RubyGems - ruby_llm - Versions diffs - 1.10.0 → 1.11.0 - Mend

ruby_llm 1.10.0 → 1.11.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.

Files changed (16) hide show

checksums.yaml +4 -4
data/README.md +2 -2
data/lib/ruby_llm/aliases.json +4 -4
data/lib/ruby_llm/configuration.rb +1 -0
data/lib/ruby_llm/models.json +920 -1005
data/lib/ruby_llm/provider.rb +5 -1
data/lib/ruby_llm/providers/anthropic/media.rb +2 -2
data/lib/ruby_llm/providers/bedrock/chat.rb +10 -1
data/lib/ruby_llm/providers/openai/media.rb +1 -1
data/lib/ruby_llm/providers/xai/chat.rb +15 -0
data/lib/ruby_llm/providers/xai/models.rb +75 -0
data/lib/ruby_llm/providers/xai.rb +28 -0
data/lib/ruby_llm/version.rb +1 -1
data/lib/ruby_llm.rb +10 -8
data/lib/tasks/models.rake +1 -0
metadata +4 -1

data/lib/ruby_llm/models.json CHANGED Viewed

@@ -1122,7 +1122,7 @@
     "id": "ai21.jamba-1-5-large-v1:0",
     "name": "Jamba 1.5 Large",
     "provider": "bedrock",
-    "family": "jamba-1.5-large",
+    "family": "jamba",
     "created_at": "2024-08-15 00:00:00 +0200",
     "context_window": 256000,
     "max_output_tokens": 4096,
@@ -1168,7 +1168,7 @@
     "id": "ai21.jamba-1-5-mini-v1:0",
     "name": "Jamba 1.5 Mini",
     "provider": "bedrock",
-    "family": "jamba-1.5-mini",
+    "family": "jamba",
     "created_at": "2024-08-15 00:00:00 +0200",
     "context_window": 256000,
     "max_output_tokens": 4096,
@@ -1462,7 +1462,7 @@
     "id": "amazon.titan-text-express-v1",
     "name": "Titan Text G1 - Express",
     "provider": "bedrock",
-    "family": "titan-text-express",
+    "family": "titan",
     "created_at": "2024-12-01 00:00:00 +0100",
     "context_window": 128000,
     "max_output_tokens": 4096,
@@ -1507,7 +1507,7 @@
     "id": "amazon.titan-text-express-v1:0:8k",
     "name": "Titan Text G1 - Express",
     "provider": "bedrock",
-    "family": "titan-text-express",
+    "family": "titan",
     "created_at": "2024-12-01 00:00:00 +0100",
     "context_window": 128000,
     "max_output_tokens": 4096,
@@ -3560,7 +3560,7 @@
     "id": "cohere.command-r-plus-v1:0",
     "name": "Command R+",
     "provider": "bedrock",
-    "family": "command-r-plus",
+    "family": "command-r",
     "created_at": "2024-04-04 00:00:00 +0200",
     "context_window": 128000,
     "max_output_tokens": 4096,
@@ -3696,7 +3696,7 @@
     "id": "deepseek.r1-v1:0",
     "name": "DeepSeek-R1",
     "provider": "bedrock",
-    "family": "deepseek-r1",
+    "family": "deepseek-thinking",
     "created_at": "2025-01-20 00:00:00 +0100",
     "context_window": 128000,
     "max_output_tokens": 32768,
@@ -3743,7 +3743,7 @@
     "id": "deepseek.v3-v1:0",
     "name": "DeepSeek-V3.1",
     "provider": "bedrock",
-    "family": "deepseek-v3",
+    "family": "deepseek",
     "created_at": "2025-09-18 00:00:00 +0200",
     "context_window": 163840,
     "max_output_tokens": 81920,
@@ -3843,7 +3843,7 @@
     "id": "google.gemma-3-12b-it",
     "name": "Google Gemma 3 12B",
     "provider": "bedrock",
-    "family": "gemma-3",
+    "family": "gemma",
     "created_at": "2024-12-01 00:00:00 +0100",
     "context_window": 131072,
     "max_output_tokens": 8192,
@@ -3890,7 +3890,7 @@
     "id": "google.gemma-3-27b-it",
     "name": "Google Gemma 3 27B Instruct",
     "provider": "bedrock",
-    "family": "gemma-3",
+    "family": "gemma",
     "created_at": "2025-07-27 00:00:00 +0200",
     "context_window": 202752,
     "max_output_tokens": 8192,
@@ -3938,7 +3938,7 @@
     "id": "google.gemma-3-4b-it",
     "name": "Gemma 3 4B IT",
     "provider": "bedrock",
-    "family": "gemma-3",
+    "family": "gemma",
     "created_at": "2024-12-01 00:00:00 +0100",
     "context_window": 128000,
     "max_output_tokens": 4096,
@@ -4631,7 +4631,7 @@
     "id": "mistral.mistral-7b-instruct-v0:2",
     "name": "Mistral-7B-Instruct-v0.3",
     "provider": "bedrock",
-    "family": "mistral-7b",
+    "family": "mistral",
     "created_at": "2025-04-01 00:00:00 +0200",
     "context_window": 127000,
     "max_output_tokens": 127000,
@@ -4722,7 +4722,7 @@
     "id": "mistral.mixtral-8x7b-instruct-v0:1",
     "name": "Mixtral-8x7B-Instruct-v0.1",
     "provider": "bedrock",
-    "family": "mixtral-8x7b",
+    "family": "mixtral",
     "created_at": "2025-04-01 00:00:00 +0200",
     "context_window": 32000,
     "max_output_tokens": 32000,
@@ -4998,7 +4998,7 @@
     "id": "openai.gpt-oss-120b-1:0",
     "name": "gpt-oss-120b",
     "provider": "bedrock",
-    "family": "openai.gpt-oss",
+    "family": "gpt-oss",
     "created_at": "2024-12-01 00:00:00 +0100",
     "context_window": 128000,
     "max_output_tokens": 4096,
@@ -5043,7 +5043,7 @@
     "id": "openai.gpt-oss-20b-1:0",
     "name": "gpt-oss-20b",
     "provider": "bedrock",
-    "family": "openai.gpt-oss",
+    "family": "gpt-oss",
     "created_at": "2024-12-01 00:00:00 +0100",
     "context_window": 128000,
     "max_output_tokens": 4096,
@@ -5088,7 +5088,7 @@
     "id": "openai.gpt-oss-safeguard-120b",
     "name": "GPT OSS Safeguard 120B",
     "provider": "bedrock",
-    "family": "openai.gpt-oss-safeguard",
+    "family": "gpt-oss",
     "created_at": "2024-12-01 00:00:00 +0100",
     "context_window": 128000,
     "max_output_tokens": 4096,
@@ -5133,7 +5133,7 @@
     "id": "openai.gpt-oss-safeguard-20b",
     "name": "GPT OSS Safeguard 20B",
     "provider": "bedrock",
-    "family": "openai.gpt-oss-safeguard",
+    "family": "gpt-oss",
     "created_at": "2024-12-01 00:00:00 +0100",
     "context_window": 128000,
     "max_output_tokens": 4096,
@@ -5178,7 +5178,7 @@
     "id": "qwen.qwen3-235b-a22b-2507-v1:0",
     "name": "Qwen3 235B A22B 2507",
     "provider": "bedrock",
-    "family": "qwen3",
+    "family": "qwen",
     "created_at": "2025-09-18 00:00:00 +0200",
     "context_window": 262144,
     "max_output_tokens": 131072,
@@ -5224,7 +5224,7 @@
     "id": "qwen.qwen3-32b-v1:0",
     "name": "Qwen3 32B (dense)",
     "provider": "bedrock",
-    "family": "qwen3",
+    "family": "qwen",
     "created_at": "2025-09-18 00:00:00 +0200",
     "context_window": 16384,
     "max_output_tokens": 16384,
@@ -5271,7 +5271,7 @@
     "id": "qwen.qwen3-coder-30b-a3b-v1:0",
     "name": "Qwen3 Coder 30B A3B Instruct",
     "provider": "bedrock",
-    "family": "qwen3-coder",
+    "family": "qwen",
     "created_at": "2025-09-18 00:00:00 +0200",
     "context_window": 262144,
     "max_output_tokens": 131072,
@@ -5317,7 +5317,7 @@
     "id": "qwen.qwen3-coder-480b-a35b-v1:0",
     "name": "Qwen3 Coder 480B A35B Instruct",
     "provider": "bedrock",
-    "family": "qwen3-coder",
+    "family": "qwen",
     "created_at": "2025-09-18 00:00:00 +0200",
     "context_window": 131072,
     "max_output_tokens": 65536,
@@ -5363,7 +5363,7 @@
     "id": "qwen.qwen3-next-80b-a3b",
     "name": "Qwen/Qwen3-Next-80B-A3B-Instruct",
     "provider": "bedrock",
-    "family": "qwen3",
+    "family": "qwen",
     "created_at": "2025-09-18 00:00:00 +0200",
     "context_window": 262000,
     "max_output_tokens": 262000,
@@ -5409,7 +5409,7 @@
     "id": "qwen.qwen3-vl-235b-a22b",
     "name": "Qwen/Qwen3-VL-235B-A22B-Instruct",
     "provider": "bedrock",
-    "family": "qwen3-vl",
+    "family": "qwen",
     "created_at": "2025-10-04 00:00:00 +0200",
     "context_window": 262000,
     "max_output_tokens": 262000,
@@ -5921,7 +5921,7 @@
     "id": "deepseek-chat",
     "name": "DeepSeek Chat",
     "provider": "deepseek",
-    "family": "deepseek-chat",
+    "family": "deepseek",
     "created_at": "2024-12-26 00:00:00 +0100",
     "context_window": 128000,
     "max_output_tokens": 8192,
@@ -5972,7 +5972,7 @@
     "id": "deepseek-reasoner",
     "name": "DeepSeek Reasoner",
     "provider": "deepseek",
-    "family": "deepseek",
+    "family": "deepseek-thinking",
     "created_at": "2025-01-20 00:00:00 +0100",
     "context_window": 128000,
     "max_output_tokens": 128000,
@@ -6819,7 +6819,7 @@
     "id": "gemini-2.5-flash-image",
     "name": "Gemini 2.5 Flash Image",
     "provider": "gemini",
-    "family": "gemini-flash-image",
+    "family": "gemini-flash",
     "created_at": "2025-08-26 00:00:00 +0200",
     "context_window": 32768,
     "max_output_tokens": 32768,
@@ -6882,7 +6882,7 @@
     "id": "gemini-2.5-flash-image-preview",
     "name": "Gemini 2.5 Flash Image (Preview)",
     "provider": "gemini",
-    "family": "gemini-flash-image",
+    "family": "gemini-flash",
     "created_at": "2025-08-26 00:00:00 +0200",
     "context_window": 32768,
     "max_output_tokens": 32768,
@@ -6899,12 +6899,7 @@
     },
     "capabilities": [
       "reasoning",
-      "vision",
-      "streaming",
-      "function_calling",
-      "structured_output",
-      "batch",
-      "caching"
+      "vision"
     ],
     "pricing": {
       "text_tokens": {
@@ -6916,13 +6911,6 @@
       }
     },
     "metadata": {
-      "version": "2.0",
-      "description": "Gemini 2.5 Flash Preview Image",
-      "supported_generation_methods": [
-        "generateContent",
-        "countTokens",
-        "batchGenerateContent"
-      ],
       "source": "models.dev",
       "provider_id": "google",
       "open_weights": false,
@@ -7131,6 +7119,55 @@
       "knowledge": "2025-01"
     }
   },
+  {
+    "id": "gemini-2.5-flash-native-audio-latest",
+    "name": "Gemini 2.5 Flash Native Audio Latest",
+    "provider": "gemini",
+    "family": "other",
+    "created_at": null,
+    "context_window": 131072,
+    "max_output_tokens": 8192,
+    "knowledge_cutoff": null,
+    "modalities": {
+      "input": [
+        "text",
+        "image",
+        "pdf",
+        "video",
+        "audio"
+      ],
+      "output": [
+        "text"
+      ]
+    },
+    "capabilities": [
+      "streaming",
+      "function_calling",
+      "structured_output",
+      "batch",
+      "caching"
+    ],
+    "pricing": {
+      "text_tokens": {
+        "standard": {
+          "input_per_million": 0.075,
+          "output_per_million": 0.3
+        },
+        "batch": {
+          "input_per_million": 0.0375,
+          "output_per_million": 0.15
+        }
+      }
+    },
+    "metadata": {
+      "version": "Gemini 2.5 Flash Native Audio Latest",
+      "description": "Latest release of Gemini 2.5 Flash Native Audio",
+      "supported_generation_methods": [
+        "countTokens",
+        "bidiGenerateContent"
+      ]
+    }
+  },
   {
     "id": "gemini-2.5-flash-preview-04-17",
     "name": "Gemini 2.5 Flash Preview 04-17",
@@ -7316,7 +7353,7 @@
     "id": "gemini-2.5-flash-preview-tts",
     "name": "Gemini 2.5 Flash Preview TTS",
     "provider": "gemini",
-    "family": "gemini-flash-tts",
+    "family": "gemini-flash",
     "created_at": "2025-05-01 00:00:00 +0200",
     "context_window": 8000,
     "max_output_tokens": 16000,
@@ -7547,7 +7584,7 @@
     "id": "gemini-2.5-pro-preview-tts",
     "name": "Gemini 2.5 Pro Preview TTS",
     "provider": "gemini",
-    "family": "gemini-flash-tts",
+    "family": "gemini-flash",
     "created_at": "2025-05-01 00:00:00 +0200",
     "context_window": 8000,
     "max_output_tokens": 16000,
@@ -9266,7 +9303,7 @@
     "id": "devstral-2512",
     "name": "Devstral 2",
     "provider": "mistral",
-    "family": "devstral-medium",
+    "family": "devstral",
     "created_at": "2025-12-09 00:00:00 +0100",
     "context_window": 262144,
     "max_output_tokens": 262144,
@@ -9341,7 +9378,7 @@
     "id": "devstral-medium-2507",
     "name": "Devstral Medium",
     "provider": "mistral",
-    "family": "devstral-medium",
+    "family": "devstral",
     "created_at": "2025-07-10 00:00:00 +0200",
     "context_window": 128000,
     "max_output_tokens": 128000,
@@ -9393,7 +9430,7 @@
     "id": "devstral-medium-latest",
     "name": "Devstral 2",
     "provider": "mistral",
-    "family": "devstral-medium",
+    "family": "devstral",
     "created_at": "2025-12-02 00:00:00 +0100",
     "context_window": 262144,
     "max_output_tokens": 262144,
@@ -9445,7 +9482,7 @@
     "id": "devstral-small-2505",
     "name": "Devstral Small 2505",
     "provider": "mistral",
-    "family": "devstral-small",
+    "family": "devstral",
     "created_at": "2025-05-07 00:00:00 +0200",
     "context_window": 128000,
     "max_output_tokens": 128000,
@@ -9491,7 +9528,7 @@
     "id": "devstral-small-2507",
     "name": "Devstral Small",
     "provider": "mistral",
-    "family": "devstral-small",
+    "family": "devstral",
     "created_at": "2025-07-10 00:00:00 +0200",
     "context_window": 128000,
     "max_output_tokens": 128000,
@@ -9573,7 +9610,7 @@
     "id": "labs-devstral-small-2512",
     "name": "Devstral Small 2",
     "provider": "mistral",
-    "family": "devstral-small",
+    "family": "devstral",
     "created_at": "2025-12-09 00:00:00 +0100",
     "context_window": 256000,
     "max_output_tokens": 256000,
@@ -9959,7 +9996,7 @@
     "id": "ministral-3b-latest",
     "name": "Ministral 3B",
     "provider": "mistral",
-    "family": "ministral-3b",
+    "family": "ministral",
     "created_at": "2024-10-01 00:00:00 +0200",
     "context_window": 128000,
     "max_output_tokens": 128000,
@@ -10071,7 +10108,7 @@
     "id": "ministral-8b-latest",
     "name": "Ministral 8B",
     "provider": "mistral",
-    "family": "ministral-8b",
+    "family": "ministral",
     "created_at": "2024-10-01 00:00:00 +0200",
     "context_window": 128000,
     "max_output_tokens": 128000,
