ruby_llm 1.6.0 → 1.6.1

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-haiku-3-5",
+    "family": "claude-3-5-haiku",
     "created_at": null,
     "context_window": 200000,
     "max_output_tokens": 8192,
@@ -35,7 +35,7 @@
     "id": "claude-3-5-sonnet-20240620",
     "name": "Claude Sonnet 3.5",
     "provider": "anthropic",
-    "family": "claude-sonnet-3-5",
+    "family": "claude-3-5-sonnet",
     "created_at": null,
     "context_window": 200000,
     "max_output_tokens": 8192,
@@ -67,7 +67,7 @@
     "id": "claude-3-5-sonnet-20241022",
     "name": "Claude Sonnet 3.5",
     "provider": "anthropic",
-    "family": "claude-sonnet-3-5",
+    "family": "claude-3-5-sonnet",
     "created_at": null,
     "context_window": 200000,
     "max_output_tokens": 8192,
@@ -99,7 +99,7 @@
     "id": "claude-3-7-sonnet-20250219",
     "name": "Claude Sonnet 3.7",
     "provider": "anthropic",
-    "family": "claude-sonnet-3-7",
+    "family": "claude-3-7-sonnet",
     "created_at": null,
     "context_window": 200000,
     "max_output_tokens": 64000,
@@ -131,7 +131,7 @@
     "id": "claude-3-haiku-20240307",
     "name": "Claude Haiku 3",
     "provider": "anthropic",
-    "family": "claude-haiku-3",
+    "family": "claude-3-haiku",
     "created_at": null,
     "context_window": 200000,
     "max_output_tokens": 4096,
@@ -5202,6 +5202,37 @@
       "owned_by": "mistralai"
     }
   },
+  {
+    "id": "mistral-medium-2508",
+    "name": "Mistral Medium",
+    "provider": "mistral",
+    "family": "mistral-medium",
+    "created_at": null,
+    "context_window": 32768,
+    "max_output_tokens": 8192,
+    "knowledge_cutoff": null,
+    "modalities": {
+      "input": [
+        "text"
+      ],
+      "output": [
+        "text"
+      ]
+    },
+    "capabilities": [
+      "streaming",
+      "function_calling",
+      "structured_output",
+      "vision",
+      "batch",
+      "fine_tuning"
+    ],
+    "pricing": {},
+    "metadata": {
+      "object": "model",
+      "owned_by": "mistralai"
+    }
+  },
   {
     "id": "mistral-medium-latest",
     "name": "Mistral Medium",
@@ -6669,31 +6700,29 @@
     "id": "gpt-4",
     "name": "GPT-4",
     "provider": "openai",
-    "family": "gpt-4",
-    "created_at": null,
+    "family": "gpt4",
+    "created_at": "2023-06-27 18:13:31 +0200",
     "context_window": 8192,
     "max_output_tokens": 8192,
     "knowledge_cutoff": null,
     "modalities": {
       "input": [
-        "text"
+        "text",
+        "image",
+        "pdf"
       ],
       "output": [
-        "embeddings",
         "text"
       ]
     },
     "capabilities": [
-      "batch"
+      "streaming",
+      "function_calling"
     ],
     "pricing": {
       "text_tokens": {
         "standard": {
-          "input_per_million": 30.0,
-          "output_per_million": 60.0
-        },
-        "batch": {
-          "input_per_million": 15.0,
+          "input_per_million": 10.0,
           "output_per_million": 30.0
         }
       }
@@ -6738,34 +6767,29 @@
   },
   {
     "id": "gpt-4-0613",
-    "name": "GPT-4",
+    "name": "GPT-4 0613",
     "provider": "openai",
-    "family": "gpt-4",
-    "created_at": null,
-    "context_window": 8192,
-    "max_output_tokens": 8192,
+    "family": "other",
+    "created_at": "2023-06-12 18:54:56 +0200",
+    "context_window": 4096,
+    "max_output_tokens": 16384,
     "knowledge_cutoff": null,
     "modalities": {
       "input": [
         "text"
       ],
       "output": [
-        "embeddings",
         "text"
       ]
     },
     "capabilities": [
-      "batch"
+      "streaming"
     ],
     "pricing": {
       "text_tokens": {
         "standard": {
-          "input_per_million": 30.0,
-          "output_per_million": 60.0
-        },
-        "batch": {
-          "input_per_million": 15.0,
-          "output_per_million": 30.0
+          "input_per_million": 0.5,
+          "output_per_million": 1.5
         }
       }
     },
@@ -6891,21 +6915,25 @@
     "id": "gpt-4-turbo-preview",
     "name": "GPT-4 Turbo Preview",
     "provider": "openai",
-    "family": "gpt-4-turbo-preview",
-    "created_at": null,
+    "family": "gpt4_turbo",
+    "created_at": "2024-01-23 20:22:57 +0100",
     "context_window": 128000,
     "max_output_tokens": 4096,
     "knowledge_cutoff": null,
     "modalities": {
       "input": [
-        "text"
+        "text",
+        "image",
+        "pdf"
       ],
       "output": [
-        "embeddings",
         "text"
       ]
     },
-    "capabilities": [],
+    "capabilities": [
+      "streaming",
+      "function_calling"
+    ],
     "pricing": {
       "text_tokens": {
         "standard": {
@@ -6923,23 +6951,23 @@
     "id": "gpt-4.1",
     "name": "GPT-4.1",
     "provider": "openai",
-    "family": "gpt-4.1",
-    "created_at": null,
+    "family": "gpt41",
+    "created_at": "2025-04-10 22:22:22 +0200",
     "context_window": 1047576,
     "max_output_tokens": 32768,
     "knowledge_cutoff": null,
     "modalities": {
       "input": [
+        "text",
         "image",
-        "text"
+        "pdf"
       ],
       "output": [
-        "embeddings",
         "text"
       ]
     },
     "capabilities": [
-      "batch",
+      "streaming",
       "function_calling",
       "structured_output"
     ],
@@ -6947,12 +6975,8 @@
       "text_tokens": {
         "standard": {
           "input_per_million": 2.0,
-          "cached_input_per_million": 0.5,
-          "output_per_million": 8.0
-        },
-        "batch": {
-          "input_per_million": 1.0,
-          "output_per_million": 4.0
+          "output_per_million": 8.0,
+          "cached_input_per_million": 0.5
         }
       }
     },
@@ -6963,25 +6987,25 @@
   },
   {
     "id": "gpt-4.1-2025-04-14",
-    "name": "GPT-4.1",
+    "name": "GPT-4.1 20250414",
     "provider": "openai",
-    "family": "gpt-4.1",
-    "created_at": null,
+    "family": "gpt41",
+    "created_at": "2025-04-10 22:09:06 +0200",
     "context_window": 1047576,
     "max_output_tokens": 32768,
     "knowledge_cutoff": null,
     "modalities": {
       "input": [
+        "text",
         "image",
-        "text"
+        "pdf"
       ],
       "output": [
-        "embeddings",
         "text"
       ]
     },
     "capabilities": [
-      "batch",
+      "streaming",
       "function_calling",
       "structured_output"
     ],
@@ -6989,12 +7013,8 @@
       "text_tokens": {
         "standard": {
           "input_per_million": 2.0,
-          "cached_input_per_million": 0.5,
-          "output_per_million": 8.0
-        },
-        "batch": {
-          "input_per_million": 1.0,
-          "output_per_million": 4.0
+          "output_per_million": 8.0,
+          "cached_input_per_million": 0.5
         }
       }
     },
@@ -8244,8 +8264,8 @@
     "provider": "openai",
     "family": "gpt-5-chat-latest",
     "created_at": null,
-    "context_window": 400000,
