llm.rb 15.4.0 → 15.4.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: de1f4eeee4762548e75eac2b5d4112de49cf446944b30c545b76e62750aad6c3
-  data.tar.gz: 4abc1d2d707717fde266b48bfa626f06d553514761653db8c3cd190cfcffb864
+  metadata.gz: 4647447cce1ccfc7e4f062cfa46b6dd0363ffd1a86537200a7877daff983cda3
+  data.tar.gz: 31502899d4a6443b893a48baf18c75d02311920166a6d791d671fa33600e93b9
 SHA512:
-  metadata.gz: c28cadd2a412e2623b472d3be7814aa51a462076782fc847bc73cdc57a601a630d909bb9b40c29d31dd7107b487bf169bdeb245e9803581df0d90d642694bc16
-  data.tar.gz: 2fd3c1905d2db4212958e98e537db76d37f0f30f5cee4dda3cbf351c7f0fffe1ce6eaa5b38553e80b9441b029e2edf78c4e9ea75c200b731638dbbe49bd947df
+  metadata.gz: ee244a4b0d7d317632e1ee2f3dc44b82926086a71f2ded6ba7e3189eff9636dba2eed5f97d4ed6c83140584d3807b4872303a20b369a123be2336c32671758a1
+  data.tar.gz: 7ed45ea9770afabb6522b6939c9d333c28a5892e40e32de271d03a8c5fb3f9fa15b5c2ace19e74ac80342bc65e04a7b5edb48b6799a612f5754b8ccccd33bdaf

data/CHANGELOG.md

@@ -17,6 +17,33 @@
 
 *No unreleased changes yet. Check back after the next release.*
 
+## v15.4.1
+
+Changes since `v15.4.0`.
+
+This release removes the gemspec's post-install message, so installing the gem
+no longer prints the r.uby.dev notice. It also refreshes the model registry
+with current model listings, limits, and pricing.
+
+### Core
+
+* **remove the gemspec post install message** <br>
+  The gemspec no longer sets `post_install_message`, so installing the
+  gem no longer prints the r.uby.dev website notice.
+
+### Registry
+
+* **refresh model metadata** <br>
+  Update `data/` with current model listings, limits, and pricing for the
+  Alibaba, Bedrock, DeepSeek, Google, Moonshot, and OpenRouter registries.
+  Bedrock adds the Kimi K3 and GPT-6 Sol and GPT-6 Luna families in both
+  the global and US regions and raises the context limit to 1M tokens for
+  two models, while Moonshot raises the Kimi K3 output limit to 1M tokens.
+  OpenRouter adds `qwen/qwen3.8-max-prime`, `z-ai/glm-5.3-prime`,
+  `upstage/solar-mini4`, the Aion 3.5 models, and `stealth/space-bunny-alpha`,
+  drops `mistralai/devstral-2512` and a free Ling 3.0 Flash VL entry, and
+  reprices several DeepSeek and Mistral models.
+
 ## v15.4.0
 
 Changes since `v15.3.0`.

data/README.md

@@ -19,10 +19,13 @@ on CRuby. It has zero runtime dependencies by default, supports
 concurrent and parallel tool execution and has a single coherent API
 that spans 14+ providers.
 
-The most effective way to learn about llm.rb is to ask [the r.uby.dev chatbot](https://r.uby.dev)
-a question. It is connected to the llm.rb GitHub repository, backed by
-ActiveRecord and uses the builtin MCP feature to connect to GitHub. The chatbot
-is an llm.rb agent that is deployed with [roda-llm](https://github.com/r-uby-dev/roda-llm#readme).
+It is possible to see llm.rb in action on the
+[the r.uby.dev website](https://r.uby.dev) where
+I am working on building an agentic platform that
+users can use to manage multiple agents that are
+specialized in different areas, and have access to
+different services (eg GitHub, etc). Check it out if
+curious. Still in early development.
 
 ## Install
 
@@ -362,9 +365,6 @@ for both Rack-based / Rails-based applications. On databases
 where it is supported, such as PostgreSQL, the column can be optimized by using
 the `jsonb` type.
 
