@desplega.ai/agent-swarm 1.156.0 → 1.158.0

package/src/be/modelsdev-cache.json

@@ -147175,6 +147175,36 @@
     "name": "Anthropic",
     "doc": "https://docs.anthropic.com/en/docs/about-claude/models",
     "models": {
+      "claude-sonnet-5-5": {
+        "id": "claude-sonnet-5-5",
+        "name": "Claude Sonnet 5.5",
+        "reasoning": true,
+        "reasoning_options": [
+          {
+            "type": "effort",
+            "values": [
+              "low",
+              "medium",
+              "high",
+              "xhigh",
+              "max"
+            ]
+          }
+        ],
+        "knowledge": "2026-06",
+        "release_date": "2026-09-28",
+        "last_updated": "2026-09-28",
+        "cost": {
+          "input": 2,
+          "output": 10,
+          "cache_read": 0.2,
+          "cache_write": 2.5
+        },
+        "limit": {
+          "context": 1000000,
+          "output": 128000
+        }
+      },
       "claude-opus-5-5": {
         "id": "claude-opus-5-5",
         "name": "Claude Opus 5.5",
@@ -271813,6 +271843,1718 @@
           "input": 0,
           "output": 0
         }
+      },
+      "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
+        }
+      },
+      "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
+        }
+      },
+      "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
+        }
+      },
+      "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": [
+          {
+            "type": "toggle"
+          }
+        ],
+        "tool_call": true,
+        "structured_output": true,
+        "temperature": true,
+        "release_date": "2026-09-22",
+        "last_updated": "2026-09-22",
+        "modalities": {
+          "input": [
+            "text",
+            "image"
+          ],
+          "output": [
+            "text"
+          ]
+        },
+        "open_weights": false,
+        "limit": {
+          "context": 192000,
+          "output": 64000
+        },
+        "cost": {
+          "input": 0.3,
+          "output": 1.5,
+          "cache_read": 0.15
+        }
+      },
+      "deepseek/deepseek-v4.1-flash": {
+        "id": "deepseek/deepseek-v4.1-flash",
+        "name": "DeepSeek V4.1 Flash",
+        "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,
+        "knowledge": "2025-05",
+        "release_date": "2026-09-10",
+        "last_updated": "2026-09-10",
+        "modalities": {
+          "input": [
+            "text",
+            "image"
+          ],
+          "output": [
+            "text"
+          ]
+        },
+        "open_weights": true,
+        "limit": {
+          "context": 1048576,
+          "output": 384000
+        },
+        "cost": {
+          "input": 0.035,
+          "output": 0.29,
+          "cache_read": 0.001
+        }
+      },
+      "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
+        }
+      },
+      "perceptron/perceptron-mk1.5": {
+        "id": "perceptron/perceptron-mk1.5",
+        "name": "Perceptron Mk1.5",
+        "description": "Multimodal reasoning model for visual analysis, planning, and tool use",
+        "attachment": true,
+        "reasoning": true,
+        "reasoning_options": [
+          {
+            "type": "effort",
+            "values": [
+              "none",
+              "minimal",
+              "low",
+              "medium",
+              "high"
+            ]
+          }
+        ],
+        "tool_call": true,
+        "structured_output": true,
+        "temperature": true,
+        "release_date": "2026-09-25",
+        "last_updated": "2026-09-25",
+        "modalities": {
+          "input": [
+            "text",
+            "image",
+            "video",
+            "audio"
+          ],
+          "output": [
+            "text"
+          ]
+        },
+        "open_weights": false,
+        "limit": {
+          "context": 36864,
+          "output": 8192
+        },
+        "cost": {
+          "input": 0.15,
+          "output": 1.5
+        }
+      },
+      "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-5.3-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": 0.37,
+          "output": 1.25,
+          "cache_read": 0.09
+        }
+      },
+      "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"
+          ],
+          "output": [
+            "text"
+          ]
+        },
+        "open_weights": true,
+        "limit": {
+          "context": 128000,
+          "output": 8192
+        },
+        "cost": {
+          "input": 0.03,
+          "output": 0.15,
+          "cache_read": 0.03
+        }
+      },
+      "~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-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": false,
+        "limit": {
+          "context": 1050000,
+          "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-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-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-astra",
+        "attachment": true,
+        "reasoning": true,
+        "reasoning_options": [
+          {
+            "type": "effort",
+            "values": [
+              "low",
+              "medium",
+              "high",
+              "xhigh",
+              "max"
+            ]
+          }
+        ],
+        "tool_call": true,
+        "structured_output": true,
+        "temperature": false,
+        "release_date": "2026-09-11",
+        "last_updated": "2026-09-11",
+        "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
+          }
+        }
+      },
+      "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
+          }
+        }
+      },
+      "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
+        }
+      },
+      "~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": 384000
+        },
+        "cost": {
+          "input": 0.035,
+          "output": 0.29,
+          "cache_read": 0.001
+        }
+      },
+      "~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"
+          },
+          {
+            "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": 943718
+        },
+        "cost": {
+          "input": 0.128,
+          "output": 1.9584,
+          "cache_read": 0.08832
+        }
+      },
+      "fireworks/ember-1": {
+        "id": "fireworks/ember-1",
+        "name": "Ember-1",
+        "description": "Multimodal reasoning model for visual analysis, planning, and tool use",
+        "attachment": true,
+        "reasoning": true,
+        "reasoning_options": [
+          {
+            "type": "toggle"
+          },
+          {
+            "type": "effort",
+            "values": [
+              "low",
+              "high",
+              "max"
+            ]
+          }
+        ],