-    "max_output_tokens": 128000,
+    "context_window": 128000,
+    "max_output_tokens": 16384,
     "knowledge_cutoff": null,
     "modalities": {
       "input": [
@@ -8257,7 +8277,9 @@
         "text"
       ]
     },
-    "capabilities": [],
+    "capabilities": [
+      "structured_output"
+    ],
     "pricing": {
       "text_tokens": {
         "standard": {
@@ -8274,38 +8296,30 @@
   },
   {
     "id": "gpt-5-mini",
-    "name": "GPT-5 mini",
+    "name": "GPT-5 Mini",
     "provider": "openai",
-    "family": "gpt-5-mini",
-    "created_at": null,
-    "context_window": 400000,
-    "max_output_tokens": 128000,
+    "family": "other",
+    "created_at": "2025-08-05 22:32:08 +0200",
+    "context_window": 4096,
+    "max_output_tokens": 16384,
     "knowledge_cutoff": null,
     "modalities": {
       "input": [
-        "image",
         "text"
       ],
       "output": [
-        "embeddings",
         "text"
       ]
     },
     "capabilities": [
-      "batch",
-      "function_calling",
-      "structured_output"
+      "streaming",
+      "reasoning"
     ],
     "pricing": {
       "text_tokens": {
         "standard": {
-          "input_per_million": 0.25,
-          "cached_input_per_million": 0.025,
-          "output_per_million": 2.0
-        },
-        "batch": {
-          "input_per_million": 0.125,
-          "output_per_million": 1.0
+          "input_per_million": 0.5,
+          "output_per_million": 1.5
         }
       }
     },
@@ -8316,38 +8330,30 @@
   },
   {
     "id": "gpt-5-mini-2025-08-07",
-    "name": "GPT-5 mini",
+    "name": "GPT-5 Mini 20250807",
     "provider": "openai",
-    "family": "gpt-5-mini",
-    "created_at": null,
-    "context_window": 400000,
-    "max_output_tokens": 128000,
+    "family": "other",
+    "created_at": "2025-08-05 22:31:07 +0200",
+    "context_window": 4096,
+    "max_output_tokens": 16384,
     "knowledge_cutoff": null,
     "modalities": {
       "input": [
-        "image",
         "text"
       ],
       "output": [
-        "embeddings",
         "text"
       ]
     },
     "capabilities": [
-      "batch",
-      "function_calling",
-      "structured_output"
+      "streaming",
+      "reasoning"
     ],
     "pricing": {
       "text_tokens": {
         "standard": {
-          "input_per_million": 0.25,
-          "cached_input_per_million": 0.025,
-          "output_per_million": 2.0
-        },
-        "batch": {
-          "input_per_million": 0.125,
-          "output_per_million": 1.0
+          "input_per_million": 0.5,
+          "output_per_million": 1.5
         }
       }
     },
@@ -8358,38 +8364,30 @@
   },
   {
     "id": "gpt-5-nano",
-    "name": "GPT-5 nano",
+    "name": "GPT-5 Nano",
     "provider": "openai",
-    "family": "gpt-5-nano",
-    "created_at": null,
-    "context_window": 400000,
-    "max_output_tokens": 128000,
+    "family": "other",
+    "created_at": "2025-08-05 22:39:44 +0200",
+    "context_window": 4096,
+    "max_output_tokens": 16384,
     "knowledge_cutoff": null,
     "modalities": {
       "input": [
-        "image",
         "text"
       ],
       "output": [
-        "embeddings",
         "text"
       ]
     },
     "capabilities": [
-      "batch",
-      "function_calling",
-      "structured_output"
+      "streaming",
+      "reasoning"
     ],
     "pricing": {
       "text_tokens": {
         "standard": {
-          "input_per_million": 0.05,
-          "cached_input_per_million": 0.005,
-          "output_per_million": 0.4
-        },
-        "batch": {
-          "input_per_million": 0.025,
-          "output_per_million": 0.2
+          "input_per_million": 0.5,
+          "output_per_million": 1.5
         }
       }
     },
@@ -8400,38 +8398,30 @@
   },
   {
     "id": "gpt-5-nano-2025-08-07",
-    "name": "GPT-5 nano",
+    "name": "GPT-5 Nano 20250807",
     "provider": "openai",
-    "family": "gpt-5-nano",
-    "created_at": null,
-    "context_window": 400000,
-    "max_output_tokens": 128000,
+    "family": "other",
+    "created_at": "2025-08-05 22:38:23 +0200",
+    "context_window": 4096,
+    "max_output_tokens": 16384,
     "knowledge_cutoff": null,
     "modalities": {
       "input": [
-        "image",
         "text"
       ],
       "output": [
-        "embeddings",
         "text"
       ]
     },
     "capabilities": [
-      "batch",
-      "function_calling",
-      "structured_output"
+      "streaming",
+      "reasoning"
     ],
     "pricing": {
       "text_tokens": {
         "standard": {
-          "input_per_million": 0.05,
-          "cached_input_per_million": 0.005,
-          "output_per_million": 0.4
-        },
-        "batch": {
-          "input_per_million": 0.025,
-          "output_per_million": 0.2
+          "input_per_million": 0.5,
+          "output_per_million": 1.5
         }
       }
     },
@@ -8500,66 +8490,36 @@
     "pricing": {},
     "metadata": {}
   },
-  {
-    "id": "gpt-oss-20b",
-    "name": "gpt-oss-20b",
-    "provider": "openai",
-    "family": "gpt-oss-20b",
-    "created_at": null,
-    "context_window": 131072,
-    "max_output_tokens": 131072,
-    "knowledge_cutoff": null,
-    "modalities": {
-      "input": [
-        "text"
-      ],
-      "output": [
-        "embeddings",
-        "text"
-      ]
-    },
-    "capabilities": [
-      "batch",
-      "function_calling",
-      "structured_output"
-    ],
-    "pricing": {},
-    "metadata": {}
-  },
   {
     "id": "o1",
-    "name": "o1",
+    "name": "O1",
     "provider": "openai",
     "family": "o1",
-    "created_at": null,
+    "created_at": "2024-12-16 20:03:36 +0100",
     "context_window": 200000,
     "max_output_tokens": 100000,
     "knowledge_cutoff": null,
     "modalities": {
       "input": [
+        "text",
         "image",
-        "text"
+        "pdf"
       ],
       "output": [
-        "embeddings",
         "text"
       ]
     },
     "capabilities": [
-      "batch",
+      "streaming",
       "function_calling",
-      "structured_output"
+      "structured_output",
+      "reasoning"
     ],
     "pricing": {
       "text_tokens": {
         "standard": {
           "input_per_million": 15.0,
-          "cached_input_per_million": 7.5,
           "output_per_million": 60.0
-        },
-        "batch": {
-          "input_per_million": 7.5,
-          "output_per_million": 30.0
         }
       }
     },
@@ -8570,38 +8530,34 @@
   },
   {
     "id": "o1-2024-12-17",
-    "name": "o1",
+    "name": "O1-20241217",
     "provider": "openai",
     "family": "o1",
-    "created_at": null,
+    "created_at": "2024-12-16 06:29:36 +0100",
     "context_window": 200000,
     "max_output_tokens": 100000,
     "knowledge_cutoff": null,
     "modalities": {
       "input": [
+        "text",
         "image",
-        "text"
+        "pdf"
       ],
       "output": [
-        "embeddings",
