.051830799999999996,
-          "output_per_million": 0.207424
+          "input_per_million": 0.06521736,
+          "output_per_million": 0.260869536
         }
       }
     },
@@ -25757,7 +25758,7 @@
     "family": "qwen",
     "created_at": "2024-11-12 00:40:00 +0100",
     "context_window": 32768,
-    "max_output_tokens": null,
+    "max_output_tokens": 16384,
     "knowledge_cutoff": null,
     "modalities": {
       "input": [
@@ -25775,8 +25776,8 @@
     "pricing": {
       "text_tokens": {
         "standard": {
-          "input_per_million": 0.0499797,
-          "output_per_million": 0.200016
+          "input_per_million": 0.06,
+          "output_per_million": 0.15
         }
       }
     },
@@ -25795,7 +25796,7 @@
       },
       "top_provider": {
         "context_length": 32768,
-        "max_completion_tokens": null,
+        "max_completion_tokens": 16384,
         "is_moderated": false
       },
       "per_request_limits": null,
@@ -26069,6 +26070,132 @@
       ]
     }
   },
+  {
+    "id": "qwen/qwen-plus-2025-07-28",
+    "name": "Qwen: Qwen Plus 0728",
+    "provider": "openrouter",
+    "family": "qwen",
+    "created_at": "2025-09-08 18:06:39 +0200",
+    "context_window": 1000000,
+    "max_output_tokens": 32768,
+    "knowledge_cutoff": null,
+    "modalities": {
+      "input": [
+        "text"
+      ],
+      "output": [
+        "text"
+      ]
+    },
+    "capabilities": [
+      "streaming",
+      "function_calling",
+      "structured_output"
+    ],
+    "pricing": {
+      "text_tokens": {
+        "standard": {
+          "input_per_million": 0.39999999999999997,
+          "output_per_million": 1.2
+        }
+      }
+    },
+    "metadata": {
+      "description": "Qwen Plus 0728, based on the Qwen3 foundation model, is a 1 million context hybrid reasoning model with a balanced performance, speed, and cost combination.",
+      "architecture": {
+        "modality": "text->text",
+        "input_modalities": [
+          "text"
+        ],
+        "output_modalities": [
+          "text"
+        ],
+        "tokenizer": "Qwen3",
+        "instruct_type": null
+      },
+      "top_provider": {
+        "context_length": 1000000,
+        "max_completion_tokens": 32768,
+        "is_moderated": false
+      },
+      "per_request_limits": null,
+      "supported_parameters": [
+        "max_tokens",
+        "presence_penalty",
+        "response_format",
+        "seed",
+        "structured_outputs",
+        "temperature",
+        "tool_choice",
+        "tools",
+        "top_p"
+      ]
+    }
+  },
+  {
+    "id": "qwen/qwen-plus-2025-07-28:thinking",
+    "name": "Qwen: Qwen Plus 0728 (thinking)",
+    "provider": "openrouter",
+    "family": "qwen",
+    "created_at": "2025-09-08 18:06:39 +0200",
+    "context_window": 1000000,
+    "max_output_tokens": 32768,
+    "knowledge_cutoff": null,
+    "modalities": {
+      "input": [
+        "text"
+      ],
+      "output": [
+        "text"
+      ]
+    },
+    "capabilities": [
+      "streaming",
+      "function_calling",
+      "structured_output"
+    ],
+    "pricing": {
+      "text_tokens": {
+        "standard": {
+          "input_per_million": 0.39999999999999997,
+          "output_per_million": 4.0
+        }
+      }
+    },
+    "metadata": {
+      "description": "Qwen Plus 0728, based on the Qwen3 foundation model, is a 1 million context hybrid reasoning model with a balanced performance, speed, and cost combination.",
+      "architecture": {
+        "modality": "text->text",
+        "input_modalities": [
+          "text"
+        ],
+        "output_modalities": [
+          "text"
+        ],
+        "tokenizer": "Qwen3",
+        "instruct_type": null
+      },
+      "top_provider": {
+        "context_length": 1000000,
+        "max_completion_tokens": 32768,
