@oh-my-pi/pi-catalog 16.1.14 → 16.1.16

package/package.json

@@ -1,7 +1,7 @@
 {
 	"type": "module",
 	"name": "@oh-my-pi/pi-catalog",
-	"version": "16.1.14",
+	"version": "16.1.16",
 	"description": "Model catalog for omp: bundled model database, provider discovery descriptors, model identity, classification, and equivalence",
 	"homepage": "https://omp.sh",
 	"author": "Can Boluk",
@@ -34,12 +34,12 @@
 	},
 	"dependencies": {
 		"@bufbuild/protobuf": "^2.12.0",
-		"@oh-my-pi/pi-utils": "16.1.14",
+		"@oh-my-pi/pi-utils": "16.1.16",
 		"arktype": "^2.2.0",
 		"zod": "^4"
 	},
 	"devDependencies": {
-		"@oh-my-pi/pi-ai": "16.1.14",
+		"@oh-my-pi/pi-ai": "16.1.16",
 		"@types/bun": "^1.3.14"
 	},
 	"engines": {

package/src/models.json

@@ -20926,7 +20926,7 @@
 	"huggingface": {
 		"deepseek-ai/DeepSeek-R1": {
 			"id": "deepseek-ai/DeepSeek-R1",
-			"name": "DeepSeek R1",
+			"name": "DeepSeek-R1",
 			"api": "openai-completions",
 			"provider": "huggingface",
 			"baseUrl": "https://router.huggingface.co/v1",
@@ -20935,13 +20935,13 @@
 				"text"
 			],
 			"cost": {
-				"input": 3,
-				"output": 7,
-				"cacheRead": 3,
-				"cacheWrite": 3
+				"input": 0.7,
+				"output": 2.5,
+				"cacheRead": 0,
+				"cacheWrite": 0
 			},
-			"contextWindow": 131072,
-			"maxTokens": 8192,
+			"contextWindow": 64000,
+			"maxTokens": 32768,
 			"thinking": {
 				"mode": "effort",
 				"efforts": [
@@ -21051,6 +21051,42 @@
 				}
 			}
 		},
+		"deepseek-ai/DeepSeek-V4-Flash": {
+			"id": "deepseek-ai/DeepSeek-V4-Flash",
+			"name": "DeepSeek V4 Flash",
+			"api": "openai-completions",
+			"provider": "huggingface",
+			"baseUrl": "https://router.huggingface.co/v1",
+			"reasoning": true,
+			"input": [
+				"text"
+			],
+			"cost": {
+				"input": 0.14,
+				"output": 0.28,
+				"cacheRead": 0,
+				"cacheWrite": 0
+			},
+			"contextWindow": 1048576,
+			"maxTokens": 384000,
+			"thinking": {
+				"mode": "effort",
+				"efforts": [
+					"minimal",
+					"low",
+					"medium",
+					"high",
+					"xhigh"
+				],
+				"effortMap": {
+					"minimal": "high",
+					"low": "high",
+					"medium": "high",
+					"high": "high",
+					"xhigh": "max"
+				}
+			}
+		},
 		"deepseek-ai/DeepSeek-V4-Pro": {
 			"id": "deepseek-ai/DeepSeek-V4-Pro",
 			"name": "DeepSeek V4 Pro",
@@ -21087,6 +21123,85 @@
 				}
 			}
 		},
+		"google/gemma-4-26B-A4B-it": {
+			"id": "google/gemma-4-26B-A4B-it",
+			"name": "Gemma 4 26B A4B IT",
+			"api": "openai-completions",
+			"provider": "huggingface",
+			"baseUrl": "https://router.huggingface.co/v1",
+			"reasoning": true,
+			"input": [
+				"text",
+				"image"
+			],
+			"cost": {
+				"input": 0.13,
+				"output": 0.4,
+				"cacheRead": 0,
+				"cacheWrite": 0
+			},
+			"contextWindow": 262144,
+			"maxTokens": 32768,
+			"thinking": {
+				"mode": "effort",
+				"efforts": [
+					"minimal",
+					"low",
+					"medium",