         "text"
       ]
     },
     "capabilities": [
-      "batch",
+      "streaming",
       "function_calling",
-      "structured_output"
+      "structured_output",
+      "reasoning"
     ],
     "pricing": {
       "text_tokens": {
         "standard": {
           "input_per_million": 15.0,
-          "cached_input_per_million": 7.5,
           "output_per_million": 60.0
-        },
-        "batch": {
-          "input_per_million": 7.5,
-          "output_per_million": 30.0
         }
       }
     },
@@ -8677,16 +8633,17 @@
     }
   },
   {
-    "id": "o1-preview",
-    "name": "o1 Preview",
+    "id": "o1-pro",
+    "name": "o1-pro",
     "provider": "openai",
-    "family": "o1-preview",
+    "family": "o1-pro",
     "created_at": null,
-    "context_window": 128000,
-    "max_output_tokens": 32768,
+    "context_window": 200000,
+    "max_output_tokens": 100000,
     "knowledge_cutoff": null,
     "modalities": {
       "input": [
+        "image",
         "text"
       ],
       "output": [
@@ -8695,74 +8652,7 @@
       ]
     },
     "capabilities": [
-      "function_calling",
-      "structured_output"
-    ],
-    "pricing": {
-      "text_tokens": {
-        "standard": {
-          "input_per_million": 15.0,
-          "cached_input_per_million": 7.5,
-          "output_per_million": 60.0
-        }
-      }
-    },
-    "metadata": {}
-  },
-  {
-    "id": "o1-preview-2024-09-12",
-    "name": "o1 Preview",
-    "provider": "openai",
-    "family": "o1-preview",
-    "created_at": null,
-    "context_window": 128000,
-    "max_output_tokens": 32768,
-    "knowledge_cutoff": null,
-    "modalities": {
-      "input": [
-        "text"
-      ],
-      "output": [
-        "embeddings",
-        "text"
-      ]
-    },
-    "capabilities": [
-      "function_calling",
-      "structured_output"
-    ],
-    "pricing": {
-      "text_tokens": {
-        "standard": {
-          "input_per_million": 15.0,
-          "cached_input_per_million": 7.5,
-          "output_per_million": 60.0
-        }
-      }
-    },
-    "metadata": {}
-  },
-  {
-    "id": "o1-pro",
-    "name": "o1-pro",
-    "provider": "openai",
-    "family": "o1-pro",
-    "created_at": null,
-    "context_window": 200000,
-    "max_output_tokens": 100000,
-    "knowledge_cutoff": null,
-    "modalities": {
-      "input": [
-        "image",
-        "text"
-      ],
-      "output": [
-        "embeddings",
-        "text"
-      ]
-    },
-    "capabilities": [
-      "batch",
+      "batch",
       "function_calling",
       "structured_output"
     ],
@@ -9345,21 +9235,22 @@
   },
   {
     "id": "omni-moderation-latest",
-    "name": "omni-moderation",
+    "name": "Omni Moderation Latest",
     "provider": "openai",
-    "family": "omni-moderation-latest",
-    "created_at": null,
+    "family": "moderation",
+    "created_at": "2024-11-15 17:47:45 +0100",
     "context_window": null,
     "max_output_tokens": null,
     "knowledge_cutoff": null,
     "modalities": {
       "input": [
+        "text",
         "image",
-        "text"
+        "pdf"
       ],
       "output": [
-        "embeddings",
-        "text"
+        "text",
+        "moderation"
       ]
     },
     "capabilities": [],
@@ -9371,10 +9262,10 @@
   },
   {
     "id": "text-embedding-3-large",
-    "name": "text-embedding-3-large",
+    "name": "text-embedding- 3 Large",
     "provider": "openai",
-    "family": "text-embedding-3-large",
-    "created_at": null,
+    "family": "embedding3_large",
+    "created_at": "2024-01-22 20:53:00 +0100",
     "context_window": null,
     "max_output_tokens": null,
     "knowledge_cutoff": null,
@@ -9383,8 +9274,8 @@
         "text"
       ],
       "output": [
-        "embeddings",
-        "text"
+        "text",
+        "embeddings"
       ]
     },
     "capabilities": [
@@ -9393,18 +9284,12 @@
     "pricing": {
       "text_tokens": {
         "standard": {
-          "input_per_million": 0.13
-        },
-        "batch": {
-          "input_per_million": 0.065
-        }
-      },
-      "embeddings": {
-        "standard": {
-          "input_per_million": 0.13
+          "input_per_million": 0.13,
+          "output_per_million": 0.13
         },
         "batch": {
-          "input_per_million": 0.065
+          "input_per_million": 0.065,
+          "output_per_million": 0.065
         }
       }
     },
@@ -9459,10 +9344,10 @@
   },
   {
     "id": "text-embedding-ada-002",
-    "name": "text-embedding-ada-002",
+    "name": "text-embedding- Ada 002",
     "provider": "openai",
-    "family": "text-embedding-ada-002",
-    "created_at": null,
+    "family": "embedding_ada",
+    "created_at": "2022-12-16 20:01:39 +0100",
     "context_window": null,
     "max_output_tokens": null,
     "knowledge_cutoff": null,
@@ -9471,8 +9356,8 @@
         "text"
       ],
       "output": [
-        "embeddings",
-        "text"
+        "text",
+        "embeddings"
       ]
     },
     "capabilities": [
@@ -9481,18 +9366,12 @@
     "pricing": {
       "text_tokens": {
         "standard": {
-          "input_per_million": 0.1
-        },
-        "batch": {
-          "input_per_million": 0.05
-        }
-      },
-      "embeddings": {
-        "standard": {
-          "input_per_million": 0.1
+          "input_per_million": 0.1,
+          "output_per_million": 0.1
         },
         "batch": {
-          "input_per_million": 0.05
+          "input_per_million": 0.05,
+          "output_per_million": 0.05
         }
       }
     },
@@ -9549,25 +9428,29 @@
     "id": "tts-1",
     "name": "TTS-1",
     "provider": "openai",
-    "family": "tts-1",
-    "created_at": null,
+    "family": "tts1",
+    "created_at": "2023-04-19 23:49:11 +0200",
     "context_window": null,
     "max_output_tokens": null,
     "knowledge_cutoff": null,
     "modalities": {
       "input": [
-        "text"
+        "text",
+        "audio"
       ],
       "output": [
-        "audio",
-        "embeddings"
+        "text",
+        "audio"
       ]
     },
-    "capabilities": [],
+    "capabilities": [
+      "streaming"
+    ],
     "pricing": {
       "text_tokens": {
         "standard": {
-          "input_per_million": 15.0
+          "input_per_million": 15.0,
+          "output_per_million": 15.0
         }
       }
     },
@@ -10190,7 +10073,7 @@
     "family": "alpindale",
     "created_at": "2023-11-10 01:00:00 +0100",
     "context_window": 6144,
-    "max_output_tokens": null,
+    "max_output_tokens": 512,
     "knowledge_cutoff": null,
     "modalities": {
       "input": [
@@ -10228,7 +10111,7 @@
       },
       "top_provider": {
         "context_length": 6144,
-        "max_completion_tokens": null,
+        "max_completion_tokens": 512,
         "is_moderated": false
       },
       "per_request_limits": null,
@@ -10618,325 +10501,13 @@
     }
   },
   {
