RubyGems - llm.rb - Versions diffs - 15.3.0 → 15.4.1 - Mend

llm.rb 15.3.0 → 15.4.1

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 (76) hide show

checksums.yaml +4 -4
data/CHANGELOG.md +148 -3
data/README.md +185 -71
data/bin/llm.rb +9 -2
data/data/alibaba.json +47 -2
data/data/anthropic.json +67 -0
data/data/bedrock.json +1828 -425
data/data/deepinfra.json +148 -16
data/data/deepseek.json +7 -4
data/data/google.json +3 -3
data/data/mistral.json +42 -0
data/data/moonshot.json +1 -1
data/data/openai.json +186 -0
data/data/openrouter.json +1783 -440
data/data/xai.json +53 -20
data/data/zai.json +90 -4
data/docs/deepdive/advanced/compaction.md +1 -2
data/docs/deepdive/advanced/context.md +214 -1
data/docs/deepdive/advanced/guard.md +9 -57
data/docs/deepdive/features/builtin_tools.md +14 -16
data/docs/deepdive/features/console.md +5 -0
data/docs/deepdive/features/database.md +85 -10
data/docs/deepdive/fundamentals/agents.md +7 -8
data/docs/deepdive/fundamentals/providers.md +45 -5
data/docs/deepdive/fundamentals/schema.md +73 -0
data/docs/deepdive/fundamentals/tools.md +80 -27
data/docs/deepdive/media/audio.md +8 -19
data/docs/deepdive/media/images.md +8 -10
data/docs/deepdive/media/ocr.md +1 -3
data/docs/deepdive/reference/cost.md +48 -0
data/docs/deepdive/reference/tracer.md +76 -0
data/docs/deepdive.md +1 -1
data/lib/llm/active_record/message.rb +113 -0
data/lib/llm/active_record.rb +1 -0
data/lib/llm/agent.rb +28 -19
data/lib/llm/console/buffer.rb +9 -1
data/lib/llm/console.rb +6 -1
data/lib/llm/context/deserializer.rb +6 -1
data/lib/llm/context.rb +8 -4
data/lib/llm/guard.rb +2 -8
data/lib/llm/provider.rb +16 -0
data/lib/llm/providers/alibaba.rb +15 -0
data/lib/llm/providers/anthropic/error_handler.rb +5 -2
data/lib/llm/providers/anthropic/files.rb +12 -12
data/lib/llm/providers/anthropic/models.rb +2 -2
data/lib/llm/providers/anthropic.rb +2 -2
data/lib/llm/providers/bedrock/error_handler.rb +3 -2
data/lib/llm/providers/bedrock/models.rb +5 -3
data/lib/llm/providers/bedrock.rb +2 -2
data/lib/llm/providers/deepinfra/audio.rb +4 -4
data/lib/llm/providers/deepinfra/images.rb +4 -4
data/lib/llm/providers/google/error_handler.rb +5 -2
data/lib/llm/providers/google/files.rb +10 -10
data/lib/llm/providers/google/images.rb +2 -2
data/lib/llm/providers/google/models.rb +2 -2
data/lib/llm/providers/google.rb +4 -4
data/lib/llm/providers/ollama/error_handler.rb +5 -2
data/lib/llm/providers/ollama/models.rb +2 -2
data/lib/llm/providers/ollama.rb +4 -4
data/lib/llm/providers/openai/audio.rb +6 -6
data/lib/llm/providers/openai/error_handler.rb +5 -2
data/lib/llm/providers/openai/files.rb +10 -10
data/lib/llm/providers/openai/images.rb +4 -4
data/lib/llm/providers/openai/models.rb +2 -2
data/lib/llm/providers/openai/moderations.rb +2 -2
data/lib/llm/providers/openai/responses.rb +6 -6
data/lib/llm/providers/openai/vector_stores.rb +22 -22
data/lib/llm/providers/openai.rb +4 -4
data/lib/llm/providers/xai/images.rb +4 -4
data/lib/llm/tracer/telemetry.rb +4 -4
data/lib/llm/tracer.rb +11 -3
data/lib/llm/transport/execution.rb +8 -4
data/lib/llm/version.rb +1 -1
data/llm.gemspec +0 -6
metadata +3 -5
data/lib/llm/guard/loop.rb +0 -89

data/data/openrouter.json CHANGED Viewed

@@ -194,7 +194,7 @@
       "open_weights": true,
       "limit": {
         "context": 262144,
-        "output": 235929
+        "output": 32768
       },
       "cost": {
         "input": 0.1,
@@ -316,11 +316,11 @@
       "open_weights": true,
       "limit": {
         "context": 131072,
-        "output": 8192
+        "output": 16384
       },
       "cost": {
-        "input": 0.2275,
-        "output": 0.91
+        "input": 0.12,
+        "output": 0.24
       }
     },
     "qwen/qwen3.6-plus": {
@@ -838,11 +838,12 @@
       "open_weights": true,
       "limit": {
         "context": 262144,
-        "output": 16384
+        "output": 235929
       },
       "cost": {
-        "input": 0.22,
-        "output": 0.88
+        "input": 0.0875,
+        "output": 0.35,
+        "cache_read": 0.0175
       }
     },
     "qwen/qwen3.5-flash-02-23": {
@@ -982,12 +983,12 @@
       "open_weights": true,
       "limit": {
         "context": 262144,
-        "output": 65536
+        "output": 262140
       },
       "cost": {
-        "input": 0.3,
-        "output": 2,
-        "cache_read": 0.03
+        "input": 0.32,
+        "output": 2.7,
+        "cache_read": 0.15
       }
     },
     "qwen/qwen3.7-flash": {
@@ -1087,6 +1088,48 @@
         "output": 2.4
       }
     },
+    "qwen/qwen3.8-omni-flash": {
+      "id": "qwen/qwen3.8-omni-flash",
+      "name": "Qwen3.8 Omni Flash",
+      "description": "Qwen omni model for text, vision, audio, and multimodal agent tasks",
+      "family": "qwen",
+      "attachment": true,
+      "reasoning": true,
+      "reasoning_options": [
+        {
+          "type": "toggle"
+        },
+        {
+          "type": "budget_tokens"
+        }
+      ],
+      "tool_call": true,
+      "structured_output": true,
+      "temperature": true,
+      "release_date": "2026-09-17",
+      "last_updated": "2026-09-17",
+      "modalities": {
+        "input": [
+          "text",
+          "image",
+          "audio",
+          "video"
+        ],
+        "output": [
+          "text"
+        ]
+      },
+      "open_weights": false,
+      "limit": {
+        "context": 1000000,
+        "output": 131072
+      },
+      "cost": {
+        "input": 0.15,
+        "output": 0.47,
+        "cache_read": 0.016
+      }
+    },
     "qwen/qwen3.6-35b-a3b": {
       "id": "qwen/qwen3.6-35b-a3b",
       "name": "Qwen3.6 35B-A3B",
@@ -1120,8 +1163,8 @@
         "output": 235929
       },
       "cost": {
-        "input": 0.1,
-        "output": 0.9,
+        "input": 0.15,
+        "output": 1,
         "cache_read": 0.05
       }
     },
@@ -1376,11 +1419,11 @@
       "open_weights": true,
       "limit": {
         "context": 262144,
-        "output": 16384
+        "output": 32768
       },
       "cost": {
-        "input": 0.15,
-        "output": 0.6
+        "input": 0.13,
+        "output": 0.52
       }
     },
     "qwen/qwen-plus": {
@@ -1471,6 +1514,51 @@
         "output": 2.08
       }
     },
+    "qwen/qwen3.8-27b:free": {
+      "id": "qwen/qwen3.8-27b:free",
+      "name": "Qwen3.8 27B (free)",
+      "description": "Qwen vision-language model for visual reasoning, documents, and agent tasks",
+      "family": "qwen",
+      "attachment": true,
+      "reasoning": true,
+      "reasoning_options": [
+        {
+          "type": "toggle"
+        },
+        {
+          "type": "effort",
+          "values": [
+            "low",
+            "medium",
+            "xhigh"
+          ]
+        }
+      ],
+      "tool_call": true,
+      "structured_output": true,
+      "temperature": true,
+      "release_date": "2026-08-14",
+      "last_updated": "2026-08-14",
+      "modalities": {
+        "input": [
+          "text",
+          "image",
+          "video"
+        ],
+        "output": [
+          "text"
+        ]
+      },
+      "open_weights": true,
+      "limit": {
+        "context": 262144,
+        "output": 235929
+      },
+      "cost": {
+        "input": 0,
+        "output": 0
+      }
+    },
     "qwen/qwen-2.5-coder-32b-instruct": {
       "id": "qwen/qwen-2.5-coder-32b-instruct",
       "name": "Qwen2.5 Coder 32B Instruct",
@@ -1587,6 +1675,51 @@
         }
       }
     },
+    "qwen/qwen3.8-max-prime": {
+      "id": "qwen/qwen3.8-max-prime",
+      "name": "Qwen3.8 Max Prime",
+      "description": "Qwen vision-language model for visual reasoning, documents, and agent tasks",
+      "family": "qwen3.8-max",
+      "attachment": true,
+      "reasoning": true,
+      "reasoning_options": [
+        {
+          "type": "effort",
+          "values": [
+            "minimal",
+            "low",
+            "medium",
+            "high",
+            "xhigh"
+          ]
+        }
+      ],
+      "tool_call": true,
+      "structured_output": true,
+      "temperature": true,
+      "release_date": "2026-09-23",
+      "last_updated": "2026-09-23",
+      "modalities": {
+        "input": [
+          "text",
+          "image",
+          "video"
+        ],
+        "output": [
+          "text"
+        ]
+      },
+      "open_weights": false,
+      "limit": {
+        "context": 1000000,
+        "output": 131072
+      },
+      "cost": {
+        "input": 4,
+        "output": 12,
+        "cache_read": 0.5
+      }
+    },
     "qwen/qwen3-30b-a3b": {
       "id": "qwen/qwen3-30b-a3b",
       "name": "Qwen3 30B A3B",
@@ -2070,6 +2203,77 @@
         "output": 1.25
       }
     },
+    "unbiased/pareto": {
+      "id": "unbiased/pareto",
+      "name": "Pareto",
+      "description": "Blended multimodal model that runs multiple language models in parallel and returns a synthesized answer",
+      "attachment": true,
+      "reasoning": false,
+      "tool_call": true,
+      "structured_output": false,
+      "temperature": true,
+      "release_date": "2026-09-17",
+      "last_updated": "2026-09-17",
+      "modalities": {
+        "input": [
+          "text",
+          "image"
+        ],
+        "output": [
+          "text"
+        ]
+      },
+      "open_weights": false,
+      "limit": {
+        "context": 262144,
+        "output": 131072
+      },
+      "cost": {
+        "input": 2.5,
+        "output": 7.5,
+        "cache_read": 0.25
+      }
+    },
+    "aion-labs/aion-3.5": {
+      "id": "aion-labs/aion-3.5",
+      "name": "Aion 3.5",
+      "description": "Reasoning model for deliberate analysis, multi-step problem solving, and tool use",
+      "attachment": false,
+      "reasoning": true,