@@ -11059,7 +11096,7 @@
     "id": "open-mistral-7b",
     "name": "Mistral 7B",
     "provider": "mistral",
-    "family": "mistral-7b",
+    "family": "mistral",
     "created_at": "2023-09-27 00:00:00 +0200",
     "context_window": 8000,
     "max_output_tokens": 8000,
@@ -11168,7 +11205,7 @@
     "id": "open-mixtral-8x22b",
     "name": "Mixtral 8x22B",
     "provider": "mistral",
-    "family": "mixtral-8x22b",
+    "family": "mixtral",
     "created_at": "2024-04-17 00:00:00 +0200",
     "context_window": 64000,
     "max_output_tokens": 64000,
@@ -11214,7 +11251,7 @@
     "id": "open-mixtral-8x7b",
     "name": "Mixtral 8x7B",
     "provider": "mistral",
-    "family": "mixtral-8x7b",
+    "family": "mixtral",
     "created_at": "2023-12-11 00:00:00 +0100",
     "context_window": 32000,
     "max_output_tokens": 32000,
@@ -11406,7 +11443,7 @@
     "id": "pixtral-large-latest",
     "name": "Pixtral Large",
     "provider": "mistral",
-    "family": "pixtral-large",
+    "family": "pixtral",
     "created_at": "2024-11-01 00:00:00 +0100",
     "context_window": 128000,
     "max_output_tokens": 128000,
@@ -11692,7 +11729,7 @@
     "id": "codex-mini-latest",
     "name": "Codex Mini",
     "provider": "openai",
-    "family": "codex",
+    "family": "gpt-codex-mini",
     "created_at": "2025-05-16 00:00:00 +0200",
     "context_window": 200000,
     "max_output_tokens": 100000,
@@ -11845,7 +11882,7 @@
     "id": "gpt-3.5-turbo",
     "name": "GPT-3.5-turbo",
     "provider": "openai",
-    "family": "gpt-3.5-turbo",
+    "family": "gpt",
     "created_at": "2023-03-01 00:00:00 +0100",
     "context_window": 16385,
     "max_output_tokens": 4096,
@@ -12060,7 +12097,7 @@
     "id": "gpt-4",
     "name": "GPT-4",
     "provider": "openai",
-    "family": "gpt-4",
+    "family": "gpt",
     "created_at": "2023-11-06 00:00:00 +0100",
     "context_window": 8192,
     "max_output_tokens": 8192,
@@ -12208,7 +12245,7 @@
     "id": "gpt-4-turbo",
     "name": "GPT-4 Turbo",
     "provider": "openai",
-    "family": "gpt-4-turbo",
+    "family": "gpt",
     "created_at": "2023-11-06 00:00:00 +0100",
     "context_window": 128000,
     "max_output_tokens": 4096,
@@ -12331,7 +12368,7 @@
     "id": "gpt-4.1",
     "name": "GPT-4.1",
     "provider": "openai",
-    "family": "gpt-4.1",
+    "family": "gpt",
     "created_at": "2025-04-14 00:00:00 +0200",
     "context_window": 1047576,
     "max_output_tokens": 32768,
@@ -12423,7 +12460,7 @@
     "id": "gpt-4.1-mini",
     "name": "GPT-4.1 mini",
     "provider": "openai",
-    "family": "gpt-4.1-mini",
+    "family": "gpt-mini",
     "created_at": "2025-04-14 00:00:00 +0200",
     "context_window": 1047576,
     "max_output_tokens": 32768,
@@ -12515,7 +12552,7 @@
     "id": "gpt-4.1-nano",
     "name": "GPT-4.1 nano",
     "provider": "openai",
-    "family": "gpt-4.1-nano",
+    "family": "gpt-nano",
     "created_at": "2025-04-14 00:00:00 +0200",
     "context_window": 1047576,
     "max_output_tokens": 32768,
@@ -12606,7 +12643,7 @@
     "id": "gpt-4o",
     "name": "GPT-4o",
     "provider": "openai",
-    "family": "gpt-4o",
+    "family": "gpt",
     "created_at": "2024-05-13 00:00:00 +0200",
     "context_window": 128000,
     "max_output_tokens": 16384,
@@ -12660,7 +12697,7 @@
     "id": "gpt-4o-2024-05-13",
     "name": "GPT-4o (2024-05-13)",
     "provider": "openai",
-    "family": "gpt-4o",
+    "family": "gpt",
     "created_at": "2024-05-13 00:00:00 +0200",
     "context_window": 128000,
     "max_output_tokens": 4096,
@@ -12712,7 +12749,7 @@
     "id": "gpt-4o-2024-08-06",
     "name": "GPT-4o (2024-08-06)",
     "provider": "openai",
-    "family": "gpt-4o",
+    "family": "gpt",
     "created_at": "2024-08-06 00:00:00 +0200",
     "context_window": 128000,
     "max_output_tokens": 16384,
@@ -12766,7 +12803,7 @@
     "id": "gpt-4o-2024-11-20",
     "name": "GPT-4o (2024-11-20)",
     "provider": "openai",
-    "family": "gpt-4o",
+    "family": "gpt",
     "created_at": "2024-11-20 00:00:00 +0100",
     "context_window": 128000,
     "max_output_tokens": 16384,
@@ -12931,7 +12968,7 @@
     "id": "gpt-4o-mini",
     "name": "GPT-4o mini",
     "provider": "openai",
-    "family": "gpt-4o-mini",
+    "family": "gpt-mini",
     "created_at": "2024-07-18 00:00:00 +0200",
     "context_window": 128000,
     "max_output_tokens": 16384,
@@ -13672,7 +13709,7 @@
     "id": "gpt-5",
     "name": "GPT-5",
     "provider": "openai",
-    "family": "gpt-5",
+    "family": "gpt",
     "created_at": "2025-08-07 00:00:00 +0200",
     "context_window": 400000,
     "max_output_tokens": 128000,
@@ -13766,7 +13803,7 @@
     "id": "gpt-5-chat-latest",
     "name": "GPT-5 Chat (latest)",
     "provider": "openai",
-    "family": "gpt-5-chat",
+    "family": "gpt-codex",
     "created_at": "2025-08-07 00:00:00 +0200",
     "context_window": 400000,
     "max_output_tokens": 128000,
@@ -13819,7 +13856,7 @@
     "id": "gpt-5-codex",
     "name": "GPT-5-Codex",
     "provider": "openai",
-    "family": "gpt-5-codex",
+    "family": "gpt-codex",
     "created_at": "2025-09-15 00:00:00 +0200",
     "context_window": 400000,
     "max_output_tokens": 128000,
@@ -13874,7 +13911,7 @@
     "id": "gpt-5-mini",
     "name": "GPT-5 Mini",
     "provider": "openai",
-    "family": "gpt-5-mini",
+    "family": "gpt-mini",
     "created_at": "2025-08-07 00:00:00 +0200",
     "context_window": 400000,
     "max_output_tokens": 128000,
@@ -13968,7 +14005,7 @@
     "id": "gpt-5-nano",
     "name": "GPT-5 Nano",
     "provider": "openai",
-    "family": "gpt-5-nano",
+    "family": "gpt-nano",
     "created_at": "2025-08-07 00:00:00 +0200",
     "context_window": 400000,
     "max_output_tokens": 128000,
@@ -14062,7 +14099,7 @@
     "id": "gpt-5-pro",
     "name": "GPT-5 Pro",
     "provider": "openai",
-    "family": "gpt-5-pro",
+    "family": "gpt-pro",
     "created_at": "2025-10-06 00:00:00 +0200",
     "context_window": 400000,
     "max_output_tokens": 272000,
@@ -14232,7 +14269,7 @@
     "id": "gpt-5.1",
     "name": "GPT-5.1",
     "provider": "openai",
-    "family": "gpt-5",
+    "family": "gpt",
     "created_at": "2025-11-13 00:00:00 +0100",
     "context_window": 400000,
     "max_output_tokens": 128000,
@@ -14326,7 +14363,7 @@
     "id": "gpt-5.1-chat-latest",
     "name": "GPT-5.1 Chat",
     "provider": "openai",
-    "family": "gpt-5-chat",
+    "family": "gpt-codex",
     "created_at": "2025-11-13 00:00:00 +0100",
     "context_window": 128000,
     "max_output_tokens": 16384,
@@ -14381,7 +14418,7 @@
     "id": "gpt-5.1-codex",
     "name": "GPT-5.1 Codex",
     "provider": "openai",
-    "family": "gpt-5-codex",
+    "family": "gpt-codex",
     "created_at": "2025-11-13 00:00:00 +0100",
     "context_window": 400000,
     "max_output_tokens": 128000,
@@ -14427,6 +14464,7 @@
       },
       "limit": {
         "context": 400000,
+        "input": 272000,
         "output": 128000
       },
       "knowledge": "2024-09-30"
@@ -14436,7 +14474,7 @@
     "id": "gpt-5.1-codex-max",
     "name": "GPT-5.1 Codex Max",
     "provider": "openai",
-    "family": "gpt-5-codex",
+    "family": "gpt-codex",
     "created_at": "2025-11-13 00:00:00 +0100",
     "context_window": 400000,
     "max_output_tokens": 128000,
@@ -14482,6 +14520,7 @@
       },
       "limit": {
         "context": 400000,
+        "input": 272000,
         "output": 128000
       },
       "knowledge": "2024-09-30"
@@ -14491,7 +14530,7 @@
     "id": "gpt-5.1-codex-mini",
     "name": "GPT-5.1 Codex mini",
     "provider": "openai",
-    "family": "gpt-5-codex-mini",
+    "family": "gpt-codex",
     "created_at": "2025-11-13 00:00:00 +0100",
     "context_window": 400000,
     "max_output_tokens": 128000,
@@ -14537,6 +14576,7 @@
       },
       "limit": {
         "context": 400000,
+        "input": 272000,
         "output": 128000
       },
       "knowledge": "2024-09-30"
@@ -14546,7 +14586,7 @@
     "id": "gpt-5.2",
     "name": "GPT-5.2",
     "provider": "openai",
-    "family": "gpt-5",
+    "family": "gpt",
     "created_at": "2025-12-11 00:00:00 +0100",
     "context_window": 400000,
     "max_output_tokens": 128000,
@@ -14640,7 +14680,7 @@
     "id": "gpt-5.2-chat-latest",
     "name": "GPT-5.2 Chat",
     "provider": "openai",
-    "family": "gpt-5-chat",
+    "family": "gpt-codex",
     "created_at": "2025-12-11 00:00:00 +0100",
     "context_window": 128000,
     "max_output_tokens": 16384,
@@ -14691,11 +14731,67 @@
       "knowledge": "2025-08-31"
     }
   },
+  {
+    "id": "gpt-5.2-codex",
+    "name": "GPT-5.2 Codex",
+    "provider": "openai",
+    "family": "gpt-codex",
+    "created_at": "2025-12-11 00:00:00 +0100",
+    "context_window": 400000,
+    "max_output_tokens": 128000,
+    "knowledge_cutoff": "2025-08-31",
+    "modalities": {
+      "input": [
+        "text",
+        "image"
+      ],
+      "output": [
+        "text"
+      ]
+    },
+    "capabilities": [
+      "function_calling",
+      "structured_output",
+      "reasoning",
+      "vision",
+      "streaming"
+    ],
+    "pricing": {
+      "text_tokens": {
+        "standard": {
+          "input_per_million": 1.75,
+          "output_per_million": 14,
+          "cached_input_per_million": 0.175
+        }
+      }
+    },
+    "metadata": {
+      "object": "model",
+      "owned_by": "system",
+      "source": "models.dev",
+      "provider_id": "openai",
+      "open_weights": false,
+      "attachment": true,
+      "temperature": false,
+      "last_updated": "2025-12-11",
+      "cost": {
+        "input": 1.75,
+        "output": 14,
+        "cache_read": 0.175
+      },
+      "limit": {
+        "context": 400000,
+        "input": 272000,
+        "output": 128000
+      },
+      "knowledge": "2025-08-31"
+    }
+  },
   {
     "id": "gpt-5.2-pro",
     "name": "GPT-5.2 Pro",
     "provider": "openai",
-    "family": "gpt-5-pro",
+    "family": "gpt-pro",
     "created_at": "2025-12-11 00:00:00 +0100",
     "context_window": 400000,
     "max_output_tokens": 128000,
@@ -15229,7 +15325,7 @@
     "id": "o1",
     "name": "o1",
     "provider": "openai",
-    "family": "o1",
+    "family": "o",
     "created_at": "2024-12-05 00:00:00 +0100",
     "context_window": 200000,
     "max_output_tokens": 100000,
@@ -15322,7 +15418,7 @@
     "id": "o1-mini",
     "name": "o1-mini",
     "provider": "openai",
-    "family": "o1-mini",
+    "family": "o-mini",
     "created_at": "2024-09-12 00:00:00 +0200",
     "context_window": 128000,
     "max_output_tokens": 65536,
@@ -15371,7 +15467,7 @@
     "id": "o1-preview",
     "name": "o1-preview",
     "provider": "openai",
-    "family": "o1-preview",
+    "family": "o",
     "created_at": "2024-09-12 00:00:00 +0200",
     "context_window": 128000,
     "max_output_tokens": 32768,
@@ -15419,7 +15515,7 @@
     "id": "o1-pro",
     "name": "o1-pro",
     "provider": "openai",
-    "family": "o1-pro",
+    "family": "o-pro",
     "created_at": "2025-03-19 00:00:00 +0100",
     "context_window": 200000,
     "max_output_tokens": 100000,
@@ -15510,7 +15606,7 @@
     "id": "o3",
     "name": "o3",
     "provider": "openai",
-    "family": "o3",
+    "family": "o",
     "created_at": "2025-04-16 00:00:00 +0200",
     "context_window": 200000,
     "max_output_tokens": 100000,
@@ -15599,7 +15695,7 @@
     "id": "o3-deep-research",
     "name": "o3-deep-research",
     "provider": "openai",
-    "family": "o3",
+    "family": "o",
     "created_at": "2024-06-26 00:00:00 +0200",
     "context_window": 200000,
     "max_output_tokens": 100000,
@@ -15687,7 +15783,7 @@
     "id": "o3-mini",
     "name": "o3-mini",
     "provider": "openai",
-    "family": "o3-mini",
+    "family": "o-mini",
     "created_at": "2024-12-20 00:00:00 +0100",
     "context_window": 200000,
     "max_output_tokens": 100000,
@@ -15776,7 +15872,7 @@
     "id": "o3-pro",
     "name": "o3-pro",
     "provider": "openai",
-    "family": "o3-pro",
+    "family": "o-pro",
     "created_at": "2025-06-10 00:00:00 +0200",
     "context_window": 200000,
     "max_output_tokens": 100000,
@@ -15863,7 +15959,7 @@
     "id": "o4-mini",
     "name": "o4-mini",
     "provider": "openai",
-    "family": "o4-mini",
+    "family": "o-mini",
     "created_at": "2025-04-16 00:00:00 +0200",
     "context_window": 200000,
     "max_output_tokens": 100000,
@@ -15952,7 +16048,7 @@
     "id": "o4-mini-deep-research",
     "name": "o4-mini-deep-research",
     "provider": "openai",
-    "family": "o4-mini",
+    "family": "o-mini",
     "created_at": "2024-06-26 00:00:00 +0200",
     "context_window": 200000,
     "max_output_tokens": 100000,
@@ -16160,7 +16256,7 @@
     "id": "text-embedding-3-large",
     "name": "text-embedding-3-large",
     "provider": "openai",
-    "family": "text-embedding-3-large",
+    "family": "text-embedding",
     "created_at": "2024-01-25 00:00:00 +0100",
     "context_window": 8191,
     "max_output_tokens": 3072,
@@ -16207,7 +16303,7 @@
     "id": "text-embedding-3-small",
     "name": "text-embedding-3-small",
     "provider": "openai",
-    "family": "text-embedding-3-small",
+    "family": "text-embedding",
     "created_at": "2024-01-25 00:00:00 +0100",
     "context_window": 8191,
     "max_output_tokens": 1536,
@@ -16254,7 +16350,7 @@
     "id": "text-embedding-ada-002",