-    "id": "anthropic/claude-3-haiku:beta",
-    "name": "Anthropic: Claude 3 Haiku (self-moderated)",
-    "provider": "openrouter",
-    "family": "anthropic",
-    "created_at": "2024-03-13 01:00:00 +0100",
-    "context_window": 200000,
-    "max_output_tokens": 4096,
-    "knowledge_cutoff": null,
-    "modalities": {
-      "input": [
-        "text",
-        "image"
-      ],
-      "output": [
-        "text"
-      ]
-    },
-    "capabilities": [
-      "streaming",
-      "function_calling"
-    ],
-    "pricing": {
-      "text_tokens": {
-        "standard": {
-          "input_per_million": 0.25,
-          "output_per_million": 1.25,
-          "cached_input_per_million": 0.03
-        }
-      }
-    },
-    "metadata": {
-      "description": "Claude 3 Haiku is Anthropic's fastest and most compact model for\nnear-instant responsiveness. Quick and accurate targeted performance.\n\nSee the launch announcement and benchmark results [here](https://www.anthropic.com/news/claude-3-haiku)\n\n#multimodal",
-      "architecture": {
-        "modality": "text+image->text",
-        "input_modalities": [
-          "text",
-          "image"
-        ],
-        "output_modalities": [
-          "text"
-        ],
-        "tokenizer": "Claude",
-        "instruct_type": null
-      },
-      "top_provider": {
-        "context_length": 200000,
-        "max_completion_tokens": 4096,
-        "is_moderated": false
-      },
-      "per_request_limits": null,
-      "supported_parameters": [
-        "max_tokens",
-        "stop",
-        "temperature",
-        "tool_choice",
-        "tools",
-        "top_k",
-        "top_p"
-      ]
-    }
-  },
-  {
-    "id": "anthropic/claude-3-opus",
-    "name": "Anthropic: Claude 3 Opus",
-    "provider": "openrouter",
-    "family": "anthropic",
-    "created_at": "2024-03-05 01:00:00 +0100",
-    "context_window": 200000,
-    "max_output_tokens": 4096,
-    "knowledge_cutoff": null,
-    "modalities": {
-      "input": [
-        "text",
-        "image"
-      ],
-      "output": [
-        "text"
-      ]
-    },
-    "capabilities": [
-      "streaming",
-      "function_calling"
-    ],
-    "pricing": {
-      "text_tokens": {
-        "standard": {
-          "input_per_million": 15.0,
-          "output_per_million": 75.0,
-          "cached_input_per_million": 1.5
-        }
-      }
-    },
-    "metadata": {
-      "description": "Claude 3 Opus is Anthropic's most powerful model for highly complex tasks. It boasts top-level performance, intelligence, fluency, and understanding.\n\nSee the launch announcement and benchmark results [here](https://www.anthropic.com/news/claude-3-family)\n\n#multimodal",
-      "architecture": {
-        "modality": "text+image->text",
-        "input_modalities": [
-          "text",
-          "image"
-        ],
-        "output_modalities": [
-          "text"
-        ],
-        "tokenizer": "Claude",
-        "instruct_type": null
-      },
-      "top_provider": {
-        "context_length": 200000,
-        "max_completion_tokens": 4096,
-        "is_moderated": true
-      },
-      "per_request_limits": null,
-      "supported_parameters": [
-        "max_tokens",
-        "stop",
-        "temperature",
-        "tool_choice",
-        "tools",
-        "top_k",
-        "top_p"
-      ]
-    }
-  },
-  {
-    "id": "anthropic/claude-3-opus:beta",
-    "name": "Anthropic: Claude 3 Opus (self-moderated)",
-    "provider": "openrouter",
-    "family": "anthropic",
-    "created_at": "2024-03-05 01:00:00 +0100",
-    "context_window": 200000,
-    "max_output_tokens": 4096,
-    "knowledge_cutoff": null,
-    "modalities": {
-      "input": [
-        "text",
-        "image"
-      ],
-      "output": [
-        "text"
-      ]
-    },
-    "capabilities": [
-      "streaming",
-      "function_calling"
-    ],
-    "pricing": {
-      "text_tokens": {
-        "standard": {
-          "input_per_million": 15.0,
-          "output_per_million": 75.0,
-          "cached_input_per_million": 1.5
-        }
-      }
-    },
-    "metadata": {
-      "description": "Claude 3 Opus is Anthropic's most powerful model for highly complex tasks. It boasts top-level performance, intelligence, fluency, and understanding.\n\nSee the launch announcement and benchmark results [here](https://www.anthropic.com/news/claude-3-family)\n\n#multimodal",
-      "architecture": {
-        "modality": "text+image->text",
-        "input_modalities": [
-          "text",
-          "image"
-        ],
-        "output_modalities": [
-          "text"
-        ],
-        "tokenizer": "Claude",
-        "instruct_type": null
-      },
-      "top_provider": {
-        "context_length": 200000,
-        "max_completion_tokens": 4096,
-        "is_moderated": false
-      },
-      "per_request_limits": null,
-      "supported_parameters": [
-        "max_tokens",
-        "stop",
-        "temperature",
-        "tool_choice",
-        "tools",
-        "top_k",
-        "top_p"
-      ]
-    }
-  },
-  {
-    "id": "anthropic/claude-3.5-haiku",
-    "name": "Anthropic: Claude 3.5 Haiku",
-    "provider": "openrouter",
-    "family": "anthropic",
-    "created_at": "2024-11-04 01:00:00 +0100",
-    "context_window": 200000,
-    "max_output_tokens": 8192,
-    "knowledge_cutoff": null,
-    "modalities": {
-      "input": [
-        "text",
-        "image"
-      ],
-      "output": [
-        "text"
-      ]
-    },
-    "capabilities": [
-      "streaming",
-      "function_calling"
-    ],
-    "pricing": {
-      "text_tokens": {
-        "standard": {
-          "input_per_million": 0.7999999999999999,
-          "output_per_million": 4.0,
-          "cached_input_per_million": 0.08
-        }
-      }
-    },
-    "metadata": {
-      "description": "Claude 3.5 Haiku features offers enhanced capabilities in speed, coding accuracy, and tool use. Engineered to excel in real-time applications, it delivers quick response times that are essential for dynamic tasks such as chat interactions and immediate coding suggestions.\n\nThis makes it highly suitable for environments that demand both speed and precision, such as software development, customer service bots, and data management systems.\n\nThis model is currently pointing to [Claude 3.5 Haiku (2024-10-22)](/anthropic/claude-3-5-haiku-20241022).",
-      "architecture": {
-        "modality": "text+image->text",
-        "input_modalities": [
-          "text",
-          "image"
-        ],
-        "output_modalities": [
-          "text"
-        ],
-        "tokenizer": "Claude",
-        "instruct_type": null
-      },
-      "top_provider": {
-        "context_length": 200000,
-        "max_completion_tokens": 8192,
-        "is_moderated": true
-      },
-      "per_request_limits": null,
-      "supported_parameters": [
-        "max_tokens",
-        "stop",
-        "temperature",