+        "is_moderated": false
+      },
+      "per_request_limits": null,
+      "supported_parameters": [
+        "include_reasoning",
+        "max_tokens",
+        "presence_penalty",
+        "reasoning",
+        "response_format",
+        "seed",
+        "structured_outputs",
+        "temperature",
+        "tool_choice",
+        "tools",
+        "top_p"
+      ]
+    }
+  },
   {
     "id": "qwen/qwen-turbo",
     "name": "Qwen: Qwen-Turbo",
@@ -26277,8 +26404,8 @@
     "pricing": {
       "text_tokens": {
         "standard": {
-          "input_per_million": 0.01999188,
-          "output_per_million": 0.0800064
+          "input_per_million": 0.035869548,
+          "output_per_million": 0.14347824480000002
         }
       }
     },
@@ -26408,8 +26535,8 @@
     "pricing": {
       "text_tokens": {
         "standard": {
-          "input_per_million": 0.0999594,
-          "output_per_million": 0.400032
+          "input_per_million": 0.24999987999999998,
+          "output_per_million": 0.999999888
         }
       }
     },
@@ -26739,8 +26866,8 @@
     "pricing": {
       "text_tokens": {
         "standard": {
-          "input_per_million": 0.077968332,
-          "output_per_million": 0.31202496
+          "input_per_million": 0.0974999532,
+          "output_per_million": 0.38999995632
         }
       }
     },
@@ -26810,8 +26937,8 @@
     "pricing": {
       "text_tokens": {
         "standard": {
-          "input_per_million": 0.077968332,
-          "output_per_million": 0.31202496
+          "input_per_million": 0.0974999532,
+          "output_per_million": 0.38999995632
         }
       }
     },
@@ -26948,8 +27075,8 @@
     "pricing": {
       "text_tokens": {
         "standard": {
-          "input_per_million": 0.01999188,
-          "output_per_million": 0.0800064
+          "input_per_million": 0.035869548,
+          "output_per_million": 0.14347824480000002
         }
       }
     },
@@ -27021,8 +27148,8 @@
     "pricing": {
       "text_tokens": {
         "standard": {
-          "input_per_million": 0.051830799999999996,
-          "output_per_million": 0.207424
+          "input_per_million": 0.07065213999999999,
+          "output_per_million": 0.282608664
         }
       }
     },
@@ -27091,8 +27218,8 @@
     "pricing": {
       "text_tokens": {
         "standard": {
-          "input_per_million": 0.0713,
-          "output_per_million": 0.2852
+          "input_per_million": 0.08967387,
+          "output_per_million": 0.358695612
         }
       }
     },
@@ -27223,8 +27350,8 @@
     "pricing": {
       "text_tokens": {
         "standard": {
-          "input_per_million": 0.017992691999999998,
-          "output_per_million": 0.07200576
+          "input_per_million": 0.0322825932,
+          "output_per_million": 0.12913042032
         }
       }
     },
@@ -27480,8 +27607,8 @@
     "pricing": {
       "text_tokens": {
         "standard": {
-          "input_per_million": 0.19999999999999998,
-          "output_per_million": 0.7999999999999999
+          "input_per_million": 0.24999987999999998,
+          "output_per_million": 0.999999888
         }
       }
     },
@@ -27551,8 +27678,8 @@
     "pricing": {
       "text_tokens": {
         "standard": {
-          "input_per_million": 0.051830799999999996,
-          "output_per_million": 0.207424
+          "input_per_million": 0.07065213999999999,
+          "output_per_million": 0.282608664
         }
       }
     },
@@ -27718,6 +27845,148 @@
       ]
     }
   },
+  {
+    "id": "qwen/qwen3-next-80b-a3b-instruct",
+    "name": "Qwen: Qwen3 Next 80B A3B Instruct",
+    "provider": "openrouter",
+    "family": "qwen",
+    "created_at": "2025-09-11 19:36:53 +0200",
+    "context_window": 262144,
+    "max_output_tokens": null,
+    "knowledge_cutoff": null,