-The following example is based on the agent used to power the
-[r.uby.dev chatbot](https://r.uby.dev).
-
 ```ruby
 require "active_record"
 require "llm"
@@ -1030,10 +1030,8 @@ IO.copy_stream res.images[0], "rocket-with-dog.svg"
 <summary>Where can I see llm.rb in action?</summary>
 <br>
 
-The [r.uby.dev](https://r.uby.dev) website deploys
-multiple llm.rb agents that guests can interact with
-and there is even an agent that is connected to this
-GitHub repository.
+The [r.uby.dev](https://r.uby.dev) website.
+
 </details>
 <details>
 <summary>What about local LLM support?</summary>

data/data/alibaba.json

@@ -38,7 +38,7 @@
       "open_weights": false,
       "limit": {
         "context": 1000000,
-        "output": 65536
+        "output": 131072
       },
       "cost": {
         "input": 2.5,
@@ -1848,7 +1848,7 @@
       "open_weights": false,
       "limit": {
         "context": 1000000,
-        "output": 65536
+        "output": 131072
       },
       "cost": {
         "input": 0.5,

data/data/bedrock.json

@@ -566,7 +566,7 @@
       },
       "open_weights": false,
       "limit": {
-        "context": 272000,
+        "context": 1000000,
         "output": 128000
       },
       "provider": {
@@ -886,7 +886,7 @@
       },
       "open_weights": false,
       "limit": {
-        "context": 272000,
+        "context": 1000000,
         "output": 128000
       },
       "provider": {
@@ -1587,6 +1587,41 @@
         "cache_write": 6.875
       }
     },
+    "global.moonshotai.kimi-k3": {
+      "id": "global.moonshotai.kimi-k3",
+      "name": "Kimi K3 (Global)",
+      "description": "Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work",
+      "family": "kimi-k3",
+      "attachment": true,
+      "reasoning": true,
+      "reasoning_options": [],
+      "tool_call": true,
+      "interleaved": true,
+      "structured_output": true,
+      "temperature": false,
+      "release_date": "2026-07-16",
+      "last_updated": "2026-07-16",
+      "modalities": {
+        "input": [
+          "text",
+          "image"
+        ],
+        "output": [
+          "text"
+        ]
+      },
+      "open_weights": true,
+      "limit": {
+        "context": 1048576,
+        "output": 131072
+      },
+      "cost": {
+        "input": 3,
+        "output": 15,
+        "cache_read": 0.3,
+        "cache_write": 3.75
+      }
+    },
     "apac.amazon.nova-pro-v1:0": {
       "id": "apac.amazon.nova-pro-v1:0",
       "name": "Nova Pro (APAC)",
@@ -1675,6 +1710,41 @@
         "cache_write": 4.125
       }
     },
+    "us.moonshotai.kimi-k3": {
+      "id": "us.moonshotai.kimi-k3",
+      "name": "Kimi K3 (US)",
+      "description": "Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work",
+      "family": "kimi-k3",
+      "attachment": true,
+      "reasoning": true,
+      "reasoning_options": [],
+      "tool_call": true,
+      "interleaved": true,
+      "structured_output": true,
+      "temperature": false,
+      "release_date": "2026-07-16",
+      "last_updated": "2026-07-16",
+      "modalities": {
+        "input": [
+          "text",
+          "image"
+        ],
+        "output": [
+          "text"
+        ]
+      },
+      "open_weights": true,
+      "limit": {
+        "context": 1048576,
+        "output": 131072
+      },
+      "cost": {
+        "input": 3.3,
+        "output": 16.5,
+        "cache_read": 0.33,
+        "cache_write": 4.125
+      }
+    },
     "apac.amazon.nova-lite-v1:0": {
       "id": "apac.amazon.nova-lite-v1:0",
       "name": "Nova Lite (APAC)",
@@ -1933,6 +2003,72 @@
         "output": 1.2
       }
     },
+    "us.openai.gpt-6-luna": {
+      "id": "us.openai.gpt-6-luna",
+      "name": "GPT-6 Luna (US)",
+      "description": "OpenAI's most efficient model for focused, high-volume 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"
+        ],
+        "output": [
+          "text"
+        ]
+      },
+      "open_weights": false,
+      "limit": {
+        "context": 1050000,
+        "input": 922000,
+        "output": 128000
+      },
+      "cost": {
+        "input": 0.11,
+        "output": 0.55,
+        "cache_read": 0.011,
+        "cache_write": 0.1375,