-        "tool_choice",
-        "tools",
-        "top_k",
-        "top_p"
-      ]
-    }
-  },
-  {
-    "id": "anthropic/claude-3.5-haiku-20241022",
-    "name": "Anthropic: Claude 3.5 Haiku (2024-10-22)",
-    "provider": "openrouter",
-    "family": "anthropic",
-    "created_at": "2024-11-04 01:00:00 +0100",
-    "context_window": 200000,
-    "max_output_tokens": 8192,
-    "knowledge_cutoff": null,
-    "modalities": {
-      "input": [
-        "text",
-        "image",
-        "file"
-      ],
-      "output": [
-        "text"
-      ]
-    },
-    "capabilities": [
-      "streaming",
-      "function_calling"
-    ],
-    "pricing": {
-      "text_tokens": {
-        "standard": {
-          "input_per_million": 0.7999999999999999,
-          "output_per_million": 4.0,
-          "cached_input_per_million": 0.08
-        }
-      }
-    },
-    "metadata": {
-      "description": "Claude 3.5 Haiku features enhancements across all skill sets including coding, tool use, and reasoning. As the fastest model in the Anthropic lineup, it offers rapid response times suitable for applications that require high interactivity and low latency, such as user-facing chatbots and on-the-fly code completions. It also excels in specialized tasks like data extraction and real-time content moderation, making it a versatile tool for a broad range of industries.\n\nIt does not support image inputs.\n\nSee the launch announcement and benchmark results [here](https://www.anthropic.com/news/3-5-models-and-computer-use)",
-      "architecture": {
-        "modality": "text+image->text",
-        "input_modalities": [
-          "text",
-          "image",
-          "file"
-        ],
-        "output_modalities": [
-          "text"
-        ],
-        "tokenizer": "Claude",
-        "instruct_type": null
-      },
-      "top_provider": {
-        "context_length": 200000,
-        "max_completion_tokens": 8192,
-        "is_moderated": false
-      },
-      "per_request_limits": null,
-      "supported_parameters": [
-        "max_tokens",
-        "stop",
-        "temperature",
-        "tool_choice",
-        "tools",
-        "top_k",
-        "top_p"
-      ]
-    }
-  },
-  {
-    "id": "anthropic/claude-3.5-haiku:beta",
-    "name": "Anthropic: Claude 3.5 Haiku (self-moderated)",
+    "id": "anthropic/claude-3-opus",
+    "name": "Anthropic: Claude 3 Opus",
     "provider": "openrouter",
     "family": "anthropic",
-    "created_at": "2024-11-04 01:00:00 +0100",
+    "created_at": "2024-03-05 01:00:00 +0100",
     "context_window": 200000,
-    "max_output_tokens": 8192,
+    "max_output_tokens": 4096,
     "knowledge_cutoff": null,
     "modalities": {
       "input": [
@@ -10954,14 +10525,14 @@
     "pricing": {
       "text_tokens": {
         "standard": {
-          "input_per_million": 0.7999999999999999,
-          "output_per_million": 4.0,
-          "cached_input_per_million": 0.08
+          "input_per_million": 15.0,
+          "output_per_million": 75.0,
+          "cached_input_per_million": 1.5
         }
       }
     },
     "metadata": {
-      "description": "Claude 3.5 Haiku features offers enhanced capabilities in speed, coding accuracy, and tool use. Engineered to excel in real-time applications, it delivers quick response times that are essential for dynamic tasks such as chat interactions and immediate coding suggestions.\n\nThis makes it highly suitable for environments that demand both speed and precision, such as software development, customer service bots, and data management systems.\n\nThis model is currently pointing to [Claude 3.5 Haiku (2024-10-22)](/anthropic/claude-3-5-haiku-20241022).",
+      "description": "Claude 3 Opus is Anthropic's most powerful model for highly complex tasks. It boasts top-level performance, intelligence, fluency, and understanding.\n\nSee the launch announcement and benchmark results [here](https://www.anthropic.com/news/claude-3-family)\n\n#multimodal",
       "architecture": {
         "modality": "text+image->text",
         "input_modalities": [
@@ -10976,8 +10547,8 @@
       },
       "top_provider": {
         "context_length": 200000,
-        "max_completion_tokens": 8192,
-        "is_moderated": false
+        "max_completion_tokens": 4096,
+        "is_moderated": true
       },
       "per_request_limits": null,
       "supported_parameters": [
@@ -10992,19 +10563,18 @@
     }
   },
   {
-    "id": "anthropic/claude-3.5-sonnet",
-    "name": "Anthropic: Claude 3.5 Sonnet",
+    "id": "anthropic/claude-3.5-haiku",
+    "name": "Anthropic: Claude 3.5 Haiku",
     "provider": "openrouter",
     "family": "anthropic",
-    "created_at": "2024-10-22 02:00:00 +0200",
+    "created_at": "2024-11-04 01:00:00 +0100",
     "context_window": 200000,
     "max_output_tokens": 8192,
     "knowledge_cutoff": null,
     "modalities": {
       "input": [
         "text",
-        "image",
-        "file"
+        "image"
       ],
       "output": [
         "text"
@@ -11017,20 +10587,19 @@
     "pricing": {
       "text_tokens": {
         "standard": {
-          "input_per_million": 3.0,
-          "output_per_million": 15.0,
-          "cached_input_per_million": 0.3
+          "input_per_million": 0.7999999999999999,
+          "output_per_million": 4.0,
+          "cached_input_per_million": 0.08
         }
       }
     },
     "metadata": {
-      "description": "New Claude 3.5 Sonnet delivers better-than-Opus capabilities, faster-than-Sonnet speeds, at the same Sonnet prices. Sonnet is particularly good at:\n\n- Coding: Scores ~49% on SWE-Bench Verified, higher than the last best score, and without any fancy prompt scaffolding\n- Data science: Augments human data science expertise; navigates unstructured data while using multiple tools for insights\n- Visual processing: excelling at interpreting charts, graphs, and images, accurately transcribing text to derive insights beyond just the text alone\n- Agentic tasks: exceptional tool use, making it great at agentic tasks (i.e. complex, multi-step problem solving tasks that require engaging with other systems)\n\n#multimodal",
+      "description": "Claude 3.5 Haiku features offers enhanced capabilities in speed, coding accuracy, and tool use. Engineered to excel in real-time applications, it delivers quick response times that are essential for dynamic tasks such as chat interactions and immediate coding suggestions.\n\nThis makes it highly suitable for environments that demand both speed and precision, such as software development, customer service bots, and data management systems.\n\nThis model is currently pointing to [Claude 3.5 Haiku (2024-10-22)](/anthropic/claude-3-5-haiku-20241022).",
       "architecture": {
         "modality": "text+image->text",
         "input_modalities": [
           "text",
-          "image",
-          "file"
+          "image"
         ],