+    "modalities": {
+      "input": [
+        "text"
+      ],
+      "output": [
+        "text"
+      ]
+    },
+    "capabilities": [
+      "streaming",
+      "function_calling",
+      "structured_output",
+      "predicted_outputs"
+    ],
+    "pricing": {
+      "text_tokens": {
+        "standard": {
+          "input_per_million": 0.09782604,
+          "output_per_million": 0.391304304
+        }
+      }
+    },
+    "metadata": {
+      "description": "Qwen3-Next-80B-A3B-Instruct is an instruction-tuned chat model in the Qwen3-Next series optimized for fast, stable responses without “thinking” traces. It targets complex tasks across reasoning, code generation, knowledge QA, and multilingual use, while remaining robust on alignment and formatting. Compared with prior Qwen3 instruct variants, it focuses on higher throughput and stability on ultra-long inputs and multi-turn dialogues, making it well-suited for RAG, tool use, and agentic workflows that require consistent final answers rather than visible chain-of-thought.\n\nThe model employs scaling-efficient training and decoding to improve parameter efficiency and inference speed, and has been validated on a broad set of public benchmarks where it reaches or approaches larger Qwen3 systems in several categories while outperforming earlier mid-sized baselines. It is best used as a general assistant, code helper, and long-context task solver in production settings where deterministic, instruction-following outputs are preferred.",
+      "architecture": {
+        "modality": "text->text",
+        "input_modalities": [
+          "text"
+        ],
+        "output_modalities": [
+          "text"
+        ],
+        "tokenizer": "Qwen3",
+        "instruct_type": null
+      },
+      "top_provider": {
+        "context_length": 262144,
+        "max_completion_tokens": null,
+        "is_moderated": false
+      },
+      "per_request_limits": null,
+      "supported_parameters": [
+        "frequency_penalty",
+        "logit_bias",
+        "logprobs",
+        "max_tokens",
+        "min_p",
+        "presence_penalty",
+        "repetition_penalty",
+        "response_format",
+        "seed",
+        "stop",
+        "temperature",
+        "tool_choice",
+        "tools",
+        "top_k",
+        "top_logprobs",
+        "top_p"
+      ]
+    }
+  },
+  {
+    "id": "qwen/qwen3-next-80b-a3b-thinking",
+    "name": "Qwen: Qwen3 Next 80B A3B Thinking",
+    "provider": "openrouter",
+    "family": "qwen",
+    "created_at": "2025-09-11 19:38:04 +0200",
+    "context_window": 262144,
+    "max_output_tokens": null,
+    "knowledge_cutoff": null,
+    "modalities": {
+      "input": [
+        "text"
+      ],
+      "output": [
+        "text"
+      ]
+    },
+    "capabilities": [
+      "streaming",
+      "function_calling",
+      "structured_output",
+      "predicted_outputs"
+    ],
+    "pricing": {
+      "text_tokens": {
+        "standard": {
+          "input_per_million": 0.09782604,
+          "output_per_million": 0.391304304
+        }
+      }
+    },
+    "metadata": {
+      "description": "Qwen3-Next-80B-A3B-Thinking is a reasoning-first chat model in the Qwen3-Next line that outputs structured “thinking” traces by default. It’s designed for hard multi-step problems; math proofs, code synthesis/debugging, logic, and agentic planning, and reports strong results across knowledge, reasoning, coding, alignment, and multilingual evaluations. Compared with prior Qwen3 variants, it emphasizes stability under long chains of thought and efficient scaling during inference, and it is tuned to follow complex instructions while reducing repetitive or off-task behavior.\n\nThe model is suitable for agent frameworks and tool use (function calling), retrieval-heavy workflows, and standardized benchmarking where step-by-step solutions are required. It supports long, detailed completions and leverages throughput-oriented techniques (e.g., multi-token prediction) for faster generation. Note that it operates in thinking-only mode.",