+        "tiers": [
+          {
+            "input": 0.22,
+            "output": 0.825,
+            "cache_read": 0.022,
+            "cache_write": 0.275,
+            "tier": {
+              "type": "context",
+              "size": 272000
+            }
+          }
+        ],
+        "context_over_200k": {
+          "input": 0.22,
+          "output": 0.825,
+          "cache_read": 0.022,
+          "cache_write": 0.275
+        }
+      }
+    },
     "meta.llama3-3-70b-instruct-v1:0": {
       "id": "meta.llama3-3-70b-instruct-v1:0",
       "name": "Llama 3.3 70B Instruct",
@@ -3258,6 +3394,72 @@
         "cache_write": 0.33
       }
     },
+    "global.openai.gpt-6-sol": {
+      "id": "global.openai.gpt-6-sol",
+      "name": "GPT-6 Sol (Global)",
+      "description": "OpenAI model for complex coding and agentic workflows",
+      "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"
+        ],
+        "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
+        }
+      }
+    },
     "global.xai.grok-4.6": {
       "id": "global.xai.grok-4.6",
       "name": "Grok 4.6 (Global)",
@@ -4572,6 +4774,72 @@
         }
       }
     },
+    "global.openai.gpt-6-luna": {
+      "id": "global.openai.gpt-6-luna",
+      "name": "GPT-6 Luna (Global)",
+      "description": "OpenAI's most efficient model for focused, high-volume 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"
+        ],
+        "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
+        }
+      }
+    },
     "us.anthropic.claude-fable-5-1": {
       "id": "us.anthropic.claude-fable-5-1",
       "name": "Claude Fable 5.1 (US)",
@@ -5349,6 +5617,72 @@
         "cache_write": 0.06
       }
     },
+    "us.openai.gpt-6-sol": {
+      "id": "us.openai.gpt-6-sol",
+      "name": "GPT-6 Sol (US)",
+      "description": "OpenAI model for complex coding and agentic workflows",
+      "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"
+        ],
+        "output": [
+          "text"
+        ]
+      },
+      "open_weights": false,
+      "limit": {
+        "context": 1050000,
+        "input": 922000,
+        "output": 128000
+      },
+      "cost": {
+        "input": 2.2,
+        "output": 11,
+        "cache_read": 0.22,
+        "cache_write": 2.75,
+        "tiers": [
+          {
+            "input": 4.4,
+            "output": 16.5,
+            "cache_read": 0.44,
+            "cache_write": 5.5,
+            "tier": {
+              "type": "context",
+              "size": 272000
+            }
+          }
+        ],
+        "context_over_200k": {
+          "input": 4.4,
+          "output": 16.5,
+          "cache_read": 0.44,
+          "cache_write": 5.5
+        }
+      }
+    },
     "global.anthropic.claude-opus-4-7": {
       "id": "global.anthropic.claude-opus-4-7",
       "name": "Claude Opus 4.7 (Global)",

data/data/deepseek.json

@@ -49,7 +49,7 @@
       "open_weights": true,
       "limit": {
         "context": 1000000,
-        "output": 384000
+        "output": 393216
       },
       "status": "deprecated",
       "cost": {
@@ -100,7 +100,7 @@
       "open_weights": true,
       "limit": {
         "context": 1000000,
-        "output": 384000
+        "output": 393216
       },
       "status": "deprecated",
       "cost": {
@@ -149,7 +149,7 @@
       "open_weights": true,
       "limit": {
         "context": 1000000,
-        "output": 384000
+        "output": 393216
       },
       "cost": {
         "input": 0.435,
@@ -199,7 +199,7 @@
       "open_weights": true,
       "limit": {
         "context": 1000000,
-        "output": 384000
+        "output": 393216
       },
       "cost": {
         "input": 0.15,

data/data/google.json

@@ -138,7 +138,7 @@
       "open_weights": false,
       "limit": {
         "context": 65536,
-        "output": 65536
+        "output": 4096
       },
       "cost": {
         "input": 0.25,
@@ -933,8 +933,8 @@
       },
       "open_weights": false,
       "limit": {
-        "context": 65536,
-        "output": 65536
+        "context": 131072,
+        "output": 32768
       },
       "cost": {
         "input": 0.5,

data/data/moonshot.json

@@ -167,7 +167,7 @@