     "name": "text-embedding-ada-002",
     "provider": "openai",
-    "family": "text-embedding-ada",
+    "family": "text-embedding",
     "created_at": "2022-12-15 00:00:00 +0100",
     "context_window": 8192,
     "max_output_tokens": 1536,
@@ -16908,6 +17004,7 @@
     },
     "capabilities": [
       "streaming",
+      "structured_output",
       "predicted_outputs"
     ],
     "pricing": {},
@@ -16936,9 +17033,9 @@
         "frequency_penalty",
         "logit_bias",
         "max_tokens",
-        "min_p",
         "presence_penalty",
         "repetition_penalty",
+        "response_format",
         "seed",
         "stop",
         "temperature",
@@ -17051,7 +17148,6 @@
         "include_reasoning",
         "logit_bias",
         "max_tokens",
-        "min_p",
         "presence_penalty",
         "reasoning",
         "repetition_penalty",
@@ -17084,7 +17180,6 @@
     },
     "capabilities": [
       "streaming",
-      "function_calling",
       "structured_output",
       "predicted_outputs"
     ],
@@ -17119,7 +17214,6 @@
         "frequency_penalty",
         "logit_bias",
         "max_tokens",
-        "min_p",
         "presence_penalty",
         "repetition_penalty",
         "response_format",
@@ -17127,8 +17221,6 @@
         "stop",
         "structured_outputs",
         "temperature",
-        "tool_choice",
-        "tools",
         "top_k",
         "top_p"
       ]
@@ -17188,7 +17280,6 @@
         "include_reasoning",
         "logit_bias",
         "max_tokens",
-        "min_p",
         "presence_penalty",
         "reasoning",
         "repetition_penalty",
@@ -17323,7 +17414,6 @@
         "include_reasoning",
         "logit_bias",
         "max_tokens",
-        "min_p",
         "presence_penalty",
         "reasoning",
         "repetition_penalty",
@@ -17922,70 +18012,6 @@
       "knowledge": "2024-07-31"
     }
   },
-  {
-    "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-sonnet",
     "name": "Anthropic: Claude 3.5 Sonnet",
@@ -19615,7 +19641,6 @@
         "frequency_penalty",
         "logit_bias",
         "max_tokens",
-        "min_p",
         "presence_penalty",
         "repetition_penalty",
         "seed",
@@ -20360,7 +20385,7 @@
     "id": "deepseek/deepseek-chat-v3-0324",
     "name": "DeepSeek V3 0324",
     "provider": "openrouter",
-    "family": "deepseek-v3",
+    "family": "deepseek",
     "created_at": "2025-03-24 00:00:00 +0100",
     "context_window": 16384,
     "max_output_tokens": 8192,
@@ -20447,7 +20472,7 @@
     "id": "deepseek/deepseek-chat-v3.1",
     "name": "DeepSeek-V3.1",
     "provider": "openrouter",
-    "family": "deepseek-v3",
+    "family": "deepseek",
     "created_at": "2025-08-21 00:00:00 +0200",
     "context_window": 163840,
     "max_output_tokens": 163840,
@@ -20532,77 +20557,14 @@
       "knowledge": "2025-07"
     }
   },
-  {
-    "id": "deepseek/deepseek-prover-v2",
-    "name": "DeepSeek: DeepSeek Prover V2",
-    "provider": "openrouter",
-    "family": "deepseek",
-    "created_at": "2025-04-30 13:38:14 +0200",
-    "context_window": 163840,
-    "max_output_tokens": null,
-    "knowledge_cutoff": null,
-    "modalities": {
-      "input": [
-        "text"
-      ],
-      "output": [
-        "text"
-      ]
-    },
-    "capabilities": [
-      "streaming",
-      "structured_output"
-    ],
-    "pricing": {
-      "text_tokens": {
-        "standard": {
-          "input_per_million": 0.5,
-          "output_per_million": 2.1799999999999997
-        }
-      }
-    },
-    "metadata": {
-      "description": "DeepSeek Prover V2 is a 671B parameter model, speculated to be geared towards logic and mathematics. Likely an upgrade from [DeepSeek-Prover-V1.5](https://huggingface.co/deepseek-ai/DeepSeek-Prover-V1.5-RL) Not much is known about the model yet, as DeepSeek released it on Hugging Face without an announcement or description.",
-      "architecture": {
-        "modality": "text->text",
-        "input_modalities": [
-          "text"
-        ],
-        "output_modalities": [
-          "text"
-        ],
-        "tokenizer": "DeepSeek",
-        "instruct_type": null
-      },
-      "top_provider": {
-        "context_length": 163840,
-        "max_completion_tokens": null,
-        "is_moderated": false
-      },
-      "per_request_limits": null,
-      "supported_parameters": [
-        "frequency_penalty",
-        "max_tokens",
-        "min_p",
-        "presence_penalty",
-        "repetition_penalty",
-        "response_format",
-        "seed",
-        "stop",
-        "temperature",
-        "top_k",
-        "top_p"
-      ]
-    }
-  },
   {
     "id": "deepseek/deepseek-r1",
     "name": "DeepSeek: R1",
     "provider": "openrouter",
     "family": "deepseek",
     "created_at": "2025-01-20 14:51:35 +0100",
-    "context_window": 163840,
-    "max_output_tokens": 163840,
+    "context_window": 64000,
+    "max_output_tokens": 16000,
     "knowledge_cutoff": null,
     "modalities": {
       "input": [
@@ -20614,14 +20576,13 @@
     },
     "capabilities": [
       "streaming",
-      "function_calling",
-      "structured_output"
+      "function_calling"
     ],
     "pricing": {
       "text_tokens": {
         "standard": {
           "input_per_million": 0.7,
-          "output_per_million": 2.4
+          "output_per_million": 2.5
         }
       }
     },
@@ -20639,8 +20600,8 @@
         "instruct_type": "deepseek-r1"
       },
       "top_provider": {
-        "context_length": 163840,
-        "max_completion_tokens": 163840,
+        "context_length": 64000,
+        "max_completion_tokens": 16000,
         "is_moderated": false
       },
       "per_request_limits": null,
@@ -20648,11 +20609,9 @@
         "frequency_penalty",
         "include_reasoning",
         "max_tokens",
-        "min_p",
         "presence_penalty",
         "reasoning",
         "repetition_penalty",
-        "response_format",
         "seed",
         "stop",
         "temperature",
@@ -20736,73 +20695,11 @@
       ]
     }
   },
-  {
-    "id": "deepseek/deepseek-r1-0528-qwen3-8b",
-    "name": "DeepSeek: DeepSeek R1 0528 Qwen3 8B",
-    "provider": "openrouter",
-    "family": "deepseek",
-    "created_at": "2025-05-29 19:09:03 +0200",
-    "context_window": 128000,
-    "max_output_tokens": 32000,
-    "knowledge_cutoff": null,
-    "modalities": {
-      "input": [
-        "text"
-      ],
-      "output": [
-        "text"
-      ]
-    },
-    "capabilities": [
-      "streaming"
-    ],
-    "pricing": {
-      "text_tokens": {
-        "standard": {
-          "input_per_million": 0.06,
-          "output_per_million": 0.09
-        }
-      }
-    },
-    "metadata": {
-      "description": "DeepSeek-R1-0528 is a lightly upgraded release of DeepSeek R1 that taps more compute and smarter post-training tricks, pushing its reasoning and inference to the brink of flagship models like O3 and Gemini 2.5 Pro.\nIt now tops math, programming, and logic leaderboards, showcasing a step-change in depth-of-thought.\nThe distilled variant, DeepSeek-R1-0528-Qwen3-8B, transfers this chain-of-thought into an 8 B-parameter form, beating standard Qwen3 8B by +10 pp and tying the 235 B “thinking” giant on AIME 2024.",
-      "architecture": {
-        "modality": "text->text",
-        "input_modalities": [
-          "text"
-        ],
-        "output_modalities": [
-          "text"
-        ],
-        "tokenizer": "Qwen",
-        "instruct_type": "deepseek-r1"
-      },
-      "top_provider": {
-        "context_length": 128000,
-        "max_completion_tokens": 32000,
-        "is_moderated": false
-      },
-      "per_request_limits": null,
-      "supported_parameters": [
-        "frequency_penalty",
-        "include_reasoning",
-        "max_tokens",
-        "presence_penalty",
-        "reasoning",
-        "repetition_penalty",
-        "seed",
-        "stop",
-        "temperature",
-        "top_k",
-        "top_p"
-      ]
-    }
-  },
   {
     "id": "deepseek/deepseek-r1-0528-qwen3-8b:free",
     "name": "Deepseek R1 0528 Qwen3 8B (free)",
     "provider": "openrouter",
-    "family": "qwen3",
+    "family": "qwen",
     "created_at": "2025-05-29 00:00:00 +0200",
     "context_window": 131072,
     "max_output_tokens": 131072,
@@ -20842,7 +20739,7 @@
     "id": "deepseek/deepseek-r1-0528:free",
     "name": "R1 0528 (free)",
     "provider": "openrouter",
-    "family": "deepseek-r1",
+    "family": "deepseek",
     "created_at": "2025-05-28 00:00:00 +0200",
     "context_window": 163840,
     "max_output_tokens": 163840,
@@ -20910,7 +20807,7 @@
     "id": "deepseek/deepseek-r1-distill-llama-70b",
     "name": "DeepSeek R1 Distill Llama 70B",
     "provider": "openrouter",
-    "family": "deepseek-r1-distill-llama",
+    "family": "deepseek-thinking",
     "created_at": "2025-01-23 00:00:00 +0100",
     "context_window": 8192,
     "max_output_tokens": 8192,
@@ -21011,52 +20908,10 @@
       ]
     },
     "capabilities": [
-      "reasoning",
-      "streaming",
-      "structured_output"
+      "reasoning"
     ],
-    "pricing": {
-      "text_tokens": {
-        "standard": {
-          "input_per_million": 0.15,
-          "output_per_million": 0.15
-        }
-      }
-    },
+    "pricing": {},
     "metadata": {
-      "description": "DeepSeek R1 Distill Qwen 14B is a distilled large language model based on [Qwen 2.5 14B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-14B), using outputs from [DeepSeek R1](/deepseek/deepseek-r1). It outperforms OpenAI's o1-mini across various benchmarks, achieving new state-of-the-art results for dense models.\n\nOther benchmark results include:\n\n- AIME 2024 pass@1: 69.7\n- MATH-500 pass@1: 93.9\n- CodeForces Rating: 1481\n\nThe model leverages fine-tuning from DeepSeek R1's outputs, enabling competitive performance comparable to larger frontier models.",
-      "architecture": {
-        "modality": "text->text",
-        "input_modalities": [
-          "text"
-        ],
-        "output_modalities": [
-          "text"
-        ],
-        "tokenizer": "Qwen",
-        "instruct_type": "deepseek-r1"
-      },
-      "top_provider": {
-        "context_length": 32768,
-        "max_completion_tokens": 16384,
-        "is_moderated": false
-      },
-      "per_request_limits": null,
-      "supported_parameters": [
-        "frequency_penalty",
-        "include_reasoning",
-        "max_tokens",
-        "presence_penalty",
-        "reasoning",
-        "repetition_penalty",
-        "response_format",
-        "seed",
-        "stop",
-        "structured_outputs",
-        "temperature",
-        "top_k",
-        "top_p"
-      ],
       "source": "models.dev",
       "provider_id": "openrouter",
       "open_weights": true,
@@ -21080,7 +20935,7 @@
     "provider": "openrouter",
     "family": "deepseek",
     "created_at": "2025-01-30 00:53:50 +0100",
-    "context_window": 131072,
+    "context_window": 32768,
     "max_output_tokens": null,
     "knowledge_cutoff": null,
     "modalities": {
@@ -21098,8 +20953,8 @@
     "pricing": {
       "text_tokens": {
         "standard": {
-          "input_per_million": 0.27,
-          "output_per_million": 0.27
+          "input_per_million": 0.29,
+          "output_per_million": 0.29
         }
       }
     },
@@ -21117,7 +20972,7 @@
         "instruct_type": "deepseek-r1"
       },
       "top_provider": {
-        "context_length": 131072,
+        "context_length": 32768,
         "max_completion_tokens": null,
         "is_moderated": false
       },
@@ -21126,7 +20981,6 @@
         "frequency_penalty",
         "include_reasoning",
         "max_tokens",
-        "min_p",
         "presence_penalty",
         "reasoning",
         "repetition_penalty",
@@ -21144,7 +20998,7 @@
     "id": "deepseek/deepseek-r1:free",
     "name": "R1 (free)",
     "provider": "openrouter",
-    "family": "deepseek-r1",
+    "family": "deepseek",
     "created_at": "2025-01-20 00:00:00 +0100",
     "context_window": 163840,
     "max_output_tokens": 163840,
@@ -21184,7 +21038,7 @@
     "id": "deepseek/deepseek-v3-base:free",
     "name": "DeepSeek V3 Base (free)",
     "provider": "openrouter",
-    "family": "deepseek-v3",
+    "family": "deepseek",
     "created_at": "2025-03-29 00:00:00 +0100",
     "context_window": 163840,
     "max_output_tokens": 163840,
@@ -21221,7 +21075,7 @@
     "id": "deepseek/deepseek-v3.1-terminus",
     "name": "DeepSeek V3.1 Terminus",
     "provider": "openrouter",
-    "family": "deepseek-v3",
+    "family": "deepseek",
     "created_at": "2025-09-22 00:00:00 +0200",
     "context_window": 131072,
     "max_output_tokens": 65536,
@@ -21306,7 +21160,7 @@
     "id": "deepseek/deepseek-v3.1-terminus:exacto",
     "name": "DeepSeek V3.1 Terminus (exacto)",
     "provider": "openrouter",
-    "family": "deepseek-v3",
+    "family": "deepseek",
     "created_at": "2025-09-22 00:00:00 +0200",
     "context_window": 131072,
     "max_output_tokens": 65536,
@@ -21391,7 +21245,7 @@
     "id": "deepseek/deepseek-v3.2",
     "name": "DeepSeek V3.2",
     "provider": "openrouter",
-    "family": "deepseek-v3",
+    "family": "deepseek",
     "created_at": "2025-12-01 00:00:00 +0100",
     "context_window": 163840,
     "max_output_tokens": 65536,
@@ -21529,7 +21383,6 @@