+      "architecture": {
+        "modality": "text->text",
+        "input_modalities": [
+          "text"
+        ],
+        "output_modalities": [
+          "text"
+        ],
+        "tokenizer": "Qwen3",
+        "instruct_type": null
+      },
+      "top_provider": {
+        "context_length": 262144,
+        "max_completion_tokens": null,
+        "is_moderated": false
+      },
+      "per_request_limits": null,
+      "supported_parameters": [
+        "frequency_penalty",
+        "include_reasoning",
+        "logit_bias",
+        "logprobs",
+        "max_tokens",
+        "min_p",
+        "presence_penalty",
+        "reasoning",
+        "repetition_penalty",
+        "response_format",
+        "seed",
+        "stop",
+        "temperature",
+        "tool_choice",
+        "tools",
+        "top_k",
+        "top_logprobs",
+        "top_p"
+      ]
+    }
+  },
   {
     "id": "qwen/qwq-32b",
     "name": "Qwen: QwQ 32B",
@@ -28315,8 +28584,8 @@
     "pricing": {
       "text_tokens": {
         "standard": {
-          "input_per_million": 0.01999188,
-          "output_per_million": 0.0800064
+          "input_per_million": 0.035869548,
+          "output_per_million": 0.14347824480000002
         }
       }
     },
@@ -28952,8 +29221,8 @@
     "pricing": {
       "text_tokens": {
         "standard": {
-          "input_per_million": 0.0481286,
-          "output_per_million": 0.192608
+          "input_per_million": 0.039130416,
+          "output_per_million": 0.1565217216
         }
       }
     },
@@ -29217,8 +29486,8 @@
     "pricing": {
       "text_tokens": {
         "standard": {
-          "input_per_million": 0.01999188,
-          "output_per_million": 0.0800064
+          "input_per_million": 0.035869548,
+          "output_per_million": 0.14347824480000002
         }
       }
     },
@@ -29284,8 +29553,8 @@
     "pricing": {
       "text_tokens": {
         "standard": {
-          "input_per_million": 0.1999188,
-          "output_per_million": 0.800064
+          "input_per_million": 0.24999987999999998,
+          "output_per_million": 0.999999888
         }
       }
     },
@@ -30127,8 +30396,8 @@
     "pricing": {
       "text_tokens": {
         "standard": {
-          "input_per_million": 0.32986602,
-          "output_per_million": 1.3201056
+          "input_per_million": 0.41249980199999997,
+          "output_per_million": 1.6499998152000002
         }
       }
     },
@@ -30375,7 +30644,7 @@
     "name": "Sonar",
     "provider": "perplexity",
     "family": "sonar",
-    "created_at": "2025-09-09 20:41:26 +0200",
+    "created_at": "2025-09-14 11:15:24 +0200",
     "context_window": 128000,
     "max_output_tokens": 4096,
     "knowledge_cutoff": null,
@@ -30407,7 +30676,7 @@
     "name": "Sonar Deep Research",
     "provider": "perplexity",
     "family": "sonar_deep_research",
-    "created_at": "2025-09-09 20:41:26 +0200",
+    "created_at": "2025-09-14 11:15:24 +0200",
     "context_window": 128000,
     "max_output_tokens": 4096,
     "knowledge_cutoff": null,
@@ -30442,7 +30711,7 @@
     "name": "Sonar Pro",
     "provider": "perplexity",
     "family": "sonar_pro",
-    "created_at": "2025-09-09 20:41:26 +0200",
+    "created_at": "2025-09-14 11:15:24 +0200",
     "context_window": 200000,
     "max_output_tokens": 8192,
     "knowledge_cutoff": null,
@@ -30474,7 +30743,7 @@
     "name": "Sonar Reasoning",
     "provider": "perplexity",
     "family": "sonar_reasoning",
-    "created_at": "2025-09-09 20:41:26 +0200",
+    "created_at": "2025-09-14 11:15:24 +0200",