+      "reasoning_options": [
+        {
+          "type": "effort",
+          "values": [
+            "low",
+            "high",
+            "max"
+          ]
+        }
+      ],
+      "tool_call": true,
+      "structured_output": false,
+      "temperature": true,
+      "release_date": "2026-09-23",
+      "last_updated": "2026-09-23",
+      "modalities": {
+        "input": [
+          "text"
+        ],
+        "output": [
+          "text"
+        ]
+      },
+      "open_weights": false,
+      "limit": {
+        "context": 262144,
+        "output": 32768
+      },
+      "cost": {
+        "input": 3,
+        "output": 6,
+        "cache_read": 0.75
+      }
+    },
     "aion-labs/aion-2.0": {
       "id": "aion-labs/aion-2.0",
       "name": "Aion-2.0",
@@ -2163,6 +2367,46 @@
         "cache_read": 0.75
       }
     },
+    "aion-labs/aion-3.5-mini": {
+      "id": "aion-labs/aion-3.5-mini",
+      "name": "Aion 3.5 Mini",
+      "description": "Efficient model for low-latency assistance, extraction, and routine automation",
+      "attachment": false,
+      "reasoning": true,
+      "reasoning_options": [
+        {
+          "type": "effort",
+          "values": [
+            "low",
+            "high",
+            "max"
+          ]
+        }
+      ],
+      "tool_call": true,
+      "structured_output": false,
+      "temperature": true,
+      "release_date": "2026-09-23",
+      "last_updated": "2026-09-23",
+      "modalities": {
+        "input": [
+          "text"
+        ],
+        "output": [
+          "text"
+        ]
+      },
+      "open_weights": false,
+      "limit": {
+        "context": 262144,
+        "output": 32768
+      },
+      "cost": {
+        "input": 0.7,
+        "output": 1.4,
+        "cache_read": 0.18
+      }
+    },
     "aion-labs/aion-3.0-mini": {
       "id": "aion-labs/aion-3.0-mini",
       "name": "Aion-3.0-Mini",
@@ -2248,9 +2492,6 @@
       "attachment": true,
       "reasoning": true,
       "reasoning_options": [
-        {
-          "type": "toggle"
-        },
         {
           "type": "effort",
           "values": [
@@ -2283,15 +2524,15 @@
         "output": 128000
       },
       "cost": {
-        "input": 5,
-        "output": 25,
-        "cache_read": 0.5,
-        "cache_write": 6.25
+        "input": 4,
+        "output": 20,
+        "cache_read": 0.2,
+        "cache_write": 5
       }
     },
     "~anthropic/claude-haiku-latest": {
       "id": "~anthropic/claude-haiku-latest",
-      "name": "Anthropic Claude Haiku Latest",
+      "name": "Claude Haiku Latest",
       "description": "Fast Claude model for responsive assistance, classification, and lightweight agents",
       "family": "claude-haiku",
       "attachment": true,
@@ -2330,7 +2571,7 @@
     },
     "~anthropic/claude-sonnet-latest": {
       "id": "~anthropic/claude-sonnet-latest",
-      "name": "Anthropic Claude Sonnet Latest",
+      "name": "Claude Sonnet Latest",
       "description": "Balanced Claude model for coding, analysis, agent workflows, and cost control",
       "family": "claude-sonnet",
       "attachment": true,
@@ -2504,27 +2745,116 @@
       "open_weights": false,
       "limit": {
         "context": 1310720,
-        "output": 393216
+        "output": 943718
       },
       "cost": {
-        "input": 0.05,
-        "output": 0.16,
-        "cache_read": 0.013
+        "input": 0.038,
+        "output": 0.55,
+        "cache_read": 0.0228
       }
     },
-    "dots-studio/dots-3-note-preview:free": {
-      "id": "dots-studio/dots-3-note-preview:free",
-      "name": "Dots3-Note Preview (free)",
-      "description": "Multimodal reasoning model for visual analysis, planning, and tool use",
-      "attachment": true,
+    "~deepseek/deepseek-pro-latest": {
+      "id": "~deepseek/deepseek-pro-latest",
+      "name": "DeepSeek Pro Latest",
+      "description": "Flagship DeepSeek model for coding, reasoning, and agentic work",
+      "family": "deepseek",
+      "attachment": false,
       "reasoning": true,
       "reasoning_options": [
         {
           "type": "toggle"
-        }
-      ],
-      "tool_call": true,
-      "structured_output": true,
+        },
+        {
+          "type": "effort",
+          "values": [
+            "low",
+            "high",
+            "max"
+          ]
+        }
+      ],
+      "tool_call": true,
+      "structured_output": true,
+      "temperature": true,
+      "release_date": "2026-09-14",
+      "last_updated": "2026-09-14",
+      "modalities": {
+        "input": [
+          "text"
+        ],
+        "output": [
+          "text"
+        ]
+      },
+      "open_weights": false,
+      "limit": {
+        "context": 1048576,
+        "output": 393216
+      },
+      "cost": {
+        "input": 0.38544,
+        "output": 1.15632,
+        "cache_read": 0.012264
+      }
+    },
+    "~deepseek/deepseek-flash-latest": {
+      "id": "~deepseek/deepseek-flash-latest",
+      "name": "DeepSeek Flash Latest",
+      "description": "Fast DeepSeek model for efficient chat, coding help, and agent loops",
+      "family": "deepseek-flash",
+      "attachment": true,
+      "reasoning": true,
+      "reasoning_options": [
+        {
+          "type": "toggle"
+        },
+        {
+          "type": "effort",
+          "values": [
+            "low",
+            "high",
+            "max"
+          ]
+        }
+      ],
+      "tool_call": true,
+      "structured_output": true,
+      "temperature": true,
+      "release_date": "2026-09-14",
+      "last_updated": "2026-09-14",
+      "modalities": {
+        "input": [
+          "text",
+          "image"
+        ],
+        "output": [
+          "text"
+        ]
+      },
+      "open_weights": false,
+      "limit": {
+        "context": 1048576,
+        "output": 943718
+      },
+      "cost": {
+        "input": 0.099,
+        "output": 0.6,
+        "cache_read": 0.06
+      }
+    },
+    "dots-studio/dots-3-note-preview:free": {
+      "id": "dots-studio/dots-3-note-preview:free",
+      "name": "Dots3-Note Preview (free)",
+      "description": "Multimodal reasoning model for visual analysis, planning, and tool use",
+      "attachment": true,
+      "reasoning": true,
+      "reasoning_options": [
+        {
+          "type": "toggle"
+        }
+      ],
+      "tool_call": true,
+      "structured_output": true,
       "temperature": true,
       "release_date": "2026-08-14",
       "last_updated": "2026-08-14",
@@ -2586,14 +2916,14 @@
         "output": 450000
       },
       "cost": {
-        "input": 2,
-        "output": 6,
-        "cache_read": 0.5,
+        "input": 1.6,
+        "output": 4.8,
+        "cache_read": 0.4,
         "tiers": [
           {
-            "input": 4,
-            "output": 12,
-            "cache_read": 1,
+            "input": 3.2,
+            "output": 9.6,
+            "cache_read": 0.8,
             "tier": {
               "type": "context",
               "size": 200000
@@ -2601,9 +2931,9 @@
           }
         ],
         "context_over_200k": {
-          "input": 4,
-          "output": 12,
-          "cache_read": 1
+          "input": 3.2,
+          "output": 9.6,
+          "cache_read": 0.8
         }
       }
     },
@@ -2646,6 +2976,48 @@
         "cache_read": 0.006
       }
     },
+    "prism-ml/ternary-bonsai-2-27b": {
+      "id": "prism-ml/ternary-bonsai-2-27b",
+      "name": "Ternary Bonsai 2 27B",
+      "description": "Multimodal reasoning model for visual analysis, planning, and tool use",
+      "attachment": true,
+      "reasoning": true,
+      "reasoning_options": [
+        {
+          "type": "toggle"
+        },
+        {
+          "type": "effort",
+          "values": [
+            "medium",
+            "xhigh"
+          ]
+        }
+      ],
+      "tool_call": true,
+      "structured_output": true,
+      "temperature": true,
+      "release_date": "2026-09-18",
+      "last_updated": "2026-09-18",
+      "modalities": {
+        "input": [
+          "text",
+          "image"
+        ],
+        "output": [
+          "text"
+        ]
+      },
+      "open_weights": true,
+      "limit": {
+        "context": 262144,
+        "output": 32768
+      },
+      "cost": {
+        "input": 0.075,
+        "output": 0.5
+      }
+    },
     "poolside/laguna-xs-2.1": {
       "id": "poolside/laguna-xs-2.1",
       "name": "Laguna XS 2.1",
@@ -2788,37 +3160,6 @@
         "cache_read": 0.009
       }
     },
-    "kwaipilot/kat-coder-pro-v2": {
-      "id": "kwaipilot/kat-coder-pro-v2",
-      "name": "KAT-Coder-Pro V2",
-      "description": "Coding model for repository understanding, refactors, and agentic engineering tasks",
-      "family": "kat-coder",
-      "attachment": false,
-      "reasoning": false,
-      "tool_call": true,
-      "structured_output": true,
-      "temperature": true,
-      "release_date": "2026-03-27",
-      "last_updated": "2026-03-27",
-      "modalities": {
-        "input": [
-          "text"
-        ],
-        "output": [
-          "text"
-        ]
-      },
-      "open_weights": false,
-      "limit": {
-        "context": 262144,
-        "output": 144000
-      },
-      "cost": {
-        "input": 0.3,
-        "output": 1.2,
-        "cache_read": 0.06
-      }
-    },
     "kwaipilot/kat-coder-pro-v2.5": {
       "id": "kwaipilot/kat-coder-pro-v2.5",
       "name": "KAT-Coder-Pro V2.5",
@@ -3064,39 +3405,6 @@
         "output": 7.5
       }
     },
-    "mistralai/devstral-2512": {
-      "id": "mistralai/devstral-2512",
-      "name": "Devstral 2",
-      "description": "Mistral coding agent model for repository tasks and software engineering workflows",