         "frequency_penalty",
         "include_reasoning",
         "max_tokens",
-        "min_p",
         "presence_penalty",
         "reasoning",
         "repetition_penalty",
@@ -21549,7 +21402,7 @@
     "id": "deepseek/deepseek-v3.2-speciale",
     "name": "DeepSeek V3.2 Speciale",
     "provider": "openrouter",
-    "family": "deepseek-v3",
+    "family": "deepseek",
     "created_at": "2025-12-01 00:00:00 +0100",
     "context_window": 163840,
     "max_output_tokens": 65536,
@@ -21601,7 +21454,6 @@
         "include_reasoning",
         "logit_bias",
         "max_tokens",
-        "min_p",
         "presence_penalty",
         "reasoning",
         "repetition_penalty",
@@ -22176,68 +22028,6 @@
       ]
     }
   },
-  {
-    "id": "google/gemini-2.5-flash-image-preview",
-    "name": "Google: Gemini 2.5 Flash Image Preview (Nano Banana)",
-    "provider": "openrouter",
-    "family": "google",
-    "created_at": "2025-08-26 16:36:17 +0200",
-    "context_window": 32768,
-    "max_output_tokens": 32768,
-    "knowledge_cutoff": null,
-    "modalities": {
-      "input": [
-        "image",
-        "text"
-      ],
-      "output": [
-        "image",
-        "text"
-      ]
-    },
-    "capabilities": [
-      "streaming",
-      "structured_output"
-    ],
-    "pricing": {
-      "text_tokens": {
-        "standard": {
-          "input_per_million": 0.3,
-          "output_per_million": 2.5
-        }
-      }
-    },
-    "metadata": {
-      "description": "Gemini 2.5 Flash Image Preview, a.k.a. \"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": [
-          "image",
-          "text"
-        ],
-        "output_modalities": [
-          "image",
-          "text"
-        ],
-        "tokenizer": "Gemini",
-        "instruct_type": null
-      },
-      "top_provider": {
-        "context_length": 32768,
-        "max_completion_tokens": 32768,
-        "is_moderated": false
-      },
-      "per_request_limits": null,
-      "supported_parameters": [
-        "max_tokens",
-        "response_format",
-        "seed",
-        "structured_outputs",
-        "temperature",
-        "top_p"
-      ]
-    }
-  },
   {
     "id": "google/gemini-2.5-flash-lite",
     "name": "Gemini 2.5 Flash Lite",
@@ -22476,7 +22266,7 @@
       },
       "top_provider": {
         "context_length": 1048576,
-        "max_completion_tokens": 65536,
+        "max_completion_tokens": 65535,
         "is_moderated": false
       },
       "per_request_limits": null,
@@ -23191,7 +22981,7 @@
     "id": "google/gemma-2-9b-it:free",
     "name": "Gemma 2 9B (free)",
     "provider": "openrouter",
-    "family": "gemma-2",
+    "family": "gemma",
     "created_at": "2024-06-28 00:00:00 +0200",
     "context_window": 8192,
     "max_output_tokens": 8192,
@@ -23230,7 +23020,7 @@
     "id": "google/gemma-3-12b-it",
     "name": "Gemma 3 12B IT",
     "provider": "openrouter",
-    "family": "gemma-3",
+    "family": "gemma",
     "created_at": "2025-03-13 00:00:00 +0100",
     "context_window": 96000,
     "max_output_tokens": 8192,
@@ -23366,7 +23156,7 @@
     "id": "google/gemma-3-27b-it",
     "name": "Gemma 3 27B IT",
     "provider": "openrouter",
-    "family": "gemma-3",
+    "family": "gemma",
     "created_at": "2025-03-12 00:00:00 +0100",
     "context_window": 96000,
     "max_output_tokens": 8192,
@@ -23683,7 +23473,7 @@
     "id": "google/gemma-3n-e4b-it",
     "name": "Gemma 3n E4B IT",
     "provider": "openrouter",
-    "family": "gemma-3",
+    "family": "gemma",
     "created_at": "2025-05-20 00:00:00 +0200",
     "context_window": 8192,
     "max_output_tokens": 8192,
@@ -23763,7 +23553,7 @@
     "id": "google/gemma-3n-e4b-it:free",
     "name": "Gemma 3n 4B (free)",
     "provider": "openrouter",
-    "family": "gemma-3",
+    "family": "gemma",
     "created_at": "2025-05-20 00:00:00 +0200",
     "context_window": 8192,
     "max_output_tokens": 8192,
@@ -24268,7 +24058,7 @@
     "id": "kwaipilot/kat-coder-pro:free",
     "name": "Kat Coder Pro (free)",
     "provider": "openrouter",
-    "family": "kat-coder-pro",
+    "family": "kat-coder",
     "created_at": "2025-11-10 00:00:00 +0100",
     "context_window": 256000,
     "max_output_tokens": 65536,
@@ -24554,7 +24344,7 @@
     "family": "meta-llama",
     "created_at": "2024-04-18 02:00:00 +0200",
     "context_window": 8192,
-    "max_output_tokens": 16384,
+    "max_output_tokens": null,
     "knowledge_cutoff": null,
     "modalities": {
       "input": [
@@ -24566,14 +24356,13 @@
     },
     "capabilities": [
       "streaming",
-      "function_calling",
       "structured_output",
       "predicted_outputs"
     ],
     "pricing": {
       "text_tokens": {
         "standard": {
-          "input_per_million": 0.3,
+          "input_per_million": 0.39999999999999997,
           "output_per_million": 0.39999999999999997
         }
       }
@@ -24593,7 +24382,7 @@
       },
       "top_provider": {
         "context_length": 8192,
-        "max_completion_tokens": 16384,
+        "max_completion_tokens": null,
         "is_moderated": false
       },
       "per_request_limits": null,
@@ -24609,8 +24398,6 @@
         "stop",
         "structured_outputs",
         "temperature",
-        "tool_choice",
-        "tools",
         "top_k",
         "top_p"
       ]
@@ -25008,7 +24795,7 @@
     "id": "meta-llama/llama-3.2-11b-vision-instruct",
     "name": "Llama 3.2 11B Vision Instruct",
     "provider": "openrouter",
-    "family": "llama-3.2",
+    "family": "llama",
     "created_at": "2024-09-25 00:00:00 +0200",
     "context_window": 131072,
     "max_output_tokens": 8192,
@@ -25165,7 +24952,6 @@
     },
     "capabilities": [
       "streaming",
-      "function_calling",
       "structured_output",
       "predicted_outputs"
     ],
@@ -25207,8 +24993,6 @@
         "seed",
         "stop",
         "temperature",
-        "tool_choice",
-        "tools",
         "top_k",
         "top_p"
       ]
@@ -25265,71 +25049,6 @@
       ]
     }
   },
-  {
-    "id": "meta-llama/llama-3.2-90b-vision-instruct",
-    "name": "Meta: Llama 3.2 90B Vision Instruct",
-    "provider": "openrouter",
-    "family": "meta-llama",
-    "created_at": "2024-09-25 02:00:00 +0200",
-    "context_window": 32768,
-    "max_output_tokens": 16384,
-    "knowledge_cutoff": null,
-    "modalities": {
-      "input": [
-        "text",
-        "image"
-      ],
-      "output": [
-        "text"
-      ]
-    },
-    "capabilities": [
-      "streaming",
-      "structured_output"
-    ],
-    "pricing": {
-      "text_tokens": {
-        "standard": {
-          "input_per_million": 0.35,
-          "output_per_million": 0.39999999999999997
-        }
-      }
-    },
-    "metadata": {
-      "description": "The Llama 90B Vision model is a top-tier, 90-billion-parameter multimodal model designed for the most challenging visual reasoning and language tasks. It offers unparalleled accuracy in image captioning, visual question answering, and advanced image-text comprehension. Pre-trained on vast multimodal datasets and fine-tuned with human feedback, the Llama 90B Vision is engineered to handle the most demanding image-based AI tasks.\n\nThis model is perfect for industries requiring cutting-edge multimodal AI capabilities, particularly those dealing with complex, real-time visual and textual analysis.\n\nClick here for the [original model card](https://github.com/meta-llama/llama-models/blob/main/models/llama3_2/MODEL_CARD_VISION.md).\n\nUsage of this model is subject to [Meta's Acceptable Use Policy](https://www.llama.com/llama3/use-policy/).",
-      "architecture": {
-        "modality": "text+image->text",
-        "input_modalities": [
-          "text",
-          "image"
-        ],
-        "output_modalities": [
-          "text"
-        ],
-        "tokenizer": "Llama3",
-        "instruct_type": "llama3"
-      },
-      "top_provider": {
-        "context_length": 32768,
-        "max_completion_tokens": 16384,
-        "is_moderated": false
-      },
-      "per_request_limits": null,
-      "supported_parameters": [
-        "frequency_penalty",
-        "max_tokens",
-        "min_p",
-        "presence_penalty",
-        "repetition_penalty",
-        "response_format",
-        "seed",
-        "stop",
-        "temperature",
-        "top_k",
-        "top_p"
-      ]
-    }
-  },
   {
     "id": "meta-llama/llama-3.3-70b-instruct",
     "name": "Meta: Llama 3.3 70B Instruct",
@@ -25405,7 +25124,7 @@
     "id": "meta-llama/llama-3.3-70b-instruct:free",
     "name": "Llama 3.3 70B Instruct (free)",
     "provider": "openrouter",
-    "family": "llama-3.3",
+    "family": "llama",
     "created_at": "2024-12-06 00:00:00 +0100",
     "context_window": 65536,
     "max_output_tokens": 65536,
@@ -25527,6 +25246,7 @@
       "supported_parameters": [
         "frequency_penalty",
         "logit_bias",
+        "logprobs",
         "max_tokens",
         "min_p",
         "presence_penalty",
@@ -25539,6 +25259,7 @@
         "tool_choice",
         "tools",
         "top_k",
+        "top_logprobs",
         "top_p"
       ]
     }
@@ -25618,7 +25339,7 @@
     "id": "meta-llama/llama-4-scout:free",
     "name": "Llama 4 Scout (free)",
     "provider": "openrouter",
-    "family": "llama-4-scout",
+    "family": "llama",
     "created_at": "2025-04-05 00:00:00 +0200",
     "context_window": 64000,
     "max_output_tokens": 64000,
@@ -25735,8 +25456,7 @@
       ]
     },
     "capabilities": [
-      "streaming",
-      "structured_output"
+      "streaming"
     ],
     "pricing": {
       "text_tokens": {
@@ -25768,12 +25488,9 @@
       "supported_parameters": [
         "frequency_penalty",
         "max_tokens",
-        "min_p",
         "presence_penalty",
         "repetition_penalty",
-        "response_format",
         "seed",
-        "stop",
         "temperature",
         "top_k",
         "top_p"
@@ -25851,7 +25568,7 @@
     "id": "microsoft/mai-ds-r1:free",
     "name": "MAI DS R1 (free)",
     "provider": "openrouter",
-    "family": "mai-ds-r1",
+    "family": "mai",
     "created_at": "2025-04-21 00:00:00 +0200",
     "context_window": 163840,
     "max_output_tokens": 163840,
@@ -25951,136 +25668,6 @@
       ]
     }
   },
-  {
-    "id": "microsoft/phi-4-multimodal-instruct",
-    "name": "Microsoft: Phi 4 Multimodal Instruct",
-    "provider": "openrouter",
-    "family": "microsoft",
-    "created_at": "2025-03-08 02:11:24 +0100",
-    "context_window": 131072,
-    "max_output_tokens": null,
-    "knowledge_cutoff": null,
-    "modalities": {
-      "input": [
-        "text",
-        "image"
-      ],
-      "output": [
-        "text"
-      ]
-    },
-    "capabilities": [
-      "streaming",
-      "structured_output"
-    ],
-    "pricing": {
-      "text_tokens": {
-        "standard": {
-          "input_per_million": 0.049999999999999996,
-          "output_per_million": 0.09999999999999999
-        }
-      }
-    },
-    "metadata": {
-      "description": "Phi-4 Multimodal Instruct is a versatile 5.6B parameter foundation model that combines advanced reasoning and instruction-following capabilities across both text and visual inputs, providing accurate text outputs. The unified architecture enables efficient, low-latency inference, suitable for edge and mobile deployments. Phi-4 Multimodal Instruct supports text inputs in multiple languages including Arabic, Chinese, English, French, German, Japanese, Spanish, and more, with visual input optimized primarily for English. It delivers impressive performance on multimodal tasks involving mathematical, scientific, and document reasoning, providing developers and enterprises a powerful yet compact model for sophisticated interactive applications. For more information, see the [Phi-4 Multimodal blog post](https://azure.microsoft.com/en-us/blog/empowering-innovation-the-next-generation-of-the-phi-family/).\n",
-      "architecture": {
-        "modality": "text+image->text",
-        "input_modalities": [
-          "text",
-          "image"
-        ],
-        "output_modalities": [
-          "text"
-        ],
-        "tokenizer": "Other",
-        "instruct_type": null
-      },
-      "top_provider": {
-        "context_length": 131072,
-        "max_completion_tokens": null,
-        "is_moderated": false
-      },
-      "per_request_limits": null,
-      "supported_parameters": [
-        "frequency_penalty",
-        "max_tokens",
-        "min_p",
-        "presence_penalty",
-        "repetition_penalty",
-        "response_format",
-        "seed",
-        "stop",
-        "temperature",
-        "top_k",
-        "top_p"
-      ]
-    }
-  },
-  {
-    "id": "microsoft/phi-4-reasoning-plus",
-    "name": "Microsoft: Phi 4 Reasoning Plus",
-    "provider": "openrouter",
-    "family": "microsoft",
-    "created_at": "2025-05-01 22:22:41 +0200",
-    "context_window": 32768,
-    "max_output_tokens": null,
-    "knowledge_cutoff": null,
-    "modalities": {
-      "input": [
-        "text"
-      ],
-      "output": [
-        "text"
-      ]
-    },
-    "capabilities": [
-      "streaming",
-      "structured_output"
-    ],
-    "pricing": {
-      "text_tokens": {
-        "standard": {
-          "input_per_million": 0.07,
-          "output_per_million": 0.35