       "open_weights": true,
       "limit": {
         "context": 1048576,
-        "output": 131072
+        "output": 1048576
       },
       "cost": {
         "input": 3,

data/data/openrouter.json

@@ -1675,6 +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",
@@ -2189,6 +2234,46 @@
         "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",
@@ -2282,6 +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",
@@ -2623,9 +2748,9 @@
         "output": 943718
       },
       "cost": {
-        "input": 0.03,
-        "output": 0.8,
-        "cache_read": 0.008
+        "input": 0.038,
+        "output": 0.55,
+        "cache_read": 0.0228
       }
     },
     "~deepseek/deepseek-pro-latest": {
@@ -2664,12 +2789,12 @@
       "open_weights": false,
       "limit": {
         "context": 1048576,
-        "output": 384000
+        "output": 393216
       },
       "cost": {
-        "input": 0.4,
-        "output": 4.3,
-        "cache_read": 0.033
+        "input": 0.38544,
+        "output": 1.15632,
+        "cache_read": 0.012264
       }
     },
     "~deepseek/deepseek-flash-latest": {
@@ -2712,9 +2837,9 @@
         "output": 943718
       },
       "cost": {
-        "input": 0.1,
-        "output": 0.5,
-        "cache_read": 0.01
+        "input": 0.099,
+        "output": 0.6,
+        "cache_read": 0.06
       }
     },
     "dots-studio/dots-3-note-preview:free": {
@@ -3280,39 +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",
@@ -3760,21 +3852,20 @@
       "tool_call": true,
       "structured_output": true,
       "temperature": true,
-      "knowledge": "2026-09-22",
       "release_date": "2026-09-22",
       "last_updated": "2026-09-22",
       "modalities": {
         "input": [
           "text",
           "image",
-          "video",
-          "audio"
+          "audio",
+          "video"
         ],
         "output": [
           "text"
         ]
       },
-      "open_weights": false,
+      "open_weights": true,
       "limit": {
         "context": 1048576,
         "output": 131072
@@ -3806,14 +3897,14 @@
         "input": [
           "text",
           "image",
-          "video",
-          "audio"
+          "audio",
+          "video"
         ],
         "output": [
           "text"
         ]
       },
-      "open_weights": false,
+      "open_weights": true,
       "limit": {
         "context": 1048576,
         "output": 131072
@@ -3839,21 +3930,20 @@
       "tool_call": true,
       "structured_output": true,
       "temperature": true,
-      "knowledge": "2026-09-22",
       "release_date": "2026-09-22",
       "last_updated": "2026-09-22",
       "modalities": {
         "input": [
           "text",
           "image",
-          "video",
-          "audio"
+          "audio",
+          "video"
         ],
         "output": [
           "text"
         ]
       },
-      "open_weights": false,
+      "open_weights": true,
       "limit": {
         "context": 1048576,
         "output": 131072
@@ -4319,10 +4409,10 @@
       "open_weights": true,
       "limit": {
         "context": 262144,
-        "output": 235929
+        "output": 131072
       },
       "cost": {
-        "input": 0.07,
+        "input": 0.08,
         "output": 0.2,
         "cache_read": 0.04
       }
@@ -8421,8 +8511,8 @@
         "output": 943718
       },
       "cost": {
-        "input": 1.05,
-        "output": 13,
+        "input": 1.4989,
+        "output": 10.758,
         "cache_read": 0.3
       }
     },
@@ -8618,9 +8708,9 @@
         "output": 384000
       },
       "cost": {
-        "input": 1.32,
-        "output": 3.96,
-        "cache_read": 0.044
+        "input": 0.462,
+        "output": 1.386,
+        "cache_read": 0.0154
       }
     },
     "deepseek/deepseek-v4-flash-0731": {
@@ -8710,9 +8800,9 @@
         "output": 384000
       },
       "cost": {
-        "input": 0.088606,
-        "output": 0.177212,
-        "cache_read": 0.017721
+        "input": 0.07168,
+        "output": 0.14336,
+        "cache_read": 0.014336
       }
     },
     "deepseek/deepseek-v4.1-flash": {
@@ -8753,12 +8843,12 @@
       "open_weights": true,
       "limit": {
         "context": 1048576,