         "output_modalities": [
           "text"
@@ -11056,11 +10625,11 @@
     }
   },
   {
-    "id": "anthropic/claude-3.5-sonnet-20240620",
-    "name": "Anthropic: Claude 3.5 Sonnet (2024-06-20)",
+    "id": "anthropic/claude-3.5-haiku-20241022",
+    "name": "Anthropic: Claude 3.5 Haiku (2024-10-22)",
     "provider": "openrouter",
     "family": "anthropic",
-    "created_at": "2024-06-20 02:00:00 +0200",
+    "created_at": "2024-11-04 01:00:00 +0100",
     "context_window": 200000,
     "max_output_tokens": 8192,
     "knowledge_cutoff": null,
@@ -11081,14 +10650,14 @@
     "pricing": {
       "text_tokens": {
         "standard": {
-          "input_per_million": 3.0,
-          "output_per_million": 15.0,
-          "cached_input_per_million": 0.3
+          "input_per_million": 0.7999999999999999,
+          "output_per_million": 4.0,
+          "cached_input_per_million": 0.08
         }
       }
     },
     "metadata": {
-      "description": "Claude 3.5 Sonnet delivers better-than-Opus capabilities, faster-than-Sonnet speeds, at the same Sonnet prices. Sonnet is particularly good at:\n\n- Coding: Autonomously writes, edits, and runs code with reasoning and troubleshooting\n- Data science: Augments human data science expertise; navigates unstructured data while using multiple tools for insights\n- Visual processing: excelling at interpreting charts, graphs, and images, accurately transcribing text to derive insights beyond just the text alone\n- Agentic tasks: exceptional tool use, making it great at agentic tasks (i.e. complex, multi-step problem solving tasks that require engaging with other systems)\n\nFor the latest version (2024-10-23), check out [Claude 3.5 Sonnet](/anthropic/claude-3.5-sonnet).\n\n#multimodal",
+      "description": "Claude 3.5 Haiku features enhancements across all skill sets including coding, tool use, and reasoning. As the fastest model in the Anthropic lineup, it offers rapid response times suitable for applications that require high interactivity and low latency, such as user-facing chatbots and on-the-fly code completions. It also excels in specialized tasks like data extraction and real-time content moderation, making it a versatile tool for a broad range of industries.\n\nIt does not support image inputs.\n\nSee the launch announcement and benchmark results [here](https://www.anthropic.com/news/3-5-models-and-computer-use)",
       "architecture": {
         "modality": "text+image->text",
         "input_modalities": [
@@ -11105,7 +10674,7 @@
       "top_provider": {
         "context_length": 200000,
         "max_completion_tokens": 8192,
-        "is_moderated": true
+        "is_moderated": false
       },
       "per_request_limits": null,
       "supported_parameters": [
@@ -11120,11 +10689,11 @@
     }
   },
   {
-    "id": "anthropic/claude-3.5-sonnet-20240620:beta",
-    "name": "Anthropic: Claude 3.5 Sonnet (2024-06-20) (self-moderated)",
+    "id": "anthropic/claude-3.5-sonnet",
+    "name": "Anthropic: Claude 3.5 Sonnet",
     "provider": "openrouter",
     "family": "anthropic",
-    "created_at": "2024-06-20 02:00:00 +0200",
+    "created_at": "2024-10-22 02:00:00 +0200",
     "context_window": 200000,
     "max_output_tokens": 8192,
     "knowledge_cutoff": null,
@@ -11152,7 +10721,7 @@
       }
     },
     "metadata": {
-      "description": "Claude 3.5 Sonnet delivers better-than-Opus capabilities, faster-than-Sonnet speeds, at the same Sonnet prices. Sonnet is particularly good at:\n\n- Coding: Autonomously writes, edits, and runs code with reasoning and troubleshooting\n- Data science: Augments human data science expertise; navigates unstructured data while using multiple tools for insights\n- Visual processing: excelling at interpreting charts, graphs, and images, accurately transcribing text to derive insights beyond just the text alone\n- Agentic tasks: exceptional tool use, making it great at agentic tasks (i.e. complex, multi-step problem solving tasks that require engaging with other systems)\n\nFor the latest version (2024-10-23), check out [Claude 3.5 Sonnet](/anthropic/claude-3.5-sonnet).\n\n#multimodal",
+      "description": "New Claude 3.5 Sonnet delivers better-than-Opus capabilities, faster-than-Sonnet speeds, at the same Sonnet prices. Sonnet is particularly good at:\n\n- Coding: Scores ~49% on SWE-Bench Verified, higher than the last best score, and without any fancy prompt scaffolding\n- Data science: Augments human data science expertise; navigates unstructured data while using multiple tools for insights\n- Visual processing: excelling at interpreting charts, graphs, and images, accurately transcribing text to derive insights beyond just the text alone\n- Agentic tasks: exceptional tool use, making it great at agentic tasks (i.e. complex, multi-step problem solving tasks that require engaging with other systems)\n\n#multimodal",
       "architecture": {
         "modality": "text+image->text",
         "input_modalities": [
@@ -11169,7 +10738,7 @@
       "top_provider": {
         "context_length": 200000,
         "max_completion_tokens": 8192,
-        "is_moderated": false
+        "is_moderated": true
       },
       "per_request_limits": null,
       "supported_parameters": [
@@ -11184,11 +10753,11 @@
     }
   },
   {
-    "id": "anthropic/claude-3.5-sonnet:beta",
-    "name": "Anthropic: Claude 3.5 Sonnet (self-moderated)",
+    "id": "anthropic/claude-3.5-sonnet-20240620",
+    "name": "Anthropic: Claude 3.5 Sonnet (2024-06-20)",
     "provider": "openrouter",
     "family": "anthropic",
-    "created_at": "2024-10-22 02:00:00 +0200",
+    "created_at": "2024-06-20 02:00:00 +0200",
     "context_window": 200000,
     "max_output_tokens": 8192,
     "knowledge_cutoff": null,
@@ -11216,7 +10785,7 @@
       }
     },
     "metadata": {
-      "description": "New Claude 3.5 Sonnet delivers better-than-Opus capabilities, faster-than-Sonnet speeds, at the same Sonnet prices. Sonnet is particularly good at:\n\n- Coding: Scores ~49% on SWE-Bench Verified, higher than the last best score, and without any fancy prompt scaffolding\n- Data science: Augments human data science expertise; navigates unstructured data while using multiple tools for insights\n- Visual processing: excelling at interpreting charts, graphs, and images, accurately transcribing text to derive insights beyond just the text alone\n- Agentic tasks: exceptional tool use, making it great at agentic tasks (i.e. complex, multi-step problem solving tasks that require engaging with other systems)\n\n#multimodal",