-        }
-      }
-    },
-    "metadata": {
-      "description": "Phi-4-reasoning-plus is an enhanced 14B parameter model from Microsoft, fine-tuned from Phi-4 with additional reinforcement learning to boost accuracy on math, science, and code reasoning tasks. It uses the same dense decoder-only transformer architecture as Phi-4, but generates longer, more comprehensive outputs structured into a step-by-step reasoning trace and final answer.\n\nWhile it offers improved benchmark scores over Phi-4-reasoning across tasks like AIME, OmniMath, and HumanEvalPlus, its responses are typically ~50% longer, resulting in higher latency. Designed for English-only applications, it is well-suited for structured reasoning workflows where output quality takes priority over response speed.",
-      "architecture": {
-        "modality": "text->text",
-        "input_modalities": [
-          "text"
-        ],
-        "output_modalities": [
-          "text"
-        ],
-        "tokenizer": "Other",
-        "instruct_type": null
-      },
-      "top_provider": {
-        "context_length": 32768,
-        "max_completion_tokens": null,
-        "is_moderated": false
-      },
-      "per_request_limits": null,
-      "supported_parameters": [
-        "frequency_penalty",
-        "include_reasoning",
-        "max_tokens",
-        "min_p",
-        "presence_penalty",
-        "reasoning",
-        "repetition_penalty",
-        "response_format",
-        "seed",
-        "stop",
-        "temperature",
-        "top_k",
-        "top_p"
-      ]
-    }
-  },
   {
     "id": "microsoft/wizardlm-2-8x22b",
     "name": "WizardLM-2 8x22B",
@@ -26778,7 +26365,7 @@
     "id": "mistralai/devstral-medium-2507",
     "name": "Devstral Medium",
     "provider": "openrouter",
-    "family": "devstral-medium",
+    "family": "devstral",
     "created_at": "2025-07-10 00:00:00 +0200",
     "context_window": 131072,
     "max_output_tokens": 131072,
@@ -26826,7 +26413,7 @@
     "provider": "openrouter",
     "family": "mistralai",
     "created_at": "2025-07-10 17:19:11 +0200",
-    "context_window": 128000,
+    "context_window": 131072,
     "max_output_tokens": null,
     "knowledge_cutoff": null,
     "modalities": {
@@ -26845,8 +26432,8 @@
     "pricing": {
       "text_tokens": {
         "standard": {
-          "input_per_million": 0.07,
-          "output_per_million": 0.28
+          "input_per_million": 0.09999999999999999,
+          "output_per_million": 0.3
         }
       }
     },
@@ -26864,7 +26451,7 @@
         "instruct_type": null
       },
       "top_provider": {
-        "context_length": 128000,
+        "context_length": 131072,
         "max_completion_tokens": null,
         "is_moderated": false
       },
@@ -26872,9 +26459,7 @@
       "supported_parameters": [
         "frequency_penalty",
         "max_tokens",
-        "min_p",
         "presence_penalty",
-        "repetition_penalty",
         "response_format",
         "seed",
         "stop",
@@ -26882,7 +26467,6 @@
         "temperature",
         "tool_choice",
         "tools",
-        "top_k",
         "top_p"
       ]
     }
@@ -26891,7 +26475,7 @@
     "id": "mistralai/devstral-small-2505",
     "name": "Devstral Small",
     "provider": "openrouter",
-    "family": "devstral-small",
+    "family": "devstral",
     "created_at": "2025-05-07 00:00:00 +0200",
     "context_window": 128000,
     "max_output_tokens": 128000,
@@ -26905,9 +26489,7 @@
       ]
     },
     "capabilities": [
-      "function_calling",
-      "streaming",
-      "structured_output"
+      "function_calling"
     ],
     "pricing": {
       "text_tokens": {
@@ -26918,37 +26500,6 @@
       }
     },
     "metadata": {
-      "description": "Devstral-Small-2505 is a 24B parameter agentic LLM fine-tuned from Mistral-Small-3.1, jointly developed by Mistral AI and All Hands AI for advanced software engineering tasks. It is optimized for codebase exploration, multi-file editing, and integration into coding agents, achieving state-of-the-art results on SWE-Bench Verified (46.8%).\n\nDevstral supports a 128k context window and uses a custom Tekken tokenizer. It is text-only, with the vision encoder removed, and is suitable for local deployment on high-end consumer hardware (e.g., RTX 4090, 32GB RAM Macs). Devstral is best used in agentic workflows via the OpenHands scaffold and is compatible with inference frameworks like vLLM, Transformers, and Ollama. It is released under the Apache 2.0 license.",
-      "architecture": {
-        "modality": "text->text",
-        "input_modalities": [
-          "text"
-        ],
-        "output_modalities": [
-          "text"
-        ],
-        "tokenizer": "Mistral",
-        "instruct_type": null
-      },
-      "top_provider": {
-        "context_length": 128000,
-        "max_completion_tokens": null,
-        "is_moderated": false
-      },
-      "per_request_limits": null,
-      "supported_parameters": [
-        "frequency_penalty",
-        "max_tokens",
-        "min_p",
-        "presence_penalty",
-        "repetition_penalty",
-        "response_format",
-        "seed",
-        "stop",
-        "temperature",
-        "top_k",
-        "top_p"
-      ],
       "source": "models.dev",
       "provider_id": "openrouter",
       "open_weights": true,
@@ -26970,7 +26521,7 @@
     "id": "mistralai/devstral-small-2505:free",
     "name": "Devstral Small 2505 (free)",
     "provider": "openrouter",
-    "family": "devstral-small",
+    "family": "devstral",
     "created_at": "2025-05-21 00:00:00 +0200",
     "context_window": 32768,
     "max_output_tokens": 32768,
@@ -27009,7 +26560,7 @@
     "id": "mistralai/devstral-small-2507",
     "name": "Devstral Small 1.1",
     "provider": "openrouter",
-    "family": "devstral-small",
+    "family": "devstral",
     "created_at": "2025-07-10 00:00:00 +0200",
     "context_window": 131072,
     "max_output_tokens": 131072,
@@ -27389,7 +26940,7 @@
     "family": "mistralai",
     "created_at": "2024-05-27 02:00:00 +0200",
     "context_window": 32768,
-    "max_output_tokens": 16384,
+    "max_output_tokens": 4096,
     "knowledge_cutoff": null,
     "modalities": {
       "input": [
@@ -27401,15 +26952,13 @@
     },
     "capabilities": [
       "streaming",
-      "function_calling",
-      "structured_output",
       "predicted_outputs"
     ],
     "pricing": {
       "text_tokens": {
         "standard": {
-          "input_per_million": 0.028,
-          "output_per_million": 0.054
+          "input_per_million": 0.19999999999999998,
+          "output_per_million": 0.19999999999999998
         }
       }
     },
@@ -27428,7 +26977,7 @@
       },
       "top_provider": {
         "context_length": 32768,
-        "max_completion_tokens": 16384,
+        "max_completion_tokens": 4096,
         "is_moderated": false
       },
       "per_request_limits": null,
@@ -27439,12 +26988,8 @@
         "min_p",
         "presence_penalty",
         "repetition_penalty",
-        "response_format",
-        "seed",
         "stop",
         "temperature",
-        "tool_choice",
-        "tools",
         "top_k",
         "top_p"
       ]
@@ -27637,7 +27182,7 @@
     "id": "mistralai/mistral-7b-instruct:free",
     "name": "Mistral 7B Instruct (free)",
     "provider": "openrouter",
-    "family": "mistral-7b",
+    "family": "mistral",
     "created_at": "2024-05-27 00:00:00 +0200",
     "context_window": 32768,
     "max_output_tokens": 32768,
@@ -27651,13 +27196,59 @@
       ]
     },
     "capabilities": [
-      "function_calling",
+      "function_calling"
+    ],
+    "pricing": {},
+    "metadata": {
+      "source": "models.dev",
+      "provider_id": "openrouter",
+      "open_weights": true,
+      "attachment": false,
+      "temperature": true,
+      "last_updated": "2024-05-27",
+      "cost": {
+        "input": 0,
+        "output": 0
+      },
+      "limit": {
+        "context": 32768,
+        "output": 32768
+      },
+      "knowledge": "2024-05"
+    }
+  },
+  {
+    "id": "mistralai/mistral-large",
+    "name": "Mistral Large",
+    "provider": "openrouter",
+    "family": "mistralai",
+    "created_at": "2024-02-26 01:00:00 +0100",
+    "context_window": 128000,
+    "max_output_tokens": null,
+    "knowledge_cutoff": null,
+    "modalities": {
+      "input": [
+        "text"
+      ],
+      "output": [
+        "text"
+      ]
+    },
+    "capabilities": [
       "streaming",
+      "function_calling",
       "structured_output"
     ],
-    "pricing": {},
+    "pricing": {
+      "text_tokens": {
+        "standard": {
+          "input_per_million": 2.0,
+          "output_per_million": 6.0
+        }
+      }
+    },
     "metadata": {
-      "description": "A high-performing, industry-standard 7.3B parameter model, with optimizations for speed and context length.\n\n*Mistral 7B Instruct has multiple version variants, and this is intended to be the latest version.*",
+      "description": "This is Mistral AI's flagship model, Mistral Large 2 (version `mistral-large-2407`). It's a proprietary weights-available model and excels at reasoning, code, JSON, chat, and more. Read the launch announcement [here](https://mistral.ai/news/mistral-large-2407/).\n\nIt supports dozens of languages including French, German, Spanish, Italian, Portuguese, Arabic, Hindi, Russian, Chinese, Japanese, and Korean, along with 80+ coding languages including Python, Java, C, C++, JavaScript, and Bash. Its long context window allows precise information recall from large documents.",
       "architecture": {
         "modality": "text->text",
         "input_modalities": [
@@ -27667,117 +27258,36 @@
           "text"
         ],
         "tokenizer": "Mistral",
-        "instruct_type": "mistral"
+        "instruct_type": null
       },
       "top_provider": {
-        "context_length": 32768,
-        "max_completion_tokens": 16384,
+        "context_length": 128000,
+        "max_completion_tokens": null,
         "is_moderated": false
       },
       "per_request_limits": null,
       "supported_parameters": [
         "frequency_penalty",
         "max_tokens",
-        "min_p",
         "presence_penalty",
-        "repetition_penalty",
         "response_format",
         "seed",
         "stop",
+        "structured_outputs",
         "temperature",
         "tool_choice",
         "tools",
-        "top_k",
         "top_p"
-      ],
-      "source": "models.dev",
-      "provider_id": "openrouter",
-      "open_weights": true,
-      "attachment": false,
-      "temperature": true,
-      "last_updated": "2024-05-27",
-      "cost": {
-        "input": 0,
-        "output": 0
-      },
-      "limit": {
-        "context": 32768,
-        "output": 32768
-      },
-      "knowledge": "2024-05"
+      ]
     }
   },
   {
-    "id": "mistralai/mistral-large",
-    "name": "Mistral Large",
+    "id": "mistralai/mistral-large-2407",
+    "name": "Mistral Large 2407",
     "provider": "openrouter",
     "family": "mistralai",
-    "created_at": "2024-02-26 01:00:00 +0100",
-    "context_window": 128000,
-    "max_output_tokens": null,
-    "knowledge_cutoff": null,
-    "modalities": {
-      "input": [
-        "text"
-      ],
-      "output": [
-        "text"
-      ]
-    },
-    "capabilities": [
-      "streaming",
-      "function_calling",
-      "structured_output"
-    ],
-    "pricing": {
-      "text_tokens": {
-        "standard": {
-          "input_per_million": 2.0,
-          "output_per_million": 6.0
-        }
-      }
-    },
-    "metadata": {
-      "description": "This is Mistral AI's flagship model, Mistral Large 2 (version `mistral-large-2407`). It's a proprietary weights-available model and excels at reasoning, code, JSON, chat, and more. Read the launch announcement [here](https://mistral.ai/news/mistral-large-2407/).\n\nIt supports dozens of languages including French, German, Spanish, Italian, Portuguese, Arabic, Hindi, Russian, Chinese, Japanese, and Korean, along with 80+ coding languages including Python, Java, C, C++, JavaScript, and Bash. Its long context window allows precise information recall from large documents.",
-      "architecture": {
-        "modality": "text->text",
-        "input_modalities": [
-          "text"
-        ],
-        "output_modalities": [
-          "text"
-        ],
-        "tokenizer": "Mistral",
-        "instruct_type": null
-      },
-      "top_provider": {
-        "context_length": 128000,
-        "max_completion_tokens": null,
-        "is_moderated": false
-      },
-      "per_request_limits": null,
-      "supported_parameters": [
-        "frequency_penalty",
-        "max_tokens",
-        "presence_penalty",
-        "response_format",
-        "seed",
-        "stop",
-        "structured_outputs",
-        "temperature",
-        "tool_choice",
-        "tools",
-        "top_p"
-      ]
-    }
-  },
-  {
-    "id": "mistralai/mistral-large-2407",
-    "name": "Mistral Large 2407",
-    "provider": "openrouter",
-    "family": "mistralai",
-    "created_at": "2024-11-19 02:06:55 +0100",
-    "context_window": 131072,
+    "created_at": "2024-11-19 02:06:55 +0100",
+    "context_window": 131072,
     "max_output_tokens": null,
     "knowledge_cutoff": null,
     "modalities": {