-        "output": 943718
+        "output": 393216
       },
       "cost": {
-        "input": 0.1,
-        "output": 0.5,
-        "cache_read": 0.01
+        "input": 0.15,
+        "output": 0.6,
+        "cache_read": 0.003
       }
     },
     "deepseek/deepseek-r1": {
@@ -9045,9 +9135,9 @@
         "output": 384000
       },
       "cost": {
-        "input": 0.95526,
-        "output": 1.91052,
-        "cache_read": 0.079605
+        "input": 0.946386,
+        "output": 1.892772,
+        "cache_read": 0.078866
       }
     },
     "deepseek/deepseek-chat-v3-0324": {
@@ -9696,43 +9786,6 @@
         "output": 0
       }
     },
-    "inclusionai/ling-3.0-flash-vl:free": {
-      "id": "inclusionai/ling-3.0-flash-vl:free",
-      "name": "Ling 3.0 Flash VL (free)",
-      "description": "Multimodal reasoning model for visual analysis, planning, and tool use",
-      "family": "ling",
-      "attachment": true,
-      "reasoning": true,
-      "reasoning_options": [
-        {
-          "type": "toggle"
-        }
-      ],
-      "tool_call": true,
-      "structured_output": false,
-      "temperature": true,
-      "release_date": "2026-09-10",
-      "last_updated": "2026-09-10",
-      "modalities": {
-        "input": [
-          "text",
-          "image",
-          "video"
-        ],
-        "output": [
-          "text"
-        ]
-      },
-      "open_weights": true,
-      "limit": {
-        "context": 262144,
-        "output": 32768
-      },
-      "cost": {
-        "input": 0,
-        "output": 0
-      }
-    },
     "inclusionai/ling-3.0-flash-vl": {
       "id": "inclusionai/ling-3.0-flash-vl",
       "name": "Ling 3.0 Flash VL",
@@ -9762,7 +9815,7 @@
       },
       "open_weights": true,
       "limit": {
-        "context": 131072,
+        "context": 262144,
         "output": 32768
       },
       "cost": {
@@ -13753,9 +13806,9 @@
         "output": 131072
       },
       "cost": {
-        "input": 0.5625,
-        "output": 2.5,
-        "cache_read": 0.125
+        "input": 0.5614,
+        "output": 1.7644,
+        "cache_read": 0.10426
       }
     },
     "moonshotai/kimi-k2-0905": {
@@ -14362,6 +14415,51 @@
         "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": {
       "id": "arcee-ai/trinity-large-thinking",
       "name": "Trinity Large Thinking",
@@ -14431,9 +14529,9 @@
         "output": 128000
       },
       "cost": {
-        "input": 0.132,
-        "output": 0.528,
-        "cache_read": 0.033
+        "input": 0.0825,
+        "output": 0.33,
+        "cache_read": 0.020625
       }
     },
     "tencent/hy4-preview": {
@@ -14914,7 +15012,7 @@
       "cost": {
         "input": 0.37,
         "output": 1.25,
-        "cache_read": 0.075
+        "cache_read": 0.09
       }
     },
     "z-ai/glm-5.3-flash": {
@@ -15155,6 +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",
@@ -15572,6 +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
+      }
     }
   }
 }

data/lib/llm/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module LLM
-  VERSION = "15.4.0"
+  VERSION = "15.4.1"
 end

data/llm.gemspec

@@ -34,12 +34,6 @@ DESCRIPTION
   ]
   spec.executables = ["llm.rb"]
   spec.require_paths = ["lib"]
-  spec.post_install_message = "\n" \
-                              "Want to see what I'm building with llm.rb? " \
-                              "\n" \
-                              "Checkout the https://r.uby.dev website." \
-                              "\n\n"
-
   spec.add_development_dependency "webmock", "~> 3.24.0"
   spec.add_development_dependency "yard", "~> 0.9.37"
   spec.add_development_dependency "redcarpet", "~> 3.6"

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: llm.rb
 version: !ruby/object:Gem::Version
-  version: 15.4.0
+  version: 15.4.1
 platform: ruby
 authors:
 - Robert Gleeson
@@ -695,8 +695,6 @@ metadata:
   source_code_uri: https://github.com/r-uby-dev/llm
   documentation_uri: https://r.uby.dev
   changelog_uri: https://github.com/r-uby-dev/llm/blob/main/CHANGELOG.md
-post_install_message: "\nWant to see what I'm building with llm.rb? \nCheckout the
-  https://r.uby.dev website.\n\n"
 rdoc_options: []
 require_paths:
 - lib