-      "family": "devstral",
-      "attachment": true,
-      "reasoning": false,
-      "tool_call": true,
-      "structured_output": true,
-      "temperature": true,
-      "knowledge": "2025-12",
-      "release_date": "2025-12-09",
-      "last_updated": "2025-12-09",
-      "modalities": {
-        "input": [
-          "text",
-          "pdf"
-        ],
-        "output": [
-          "text"
-        ]
-      },
-      "open_weights": true,
-      "limit": {
-        "context": 262144,
-        "output": 209715
-      },
-      "cost": {
-        "input": 0.4,
-        "output": 2,
-        "cache_read": 0.04
-      }
-    },
     "mistralai/mistral-large-2407": {
       "id": "mistralai/mistral-large-2407",
       "name": "Mistral Large 2407",
@@ -3154,12 +3462,12 @@
       },
       "open_weights": true,
       "limit": {
-        "context": 131072,
+        "context": 256000,
         "output": 16384
       },
       "cost": {
-        "input": 0.075,
-        "output": 0.2
+        "input": 0.09375,
+        "output": 0.25
       }
     },
     "mistralai/mixtral-8x22b-instruct": {
@@ -3228,40 +3536,6 @@
         "cache_read": 0.02
       }
     },
-    "mistralai/mistral-large-2512": {
-      "id": "mistralai/mistral-large-2512",
-      "name": "Mistral Large 3",
-      "description": "Mistral's largest general model for enterprise agents, coding, and multilingual reasoning",
-      "family": "mistral-large",
-      "attachment": true,
-      "reasoning": false,
-      "tool_call": true,
-      "structured_output": true,
-      "temperature": true,
-      "knowledge": "2024-11",
-      "release_date": "2024-11-01",
-      "last_updated": "2025-12-02",
-      "modalities": {
-        "input": [
-          "text",
-          "image",
-          "pdf"
-        ],
-        "output": [
-          "text"
-        ]
-      },
-      "open_weights": true,
-      "limit": {
-        "context": 262144,
-        "output": 209715
-      },
-      "cost": {
-        "input": 0.5,
-        "output": 1.5,
-        "cache_read": 0.05
-      }
-    },
     "mistralai/ministral-3b-2512": {
       "id": "mistralai/ministral-3b-2512",
       "name": "Ministral 3 3B 2512",
@@ -3397,7 +3671,7 @@
       "family": "mistral-small",
       "attachment": true,
       "reasoning": false,
-      "tool_call": false,
+      "tool_call": true,
       "structured_output": false,
       "temperature": true,
       "knowledge": "2023-10-31",
@@ -3500,14 +3774,14 @@
       "id": "mistralai/voxtral-small-24b-2507",
       "name": "Voxtral Small 24B 2507",
       "description": "Efficient Mistral model for fast chat, extraction, and production assistants",
-      "family": "mistral",
+      "family": "voxtral",
       "attachment": true,
       "reasoning": false,
       "tool_call": true,
       "structured_output": true,
       "temperature": true,
-      "release_date": "2025-10-30",
-      "last_updated": "2025-10-30",
+      "release_date": "2025-07-15",
+      "last_updated": "2025-07-15",
       "modalities": {
         "input": [
           "text",
@@ -3554,13 +3828,130 @@
       },
       "open_weights": false,
       "limit": {
-        "context": 131072,
-        "output": 104857
+        "context": 131072,
+        "output": 104857
+      },
+      "cost": {
+        "input": 0.4,
+        "output": 2,
+        "cache_read": 0.04
+      }
+    },
+    "xiaomi/mimo-v2.6-pro": {
+      "id": "xiaomi/mimo-v2.6-pro",
+      "name": "MiMo-V2.6-Pro",
+      "description": "MiMo pro model for strong multimodal reasoning and agent execution",
+      "family": "mimo",
+      "attachment": true,
+      "reasoning": true,
+      "reasoning_options": [
+        {
+          "type": "toggle"
+        }
+      ],
+      "tool_call": true,
+      "structured_output": true,
+      "temperature": true,
+      "release_date": "2026-09-22",
+      "last_updated": "2026-09-22",
+      "modalities": {
+        "input": [
+          "text",
+          "image",
+          "audio",
+          "video"
+        ],
+        "output": [
+          "text"
+        ]
+      },
+      "open_weights": true,
+      "limit": {
+        "context": 1048576,
+        "output": 131072
+      },
+      "cost": {
+        "input": 0.435,
+        "output": 0.87,
+        "cache_read": 0.0036
+      }
+    },
+    "xiaomi/mimo-v2.6-pro-ultraspeed": {
+      "id": "xiaomi/mimo-v2.6-pro-ultraspeed",
+      "name": "MiMo-V2.6-Pro-UltraSpeed",
+      "description": "MiMo pro model for strong multimodal reasoning and agent execution",
+      "family": "mimo",
+      "attachment": true,
+      "reasoning": true,
+      "reasoning_options": [
+        {
+          "type": "toggle"
+        }
+      ],
+      "tool_call": true,
+      "structured_output": true,
+      "temperature": true,
+      "release_date": "2026-09-21",
+      "last_updated": "2026-09-21",
+      "modalities": {
+        "input": [
+          "text",
+          "image",
+          "audio",
+          "video"
+        ],
+        "output": [
+          "text"
+        ]
+      },
+      "open_weights": true,
+      "limit": {
+        "context": 1048576,
+        "output": 131072
+      },
+      "cost": {
+        "input": 4.35,
+        "output": 8.7,
+        "cache_read": 0.036
+      }
+    },
+    "xiaomi/mimo-v2.6-flash": {
+      "id": "xiaomi/mimo-v2.6-flash",
+      "name": "MiMo-V2.6-Flash",
+      "description": "MiMo flash model for fast multimodal assistance and agent workflows",
+      "family": "mimo",
+      "attachment": true,
+      "reasoning": true,
+      "reasoning_options": [
+        {
+          "type": "toggle"
+        }
+      ],
+      "tool_call": true,
+      "structured_output": true,
+      "temperature": true,
+      "release_date": "2026-09-22",
+      "last_updated": "2026-09-22",
+      "modalities": {
+        "input": [
+          "text",
+          "image",
+          "audio",
+          "video"
+        ],
+        "output": [
+          "text"
+        ]
+      },
+      "open_weights": true,
+      "limit": {
+        "context": 1048576,
+        "output": 131072
       },
       "cost": {
-        "input": 0.4,
-        "output": 2,
-        "cache_read": 0.04
+        "input": 0.14,
+        "output": 0.28,
+        "cache_read": 0.0028
       }
     },
     "xiaomi/mimo-v2.5": {
@@ -3883,7 +4274,7 @@
         "output": 40000
       },
       "cost": {
-        "input": 0.55,
+        "input": 0.4,
         "output": 2.2
       }
     },
@@ -4090,7 +4481,7 @@
         }
       ],
       "tool_call": true,
-      "structured_output": false,
+      "structured_output": true,
       "temperature": true,
       "release_date": "2026-03-11",
       "last_updated": "2026-03-11",
@@ -4105,11 +4496,11 @@
       "open_weights": true,
       "limit": {
         "context": 262144,
-        "output": 16384
+        "output": 235929
       },
       "cost": {
-        "input": 0.085,
-        "output": 0.4
+        "input": 0.08,
+        "output": 0.45
       }
     },
     "nvidia/nemotron-3-ultra-550b-a55b:free": {
@@ -4276,12 +4667,12 @@
       "open_weights": true,
       "limit": {
         "context": 262144,
-        "output": 32768
+        "output": 182520
       },
       "cost": {
-        "input": 0.625,
-        "output": 3.125,
-        "cache_read": 0.1875
+        "input": 0.6,
+        "output": 2.4,
+        "cache_read": 0.12
       }
     },
     "nvidia/nemotron-3-nano-30b-a3b": {
@@ -4595,6 +4986,53 @@
         }
       }
     },
+    "anthropic/claude-opus-5.5": {
+      "id": "anthropic/claude-opus-5.5",
+      "name": "Claude Opus 5.5",
+      "description": "Flagship Claude model for deep reasoning, coding, and long-horizon agents",
+      "family": "claude-opus",
+      "attachment": true,
+      "reasoning": true,
+      "reasoning_options": [
+        {
+          "type": "effort",
+          "values": [
+            "low",
+            "medium",
+            "high",
+            "xhigh",
+            "max"
+          ]
+        }
+      ],
+      "tool_call": true,
+      "structured_output": true,
+      "temperature": true,
+      "knowledge": "2026-06",
+      "release_date": "2026-09-22",
+      "last_updated": "2026-09-22",
+      "modalities": {
+        "input": [
+          "text",
+          "image",
+          "pdf"
+        ],
+        "output": [
+          "text"
+        ]
+      },
+      "open_weights": false,
+      "limit": {
+        "context": 1000000,
+        "output": 128000
+      },
+      "cost": {
+        "input": 4,
+        "output": 20,
+        "cache_read": 0.2,
+        "cache_write": 5
+      }
+    },
     "anthropic/claude-3-haiku": {
       "id": "anthropic/claude-3-haiku",
       "name": "Claude 3 Haiku",
@@ -4786,46 +5224,6 @@
         "cache_write": 12.5
       }
     },
-    "anthropic/claude-opus-4": {
-      "id": "anthropic/claude-opus-4",
-      "name": "Claude Opus 4",
-      "description": "Flagship Claude model for deep reasoning, coding, and long-horizon agents",
-      "family": "claude-opus",
-      "attachment": true,
-      "reasoning": true,
-      "reasoning_options": [
-        {
-          "type": "toggle"
-        }
-      ],
-      "tool_call": true,
-      "structured_output": false,
-      "temperature": true,
-      "knowledge": "2025-01-31",
-      "release_date": "2025-05-22",
-      "last_updated": "2025-05-22",
-      "modalities": {
-        "input": [
-          "image",
-          "text",
-          "pdf"
-        ],
-        "output": [
-          "text"
-        ]
-      },
-      "open_weights": false,
-      "limit": {
-        "context": 200000,
-        "output": 32000
-      },
-      "cost": {
-        "input": 15,