@@ -28136,7 +27646,7 @@
     "family": "mistralai",
     "created_at": "2024-07-19 02:00:00 +0200",
     "context_window": 131072,
-    "max_output_tokens": 16384,
+    "max_output_tokens": 131072,
     "knowledge_cutoff": null,
     "modalities": {
       "input": [
@@ -28174,14 +27684,13 @@
       },
       "top_provider": {
         "context_length": 131072,
-        "max_completion_tokens": 16384,
+        "max_completion_tokens": 131072,
         "is_moderated": false
       },
       "per_request_limits": null,
       "supported_parameters": [
         "frequency_penalty",
         "max_tokens",
-        "min_p",
         "presence_penalty",
         "repetition_penalty",
         "response_format",
@@ -29195,7 +28704,7 @@
     "id": "moonshotai/kimi-k2",
     "name": "Kimi K2",
     "provider": "openrouter",
-    "family": "kimi-k2",
+    "family": "kimi",
     "created_at": "2025-07-11 00:00:00 +0200",
     "context_window": 131072,
     "max_output_tokens": 32768,
@@ -29279,7 +28788,7 @@
     "id": "moonshotai/kimi-k2-0905",
     "name": "Kimi K2 Instruct 0905",
     "provider": "openrouter",
-    "family": "kimi-k2",
+    "family": "kimi",
     "created_at": "2025-09-05 00:00:00 +0200",
     "context_window": 262144,
     "max_output_tokens": 16384,
@@ -29365,7 +28874,7 @@
     "id": "moonshotai/kimi-k2-0905:exacto",
     "name": "Kimi K2 Instruct 0905 (exacto)",
     "provider": "openrouter",
-    "family": "kimi-k2",
+    "family": "kimi",
     "created_at": "2025-09-05 00:00:00 +0200",
     "context_window": 262144,
     "max_output_tokens": 16384,
@@ -29444,7 +28953,7 @@
     "id": "moonshotai/kimi-k2-thinking",
     "name": "Kimi K2 Thinking",
     "provider": "openrouter",
-    "family": "kimi-k2",
+    "family": "kimi-thinking",
     "created_at": "2025-11-06 00:00:00 +0100",
     "context_window": 262144,
     "max_output_tokens": 262144,
@@ -29538,7 +29047,7 @@
     "id": "moonshotai/kimi-k2:free",
     "name": "Kimi K2 (free)",
     "provider": "openrouter",
-    "family": "kimi-k2",
+    "family": "kimi",
     "created_at": "2025-07-11 00:00:00 +0200",
     "context_window": 32800,
     "max_output_tokens": 32800,
@@ -29900,7 +29409,7 @@
     "id": "nousresearch/deephermes-3-llama-3-8b-preview",
     "name": "DeepHermes 3 Llama 3 8B Preview",
     "provider": "openrouter",
-    "family": "llama-3",
+    "family": "llama",
     "created_at": "2025-02-28 00:00:00 +0100",
     "context_window": 131072,
     "max_output_tokens": 8192,
@@ -31061,70 +30570,6 @@
       ]
     }
   },
-  {
-    "id": "openai/codex-mini",
-    "name": "OpenAI: Codex Mini",
-    "provider": "openrouter",
-    "family": "openai",
-    "created_at": "2025-05-16 17:36:01 +0200",
-    "context_window": 200000,
-    "max_output_tokens": 100000,
-    "knowledge_cutoff": null,
-    "modalities": {
-      "input": [
-        "image",
-        "text"
-      ],
-      "output": [
-        "text"
-      ]
-    },
-    "capabilities": [
-      "streaming",
-      "function_calling",
-      "structured_output"
-    ],
-    "pricing": {
-      "text_tokens": {
-        "standard": {
-          "input_per_million": 1.5,
-          "output_per_million": 6.0,
-          "cached_input_per_million": 0.375
-        }
-      }
-    },
-    "metadata": {
-      "description": "codex-mini-latest is a fine-tuned version of o4-mini specifically for use in Codex CLI. For direct use in the API, we recommend starting with gpt-4.1.",
-      "architecture": {
-        "modality": "text+image->text",
-        "input_modalities": [
-          "image",
-          "text"
-        ],
-        "output_modalities": [
-          "text"
-        ],
-        "tokenizer": "GPT",
-        "instruct_type": null
-      },
-      "top_provider": {
-        "context_length": 200000,
-        "max_completion_tokens": 100000,
-        "is_moderated": true
-      },
-      "per_request_limits": null,
-      "supported_parameters": [
-        "include_reasoning",
-        "max_tokens",
-        "reasoning",
-        "response_format",
-        "seed",
-        "structured_outputs",
-        "tool_choice",
-        "tools"
-      ]
-    }
-  },
   {
     "id": "openai/gpt-3.5-turbo",
     "name": "OpenAI: GPT-3.5 Turbo",
@@ -31731,7 +31176,7 @@
     "id": "openai/gpt-4.1",
     "name": "GPT-4.1",
     "provider": "openrouter",
-    "family": "gpt-4.1",
+    "family": "gpt",
     "created_at": "2025-04-14 00:00:00 +0200",
     "context_window": 1047576,
     "max_output_tokens": 32768,
@@ -31813,7 +31258,7 @@
     "id": "openai/gpt-4.1-mini",
     "name": "GPT-4.1 Mini",
     "provider": "openrouter",
-    "family": "gpt-4.1-mini",
+    "family": "gpt-mini",
     "created_at": "2025-04-14 00:00:00 +0200",
     "context_window": 1047576,
     "max_output_tokens": 32768,
@@ -32321,7 +31766,7 @@
     "id": "openai/gpt-4o-mini",
     "name": "GPT-4o-mini",
     "provider": "openrouter",
-    "family": "gpt-4o-mini",
+    "family": "gpt-mini",
     "created_at": "2024-07-18 00:00:00 +0200",
     "context_window": 128000,
     "max_output_tokens": 16384,
@@ -32667,7 +32112,7 @@
     "id": "openai/gpt-5",
     "name": "GPT-5",
     "provider": "openrouter",
-    "family": "gpt-5",
+    "family": "gpt",
     "created_at": "2025-08-07 00:00:00 +0200",
     "context_window": 400000,
     "max_output_tokens": 128000,
@@ -32748,7 +32193,7 @@
     "id": "openai/gpt-5-chat",
     "name": "GPT-5 Chat (latest)",
     "provider": "openrouter",
-    "family": "gpt-5-chat",
+    "family": "gpt-codex",
     "created_at": "2025-08-07 00:00:00 +0200",
     "context_window": 400000,
     "max_output_tokens": 128000,
@@ -32824,7 +32269,7 @@
     "id": "openai/gpt-5-codex",
     "name": "GPT-5 Codex",
     "provider": "openrouter",
-    "family": "gpt-5-codex",
+    "family": "gpt-codex",
     "created_at": "2025-09-15 00:00:00 +0200",
     "context_window": 400000,
     "max_output_tokens": 128000,
@@ -32906,7 +32351,7 @@
     "id": "openai/gpt-5-image",
     "name": "GPT-5 Image",
     "provider": "openrouter",
-    "family": "gpt-5",
+    "family": "gpt",
     "created_at": "2025-10-14 00:00:00 +0200",
     "context_window": 400000,
     "max_output_tokens": 128000,
@@ -33076,7 +32521,7 @@
     "id": "openai/gpt-5-mini",
     "name": "GPT-5 Mini",
     "provider": "openrouter",
-    "family": "gpt-5-mini",
+    "family": "gpt-mini",
     "created_at": "2025-08-07 00:00:00 +0200",
     "context_window": 400000,
     "max_output_tokens": 128000,
@@ -33157,7 +32602,7 @@
     "id": "openai/gpt-5-nano",
     "name": "GPT-5 Nano",
     "provider": "openrouter",
-    "family": "gpt-5-nano",
+    "family": "gpt-nano",
     "created_at": "2025-08-07 00:00:00 +0200",
     "context_window": 400000,
     "max_output_tokens": 128000,
@@ -33238,7 +32683,7 @@
     "id": "openai/gpt-5-pro",
     "name": "GPT-5 Pro",
     "provider": "openrouter",
-    "family": "gpt-5-pro",
+    "family": "gpt-pro",
     "created_at": "2025-10-06 00:00:00 +0200",
     "context_window": 400000,
     "max_output_tokens": 272000,
@@ -33319,7 +32764,7 @@
     "id": "openai/gpt-5.1",
     "name": "GPT-5.1",
     "provider": "openrouter",
-    "family": "gpt-5",
+    "family": "gpt",
     "created_at": "2025-11-13 00:00:00 +0100",
     "context_window": 400000,
     "max_output_tokens": 128000,
@@ -33402,7 +32847,7 @@
     "id": "openai/gpt-5.1-chat",
     "name": "GPT-5.1 Chat",
     "provider": "openrouter",
-    "family": "gpt-5-chat",
+    "family": "gpt-codex",
     "created_at": "2025-11-13 00:00:00 +0100",
     "context_window": 128000,
     "max_output_tokens": 16384,
@@ -33483,7 +32928,7 @@
     "id": "openai/gpt-5.1-codex",
     "name": "GPT-5.1-Codex",
     "provider": "openrouter",
-    "family": "gpt-5-codex",
+    "family": "gpt-codex",
     "created_at": "2025-11-13 00:00:00 +0100",
     "context_window": 400000,
     "max_output_tokens": 128000,
@@ -33629,7 +33074,7 @@
     "id": "openai/gpt-5.1-codex-mini",
     "name": "GPT-5.1-Codex-Mini",
     "provider": "openrouter",
-    "family": "gpt-5-codex-mini",
+    "family": "gpt-codex",
     "created_at": "2025-11-13 00:00:00 +0100",
     "context_window": 400000,
     "max_output_tokens": 100000,
@@ -33711,7 +33156,7 @@
     "id": "openai/gpt-5.2",
     "name": "GPT-5.2",
     "provider": "openrouter",
-    "family": "gpt-5",
+    "family": "gpt",
     "created_at": "2025-12-11 00:00:00 +0100",
     "context_window": 400000,
     "max_output_tokens": 128000,
@@ -33858,7 +33303,7 @@
     "id": "openai/gpt-5.2-chat-latest",
     "name": "GPT-5.2 Chat",
     "provider": "openrouter",
-    "family": "gpt-5-chat",
+    "family": "gpt-codex",
     "created_at": "2025-12-11 00:00:00 +0100",
     "context_window": 128000,
     "max_output_tokens": 16384,
@@ -33906,11 +33351,99 @@
       "knowledge": "2025-08-31"
     }
   },
+  {
+    "id": "openai/gpt-5.2-codex",
+    "name": "GPT-5.2-Codex",
+    "provider": "openrouter",
+    "family": "gpt-codex",
+    "created_at": "2026-01-14 00:00:00 +0100",
+    "context_window": 400000,
+    "max_output_tokens": 128000,
+    "knowledge_cutoff": "2025-08-31",
+    "modalities": {
+      "input": [
+        "text",
+        "image"
+      ],
+      "output": [
+        "text"
+      ]
+    },
+    "capabilities": [
+      "function_calling",
+      "structured_output",
+      "reasoning",
+      "vision",
+      "streaming"
+    ],
+    "pricing": {
+      "text_tokens": {
+        "standard": {
+          "input_per_million": 1.75,
+          "output_per_million": 14,
+          "cached_input_per_million": 0.175
+        }
+      }
+    },
+    "metadata": {
+      "description": "GPT-5.2-Codex is an upgraded version of GPT-5.1-Codex optimized for software engineering and coding workflows. It is designed for both interactive development sessions and long, independent execution of complex engineering tasks. The model supports building projects from scratch, feature development, debugging, large-scale refactoring, and code review. Compared to GPT-5.1-Codex, 5.2-Codex is more steerable, adheres closely to developer instructions, and produces cleaner, higher-quality code outputs. Reasoning effort can be adjusted with the `reasoning.effort` parameter. Read the [docs here](https://openrouter.ai/docs/use-cases/reasoning-tokens#reasoning-effort-level)\n\nCodex integrates into developer environments including the CLI, IDE extensions, GitHub, and cloud tasks. It adapts reasoning effort dynamically—providing fast responses for small tasks while sustaining extended multi-hour runs for large projects. The model is trained to perform structured code reviews, catching critical flaws by reasoning over dependencies and validating behavior against tests. It also supports multimodal inputs such as images or screenshots for UI development and integrates tool use for search, dependency installation, and environment setup. Codex is intended specifically for agentic coding applications.",
+      "architecture": {
+        "modality": "text+image->text",
+        "input_modalities": [
+          "text",
+          "image"
+        ],
+        "output_modalities": [
+          "text"
+        ],
+        "tokenizer": "GPT",
+        "instruct_type": null
+      },
+      "top_provider": {
+        "context_length": 400000,
+        "max_completion_tokens": 128000,
+        "is_moderated": true
+      },
+      "per_request_limits": null,
+      "supported_parameters": [
+        "frequency_penalty",
+        "include_reasoning",
+        "logit_bias",
+        "logprobs",
+        "max_tokens",
+        "presence_penalty",
+        "reasoning",
+        "response_format",
+        "seed",
+        "stop",
+        "structured_outputs",
+        "tool_choice",
+        "tools",
+        "top_logprobs"
+      ],
+      "source": "models.dev",
+      "provider_id": "openrouter",
+      "open_weights": false,
+      "attachment": true,
+      "temperature": true,
+      "last_updated": "2026-01-14",
+      "cost": {
+        "input": 1.75,
+        "output": 14,
+        "cache_read": 0.175
+      },
+      "limit": {
+        "context": 400000,
+        "output": 128000
+      },
+      "knowledge": "2025-08-31"
+    }
+  },
   {
     "id": "openai/gpt-5.2-pro",
     "name": "GPT-5.2 Pro",
     "provider": "openrouter",
-    "family": "gpt-5-pro",
+    "family": "gpt-pro",
     "created_at": "2025-12-11 00:00:00 +0100",
     "context_window": 400000,
     "max_output_tokens": 128000,
@@ -34890,7 +34423,7 @@
     "id": "openai/o4-mini",
     "name": "o4 Mini",
     "provider": "openrouter",
-    "family": "o4-mini",
+    "family": "o-mini",
     "created_at": "2025-04-16 00:00:00 +0200",
     "context_window": 200000,
     "max_output_tokens": 100000,
@@ -35704,7 +35237,6 @@
         "include_reasoning",
         "logit_bias",
         "max_tokens",
-        "min_p",
         "presence_penalty",
         "reasoning",
         "repetition_penalty",
@@ -36622,7 +36154,7 @@
     "id": "qwen/qwen2.5-vl-32b-instruct:free",
     "name": "Qwen2.5 VL 32B Instruct (free)",
     "provider": "openrouter",
-    "family": "qwen2.5-vl",
+    "family": "qwen",
     "created_at": "2025-03-24 00:00:00 +0100",
     "context_window": 8192,
     "max_output_tokens": 8192,
@@ -36664,7 +36196,7 @@
     "id": "qwen/qwen2.5-vl-72b-instruct",
     "name": "Qwen2.5 VL 72B Instruct",