     "context_window": 128000,
     "max_output_tokens": 4096,
     "knowledge_cutoff": null,
@@ -30506,7 +30775,7 @@
     "name": "Sonar Reasoning Pro",
     "provider": "perplexity",
     "family": "sonar_reasoning_pro",
-    "created_at": "2025-09-09 20:41:26 +0200",
+    "created_at": "2025-09-14 11:15:24 +0200",
     "context_window": 128000,
     "max_output_tokens": 8192,
     "knowledge_cutoff": null,
@@ -30646,7 +30915,7 @@
     "id": "gemini-1.5-flash",
     "name": "Gemini 1.5 Flash",
     "provider": "vertexai",
-    "family": "gemini-1.5-flash",
+    "family": "models/gemini-1.5-flash",
     "created_at": null,
     "context_window": 1048576,
     "max_output_tokens": 8192,
@@ -30682,7 +30951,7 @@
     "id": "gemini-1.5-flash-002",
     "name": "Gemini 1.5 Flash",
     "provider": "vertexai",
-    "family": "gemini-1.5-flash",
+    "family": "models/gemini-1.5-flash",
     "created_at": null,
     "context_window": 1048576,
     "max_output_tokens": 8192,
@@ -30718,7 +30987,7 @@
     "id": "gemini-1.5-flash-8b",
     "name": "Gemini 1.5 Flash-8B",
     "provider": "vertexai",
-    "family": "gemini-1.5-flash-8b",
+    "family": "models/gemini-1.5-flash-8b",
     "created_at": null,
     "context_window": 1048576,
     "max_output_tokens": 8192,
@@ -30754,7 +31023,7 @@
     "id": "gemini-1.5-pro",
     "name": "Gemini 1.5 Pro",
     "provider": "vertexai",
-    "family": "gemini-1.5-pro",
+    "family": "models/gemini-1.5-pro",
     "created_at": null,
     "context_window": 2097152,
     "max_output_tokens": 8192,
@@ -30790,7 +31059,7 @@
     "id": "gemini-1.5-pro-002",
     "name": "Gemini 1.5 Pro",
     "provider": "vertexai",
-    "family": "gemini-1.5-pro",
+    "family": "models/gemini-1.5-pro",
     "created_at": null,
     "context_window": 2097152,
     "max_output_tokens": 8192,
@@ -30826,7 +31095,7 @@
     "id": "gemini-2.0-flash",
     "name": "Gemini 2.0 Flash",
     "provider": "vertexai",
-    "family": "gemini-2.0-flash",
+    "family": "models/gemini-2.0-flash",
     "created_at": null,
     "context_window": 1048576,
     "max_output_tokens": 8192,
@@ -30867,7 +31136,7 @@
     "id": "gemini-2.0-flash-001",
     "name": "Gemini 2.0 Flash",
     "provider": "vertexai",
-    "family": "gemini-2.0-flash",
+    "family": "models/gemini-2.0-flash",
     "created_at": null,
     "context_window": 1048576,
     "max_output_tokens": 8192,
@@ -30908,7 +31177,7 @@
     "id": "gemini-2.0-flash-exp",
     "name": "Gemini 2.0 Flash",
     "provider": "vertexai",
-    "family": "gemini-2.0-flash",
+    "family": "models/gemini-2.0-flash",
     "created_at": null,
     "context_window": 1048576,
     "max_output_tokens": 8192,
@@ -30949,7 +31218,7 @@
     "id": "gemini-2.0-flash-lite-001",
     "name": "Gemini 2.0 Flash-Lite",
     "provider": "vertexai",
-    "family": "gemini-2.0-flash-lite",
+    "family": "models/gemini-2.0-flash-lite",
     "created_at": null,
     "context_window": 1048576,
     "max_output_tokens": 8192,
@@ -30990,7 +31259,7 @@
     "id": "gemini-2.5-flash",
     "name": "Gemini 2.5 Flash",
     "provider": "vertexai",
-    "family": "gemini-2.5-flash",
+    "family": "models/gemini-2.5-flash",
     "created_at": null,
     "context_window": 1048576,
     "max_output_tokens": 65536,
@@ -31031,7 +31300,7 @@
     "id": "gemini-2.5-flash-lite",
     "name": "Gemini 2.5 Flash-Lite",
     "provider": "vertexai",
-    "family": "gemini-2.5-flash-lite",
+    "family": "models/gemini-2.5-flash-lite",
     "created_at": null,
     "context_window": 1048576,
     "max_output_tokens": 65536,
@@ -31072,7 +31341,7 @@
     "id": "gemini-2.5-pro",
     "name": "Gemini 2.5 Pro",
     "provider": "vertexai",
-    "family": "gemini-2.5-pro",
+    "family": "models/gemini-2.5-pro",
     "created_at": null,
     "context_window": 1048576,
     "max_output_tokens": 65536,