-        "output": 75,
-        "cache_read": 1.5,
-        "cache_write": 18.75
-      }
-    },
     "anthropic/claude-sonnet-4.5": {
       "id": "anthropic/claude-sonnet-4.5",
       "name": "Claude Sonnet 4.5 (latest)",
@@ -4954,7 +5352,7 @@
       },
       "open_weights": false,
       "limit": {
-        "context": 1000000,
+        "context": 200000,
         "output": 64000
       },
       "cost": {
@@ -5109,11 +5507,12 @@
       "open_weights": true,
       "limit": {
         "context": 262144,
-        "output": 32768
+        "output": 235929
       },
       "cost": {
-        "input": 0.042,
-        "output": 0.22
+        "input": 0.09,
+        "output": 0.3,
+        "cache_read": 0.05
       }
     },
     "google/gemini-3.1-pro-preview-customtools": {
@@ -5230,7 +5629,7 @@
     },
     "google/gemma-3-4b-it": {
       "id": "google/gemma-3-4b-it",
-      "name": "Gemma 3 4B",
+      "name": "Gemma 3 4B IT",
       "description": "Open Gemma instruction model for efficient chat and self-hosted deployments",
       "family": "gemma",
       "attachment": true,
@@ -5238,9 +5637,9 @@
       "tool_call": false,
       "structured_output": true,
       "temperature": true,
-      "knowledge": "2024-08-31",
-      "release_date": "2025-03-13",
-      "last_updated": "2025-03-13",
+      "knowledge": "2024-08",
+      "release_date": "2025-03-12",
+      "last_updated": "2025-03-12",
       "modalities": {
         "input": [
           "text",
@@ -5678,7 +6077,7 @@
     },
     "google/gemma-3-27b-it": {
       "id": "google/gemma-3-27b-it",
-      "name": "Gemma 3 27B",
+      "name": "Gemma 3 27B IT",
       "description": "Open Gemma instruction model for efficient chat and self-hosted deployments",
       "family": "gemma",
       "attachment": true,
@@ -5686,7 +6085,7 @@
       "tool_call": true,
       "structured_output": true,
       "temperature": true,
-      "knowledge": "2024-08-31",
+      "knowledge": "2024-08",
       "release_date": "2025-03-12",
       "last_updated": "2025-03-12",
       "modalities": {
@@ -6306,70 +6705,9 @@
         "cache_write": 0.083333
       }
     },
-    "google/gemini-2.5-pro-preview-05-06": {
-      "id": "google/gemini-2.5-pro-preview-05-06",
-      "name": "Gemini 2.5 Pro Preview 05-06",
-      "description": "Advanced Gemini model for complex reasoning, coding, and multimodal analysis",
-      "family": "gemini-pro",
-      "attachment": true,
-      "reasoning": true,
-      "reasoning_options": [
-        {
-          "type": "budget_tokens",
-          "min": 128,
-          "max": 32768
-        }
-      ],
-      "tool_call": true,
-      "structured_output": true,
-      "temperature": true,
-      "knowledge": "2025-01-31",
-      "release_date": "2025-05-07",
-      "last_updated": "2025-05-07",
-      "modalities": {
-        "input": [
-          "text",
-          "image",
-          "pdf",
-          "audio",
-          "video"
-        ],
-        "output": [
-          "text"
-        ]
-      },
-      "open_weights": false,
-      "limit": {
-        "context": 1048576,
-        "output": 65535
-      },
-      "cost": {
-        "input": 1.25,
-        "output": 10,
-        "reasoning": 10,
-        "cache_read": 0.125,
-        "cache_write": 0.375,
-        "tiers": [
-          {
-            "input": 2.5,
-            "output": 15,
-            "cache_read": 0.25,
-            "tier": {
-              "type": "context",
-              "size": 200000
-            }
-          }
-        ],
-        "context_over_200k": {
-          "input": 2.5,
-          "output": 15,
-          "cache_read": 0.25
-        }
-      }
-    },
     "google/gemma-3-12b-it": {
       "id": "google/gemma-3-12b-it",
-      "name": "Gemma 3 12B",
+      "name": "Gemma 3 12B IT",
       "description": "Open Gemma instruction model for efficient chat and self-hosted deployments",
       "family": "gemma",
       "attachment": true,
@@ -6377,9 +6715,9 @@
       "tool_call": true,
       "structured_output": true,
       "temperature": true,
-      "knowledge": "2024-08-31",
-      "release_date": "2025-03-13",
-      "last_updated": "2025-03-13",
+      "knowledge": "2024-08",
+      "release_date": "2025-03-12",
+      "last_updated": "2025-03-12",
       "modalities": {
         "input": [
           "text",
@@ -6566,6 +6904,48 @@
         "output": 0
       }
     },
+    "nex-agi/nex-n2.5-pro": {
+      "id": "nex-agi/nex-n2.5-pro",
+      "name": "Nex-N2.5-Pro",
+      "description": "Multimodal reasoning model for visual analysis, planning, and tool use",
+      "family": "agi",
+      "attachment": true,
+      "reasoning": true,
+      "reasoning_options": [
+        {
+          "type": "effort",
+          "values": [
+            "none",
+            "medium",
+            "high"
+          ]
+        }
+      ],
+      "tool_call": true,
+      "structured_output": true,
+      "temperature": true,
+      "release_date": "2026-09-08",
+      "last_updated": "2026-09-08",
+      "modalities": {
+        "input": [
+          "text",
+          "image"
+        ],
+        "output": [
+          "text"
+        ]
+      },
+      "open_weights": true,
+      "limit": {
+        "context": 262144,
+        "output": 235929
+      },
+      "cost": {
+        "input": 0.075,
+        "output": 0.25,
+        "cache_read": 0.015
+      }
+    },
     "nex-agi/nex-n2.5-pro:free": {
       "id": "nex-agi/nex-n2.5-pro:free",
       "name": "Nex-N2.5-Pro (free)",
@@ -6607,6 +6987,48 @@
         "output": 0
       }
     },
+    "nex-agi/nex-n2.5-mini": {
+      "id": "nex-agi/nex-n2.5-mini",
+      "name": "Nex-N2.5-Mini",
+      "description": "Multimodal reasoning model for visual analysis, planning, and tool use",
+      "family": "agi",
+      "attachment": true,
+      "reasoning": true,
+      "reasoning_options": [
+        {
+          "type": "effort",
+          "values": [
+            "none",
+            "medium",
+            "high"
+          ]
+        }
+      ],
+      "tool_call": false,
+      "structured_output": true,
+      "temperature": true,
+      "release_date": "2026-09-08",
+      "last_updated": "2026-09-08",
+      "modalities": {
+        "input": [
+          "text",
+          "image"
+        ],
+        "output": [
+          "text"
+        ]
+      },
+      "open_weights": true,
+      "limit": {
+        "context": 262144,
+        "output": 235929
+      },
+      "cost": {
+        "input": 0.025,
+        "output": 0.1,
+        "cache_read": 0.0025
+      }
+    },
     "thinkingmachines/inkling-small": {
       "id": "thinkingmachines/inkling-small",
       "name": "Inkling Small",
@@ -6781,7 +7203,7 @@
       "open_weights": true,
       "limit": {
         "context": 1048576,
-        "output": 32768
+        "output": 471859
       },
       "cost": {
         "input": 1,
@@ -6815,8 +7237,8 @@
         "output": 3686
       },
       "cost": {
-        "input": 0.06,
-        "output": 0.06
+        "input": 0.08,
+        "output": 0.11
       }
     },
     "meta/muse-spark-1.3": {
@@ -7092,11 +7514,11 @@
       "open_weights": true,
       "limit": {
         "context": 131072,
-        "output": 117964
+        "output": 16384
       },
       "cost": {
         "input": 0.3,
-        "output": 1.1,
+        "output": 1.2,
         "cache_read": 0.04
       }
     },
@@ -7173,7 +7595,7 @@
       "description": "Open-weight instruction model for adaptable chat and self-hosted production workloads",
       "attachment": false,
       "reasoning": false,
-      "tool_call": true,
+      "tool_call": false,
       "structured_output": true,
       "temperature": true,
       "knowledge": "2024-04-30",
@@ -7674,7 +8096,7 @@
     },
     "~google/gemini-pro-latest": {
       "id": "~google/gemini-pro-latest",
-      "name": "Google Gemini Pro Latest",
+      "name": "Gemini Pro Latest",
       "description": "Advanced Gemini model for complex reasoning, coding, and multimodal analysis",
       "family": "gemini-pro",
       "attachment": true,
@@ -7738,7 +8160,7 @@
     },
     "~google/gemini-flash-latest": {
       "id": "~google/gemini-flash-latest",
-      "name": "Google Gemini Flash Latest",
+      "name": "Gemini Flash Latest",
       "description": "Fast Gemini model balancing multimodal reasoning, tool use, and cost",
       "family": "gemini-flash",
       "attachment": true,
@@ -7903,6 +8325,49 @@
         }
       }
     },
+    "sakana/fugu-max": {
+      "id": "sakana/fugu-max",
+      "name": "Fugu Max",
+      "description": "Multi-agent model for routing expert agents across complex analytical tasks",
+      "family": "fugu",
+      "attachment": true,
+      "reasoning": true,
+      "reasoning_options": [
+        {
+          "type": "effort",
+          "values": [
+            "high",
+            "xhigh",
+            "max"
+          ]
+        }
+      ],
+      "tool_call": true,
+      "structured_output": true,
+      "temperature": false,
+      "release_date": "2026-09-11",
+      "last_updated": "2026-09-11",
+      "modalities": {
+        "input": [
+          "text",
+          "image",
+          "pdf"
+        ],
+        "output": [
+          "text"
+        ]
+      },
+      "open_weights": false,
+      "limit": {
+        "context": 1000000,
+        "output": 128000
+      },
+      "cost": {
+        "input": 2,
+        "output": 6,
+        "cache_read": 0.25
+      }
+    },
     "sakana/sakana-namazu": {
       "id": "sakana/sakana-namazu",
       "name": "Sakana Namazu",
@@ -7945,9 +8410,69 @@
         "cache_read": 0.15
       }
     },
+    "sakana/fugu-ultra-v2": {
+      "id": "sakana/fugu-ultra-v2",