     "provider": "openrouter",
-    "family": "qwen2.5-vl",
+    "family": "qwen",
     "created_at": "2025-02-01 00:00:00 +0100",
     "context_window": 32768,
     "max_output_tokens": 8192,
@@ -36748,7 +36280,7 @@
     "id": "qwen/qwen2.5-vl-72b-instruct:free",
     "name": "Qwen2.5 VL 72B Instruct (free)",
     "provider": "openrouter",
-    "family": "qwen2.5-vl",
+    "family": "qwen",
     "created_at": "2025-02-01 00:00:00 +0100",
     "context_window": 32768,
     "max_output_tokens": 32768,
@@ -36858,7 +36390,7 @@
     "id": "qwen/qwen3-14b:free",
     "name": "Qwen3 14B (free)",
     "provider": "openrouter",
-    "family": "qwen3",
+    "family": "qwen",
     "created_at": "2025-04-28 00:00:00 +0200",
     "context_window": 40960,
     "max_output_tokens": 40960,
@@ -36901,7 +36433,7 @@
     "family": "qwen",
     "created_at": "2025-04-28 23:29:17 +0200",
     "context_window": 40960,
-    "max_output_tokens": 40960,
+    "max_output_tokens": null,
     "knowledge_cutoff": null,
     "modalities": {
       "input": [
@@ -36920,8 +36452,8 @@
     "pricing": {
       "text_tokens": {
         "standard": {
-          "input_per_million": 0.18,
-          "output_per_million": 0.54
+          "input_per_million": 0.19999999999999998,
+          "output_per_million": 0.6
         }
       }
     },
@@ -36940,7 +36472,7 @@
       },
       "top_provider": {
         "context_length": 40960,
-        "max_completion_tokens": 40960,
+        "max_completion_tokens": null,
         "is_moderated": false
       },
       "per_request_limits": null,
@@ -36971,7 +36503,7 @@
     "id": "qwen/qwen3-235b-a22b-07-25",
     "name": "Qwen3 235B A22B Instruct 2507",
     "provider": "openrouter",
-    "family": "qwen3",
+    "family": "qwen",
     "created_at": "2025-04-28 00:00:00 +0200",
     "context_window": 262144,
     "max_output_tokens": 131072,
@@ -37017,7 +36549,7 @@
     "id": "qwen/qwen3-235b-a22b-07-25:free",
     "name": "Qwen3 235B A22B Instruct 2507 (free)",
     "provider": "openrouter",
-    "family": "qwen3",
+    "family": "qwen",
     "created_at": "2025-04-28 00:00:00 +0200",
     "context_window": 262144,
     "max_output_tokens": 131072,
@@ -37130,7 +36662,7 @@
     "id": "qwen/qwen3-235b-a22b-thinking-2507",
     "name": "Qwen3 235B A22B Thinking 2507",
     "provider": "openrouter",
-    "family": "qwen3",
+    "family": "qwen",
     "created_at": "2025-07-25 00:00:00 +0200",
     "context_window": 262144,
     "max_output_tokens": 81920,
@@ -37217,7 +36749,7 @@
     "id": "qwen/qwen3-235b-a22b:free",
     "name": "Qwen3 235B A22B (free)",
     "provider": "openrouter",
-    "family": "qwen3",
+    "family": "qwen",
     "created_at": "2025-04-28 00:00:00 +0200",
     "context_window": 131072,
     "max_output_tokens": 131072,
@@ -37273,7 +36805,8 @@
     "capabilities": [
       "streaming",
       "function_calling",
-      "structured_output"
+      "structured_output",
+      "predicted_outputs"
     ],
     "pricing": {
       "text_tokens": {
@@ -37305,6 +36838,8 @@
       "supported_parameters": [
         "frequency_penalty",
         "include_reasoning",
+        "logit_bias",
+        "logprobs",
         "max_tokens",
         "min_p",
         "presence_penalty",
@@ -37318,6 +36853,7 @@
         "tool_choice",
         "tools",
         "top_k",
+        "top_logprobs",
         "top_p"
       ]
     }
@@ -37326,7 +36862,7 @@
     "id": "qwen/qwen3-30b-a3b-instruct-2507",
     "name": "Qwen3 30B A3B Instruct 2507",
     "provider": "openrouter",
-    "family": "qwen3",
+    "family": "qwen",
     "created_at": "2025-07-29 00:00:00 +0200",
     "context_window": 262000,
     "max_output_tokens": 262000,
@@ -37407,7 +36943,7 @@
     "id": "qwen/qwen3-30b-a3b-thinking-2507",
     "name": "Qwen3 30B A3B Thinking 2507",
     "provider": "openrouter",
-    "family": "qwen3",
+    "family": "qwen",
     "created_at": "2025-07-29 00:00:00 +0200",
     "context_window": 262000,
     "max_output_tokens": 262000,
@@ -37490,7 +37026,7 @@
     "id": "qwen/qwen3-30b-a3b:free",
     "name": "Qwen3 30B A3B (free)",
     "provider": "openrouter",
-    "family": "qwen3",
+    "family": "qwen",
     "created_at": "2025-04-28 00:00:00 +0200",
     "context_window": 40960,
     "max_output_tokens": 40960,
@@ -37601,7 +37137,7 @@
     "id": "qwen/qwen3-32b:free",
     "name": "Qwen3 32B (free)",
     "provider": "openrouter",
-    "family": "qwen3",
+    "family": "qwen",
     "created_at": "2025-04-28 00:00:00 +0200",
     "context_window": 40960,
     "max_output_tokens": 40960,
@@ -37702,8 +37238,8 @@
     "provider": "openrouter",
     "family": "qwen",
     "created_at": "2025-04-28 23:43:52 +0200",
-    "context_window": 128000,
-    "max_output_tokens": 20000,
+    "context_window": 32000,
+    "max_output_tokens": 8192,
     "knowledge_cutoff": null,
     "modalities": {
       "input": [
@@ -37722,8 +37258,8 @@
     "pricing": {
       "text_tokens": {
         "standard": {
-          "input_per_million": 0.035,
-          "output_per_million": 0.13799999999999998
+          "input_per_million": 0.049999999999999996,
+          "output_per_million": 0.25
         }
       }
     },
@@ -37741,8 +37277,8 @@
         "instruct_type": "qwen3"
       },
       "top_provider": {
-        "context_length": 128000,
-        "max_completion_tokens": 20000,
+        "context_length": 32000,
+        "max_completion_tokens": 8192,
         "is_moderated": false
       },
       "per_request_limits": null,
@@ -37756,7 +37292,6 @@
         "reasoning",
         "repetition_penalty",
         "response_format",
-        "seed",
         "stop",
         "structured_outputs",
         "temperature",
@@ -37772,7 +37307,7 @@
     "id": "qwen/qwen3-8b:free",
     "name": "Qwen3 8B (free)",
     "provider": "openrouter",
-    "family": "qwen3",
+    "family": "qwen",
     "created_at": "2025-04-28 00:00:00 +0200",
     "context_window": 40960,
     "max_output_tokens": 40960,
@@ -37812,7 +37347,7 @@
     "id": "qwen/qwen3-coder",
     "name": "Qwen3 Coder",
     "provider": "openrouter",
-    "family": "qwen3-coder",
+    "family": "qwen",
     "created_at": "2025-07-23 00:00:00 +0200",
     "context_window": 262144,
     "max_output_tokens": 66536,
@@ -37899,7 +37434,7 @@
     "id": "qwen/qwen3-coder-30b-a3b-instruct",
     "name": "Qwen3 Coder 30B A3B Instruct",
     "provider": "openrouter",
-    "family": "qwen3-coder",
+    "family": "qwen",
     "created_at": "2025-07-31 00:00:00 +0200",
     "context_window": 160000,
     "max_output_tokens": 65536,
@@ -37980,7 +37515,7 @@
     "id": "qwen/qwen3-coder-flash",
     "name": "Qwen3 Coder Flash",
     "provider": "openrouter",
-    "family": "qwen3-coder",
+    "family": "qwen",
     "created_at": "2025-07-23 00:00:00 +0200",
     "context_window": 128000,
     "max_output_tokens": 66536,
@@ -38119,7 +37654,7 @@
     "id": "qwen/qwen3-coder:exacto",
     "name": "Qwen3 Coder (exacto)",
     "provider": "openrouter",
-    "family": "qwen3-coder",
+    "family": "qwen",
     "created_at": "2025-07-23 00:00:00 +0200",
     "context_window": 131072,
     "max_output_tokens": 32768,
@@ -38201,7 +37736,7 @@
     "id": "qwen/qwen3-coder:free",
     "name": "Qwen3 Coder 480B A35B Instruct (free)",
     "provider": "openrouter",
-    "family": "qwen3-coder",
+    "family": "qwen",
     "created_at": "2025-07-23 00:00:00 +0200",
     "context_window": 262144,
     "max_output_tokens": 66536,
@@ -38271,7 +37806,7 @@
     "id": "qwen/qwen3-max",
     "name": "Qwen3 Max",
     "provider": "openrouter",
-    "family": "qwen3",
+    "family": "qwen",
     "created_at": "2025-09-05 00:00:00 +0200",
     "context_window": 262144,
     "max_output_tokens": 32768,
@@ -38347,7 +37882,7 @@
     "id": "qwen/qwen3-next-80b-a3b-instruct",
     "name": "Qwen3 Next 80B A3B Instruct",
     "provider": "openrouter",
-    "family": "qwen3",
+    "family": "qwen",
     "created_at": "2025-09-11 00:00:00 +0200",
     "context_window": 262144,
     "max_output_tokens": 262144,
@@ -38427,11 +37962,68 @@
       "knowledge": "2025-04"
     }
   },
+  {
+    "id": "qwen/qwen3-next-80b-a3b-instruct:free",
+    "name": "Qwen: Qwen3 Next 80B A3B Instruct (free)",
+    "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"
+    ],
+    "pricing": {},
+    "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",
+        "max_tokens",
+        "presence_penalty",
+        "response_format",
+        "stop",
+        "structured_outputs",
+        "temperature",
+        "tool_choice",
+        "tools",
+        "top_k",
+        "top_p"
+      ]
+    }
+  },
   {
     "id": "qwen/qwen3-next-80b-a3b-thinking",
     "name": "Qwen3 Next 80B A3B Thinking",
     "provider": "openrouter",
-    "family": "qwen3",
+    "family": "qwen",
     "created_at": "2025-09-11 00:00:00 +0200",
     "context_window": 262144,
     "max_output_tokens": 262144,
@@ -39079,7 +38671,7 @@
     "id": "qwen/qwq-32b:free",
     "name": "QwQ 32B (free)",
     "provider": "openrouter",
-    "family": "qwq",
+    "family": "qwen",
     "created_at": "2025-03-05 00:00:00 +0100",
     "context_window": 32768,
     "max_output_tokens": 32768,
@@ -39182,7 +38774,7 @@
     "id": "rekaai/reka-flash-3",
     "name": "Reka Flash 3",
     "provider": "openrouter",
-    "family": "reka-flash",
+    "family": "reka",
     "created_at": "2025-03-12 00:00:00 +0100",
     "context_window": 32768,
     "max_output_tokens": 8192,
@@ -39656,7 +39248,7 @@
     "id": "sarvamai/sarvam-m:free",
     "name": "Sarvam-M (free)",
     "provider": "openrouter",
-    "family": "sarvam-m",
+    "family": "sarvam",
     "created_at": "2025-05-25 00:00:00 +0200",
     "context_window": 32768,
     "max_output_tokens": 32768,
@@ -39929,7 +39521,6 @@
         "frequency_penalty",
         "logit_bias",
         "max_tokens",
-        "min_p",
         "presence_penalty",
         "repetition_penalty",
         "response_format",
@@ -40063,7 +39654,6 @@
         "frequency_penalty",
         "logit_bias",
         "max_tokens",
-        "min_p",
         "presence_penalty",
         "repetition_penalty",
         "seed",
@@ -40137,75 +39727,11 @@
       ]
     }
   },
-  {
-    "id": "thudm/glm-4.1v-9b-thinking",
-    "name": "THUDM: GLM 4.1V 9B Thinking",
-    "provider": "openrouter",
-    "family": "thudm",
-    "created_at": "2025-07-11 16:33:05 +0200",
-    "context_window": 65536,
-    "max_output_tokens": 8000,
-    "knowledge_cutoff": null,
-    "modalities": {
-      "input": [
-        "image",
-        "text"
-      ],
-      "output": [
-        "text"
-      ]
-    },
-    "capabilities": [
-      "streaming"
-    ],
-    "pricing": {
-      "text_tokens": {
-        "standard": {
-          "input_per_million": 0.035,
-          "output_per_million": 0.13799999999999998
-        }
-      }
-    },
-    "metadata": {
-      "description": "GLM-4.1V-9B-Thinking is a 9B parameter vision-language model developed by THUDM, based on the GLM-4-9B foundation. It introduces a reasoning-centric \"thinking paradigm\" enhanced with reinforcement learning to improve multimodal reasoning, long-context understanding (up to 64K tokens), and complex problem solving. It achieves state-of-the-art performance among models in its class, outperforming even larger models like Qwen-2.5-VL-72B on a majority of benchmark tasks. ",
-      "architecture": {
-        "modality": "text+image->text",
-        "input_modalities": [
-          "image",
-          "text"
-        ],
-        "output_modalities": [
-          "text"
-        ],
-        "tokenizer": "Other",
-        "instruct_type": null
-      },
-      "top_provider": {
-        "context_length": 65536,
-        "max_completion_tokens": 8000,
-        "is_moderated": false
-      },
-      "per_request_limits": null,
-      "supported_parameters": [
-        "frequency_penalty",
-        "include_reasoning",
-        "max_tokens",
-        "presence_penalty",
-        "reasoning",
-        "repetition_penalty",
-        "seed",
-        "stop",
-        "temperature",
-        "top_k",
-        "top_p"
-      ]
-    }
-  },
   {
     "id": "thudm/glm-z1-32b:free",
     "name": "GLM Z1 32B (free)",
     "provider": "openrouter",
-    "family": "glm-z1",
+    "family": "glm-z",
     "created_at": "2025-04-17 00:00:00 +0200",
     "context_window": 32768,
     "max_output_tokens": 32768,
@@ -40433,7 +39959,7 @@
     "id": "tngtech/deepseek-r1t2-chimera:free",
     "name": "DeepSeek R1T2 Chimera (free)",
     "provider": "openrouter",
-    "family": "deepseek-r1",
+    "family": "deepseek-thinking",
     "created_at": "2025-07-08 00:00:00 +0200",
     "context_window": 163840,
     "max_output_tokens": 163840,
@@ -40702,7 +40228,7 @@
     "id": "x-ai/grok-3",
     "name": "Grok 3",
     "provider": "openrouter",
-    "family": "grok-3",
+    "family": "grok",
     "created_at": "2025-02-17 00:00:00 +0100",
     "context_window": 131072,
     "max_output_tokens": 8192,
@@ -40786,7 +40312,7 @@
     "id": "x-ai/grok-3-beta",
     "name": "Grok 3 Beta",
     "provider": "openrouter",
-    "family": "grok-3",
+    "family": "grok",
     "created_at": "2025-02-17 00:00:00 +0100",
     "context_window": 131072,
     "max_output_tokens": 8192,
@@ -40869,7 +40395,7 @@
     "id": "x-ai/grok-3-mini",
     "name": "Grok 3 Mini",