+					"high",
+					"xhigh"
+				]
+			}
+		},
+		"google/gemma-4-31B-it": {
+			"id": "google/gemma-4-31B-it",
+			"name": "Gemma 4 31B IT",
+			"api": "openai-completions",
+			"provider": "huggingface",
+			"baseUrl": "https://router.huggingface.co/v1",
+			"reasoning": true,
+			"input": [
+				"text",
+				"image"
+			],
+			"cost": {
+				"input": 0.14,
+				"output": 0.4,
+				"cacheRead": 0,
+				"cacheWrite": 0
+			},
+			"contextWindow": 262144,
+			"maxTokens": 32768,
+			"thinking": {
+				"mode": "effort",
+				"efforts": [
+					"minimal",
+					"low",
+					"medium",
+					"high",
+					"xhigh"
+				]
+			}
+		},
+		"meta-llama/Llama-3.3-70B-Instruct": {
+			"id": "meta-llama/Llama-3.3-70B-Instruct",
+			"name": "Llama-3.3-70B-Instruct",
+			"api": "openai-completions",
+			"provider": "huggingface",
+			"baseUrl": "https://router.huggingface.co/v1",
+			"reasoning": false,
+			"input": [
+				"text"
+			],
+			"cost": {
+				"input": 0.59,
+				"output": 0.79,
+				"cacheRead": 0,
+				"cacheWrite": 0
+			},
+			"contextWindow": 131072,
+			"maxTokens": 4096
+		},
 		"meta-llama/Llama-3.3-70B-Instruct-Turbo": {
 			"id": "meta-llama/Llama-3.3-70B-Instruct-Turbo",
 			"name": "Llama 3.3 70B",
@@ -21106,6 +21221,34 @@
 			"contextWindow": 131072,
 			"maxTokens": 8192
 		},
+		"MiniMaxAI/MiniMax-M2": {
+			"id": "MiniMaxAI/MiniMax-M2",
+			"name": "MiniMax-M2",
+			"api": "openai-completions",
+			"provider": "huggingface",
+			"baseUrl": "https://router.huggingface.co/v1",
+			"reasoning": true,
+			"input": [
+				"text"
+			],
+			"cost": {
+				"input": 0.3,
+				"output": 1.2,
+				"cacheRead": 0,
+				"cacheWrite": 0
+			},
+			"contextWindow": 204800,
+			"maxTokens": 128000,
+			"thinking": {
+				"mode": "effort",
+				"efforts": [
+					"low",
+					"medium",
+					"high"
+				],
+				"requiresEffort": true
+			}
+		},
 		"MiniMaxAI/MiniMax-M2.1": {
 			"id": "MiniMaxAI/MiniMax-M2.1",
 			"name": "MiniMax-M2.1",
@@ -21190,6 +21333,36 @@
 				"requiresEffort": true
 			}
 		},
+		"MiniMaxAI/MiniMax-M3": {
+			"id": "MiniMaxAI/MiniMax-M3",
+			"name": "MiniMax-M3",
+			"api": "openai-completions",
+			"provider": "huggingface",
+			"baseUrl": "https://router.huggingface.co/v1",
+			"reasoning": true,
+			"input": [
+				"text",
+				"image"
+			],
+			"cost": {
+				"input": 0.3,
+				"output": 1.2,
+				"cacheRead": 0,
+				"cacheWrite": 0
+			},
+			"contextWindow": 524288,
+			"maxTokens": 128000,
+			"thinking": {
+				"mode": "effort",
+				"efforts": [
+					"minimal",
+					"low",
+					"medium",
+					"high",
+					"xhigh"
+				]
+			}
+		},
 		"moonshotai/Kimi-K2-Instruct": {
 			"id": "moonshotai/Kimi-K2-Instruct",
 			"name": "Kimi-K2-Instruct",
@@ -21318,6 +21491,36 @@
 				]
 			}
 		},
+		"moonshotai/Kimi-K2.7-Code": {
+			"id": "moonshotai/Kimi-K2.7-Code",
+			"name": "Kimi K2.7 Code",
+			"api": "openai-completions",