+      "name": "Fugu Ultra v2",
+      "description": "Quality-first multi-agent model for hard research, analysis, and competitions",
+      "family": "fugu",
+      "attachment": true,
+      "reasoning": true,
+      "reasoning_options": [
+        {
+          "type": "effort",
+          "values": [
+            "high",
+            "xhigh",
+            "max"
+          ]
+        }
+      ],
+      "tool_call": true,
+      "structured_output": true,
+      "temperature": false,
+      "knowledge": "2026-08-28",
+      "release_date": "2026-09-11",
+      "last_updated": "2026-09-11",
+      "modalities": {
+        "input": [
+          "text",
+          "image",
+          "pdf"
+        ],
+        "output": [
+          "text"
+        ]
+      },
+      "open_weights": false,
+      "limit": {
+        "context": 1000000,
+        "output": 128000
+      },
+      "cost": {
+        "input": 5,
+        "output": 30,
+        "cache_read": 0.5,
+        "tiers": [
+          {
+            "input": 10,
+            "output": 45,
+            "cache_read": 1,
+            "tier": {
+              "type": "context",
+              "size": 272000
+            }
+          }
+        ],
+        "context_over_200k": {
+          "input": 10,
+          "output": 45,
+          "cache_read": 1
+        }
+      }
+    },
     "~moonshotai/kimi-latest": {
       "id": "~moonshotai/kimi-latest",
-      "name": "MoonshotAI Kimi Latest",
+      "name": "Kimi Latest",
       "description": "Kimi multimodal agent model for visual understanding, coding, and planning",
       "family": "kimi",
       "attachment": true,
@@ -7986,9 +8511,9 @@
         "output": 943718
       },
       "cost": {
-        "input": 2.4,
-        "output": 12,
-        "cache_read": 0.24
+        "input": 1.4989,
+        "output": 10.758,
+        "cache_read": 0.3
       }
     },
     "ibm-granite/granite-4.2-8b": {
@@ -8123,7 +8648,7 @@
       "structured_output": true,
       "temperature": true,
       "release_date": "2026-08-21",
-      "last_updated": "2026-08-21",
+      "last_updated": "2026-09-01",
       "modalities": {
         "input": [
           "text",
@@ -8133,7 +8658,7 @@
           "text"
         ]
       },
-      "open_weights": false,
+      "open_weights": true,
       "limit": {
         "context": 1048576,
         "output": 943718
@@ -8180,12 +8705,12 @@
       "open_weights": true,
       "limit": {
         "context": 1048576,
-        "output": 393216
+        "output": 384000
       },
       "cost": {
-        "input": 0.57948,
-        "output": 1.73844,
-        "cache_read": 0.018438
+        "input": 0.462,
+        "output": 1.386,
+        "cache_read": 0.0154
       }
     },
     "deepseek/deepseek-v4-flash-0731": {
@@ -8228,8 +8753,8 @@
         "output": 943718
       },
       "cost": {
-        "input": 0.065,
-        "output": 0.18,
+        "input": 0.04,
+        "output": 0.64,
         "cache_read": 0.016
       }
     },
@@ -8275,9 +8800,9 @@
         "output": 384000
       },
       "cost": {
-        "input": 0.08554,
-        "output": 0.17108,
-        "cache_read": 0.017108
+        "input": 0.07168,
+        "output": 0.14336,
+        "cache_read": 0.014336
       }
     },
     "deepseek/deepseek-v4.1-flash": {
@@ -8318,7 +8843,7 @@
       "open_weights": true,
       "limit": {
         "context": 1048576,
-        "output": 384000
+        "output": 393216
       },
       "cost": {
         "input": 0.15,
@@ -8335,7 +8860,7 @@
       "reasoning": true,
       "reasoning_options": [],
       "tool_call": true,
-      "structured_output": true,
+      "structured_output": false,
       "temperature": true,
       "knowledge": "2024-07",
       "release_date": "2025-01-20",
@@ -8382,11 +8907,11 @@
       "open_weights": true,
       "limit": {
         "context": 163840,
-        "output": 16000
+        "output": 16384
       },
       "cost": {
-        "input": 0.2574,
-        "output": 1.0287
+        "input": 0.32,
+        "output": 0.89
       }
     },
     "deepseek/deepseek-r1-0528": {
@@ -8610,9 +9135,9 @@
         "output": 384000
       },
       "cost": {
-        "input": 0.87,
-        "output": 1.74,
-        "cache_read": 0.0725
+        "input": 0.946386,
+        "output": 1.892772,
+        "cache_read": 0.078866
       }
     },
     "deepseek/deepseek-chat-v3-0324": {
@@ -8624,41 +9149,237 @@
       "reasoning": false,
       "tool_call": true,
       "structured_output": true,
-      "temperature": true,
-      "knowledge": "2024-07-31",
-      "release_date": "2025-03-24",
-      "last_updated": "2025-03-24",
+      "temperature": true,
+      "knowledge": "2024-07-31",
+      "release_date": "2025-03-24",
+      "last_updated": "2025-03-24",
+      "modalities": {
+        "input": [
+          "text"
+        ],
+        "output": [
+          "text"
+        ]
+      },
+      "open_weights": true,
+      "limit": {
+        "context": 163840,
+        "output": 147456
+      },
+      "cost": {
+        "input": 0.25,
+        "output": 1
+      }
+    },
+    "~openai/gpt-terra-latest": {
+      "id": "~openai/gpt-terra-latest",
+      "name": "GPT Terra Latest",
+      "description": "GPT model for general reasoning, writing, coding, and tool-assisted tasks",
+      "family": "gpt-terra",
+      "attachment": true,
+      "reasoning": true,
+      "reasoning_options": [
+        {
+          "type": "effort",
+          "values": [
+            "none",
+            "low",
+            "medium",
+            "high",
+            "xhigh",
+            "max"
+          ]
+        }
+      ],
+      "tool_call": true,
+      "structured_output": true,
+      "temperature": false,
+      "knowledge": "2026-02-16",
+      "release_date": "2026-09-11",
+      "last_updated": "2026-09-11",
+      "modalities": {
+        "input": [
+          "pdf",
+          "image",
+          "text"
+        ],
+        "output": [
+          "text"
+        ]
+      },
+      "open_weights": false,
+      "limit": {
+        "context": 1050000,
+        "output": 128000
+      },
+      "cost": {
+        "input": 2,
+        "output": 12,
+        "cache_read": 0.2,
+        "cache_write": 2.5,
+        "tiers": [
+          {
+            "input": 4,
+            "output": 18,
+            "cache_read": 0.4,
+            "cache_write": 5,
+            "tier": {
+              "type": "context",
+              "size": 272000
+            }
+          }
+        ],
+        "context_over_200k": {
+          "input": 4,
+          "output": 18,
+          "cache_read": 0.4,
+          "cache_write": 5
+        }
+      }
+    },
+    "~openai/gpt-sol-latest": {
+      "id": "~openai/gpt-sol-latest",
+      "name": "GPT Sol Latest",
+      "description": "GPT model for general reasoning, writing, coding, and tool-assisted tasks",
+      "family": "gpt-sol",
+      "attachment": true,
+      "reasoning": true,
+      "reasoning_options": [
+        {
+          "type": "effort",
+          "values": [
+            "none",
+            "low",
+            "medium",
+            "high",
+            "xhigh",
+            "max"
+          ]
+        }
+      ],
+      "tool_call": true,
+      "structured_output": true,
+      "temperature": false,
+      "knowledge": "2026-02-16",
+      "release_date": "2026-09-11",
+      "last_updated": "2026-09-11",
+      "modalities": {
+        "input": [
+          "pdf",
+          "image",
+          "text"
+        ],
+        "output": [
+          "text"
+        ]
+      },
+      "open_weights": false,
+      "limit": {
+        "context": 1050000,
+        "output": 128000
+      },
+      "cost": {
+        "input": 2,
+        "output": 10,
+        "cache_read": 0.2,
+        "cache_write": 2.5,
+        "tiers": [
+          {
+            "input": 4,
+            "output": 15,
+            "cache_read": 0.4,
+            "cache_write": 5,
+            "tier": {
+              "type": "context",
+              "size": 272000
+            }
+          }
+        ],
+        "context_over_200k": {
+          "input": 4,
+          "output": 15,
+          "cache_read": 0.4,
+          "cache_write": 5
+        }
+      }
+    },
+    "~openai/gpt-luna-latest": {
+      "id": "~openai/gpt-luna-latest",
+      "name": "GPT Luna Latest",
+      "description": "GPT model for general reasoning, writing, coding, and tool-assisted tasks",
+      "family": "gpt-luna",
+      "attachment": true,
+      "reasoning": true,
+      "reasoning_options": [
+        {
+          "type": "effort",
+          "values": [
+            "none",
+            "low",
+            "medium",
+            "high",
+            "xhigh",
+            "max"
+          ]
+        }
+      ],
+      "tool_call": true,
+      "structured_output": true,
+      "temperature": false,
+      "knowledge": "2026-02-16",
+      "release_date": "2026-09-11",
+      "last_updated": "2026-09-11",
       "modalities": {
         "input": [
+          "pdf",
+          "image",
           "text"
         ],
         "output": [
           "text"
         ]
       },
-      "open_weights": true,
+      "open_weights": false,
       "limit": {
-        "context": 163840,
-        "output": 147456
+        "context": 1050000,
+        "output": 128000
       },
       "cost": {
-        "input": 0.29,
-        "output": 1.14,
-        "cache_read": 0.11
+        "input": 0.1,
+        "output": 0.5,
+        "cache_read": 0.01,
+        "cache_write": 0.125,
+        "tiers": [
+          {
+            "input": 0.2,
+            "output": 0.75,
+            "cache_read": 0.02,
+            "cache_write": 0.25,
+            "tier": {