     "provider": "openrouter",
-    "family": "grok-3",
+    "family": "grok",
     "created_at": "2025-02-17 00:00:00 +0100",
     "context_window": 131072,
     "max_output_tokens": 8192,
@@ -40954,7 +40480,7 @@
     "id": "x-ai/grok-3-mini-beta",
     "name": "Grok 3 Mini Beta",
     "provider": "openrouter",
-    "family": "grok-3",
+    "family": "grok",
     "created_at": "2025-02-17 00:00:00 +0100",
     "context_window": 131072,
     "max_output_tokens": 8192,
@@ -41038,7 +40564,7 @@
     "id": "x-ai/grok-4",
     "name": "Grok 4",
     "provider": "openrouter",
-    "family": "grok-4",
+    "family": "grok",
     "created_at": "2025-07-09 00:00:00 +0200",
     "context_window": 256000,
     "max_output_tokens": 64000,
@@ -41123,7 +40649,7 @@
     "id": "x-ai/grok-4-fast",
     "name": "Grok 4 Fast",
     "provider": "openrouter",
-    "family": "grok-4",
+    "family": "grok",
     "created_at": "2025-08-19 00:00:00 +0200",
     "context_window": 2000000,
     "max_output_tokens": 30000,
@@ -41210,7 +40736,7 @@
     "id": "x-ai/grok-4.1-fast",
     "name": "Grok 4.1 Fast",
     "provider": "openrouter",
-    "family": "grok-4",
+    "family": "grok",
     "created_at": "2025-11-19 00:00:00 +0100",
     "context_window": 2000000,
     "max_output_tokens": 30000,
@@ -41377,6 +40903,75 @@
       "knowledge": "2025-08"
     }
   },
+  {
+    "id": "xiaomi/mimo-v2-flash",
+    "name": "Xiaomi: MiMo-V2-Flash",
+    "provider": "openrouter",
+    "family": "xiaomi",
+    "created_at": "2025-12-14 17:55:08 +0100",
+    "context_window": 262144,
+    "max_output_tokens": 32000,
+    "knowledge_cutoff": null,
+    "modalities": {
+      "input": [
+        "text"
+      ],
+      "output": [
+        "text"
+      ]
+    },
+    "capabilities": [
+      "streaming",
+      "function_calling",
+      "structured_output"
+    ],
+    "pricing": {
+      "text_tokens": {
+        "standard": {
+          "input_per_million": 0.09999999999999999,
+          "output_per_million": 0.3,
+          "cached_input_per_million": 0.02
+        }
+      }
+    },
+    "metadata": {
+      "description": "MiMo-V2-Flash is an open-source foundation language model developed by Xiaomi. It is a Mixture-of-Experts model with 309B total parameters and 15B active parameters, adopting hybrid attention architecture. MiMo-V2-Flash supports a hybrid-thinking toggle and a 256K context window, and excels at reasoning, coding, and agent scenarios. On SWE-bench Verified and SWE-bench Multilingual, MiMo-V2-Flash ranks as the top #1 open-source model globally, delivering performance comparable to Claude Sonnet 4.5 while costing only about 3.5% as much.\n\nNote: when integrating with agentic tools such as Claude Code, Cline, or Roo Code, **turn off reasoning mode** for the best and fastest performance—this model is deeply optimized for this scenario.\n\nUsers can control the reasoning behaviour with 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->text",
+        "input_modalities": [
+          "text"
+        ],
+        "output_modalities": [
+          "text"
+        ],
+        "tokenizer": "Other",
+        "instruct_type": null
+      },
+      "top_provider": {
+        "context_length": 262144,
+        "max_completion_tokens": 32000,
+        "is_moderated": false
+      },
+      "per_request_limits": null,
+      "supported_parameters": [
+        "frequency_penalty",
+        "include_reasoning",
+        "max_tokens",
+        "presence_penalty",
+        "reasoning",
+        "repetition_penalty",
+        "response_format",
+        "seed",
+        "stop",
+        "structured_outputs",
+        "temperature",
+        "tool_choice",
+        "tools",
+        "top_k",
+        "top_p"
+      ]
+    }
+  },
   {
     "id": "xiaomi/mimo-v2-flash:free",
     "name": "Xiaomi: MiMo-V2-Flash (free)",
@@ -41495,7 +41090,7 @@
     "id": "z-ai/glm-4.5",
     "name": "GLM 4.5",
     "provider": "openrouter",
-    "family": "glm-4.5",
+    "family": "glm",
     "created_at": "2025-07-28 00:00:00 +0200",
     "context_window": 128000,
     "max_output_tokens": 96000,
@@ -41545,7 +41140,6 @@
         "frequency_penalty",
         "include_reasoning",
         "max_tokens",
-        "min_p",
         "presence_penalty",
         "reasoning",
         "repetition_penalty",
@@ -41580,7 +41174,7 @@
     "id": "z-ai/glm-4.5-air",
     "name": "GLM 4.5 Air",
     "provider": "openrouter",
-    "family": "glm-4.5-air",
+    "family": "glm-air",
     "created_at": "2025-07-28 00:00:00 +0200",
     "context_window": 128000,
     "max_output_tokens": 96000,
@@ -41664,7 +41258,7 @@
     "id": "z-ai/glm-4.5-air:free",
     "name": "GLM 4.5 Air (free)",
     "provider": "openrouter",
-    "family": "glm-4.5-air",
+    "family": "glm-air",
     "created_at": "2025-07-28 00:00:00 +0200",
     "context_window": 128000,
     "max_output_tokens": 96000,
@@ -41732,7 +41326,7 @@
     "id": "z-ai/glm-4.5v",
     "name": "GLM 4.5V",
     "provider": "openrouter",
-    "family": "glm-4.5v",
+    "family": "glm",
     "created_at": "2025-08-11 00:00:00 +0200",
     "context_window": 64000,
     "max_output_tokens": 16384,
@@ -41820,7 +41414,7 @@
     "id": "z-ai/glm-4.6",
     "name": "GLM 4.6",
     "provider": "openrouter",
-    "family": "glm-4.6",
+    "family": "glm",
     "created_at": "2025-09-30 00:00:00 +0200",
     "context_window": 200000,
     "max_output_tokens": 128000,
@@ -41912,7 +41506,7 @@
     "id": "z-ai/glm-4.6:exacto",
     "name": "GLM 4.6 (exacto)",
     "provider": "openrouter",
-    "family": "glm-4.6",
+    "family": "glm",
     "created_at": "2025-09-30 00:00:00 +0200",
     "context_window": 200000,
     "max_output_tokens": 128000,
@@ -42073,7 +41667,7 @@
     "id": "z-ai/glm-4.7",
     "name": "GLM-4.7",
     "provider": "openrouter",
-    "family": "glm-4.7",
+    "family": "glm",
     "created_at": "2025-12-22 00:00:00 +0100",
     "context_window": 204800,
     "max_output_tokens": 131072,
@@ -42217,7 +41811,7 @@
     "name": "Sonar Deep Research",
     "provider": "perplexity",
     "family": "sonar_deep_research",
-    "created_at": "2026-01-13 19:17:42 +0100",
+    "created_at": "2026-01-16 16:37:16 +0100",
     "context_window": 128000,
     "max_output_tokens": 4096,
     "knowledge_cutoff": null,
@@ -42301,7 +41895,7 @@
     "name": "Sonar Reasoning",
     "provider": "perplexity",
     "family": "sonar_reasoning",
-    "created_at": "2026-01-13 19:17:42 +0100",
+    "created_at": "2026-01-16 16:37:16 +0100",
     "context_window": 128000,
     "max_output_tokens": 4096,
     "knowledge_cutoff": null,
@@ -44083,5 +43677,326 @@
     "metadata": {
       "source": "known_models"
     }
+  },
+  {
+    "id": "grok-2-1212",
+    "name": "Grok 2 1212",
+    "provider": "xai",
+    "family": "grok",
+    "created_at": "2025-01-20 01:00:00 +0100",
+    "context_window": null,
+    "max_output_tokens": null,
+    "knowledge_cutoff": null,
+    "modalities": {
+      "input": [
+        "text"
+      ],
+      "output": [
+        "text"
+      ]
+    },
+    "capabilities": [
+      "streaming",
+      "function_calling",
+      "structured_output"
+    ],
+    "pricing": {},
+    "metadata": {
+      "object": "model",
+      "owned_by": "xai"
+    }
+  },
+  {
+    "id": "grok-2-image-1212",
+    "name": "Grok 2 Image 1212",
+    "provider": "xai",
+    "family": "grok",
+    "created_at": "2025-01-13 01:00:00 +0100",
+    "context_window": null,
+    "max_output_tokens": null,
+    "knowledge_cutoff": null,
+    "modalities": {
+      "input": [
+        "text"
+      ],
+      "output": [
+        "image"
+      ]
+    },
+    "capabilities": [],
+    "pricing": {},
+    "metadata": {
+      "object": "model",
+      "owned_by": "xai"
+    }
+  },
+  {
+    "id": "grok-2-vision-1212",
+    "name": "Grok 2 Vision 1212",
+    "provider": "xai",
+    "family": "grok",
+    "created_at": "2024-12-12 01:00:00 +0100",
+    "context_window": null,
+    "max_output_tokens": null,
+    "knowledge_cutoff": null,
+    "modalities": {
+      "input": [
+        "text",
+        "image"
+      ],
+      "output": [
+        "text"
+      ]
+    },
+    "capabilities": [
+      "streaming",
+      "function_calling",
+      "structured_output",
+      "vision"
+    ],
+    "pricing": {},
+    "metadata": {
+      "object": "model",
+      "owned_by": "xai"
+    }
+  },
+  {
+    "id": "grok-3",
+    "name": "Grok 3",
+    "provider": "xai",
+    "family": "grok",
+    "created_at": "2025-04-04 02:00:00 +0200",
+    "context_window": null,
+    "max_output_tokens": null,
+    "knowledge_cutoff": null,
+    "modalities": {
+      "input": [
+        "text"
+      ],
+      "output": [
+        "text"
+      ]
+    },
+    "capabilities": [
+      "streaming",
+      "function_calling",
+      "structured_output"
+    ],
+    "pricing": {},
+    "metadata": {
+      "object": "model",
+      "owned_by": "xai"
+    }
+  },
+  {
+    "id": "grok-3-mini",
+    "name": "Grok 3 Mini",
+    "provider": "xai",
+    "family": "grok",
+    "created_at": "2025-04-04 02:00:00 +0200",
+    "context_window": null,
+    "max_output_tokens": null,
+    "knowledge_cutoff": null,
+    "modalities": {
+      "input": [
+        "text"
+      ],
+      "output": [
+        "text"
+      ]
+    },
+    "capabilities": [
+      "streaming",
+      "function_calling",
+      "structured_output",
+      "reasoning"
+    ],
+    "pricing": {},
+    "metadata": {
+      "object": "model",
+      "owned_by": "xai"
+    }
+  },
+  {
+    "id": "grok-4-0709",
+    "name": "Grok 4 0709",
+    "provider": "xai",
+    "family": "grok",
+    "created_at": "2025-07-09 02:00:00 +0200",
+    "context_window": null,
+    "max_output_tokens": null,
+    "knowledge_cutoff": null,
+    "modalities": {
+      "input": [
+        "text",
+        "image"
+      ],
+      "output": [
+        "text"
+      ]
+    },
+    "capabilities": [
+      "streaming",
+      "function_calling",
+      "structured_output",
+      "reasoning",
+      "vision"
+    ],
+    "pricing": {},
+    "metadata": {
+      "object": "model",
+      "owned_by": "xai"
+    }
+  },
+  {
+    "id": "grok-4-1-fast-non-reasoning",
+    "name": "Grok 4 1 Fast Non Reasoning",
+    "provider": "xai",
+    "family": "grok",
+    "created_at": "2025-11-19 01:00:00 +0100",
+    "context_window": null,
+    "max_output_tokens": null,
+    "knowledge_cutoff": null,
+    "modalities": {
+      "input": [
+        "text",
+        "image"
+      ],
+      "output": [
+        "text"
+      ]
+    },
+    "capabilities": [
+      "streaming",
+      "function_calling",
+      "structured_output",
+      "vision"
+    ],
+    "pricing": {},
+    "metadata": {
+      "object": "model",
+      "owned_by": "xai"
+    }
+  },
+  {
+    "id": "grok-4-1-fast-reasoning",
+    "name": "Grok 4 1 Fast Reasoning",
+    "provider": "xai",
+    "family": "grok",
+    "created_at": "2025-11-19 01:00:00 +0100",
+    "context_window": null,
+    "max_output_tokens": null,
+    "knowledge_cutoff": null,
+    "modalities": {
+      "input": [
+        "text",
+        "image"
+      ],
+      "output": [
+        "text"
+      ]
+    },
+    "capabilities": [
+      "streaming",
+      "function_calling",
+      "structured_output",
+      "reasoning",
+      "vision"
+    ],
+    "pricing": {},
+    "metadata": {
+      "object": "model",
+      "owned_by": "xai"
+    }
+  },
+  {
+    "id": "grok-4-fast-non-reasoning",
+    "name": "Grok 4 Fast Non Reasoning",
+    "provider": "xai",
+    "family": "grok",
+    "created_at": "2025-09-04 02:00:00 +0200",
+    "context_window": null,
+    "max_output_tokens": null,
+    "knowledge_cutoff": null,
+    "modalities": {
+      "input": [
+        "text",
+        "image"
+      ],
+      "output": [
+        "text"
+      ]
+    },
+    "capabilities": [
+      "streaming",
+      "function_calling",
+      "structured_output",
+      "vision"
+    ],
+    "pricing": {},
+    "metadata": {
+      "object": "model",
+      "owned_by": "xai"
+    }
+  },
+  {
+    "id": "grok-4-fast-reasoning",
+    "name": "Grok 4 Fast Reasoning",
+    "provider": "xai",
+    "family": "grok",
+    "created_at": "2025-09-04 02:00:00 +0200",
+    "context_window": null,
+    "max_output_tokens": null,
+    "knowledge_cutoff": null,
+    "modalities": {
+      "input": [
+        "text",
+        "image"
+      ],
+      "output": [
+        "text"
+      ]
+    },
+    "capabilities": [
+      "streaming",
+      "function_calling",
+      "structured_output",
+      "reasoning",
+      "vision"
+    ],
+    "pricing": {},
+    "metadata": {
+      "object": "model",
+      "owned_by": "xai"
+    }
+  },
+  {
+    "id": "grok-code-fast-1",
+    "name": "Grok Code Fast 1",
+    "provider": "xai",
+    "family": "grok",
+    "created_at": "2025-08-24 02:00:00 +0200",
+    "context_window": null,
+    "max_output_tokens": null,
+    "knowledge_cutoff": null,
+    "modalities": {
+      "input": [
+        "text"
+      ],
+      "output": [
+        "text"
+      ]
+    },
+    "capabilities": [
+      "streaming",
+      "function_calling",
+      "structured_output",
+      "reasoning"
+    ],
+    "pricing": {},
+    "metadata": {
+      "object": "model",
+      "owned_by": "xai"
+    }
   }
 ]