+      "description": "Claude 3.5 Sonnet delivers better-than-Opus capabilities, faster-than-Sonnet speeds, at the same Sonnet prices. Sonnet is particularly good at:\n\n- Coding: Autonomously writes, edits, and runs code with reasoning and troubleshooting\n- Data science: Augments human data science expertise; navigates unstructured data while using multiple tools for insights\n- Visual processing: excelling at interpreting charts, graphs, and images, accurately transcribing text to derive insights beyond just the text alone\n- Agentic tasks: exceptional tool use, making it great at agentic tasks (i.e. complex, multi-step problem solving tasks that require engaging with other systems)\n\nFor the latest version (2024-10-23), check out [Claude 3.5 Sonnet](/anthropic/claude-3.5-sonnet).\n\n#multimodal",
       "architecture": {
         "modality": "text+image->text",
         "input_modalities": [
@@ -11233,7 +10802,7 @@
       "top_provider": {
         "context_length": 200000,
         "max_completion_tokens": 8192,
-        "is_moderated": false
+        "is_moderated": true
       },
       "per_request_limits": null,
       "supported_parameters": [
@@ -14133,63 +13702,6 @@
       ]
     }
   },
-  {
-    "id": "deepseek/deepseek-r1-distill-qwen-7b",
-    "name": "DeepSeek: R1 Distill Qwen 7B",
-    "provider": "openrouter",
-    "family": "deepseek",
-    "created_at": "2025-05-30 20:03:57 +0200",
-    "context_window": 131072,
-    "max_output_tokens": null,
-    "knowledge_cutoff": null,
-    "modalities": {
-      "input": [
-        "text"
-      ],
-      "output": [
-        "text"
-      ]
-    },
-    "capabilities": [
-      "streaming"
-    ],
-    "pricing": {
-      "text_tokens": {
-        "standard": {
-          "input_per_million": 0.09999999999999999,
-          "output_per_million": 0.19999999999999998
-        }
-      }
-    },
-    "metadata": {
-      "description": "DeepSeek-R1-Distill-Qwen-7B is a 7 billion parameter dense language model distilled from DeepSeek-R1, leveraging reinforcement learning-enhanced reasoning data generated by DeepSeek's larger models. The distillation process transfers advanced reasoning, math, and code capabilities into a smaller, more efficient model architecture based on Qwen2.5-Math-7B. This model demonstrates strong performance across mathematical benchmarks (92.8% pass@1 on MATH-500), coding tasks (Codeforces rating 1189), and general reasoning (49.1% pass@1 on GPQA Diamond), achieving competitive accuracy relative to larger models while maintaining smaller inference costs.",
-      "architecture": {
-        "modality": "text->text",
-        "input_modalities": [
-          "text"
-        ],
-        "output_modalities": [
-          "text"
-        ],
-        "tokenizer": "Qwen",
-        "instruct_type": "deepseek-r1"
-      },
-      "top_provider": {
-        "context_length": 131072,
-        "max_completion_tokens": null,
-        "is_moderated": false
-      },
-      "per_request_limits": null,
-      "supported_parameters": [
-        "include_reasoning",
-        "max_tokens",
-        "reasoning",
-        "seed",
-        "temperature",
-        "top_p"
-      ]
-    }
-  },
   {
     "id": "deepseek/deepseek-r1:free",
     "name": "DeepSeek: R1 (free)",
@@ -17142,7 +16654,6 @@
     },
     "capabilities": [
       "streaming",
-      "function_calling",
       "structured_output",
       "predicted_outputs"
     ],
@@ -17177,7 +16688,6 @@
       "supported_parameters": [
         "frequency_penalty",
         "logit_bias",
-        "logprobs",
         "max_tokens",
         "min_p",
         "presence_penalty",
@@ -17187,8 +16697,6 @@
         "stop",
         "structured_outputs",
         "temperature",
-        "tool_choice",
-        "tools",
         "top_k",
         "top_logprobs",
         "top_p"
@@ -17938,8 +17446,8 @@
     "pricing": {
       "text_tokens": {
         "standard": {
-          "input_per_million": 0.049999999999999996,
-          "output_per_million": 0.049999999999999996
+          "input_per_million": 0.18,
+          "output_per_million": 0.18
         }
       }
     },
@@ -18932,7 +18440,7 @@
     "provider": "openrouter",
     "family": "mistralai",
     "created_at": "2025-05-21 16:22:59 +0200",
-    "context_window": 32768,
+    "context_window": 131072,
     "max_output_tokens": null,
     "knowledge_cutoff": null,
     "modalities": {
@@ -18971,7 +18479,7 @@
         "instruct_type": null
       },
       "top_provider": {
-        "context_length": 32768,
+        "context_length": 131072,
         "max_completion_tokens": null,
         "is_moderated": false
       },
@@ -20969,7 +20477,7 @@
   },
   {
     "id": "moonshotai/kimi-dev-72b:free",
-    "name": "Kimi Dev 72b (free)",
+    "name": "MoonshotAI: Kimi Dev 72B (free)",
     "provider": "openrouter",
     "family": "moonshotai",
     "created_at": "2025-06-17 01:18:29 +0200",
@@ -21161,7 +20669,7 @@
   },
   {
     "id": "moonshotai/kimi-vl-a3b-thinking",
-    "name": "Moonshot AI: Kimi VL A3B Thinking",
+    "name": "MoonshotAI: Kimi VL A3B Thinking",
     "provider": "openrouter",
     "family": "moonshotai",
     "created_at": "2025-04-10 19:07:21 +0200",
@@ -21230,7 +20738,7 @@
   },
   {
     "id": "moonshotai/kimi-vl-a3b-thinking:free",
-    "name": "Moonshot AI: Kimi VL A3B Thinking (free)",
+    "name": "MoonshotAI: Kimi VL A3B Thinking (free)",
     "provider": "openrouter",
     "family": "moonshotai",
     "created_at": "2025-04-10 19:07:21 +0200",
@@ -24100,8 +23608,8 @@
     "pricing": {
       "text_tokens": {
         "standard": {
-          "input_per_million": 0.09,
-          "output_per_million": 0.44999999999999996
+          "input_per_million": 0.07256312,
+          "output_per_million": 0.2903936
         }
       }
     },
@@ -26305,7 +25813,7 @@
     "provider": "openrouter",
     "family": "qwen",
     "created_at": "2025-02-01 12:45:11 +0100",
-    "context_window": 32000,
+    "context_window": 32768,
     "max_output_tokens": null,
     "knowledge_cutoff": null,
     "modalities": {
@@ -26324,8 +25832,8 @@
     "pricing": {
       "text_tokens": {
         "standard": {
-          "input_per_million": 0.25,
-          "output_per_million": 0.75
+          "input_per_million": 0.0999594,
+          "output_per_million": 0.400032
         }
       }
     },
@@ -26344,7 +25852,7 @@
         "instruct_type": null
       },
       "top_provider": {
-        "context_length": 32000,
+        "context_length": 32768,
         "max_completion_tokens": null,
         "is_moderated": false
       },
@@ -26430,7 +25938,7 @@
     "family": "qwen",
     "created_at": "2025-04-28 23:41:18 +0200",
     "context_window": 40960,
-    "max_output_tokens": null,
+    "max_output_tokens": 40960,
     "knowledge_cutoff": null,
     "modalities": {
       "input": [
@@ -26469,7 +25977,7 @@
       },
       "top_provider": {
         "context_length": 40960,
-        "max_completion_tokens": null,
+        "max_completion_tokens": 40960,
         "is_moderated": false
       },
       "per_request_limits": null,
@@ -27312,8 +26820,8 @@
     "pricing": {
       "text_tokens": {
         "standard": {
-          "input_per_million": 0.1999188,