+              "type": "context",
+              "size": 272000
+            }
+          }
+        ],
+        "context_over_200k": {
+          "input": 0.2,
+          "output": 0.75,
+          "cache_read": 0.02,
+          "cache_write": 0.25
+        }
       }
     },
-    "~openai/gpt-latest": {
-      "id": "~openai/gpt-latest",
-      "name": "OpenAI GPT Latest",
+    "~openai/gpt-astra-latest": {
+      "id": "~openai/gpt-astra-latest",
+      "name": "GPT Astra Latest",
       "description": "GPT model for general reasoning, writing, coding, and tool-assisted tasks",
-      "family": "gpt",
+      "family": "gpt-astra",
       "attachment": true,
       "reasoning": true,
       "reasoning_options": [
         {
           "type": "effort",
           "values": [
-            "none",
             "low",
             "medium",
             "high",
@@ -8670,9 +9391,8 @@
       "tool_call": true,
       "structured_output": true,
       "temperature": false,
-      "knowledge": "2026-02-16",
-      "release_date": "2026-04-27",
-      "last_updated": "2026-04-27",
+      "release_date": "2026-09-11",
+      "last_updated": "2026-09-11",
       "modalities": {
         "input": [
           "pdf",
@@ -8689,16 +9409,16 @@
         "output": 128000
       },
       "cost": {
-        "input": 2,
-        "output": 10,
-        "cache_read": 0.2,
-        "cache_write": 2.5,
+        "input": 10,
+        "output": 50,
+        "cache_read": 1,
+        "cache_write": 12.5,
         "tiers": [
           {
-            "input": 4,
-            "output": 15,
-            "cache_read": 0.4,
-            "cache_write": 5,
+            "input": 20,
+            "output": 75,
+            "cache_read": 2,
+            "cache_write": 25,
             "tier": {
               "type": "context",
               "size": 272000
@@ -8706,16 +9426,16 @@
           }
         ],
         "context_over_200k": {
-          "input": 4,
-          "output": 15,
-          "cache_read": 0.4,
-          "cache_write": 5
+          "input": 20,
+          "output": 75,
+          "cache_read": 2,
+          "cache_write": 25
         }
       }
     },
     "~openai/gpt-mini-latest": {
       "id": "~openai/gpt-mini-latest",
-      "name": "OpenAI GPT Mini Latest",
+      "name": "GPT Mini Latest",
       "description": "Compact GPT model for low-latency assistance and high-volume workloads",
       "family": "gpt-mini",
       "attachment": true,
@@ -9066,9 +9786,9 @@
         "output": 0
       }
     },
-    "inclusionai/ling-3.0-flash-vl:free": {
-      "id": "inclusionai/ling-3.0-flash-vl:free",
-      "name": "Ling 3.0 Flash VL (free)",
+    "inclusionai/ling-3.0-flash-vl": {
+      "id": "inclusionai/ling-3.0-flash-vl",
+      "name": "Ling 3.0 Flash VL",
       "description": "Multimodal reasoning model for visual analysis, planning, and tool use",
       "family": "ling",
       "attachment": true,
@@ -9079,7 +9799,7 @@
         }
       ],
       "tool_call": true,
-      "structured_output": false,
+      "structured_output": true,
       "temperature": true,
       "release_date": "2026-09-10",
       "last_updated": "2026-09-10",
@@ -9099,8 +9819,9 @@
         "output": 32768
       },
       "cost": {
-        "input": 0,
-        "output": 0
+        "input": 0.06,
+        "output": 0.18,
+        "cache_read": 0.012
       }
     },
     "anthracite-org/magnum-v4-72b": {
@@ -9742,6 +10463,67 @@
         }
       }
     },
+    "x-ai/grok-4.7": {
+      "id": "x-ai/grok-4.7",
+      "name": "Grok 4.7",
+      "description": "Grok model for agentic tool use, reasoning, coding, and live assistance",
+      "family": "grok",
+      "attachment": true,
+      "reasoning": true,
+      "reasoning_options": [
+        {
+          "type": "effort",
+          "values": [
+            "low",
+            "medium",
+            "high",
+            "xhigh"
+          ]
+        }
+      ],
+      "tool_call": true,
+      "structured_output": true,
+      "temperature": true,
+      "knowledge": "2026-05",
+      "release_date": "2026-09-21",
+      "last_updated": "2026-09-21",
+      "modalities": {
+        "input": [
+          "text",
+          "image",
+          "pdf"
+        ],
+        "output": [
+          "text"
+        ]
+      },
+      "open_weights": false,
+      "limit": {
+        "context": 500000,
+        "output": 450000
+      },
+      "cost": {
+        "input": 1.6,
+        "output": 4.8,
+        "cache_read": 0.4,
+        "tiers": [
+          {
+            "input": 3.2,
+            "output": 9.6,
+            "cache_read": 0.8,
+            "tier": {
+              "type": "context",
+              "size": 200000
+            }
+          }
+        ],
+        "context_over_200k": {
+          "input": 3.2,
+          "output": 9.6,
+          "cache_read": 0.8
+        }
+      }
+    },
     "meta-llama/llama-3.1-8b-instruct": {
       "id": "meta-llama/llama-3.1-8b-instruct",
       "name": "Llama-3.1-8B-Instruct",
@@ -9893,11 +10675,11 @@
       "open_weights": true,
       "limit": {
         "context": 1048576,
-        "output": 115200
+        "output": 16384
       },
       "cost": {
-        "input": 0.2,
-        "output": 0.696
+        "input": 0.1875,
+        "output": 0.6525
       }
     },
     "meta-llama/llama-4-scout": {
@@ -10364,6 +11146,73 @@
         "cache_read": 0.55
       }
     },
+    "openai/gpt-6-sol": {
+      "id": "openai/gpt-6-sol",
+      "name": "GPT-6 Sol",
+      "description": "GPT model for general reasoning, writing, coding, and tool-assisted tasks",
+      "family": "gpt-sol",
+      "attachment": true,
+      "reasoning": true,
+      "reasoning_options": [
+        {
+          "type": "effort",
+          "values": [
+            "none",
+            "low",
+            "medium",
+            "high",
+            "xhigh",
+            "max"
+          ]
+        }
+      ],
+      "tool_call": true,
+      "structured_output": true,
+      "temperature": false,
+      "knowledge": "2026-04-20",
+      "release_date": "2026-09-22",
+      "last_updated": "2026-09-22",
+      "modalities": {
+        "input": [
+          "text",
+          "image",
+          "pdf"
+        ],
+        "output": [
+          "text"
+        ]
+      },
+      "open_weights": false,
+      "limit": {
+        "context": 1050000,
+        "input": 922000,
+        "output": 128000
+      },
+      "cost": {
+        "input": 2,
+        "output": 10,
+        "cache_read": 0.2,
+        "cache_write": 2.5,
+        "tiers": [
+          {
+            "input": 4,
+            "output": 15,
+            "cache_read": 0.4,
+            "cache_write": 5,
+            "tier": {
+              "type": "context",
+              "size": 272000
+            }
+          }
+        ],
+        "context_over_200k": {
+          "input": 4,
+          "output": 15,
+          "cache_read": 0.4,
+          "cache_write": 5
+        }
+      }
+    },
     "openai/gpt-5.1-codex-mini": {
       "id": "openai/gpt-5.1-codex-mini",
       "name": "GPT-5.1 Codex mini",
@@ -10411,9 +11260,73 @@
         "cache_read": 0.03
       }
     },
-    "openai/gpt-6-astra-pro": {
-      "id": "openai/gpt-6-astra-pro",
-      "name": "GPT-6 Astra Pro",
+    "openai/gpt-6-astra-pro": {
+      "id": "openai/gpt-6-astra-pro",
+      "name": "GPT-6 Astra Pro",
+      "description": "Frontier GPT model for professional reasoning, coding, and multimodal work",
+      "family": "gpt",
+      "attachment": true,
+      "reasoning": true,
+      "reasoning_options": [
+        {
+          "type": "effort",
+          "values": [
+            "low",
+            "medium",
+            "high",
+            "xhigh",
+            "max"
+          ]
+        }
+      ],
+      "tool_call": true,
+      "structured_output": true,
+      "temperature": false,
+      "release_date": "2026-09-04",
+      "last_updated": "2026-09-04",
+      "modalities": {
+        "input": [
+          "pdf",
+          "image",
+          "text"
+        ],
+        "output": [
+          "text"
+        ]
+      },
+      "open_weights": false,
+      "limit": {
+        "context": 1050000,
+        "output": 128000
+      },
+      "cost": {
+        "input": 10,
+        "output": 50,
+        "cache_read": 1,
+        "cache_write": 12.5,
+        "tiers": [
+          {
+            "input": 20,
+            "output": 75,
+            "cache_read": 2,
+            "cache_write": 25,
+            "tier": {
+              "type": "context",
+              "size": 272000
+            }
+          }
+        ],
+        "context_over_200k": {
+          "input": 20,
+          "output": 75,
+          "cache_read": 2,
+          "cache_write": 25
+        }
+      }
+    },
+    "openai/gpt-6-luna-pro": {
+      "id": "openai/gpt-6-luna-pro",
+      "name": "GPT-6 Luna Pro",
       "description": "Frontier GPT model for professional reasoning, coding, and multimodal work",
       "family": "gpt",
       "attachment": true,
@@ -10422,6 +11335,7 @@
         {
           "type": "effort",
           "values": [
+            "none",
             "low",
             "medium",
             "high",
@@ -10433,8 +11347,8 @@
       "tool_call": true,
       "structured_output": true,
       "temperature": false,
-      "release_date": "2026-09-04",
-      "last_updated": "2026-09-04",
+      "release_date": "2026-09-22",
+      "last_updated": "2026-09-22",
       "modalities": {
         "input": [
           "pdf",
@@ -10451,16 +11365,16 @@
         "output": 128000
       },
       "cost": {
-        "input": 10,
-        "output": 50,
-        "cache_read": 1,
-        "cache_write": 12.5,