+        "tool_call": true,
+        "structured_output": true,
+        "temperature": true,
+        "release_date": "2026-09-24",
+        "last_updated": "2026-09-24",
+        "modalities": {
+          "input": [
+            "text",
+            "image"
+          ],
+          "output": [
+            "text"
+          ]
+        },
+        "open_weights": false,
+        "limit": {
+          "context": 1048576,
+          "output": 943718
+        },
+        "cost": {
+          "input": 3,
+          "output": 15,
+          "cache_read": 0.3
+        }
+      },
+      "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/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
+          }
+        }
+      },
+      "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,
+        "reasoning": true,
+        "reasoning_options": [
+          {
+            "type": "toggle"
+          }
+        ],
+        "tool_call": true,
+        "structured_output": true,
+        "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": 0.021,
+          "output": 0.0616,
+          "cache_read": 0.0042
+        }
+      },
+      "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": 1050000,
+          "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": 0.14,
+          "output": 0.28,
+          "cache_read": 0.0028
+        }
+      },
+      "inception/mercury-2.5": {
+        "id": "inception/mercury-2.5",
+        "name": "Mercury 2.5",
+        "description": "Reasoning model for deliberate analysis, multi-step problem solving, and tool use",
+        "family": "mercury",
+        "attachment": false,
+        "reasoning": true,
+        "reasoning_options": [
+          {
+            "type": "effort",
+            "values": [
+              "none",
+              "low",
+              "medium",
+              "high"
+            ]
+          }
+        ],
+        "tool_call": true,
+        "structured_output": true,
+        "temperature": true,
+        "release_date": "2026-09-08",
+        "last_updated": "2026-09-08",
+        "modalities": {
+          "input": [
+            "text"
+          ],
+          "output": [
+            "text"
+          ]
+        },
+        "open_weights": false,
+        "limit": {
+          "context": 260000,
+          "output": 65536
+        },
+        "cost": {
+          "input": 0.04,
+          "output": 0.15,
+          "cache_read": 0.004
+        }
+      },
+      "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-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
+        }
+      },
+      "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/qwen3.8-max-prime": {
+        "id": "qwen/qwen3.8-max-prime",
+        "name": "Qwen 3.8 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/qwen3.8-27b: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
+        }
+      },
+      "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": true,
+        "reasoning": true,
+        "reasoning_options": [
+          {
+            "type": "effort",
+            "values": [
+              "none",
+              "low",
+              "medium",
+              "high",
+              "xhigh",
+              "max"
+            ]
+          }
+        ],
+        "tool_call": true,
+        "structured_output": true,
+        "temperature": false,
+        "release_date": "2026-09-22",
+        "last_updated": "2026-09-22",
+        "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-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-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,
+        "reasoning": true,
+        "reasoning_options": [
+          {
+            "type": "effort",
+            "values": [
+              "none",
+              "low",
+              "medium",
+              "high",
+              "xhigh",
+              "max"
+            ]
+          }
+        ],
+        "tool_call": true,
+        "structured_output": true,
+        "temperature": false,
+        "release_date": "2026-09-22",
+        "last_updated": "2026-09-22",
+        "modalities": {
+          "input": [
+            "pdf",
+            "image",
+            "text"
+          ],
+          "output": [
+            "text"
+          ]
+        },
+        "open_weights": false,
+        "limit": {
+          "context": 1050000,
+          "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-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
+          }
+        }
       }
     }
   },
@@ -285547,6 +287289,121 @@
             "cache_write": 0.25
           }
         }
+      },
+      "gpt-daybreak-blue-latest": {
+        "id": "gpt-daybreak-blue-latest",
+        "name": "Daybreak Blue",
+        "description": "Alias for flagship general-purpose models with safeguards for defensive cybersecurity work",
+        "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": "2026-08-07",
+        "last_updated": "2026-08-07",
+        "modalities": {
+          "input": [
+            "text",
+            "image",
+            "pdf"
+          ],
+          "output": [
+            "text"
+          ]
+        },
+        "open_weights": false,
+        "limit": {
+          "context": 1050000,
+          "input": 922000,
+          "output": 128000
+        },
+        "cost": {
+          "input": 4,
+          "output": 20,
+          "cache_read": 0.4,
+          "cache_write": 5,
+          "tiers": [
+            {
+              "input": 8,
+              "output": 30,
+              "cache_read": 0.8,
+              "cache_write": 10,
+              "tier": {
+                "type": "context",
+                "size": 272000
+              }
+            }
+          ],
+          "context_over_200k": {
+            "input": 8,
+            "output": 30,
+            "cache_read": 0.8,
+            "cache_write": 10
+          }
+        }
+      },
+      "gpt-daybreak-red-latest": {
+        "id": "gpt-daybreak-red-latest",
+        "name": "Daybreak Red",
+        "description": "Alias for advanced cybersecurity models for authorized vulnerability research and security testing",
+        "family": "gpt",
+        "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": "2026-08-07",
+        "last_updated": "2026-08-07",
+        "modalities": {
+          "input": [
+            "text",
+            "image"
+          ],
+          "output": [
+            "text"
+          ]
+        },
+        "open_weights": false,
+        "limit": {
+          "context": 400000,
+          "input": 272000,
+          "output": 128000
+        },
+        "cost": {
+          "input": 12.5,
+          "output": 75,
+          "cache_read": 1.25,
+          "cache_write": 15.625
+        }
       }
     }
   },