-          "output_per_million": 0.800064
+          "input_per_million": 0.19999999999999998,
+          "output_per_million": 0.7999999999999999
         }
       }
     },
@@ -27363,8 +26871,8 @@
     "provider": "openrouter",
     "family": "qwen",
     "created_at": "2025-07-23 02:29:06 +0200",
-    "context_window": 32000,
-    "max_output_tokens": 4000,
+    "context_window": 262144,
+    "max_output_tokens": null,
     "knowledge_cutoff": null,
     "modalities": {
       "input": [
@@ -27375,7 +26883,9 @@
       ]
     },
     "capabilities": [
-      "streaming"
+      "streaming",
+      "function_calling",
+      "predicted_outputs"
     ],
     "pricing": {},
     "metadata": {
@@ -27392,16 +26902,27 @@
         "instruct_type": null
       },
       "top_provider": {
-        "context_length": 32000,
-        "max_completion_tokens": 4000,
-        "is_moderated": true
+        "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",
         "seed",
         "stop",
-        "temperature"
+        "temperature",
+        "tool_choice",
+        "tools",
+        "top_k",
+        "top_logprobs",
+        "top_p"
       ]
     }
   },
@@ -27918,7 +27439,7 @@
     "family": "sao10k",
     "created_at": "2024-12-18 16:32:08 +0100",
     "context_window": 131072,
-    "max_output_tokens": null,
+    "max_output_tokens": 16384,
     "knowledge_cutoff": null,
     "modalities": {
       "input": [
@@ -27956,7 +27477,7 @@
       },
       "top_provider": {
         "context_length": 131072,
-        "max_completion_tokens": null,
+        "max_completion_tokens": 16384,
         "is_moderated": false
       },
       "per_request_limits": null,
@@ -28996,8 +28517,8 @@
     }
   },
   {
-    "id": "thudm/glm-z1-32b:free",
-    "name": "THUDM: GLM Z1 32B (free)",
+    "id": "thudm/glm-z1-32b",
+    "name": "THUDM: GLM Z1 32B",
     "provider": "openrouter",
     "family": "thudm",
     "created_at": "2025-04-17 23:09:08 +0200",
@@ -29016,7 +28537,14 @@
       "streaming",
       "predicted_outputs"
     ],
-    "pricing": {},
+    "pricing": {
+      "text_tokens": {
+        "standard": {
+          "input_per_million": 0.01999188,
+          "output_per_million": 0.0800064
+        }
+      }
+    },
     "metadata": {
       "description": "GLM-Z1-32B-0414 is an enhanced reasoning variant of GLM-4-32B, built for deep mathematical, logical, and code-oriented problem solving. It applies extended reinforcement learning—both task-specific and general pairwise preference-based—to improve performance on complex multi-step tasks. Compared to the base GLM-4-32B model, Z1 significantly boosts capabilities in structured reasoning and formal domains.\n\nThe model supports enforced “thinking” steps via prompt engineering and offers improved coherence for long-form outputs. It’s optimized for use in agentic workflows, and includes support for long context (via YaRN), JSON tool calling, and fine-grained sampling configuration for stable inference. Ideal for use cases requiring deliberate, multi-step reasoning or formal derivations.",
       "architecture": {
@@ -30097,12 +29625,82 @@
       ]
     }
   },
+  {
+    "id": "z-ai/glm-4.5v",
+    "name": "Z.AI: GLM 4.5V",
+    "provider": "openrouter",
+    "family": "z-ai",
+    "created_at": "2025-08-11 16:24:48 +0200",
+    "context_window": 65536,
+    "max_output_tokens": 65536,
+    "knowledge_cutoff": null,
+    "modalities": {
+      "input": [
+        "text",
+        "image"
+      ],
+      "output": [
+        "text"
+      ]
+    },
+    "capabilities": [
+      "streaming",
+      "function_calling",
+      "predicted_outputs"
+    ],
+    "pricing": {
+      "text_tokens": {
+        "standard": {
+          "input_per_million": 0.5,
+          "output_per_million": 1.7999999999999998
+        }
+      }
+    },
+    "metadata": {
+      "description": "GLM-4.5V is a vision-language foundation model for multimodal agent applications. Built on a Mixture-of-Experts (MoE) architecture with 106B parameters and 12B activated parameters, it achieves state-of-the-art results in video understanding, image Q&A, OCR, and document parsing, with strong gains in front-end web coding, grounding, and spatial reasoning. It offers a hybrid inference mode: a \"thinking mode\" for deep reasoning and a \"non-thinking mode\" for fast responses. Reasoning behavior can be toggled via the `reasoning` `enabled` boolean. [Learn more in our docs](https://openrouter.ai/docs/use-cases/reasoning-tokens#enable-reasoning-with-default-config)",
+      "architecture": {
+        "modality": "text+image->text",
+        "input_modalities": [
+          "text",
+          "image"
+        ],
+        "output_modalities": [
+          "text"
+        ],
+        "tokenizer": "Other",
+        "instruct_type": null
+      },
+      "top_provider": {
+        "context_length": 65536,
+        "max_completion_tokens": 65536,
+        "is_moderated": false
+      },
+      "per_request_limits": null,
+      "supported_parameters": [
+        "frequency_penalty",
+        "include_reasoning",
+        "logit_bias",
+        "max_tokens",
+        "min_p",
+        "presence_penalty",
+        "reasoning",
+        "repetition_penalty",
+        "seed",
+        "stop",
+        "temperature",
+        "tool_choice",
+        "tools",
+        "top_k",
+        "top_p"
+      ]
+    }
+  },
   {
     "id": "sonar",
     "name": "Sonar",
     "provider": "perplexity",
     "family": "sonar",
-    "created_at": "2025-08-10 12:24:55 +0200",
+    "created_at": "2025-08-13 11:35:41 +0200",
     "context_window": 128000,
     "max_output_tokens": 4096,
     "knowledge_cutoff": null,
@@ -30134,7 +29732,7 @@
     "name": "Sonar Deep Research",
     "provider": "perplexity",
     "family": "sonar_deep_research",
-    "created_at": "2025-08-10 12:24:55 +0200",
+    "created_at": "2025-08-13 11:35:41 +0200",
     "context_window": 128000,
     "max_output_tokens": 4096,
     "knowledge_cutoff": null,
@@ -30169,7 +29767,7 @@
     "name": "Sonar Pro",
     "provider": "perplexity",
     "family": "sonar_pro",
-    "created_at": "2025-08-10 12:24:55 +0200",
+    "created_at": "2025-08-13 11:35:41 +0200",
     "context_window": 200000,
     "max_output_tokens": 8192,
     "knowledge_cutoff": null,
@@ -30201,7 +29799,7 @@
     "name": "Sonar Reasoning",
     "provider": "perplexity",
     "family": "sonar_reasoning",
-    "created_at": "2025-08-10 12:24:55 +0200",
+    "created_at": "2025-08-13 11:35:41 +0200",
     "context_window": 128000,
     "max_output_tokens": 4096,
     "knowledge_cutoff": null,
@@ -30233,7 +29831,7 @@
     "name": "Sonar Reasoning Pro",
     "provider": "perplexity",
     "family": "sonar_reasoning_pro",
-    "created_at": "2025-08-10 12:24:55 +0200",
+    "created_at": "2025-08-13 11:35:41 +0200",
     "context_window": 128000,
     "max_output_tokens": 8192,
     "knowledge_cutoff": null,