+        "input": 0.1,
+        "output": 0.5,
+        "cache_read": 0.01,
+        "cache_write": 0.125,
         "tiers": [
           {
-            "input": 20,
-            "output": 75,
-            "cache_read": 2,
-            "cache_write": 25,
+            "input": 0.2,
+            "output": 0.75,
+            "cache_read": 0.02,
+            "cache_write": 0.25,
             "tier": {
               "type": "context",
               "size": 272000
@@ -10468,10 +11382,10 @@
           }
         ],
         "context_over_200k": {
-          "input": 20,
-          "output": 75,
-          "cache_read": 2,
-          "cache_write": 25
+          "input": 0.2,
+          "output": 0.75,
+          "cache_read": 0.02,
+          "cache_write": 0.25
         }
       }
     },
@@ -10618,21 +11532,35 @@
         }
       }
     },
-    "openai/gpt-4-turbo-preview": {
-      "id": "openai/gpt-4-turbo-preview",
-      "name": "GPT-4 Turbo Preview",
-      "description": "Compact GPT model for low-latency assistance and high-volume workloads",
+    "openai/gpt-6-sol-pro": {
+      "id": "openai/gpt-6-sol-pro",
+      "name": "GPT-6 Sol Pro",
+      "description": "Frontier GPT model for professional reasoning, coding, and multimodal work",
       "family": "gpt",
-      "attachment": false,
-      "reasoning": false,
+      "attachment": true,
+      "reasoning": true,
+      "reasoning_options": [
+        {
+          "type": "effort",
+          "values": [
+            "none",
+            "low",
+            "medium",
+            "high",
+            "xhigh",
+            "max"
+          ]
+        }
+      ],
       "tool_call": true,
       "structured_output": true,
-      "temperature": true,
-      "knowledge": "2023-12-31",
-      "release_date": "2024-01-25",
-      "last_updated": "2024-01-25",
+      "temperature": false,
+      "release_date": "2026-09-22",
+      "last_updated": "2026-09-22",
       "modalities": {
         "input": [
+          "pdf",
+          "image",
           "text"
         ],
         "output": [
@@ -10641,12 +11569,32 @@
       },
       "open_weights": false,
       "limit": {
-        "context": 128000,
-        "output": 4096
+        "context": 1050000,
+        "output": 128000
       },
       "cost": {
-        "input": 10,
-        "output": 30
+        "input": 2,
+        "output": 10,
+        "cache_read": 0.2,
+        "cache_write": 2.5,
+        "tiers": [
+          {
+            "input": 4,
+            "output": 15,
+            "cache_read": 0.4,
+            "cache_write": 5,
+            "tier": {
+              "type": "context",
+              "size": 272000
+            }
+          }
+        ],
+        "context_over_200k": {
+          "input": 4,
+          "output": 15,
+          "cache_read": 0.4,
+          "cache_write": 5
+        }
       }
     },
     "openai/gpt-4o-2024-08-06": {
@@ -11069,12 +12017,11 @@
       "open_weights": true,
       "limit": {
         "context": 131072,
-        "output": 117964
+        "output": 32768
       },
       "cost": {
-        "input": 0.03,
-        "output": 0.13,
-        "cache_read": 0.03
+        "input": 0.018,
+        "output": 0.09
       }
     },
     "openai/gpt-4-turbo": {
@@ -11214,7 +12161,7 @@
     },
     "openai/gpt-oss-safeguard-20b": {
       "id": "openai/gpt-oss-safeguard-20b",
-      "name": "gpt-oss-safeguard-20b",
+      "name": "GPT OSS Safeguard 20B",
       "description": "Safety model for policy screening, moderation, and risk-aware routing workflows",
       "family": "gpt-oss",
       "attachment": false,
@@ -11526,6 +12473,73 @@
         "cache_read": 1.25
       }
     },
+    "openai/gpt-6-luna": {
+      "id": "openai/gpt-6-luna",
+      "name": "GPT-6 Luna",
+      "description": "GPT model for general reasoning, writing, coding, and tool-assisted tasks",
+      "family": "gpt-luna",
+      "attachment": true,
+      "reasoning": true,
+      "reasoning_options": [
+        {
+          "type": "effort",
+          "values": [
+            "none",
+            "low",
+            "medium",
+            "high",
+            "xhigh",
+            "max"
+          ]
+        }
+      ],
+      "tool_call": true,
+      "structured_output": true,
+      "temperature": false,
+      "knowledge": "2026-05-18",
+      "release_date": "2026-09-22",
+      "last_updated": "2026-09-22",
+      "modalities": {
+        "input": [
+          "text",
+          "image",
+          "pdf"
+        ],
+        "output": [
+          "text"
+        ]
+      },
+      "open_weights": false,
+      "limit": {
+        "context": 1050000,
+        "input": 922000,
+        "output": 128000
+      },
+      "cost": {
+        "input": 0.1,
+        "output": 0.5,
+        "cache_read": 0.01,
+        "cache_write": 0.125,
+        "tiers": [
+          {
+            "input": 0.2,
+            "output": 0.75,
+            "cache_read": 0.02,
+            "cache_write": 0.25,
+            "tier": {
+              "type": "context",
+              "size": 272000
+            }
+          }
+        ],
+        "context_over_200k": {
+          "input": 0.2,
+          "output": 0.75,
+          "cache_read": 0.02,
+          "cache_write": 0.25
+        }
+      }
+    },
     "openai/gpt-5.6-luna": {
       "id": "openai/gpt-5.6-luna",
       "name": "GPT-5.6 Luna",
@@ -12174,11 +13188,12 @@
       "open_weights": true,
       "limit": {
         "context": 131072,
-        "output": 117964
+        "output": 65536
       },
       "cost": {
-        "input": 0.037,
-        "output": 0.17
+        "input": 0.15,
+        "output": 0.6,
+        "cache_read": 0.075
       }
     },
     "openai/gpt-5.4-pro": {
@@ -12788,12 +13803,12 @@
       "open_weights": false,
       "limit": {
         "context": 1310720,
-        "output": 128000
+        "output": 131072
       },
       "cost": {
-        "input": 0.7,
-        "output": 2.2,
-        "cache_read": 0.13
+        "input": 0.5614,
+        "output": 1.7644,
+        "cache_read": 0.10426
       }
     },
     "moonshotai/kimi-k2-0905": {
@@ -12820,7 +13835,7 @@
       "open_weights": true,
       "limit": {
         "context": 262144,
-        "output": 100352
+        "output": 98304
       },
       "cost": {
         "input": 0.6,
@@ -12897,9 +13912,9 @@
         "output": 235929
       },
       "cost": {
-        "input": 0.71,
-        "output": 3.5,
-        "cache_read": 0.15
+        "input": 0.7062,
+        "output": 3.3,
+        "cache_read": 0.18
       }
     },
     "moonshotai/kimi-k2-thinking": {
@@ -12930,7 +13945,7 @@
       "open_weights": true,
       "limit": {
         "context": 262144,
-        "output": 100352
+        "output": 98304
       },
       "cost": {
         "input": 0.6,
@@ -12994,9 +14009,109 @@
       "tool_call": true,
       "structured_output": false,
       "temperature": true,
-      "knowledge": "2024-12-31",
-      "release_date": "2025-07-11",
-      "last_updated": "2025-07-11",
+      "knowledge": "2024-12-31",
+      "release_date": "2025-07-11",
+      "last_updated": "2025-07-11",
+      "modalities": {
+        "input": [
+          "text"
+        ],
+        "output": [
+          "text"
+        ]
+      },
+      "open_weights": true,
+      "limit": {
+        "context": 131072,
+        "output": 98304
+      },
+      "cost": {
+        "input": 0.57,
+        "output": 2.3
+      }
+    },
+    "moonshotai/kimi-k2.5": {
+      "id": "moonshotai/kimi-k2.5",
+      "name": "Kimi K2.5",
+      "description": "Earlier Kimi frontier model for long-context agents, coding, and multimodal work",
+      "family": "kimi-k2",
+      "attachment": true,
+      "reasoning": true,
+      "reasoning_options": [
+        {
+          "type": "toggle"
+        }
+      ],
+      "tool_call": true,
+      "interleaved": {
+        "field": "reasoning_details"
+      },
+      "structured_output": true,
+      "temperature": true,
+      "knowledge": "2025-01",
+      "release_date": "2026-01",
+      "last_updated": "2026-01",
+      "modalities": {
+        "input": [
+          "text",
+          "image"
+        ],
+        "output": [
+          "text"
+        ]
+      },
+      "open_weights": true,
+      "limit": {
+        "context": 262144,
+        "output": 235929
+      },
+      "cost": {
+        "input": 0.45,
+        "output": 2.25,
+        "cache_read": 0.07
+      }
+    },
+    "inference-net/schematron-v2-small": {
+      "id": "inference-net/schematron-v2-small",
+      "name": "Schematron V2 Small",
+      "description": "Efficient model for low-latency assistance, extraction, and routine automation",
+      "attachment": false,
+      "reasoning": false,
+      "tool_call": false,
+      "structured_output": true,
+      "temperature": true,
+      "release_date": "2026-09-12",
+      "last_updated": "2026-09-12",
+      "modalities": {
+        "input": [
+          "text"
+        ],
+        "output": [
+          "text"
+        ]
+      },
+      "open_weights": true,
+      "limit": {
+        "context": 128000,
+        "output": 4096
+      },
+      "cost": {
+        "input": 0.05,
+        "output": 0.23,
+        "cache_read": 0.05
+      }
+    },
+    "inference-net/schematron-v2-turbo": {
+      "id": "inference-net/schematron-v2-turbo",
+      "name": "Schematron V2 Turbo",
+      "description": "Efficient model for low-latency assistance, extraction, and routine automation",
+      "attachment": false,
+      "reasoning": false,
+      "tool_call": false,
+      "structured_output": true,
+      "temperature": true,
+      "release_date": "2026-09-12",
+      "last_updated": "2026-09-12",
       "modalities": {
         "input": [
           "text"
@@ -13007,19 +14122,20 @@
       },
       "open_weights": true,
       "limit": {
-        "context": 131072,
-        "output": 100352
+        "context": 128000,
+        "output": 8192
       },
       "cost": {
-        "input": 0.57,
-        "output": 2.3
+        "input": 0.03,
+        "output": 0.15,
+        "cache_read": 0.03
       }
     },
-    "moonshotai/kimi-k2.5": {
-      "id": "moonshotai/kimi-k2.5",
-      "name": "Kimi K2.5",
-      "description": "Earlier Kimi frontier model for long-context agents, coding, and multimodal work",
-      "family": "kimi-k2",
+    "cohere/command-a-plus": {
+      "id": "cohere/command-a-plus",
+      "name": "Command A+",
+      "description": "Cohere command model for multilingual enterprise agents, tools, and chat",
+      "family": "command-a",
       "attachment": true,
       "reasoning": true,
       "reasoning_options": [
@@ -13028,14 +14144,10 @@
         }
       ],
       "tool_call": true,
-      "interleaved": {
-        "field": "reasoning_details"
-      },
       "structured_output": true,
       "temperature": true,
-      "knowledge": "2025-01",
-      "release_date": "2026-01",
-      "last_updated": "2026-01",
+      "release_date": "2026-09-22",
+      "last_updated": "2026-09-22",
       "modalities": {
         "input": [
           "text",
@@ -13045,15 +14157,15 @@
           "text"
         ]
       },
-      "open_weights": true,
+      "open_weights": false,
       "limit": {
-        "context": 262144,
-        "output": 235929
+        "context": 192000,
+        "output": 64000
       },
       "cost": {
-        "input": 0.45,
-        "output": 2.25,
-        "cache_read": 0.07
+        "input": 0.3,
+        "output": 1.5,
+        "cache_read": 0.15
       }
     },
     "cohere/north-mini-code:free": {
@@ -13224,7 +14336,14 @@
       "reasoning": true,
       "reasoning_options": [
         {
-          "type": "toggle"
+          "type": "effort",
+          "values": [
+            "none",
+            "minimal",
+            "low",
+            "medium",
+            "high"
+          ]
         }
       ],
       "tool_call": true,
@@ -13260,7 +14379,16 @@
       "reasoning": true,
       "reasoning_options": [
         {
-          "type": "toggle"
+          "type": "effort",
+          "values": [
+            "none",
+            "minimal",
+            "low",
+            "medium",
+            "high",
+            "xhigh",
+            "max"
+          ]
         }
       ],
       "tool_call": true,
@@ -13282,9 +14410,54 @@
         "output": 131072
       },
       "cost": {
-        "input": 0.03,
-        "output": 0.12,
-        "cache_read": 0.006
+        "input": 0.09,
+        "output": 0.36,
+        "cache_read": 0.018
+      }
+    },
+    "upstage/solar-mini4": {
+      "id": "upstage/solar-mini4",
+      "name": "Solar Mini 4",
+      "description": "Efficient model for low-latency assistance, extraction, and routine automation",
+      "family": "solar",
+      "attachment": false,
+      "reasoning": true,
+      "reasoning_options": [
+        {
+          "type": "effort",
+          "values": [
+            "none",
+            "minimal",
+            "low",
+            "medium",
+            "high",
+            "xhigh",
+            "max"
+          ]
+        }
+      ],
+      "tool_call": true,
+      "structured_output": true,
+      "temperature": true,
+      "release_date": "2026-09-23",
+      "last_updated": "2026-09-23",
+      "modalities": {
+        "input": [
+          "text"
+        ],
+        "output": [
+          "text"
+        ]
+      },
+      "open_weights": false,
+      "limit": {
+        "context": 524288,
+        "output": 131072
+      },
+      "cost": {
+        "input": 0.05,
+        "output": 0.2,
+        "cache_read": 0.005
       }
     },
     "arcee-ai/trinity-large-thinking": {
@@ -13791,19 +14964,62 @@
       "open_weights": true,
       "limit": {
         "context": 1048576,
-        "output": 128000
+        "output": 131072
+      },
+      "cost": {
+        "input": 0.6496,
+        "output": 2.0416,
+        "cache_read": 0.12064
+      }
+    },
+    "z-ai/glm-5.3-flashx": {
+      "id": "z-ai/glm-5.3-flashx",
+      "name": "GLM 5.3 FlashX",
+      "description": "GLM vision model for visual reasoning, documents, and multimodal agents",
+      "family": "glm",
+      "attachment": true,
+      "reasoning": true,
+      "reasoning_options": [
+        {
+          "type": "effort",
+          "values": [
+            "low",
+            "high",
+            "max"
+          ]
+        }
+      ],
+      "tool_call": true,
+      "structured_output": false,
+      "temperature": true,
+      "release_date": "2026-09-18",
+      "last_updated": "2026-09-18",
+      "modalities": {
+        "input": [
+          "text",
+          "image",
+          "video"
+        ],
+        "output": [
+          "text"
+        ]
+      },
+      "open_weights": false,
+      "limit": {
+        "context": 1048576,
+        "output": 131072
       },
       "cost": {
-        "input": 0.28,
-        "output": 0.88,
-        "cache_read": 0.052
+        "input": 0.37,
+        "output": 1.25,
+        "cache_read": 0.09
       }
     },
     "z-ai/glm-5.3-flash": {
       "id": "z-ai/glm-5.3-flash",
       "name": "GLM-5.3-Flash",
       "description": "GLM vision model for visual reasoning, documents, and multimodal agents",
-      "family": "glm",
+      "family": "glm-flash",
       "attachment": true,
       "reasoning": true,
       "reasoning_options": [
@@ -13834,12 +15050,12 @@
       "open_weights": true,
       "limit": {
         "context": 1310720,
-        "output": 131072
+        "output": 943718
       },
       "cost": {
         "input": 0.15,
         "output": 0.5,
-        "cache_read": 0.03
+        "cache_read": 0.05
       }
     },
     "z-ai/glm-4.5": {
@@ -13917,6 +15133,48 @@
         "cache_read": 0.11
       }
     },
+    "z-ai/glm-5.2:free": {
+      "id": "z-ai/glm-5.2:free",
+      "name": "GLM 5.2 (free)",
+      "description": "Flagship GLM model for hybrid reasoning, coding, and agentic engineering",
+      "family": "glm",
+      "attachment": false,
+      "reasoning": true,
+      "reasoning_options": [
+        {
+          "type": "toggle"
+        },
+        {
+          "type": "effort",
+          "values": [
+            "high",
+            "xhigh"
+          ]
+        }
+      ],
+      "tool_call": false,
+      "structured_output": false,
+      "temperature": true,
+      "release_date": "2026-06-13",
+      "last_updated": "2026-06-13",
+      "modalities": {
+        "input": [
+          "text"
+        ],
+        "output": [
+          "text"
+        ]
+      },
+      "open_weights": true,
+      "limit": {
+        "context": 32768,
+        "output": 29491
+      },
+      "cost": {
+        "input": 0,
+        "output": 0
+      }
+    },
     "z-ai/glm-5": {
       "id": "z-ai/glm-5",
       "name": "GLM-5",
@@ -13995,6 +15253,47 @@
         "cache_read": 0.1794
       }
     },
+    "z-ai/glm-5.3-prime": {
+      "id": "z-ai/glm-5.3-prime",
+      "name": "GLM 5.3 Prime",
+      "description": "Flagship GLM model for hybrid reasoning, coding, and agentic engineering",
+      "family": "glm",
+      "attachment": false,
+      "reasoning": true,
+      "reasoning_options": [
+        {
+          "type": "effort",
+          "values": [
+            "low",
+            "high",
+            "max"
+          ]
+        }
+      ],
+      "tool_call": true,
+      "structured_output": false,
+      "temperature": true,
+      "release_date": "2026-09-23",
+      "last_updated": "2026-09-23",
+      "modalities": {
+        "input": [
+          "text"
+        ],
+        "output": [
+          "text"
+        ]
+      },
+      "open_weights": false,
+      "limit": {
+        "context": 1000000,
+        "output": 131072
+      },
+      "cost": {
+        "input": 2.8,
+        "output": 8.8,
+        "cache_read": 0.56
+      }
+    },
     "z-ai/glm-5-turbo": {
       "id": "z-ai/glm-5-turbo",
       "name": "GLM-5-Turbo",
@@ -14067,12 +15366,12 @@
       "open_weights": true,
       "limit": {
         "context": 1310720,
-        "output": 943718
+        "output": 131072
       },
       "cost": {
-        "input": 1.4,
-        "output": 4.4,
-        "cache_read": 0.26
+        "input": 0.84,
+        "output": 2.64,
+        "cache_read": 0.156
       }
     },
     "z-ai/glm-5v-turbo": {
@@ -14412,6 +15711,50 @@
         "input": 0.1,
         "output": 0.2
       }
+    },
+    "stealth/space-bunny-alpha": {
+      "id": "stealth/space-bunny-alpha",
+      "name": "Space Bunny Alpha",
+      "description": "Multimodal reasoning model for visual analysis, planning, and tool use",
+      "family": "alpha",
+      "attachment": true,
+      "reasoning": true,
+      "reasoning_options": [
+        {
+          "type": "effort",
+          "values": [
+            "low",
+            "medium",
+            "high",
+            "xhigh",
+            "max"
+          ]
+        }
+      ],
+      "tool_call": true,
+      "structured_output": false,
+      "temperature": true,
+      "release_date": "2026-09-23",
+      "last_updated": "2026-09-23",
+      "modalities": {
+        "input": [
+          "text",
+          "image",
+          "video"
+        ],
+        "output": [
+          "text"
+        ]
+      },
+      "open_weights": false,
+      "limit": {
+        "context": 1000000,
+        "output": 524288
+      },
+      "cost": {
+        "input": 0,
+        "output": 0
+      }
     }
   }
 }