+			"provider": "huggingface",
+			"baseUrl": "https://router.huggingface.co/v1",
+			"reasoning": true,
+			"input": [
+				"text",
+				"image"
+			],
+			"cost": {
+				"input": 0.95,
+				"output": 4,
+				"cacheRead": 0,
+				"cacheWrite": 0
+			},
+			"contextWindow": 262144,
+			"maxTokens": 262144,
+			"thinking": {
+				"mode": "effort",
+				"efforts": [
+					"minimal",
+					"low",
+					"medium",
+					"high",
+					"xhigh"
+				]
+			}
+		},
 		"openai/gpt-oss-120b": {
 			"id": "openai/gpt-oss-120b",
 			"name": "GPT OSS 120B",
@@ -21345,6 +21548,34 @@
 				]
 			}
 		},
+		"Qwen/Qwen3-235B-A22B": {
+			"id": "Qwen/Qwen3-235B-A22B",
+			"name": "Qwen3 235B-A22B",
+			"api": "openai-completions",
+			"provider": "huggingface",
+			"baseUrl": "https://router.huggingface.co/v1",
+			"reasoning": true,
+			"input": [
+				"text"
+			],
+			"cost": {
+				"input": 0.2,
+				"output": 0.8,
+				"cacheRead": 0,
+				"cacheWrite": 0
+			},
+			"contextWindow": 40960,
+			"maxTokens": 16384,
+			"thinking": {
+				"mode": "effort",
+				"efforts": [
+					"minimal",
+					"low",
+					"medium",
+					"high"
+				]
+			}
+		},
 		"Qwen/Qwen3-235B-A22B-Thinking-2507": {
 			"id": "Qwen/Qwen3-235B-A22B-Thinking-2507",
 			"name": "Qwen3-235B-A22B-Thinking-2507",
@@ -21374,6 +21605,53 @@
 				"requiresEffort": true
 			}
 		},
+		"Qwen/Qwen3-32B": {
+			"id": "Qwen/Qwen3-32B",
+			"name": "Qwen3 32B",
+			"api": "openai-completions",
+			"provider": "huggingface",
+			"baseUrl": "https://router.huggingface.co/v1",
+			"reasoning": true,
+			"input": [
+				"text"
+			],
+			"cost": {
+				"input": 0.29,
+				"output": 0.59,
+				"cacheRead": 0,
+				"cacheWrite": 0
+			},
+			"contextWindow": 131072,
+			"maxTokens": 16384,
+			"thinking": {
+				"mode": "effort",
+				"efforts": [
+					"minimal",
+					"low",
+					"medium",
+					"high"
+				]
+			}
+		},
+		"Qwen/Qwen3-Coder-30B-A3B-Instruct": {
+			"id": "Qwen/Qwen3-Coder-30B-A3B-Instruct",
+			"name": "Qwen3-Coder 30B-A3B Instruct",
+			"api": "openai-completions",
+			"provider": "huggingface",
+			"baseUrl": "https://router.huggingface.co/v1",
+			"reasoning": false,
+			"input": [
+				"text"
+			],
+			"cost": {
+				"input": 0.07,
+				"output": 0.26,
+				"cacheRead": 0,
+				"cacheWrite": 0
+			},
+			"contextWindow": 262144,
+			"maxTokens": 65536
+		},
 		"Qwen/Qwen3-Coder-480B-A35B-Instruct": {
 			"id": "Qwen/Qwen3-Coder-480B-A35B-Instruct",
 			"name": "Qwen3-Coder-480B-A35B-Instruct",
@@ -21450,6 +21728,93 @@
 			"contextWindow": 262144,
 			"maxTokens": 131072
 		},
+		"Qwen/Qwen3.5-122B-A10B": {
+			"id": "Qwen/Qwen3.5-122B-A10B",
+			"name": "Qwen3.5 122B-A10B",
+			"api": "openai-completions",
+			"provider": "huggingface",
+			"baseUrl": "https://router.huggingface.co/v1",
+			"reasoning": true,
+			"input": [
+				"text",
+				"image"
+			],
+			"cost": {
+				"input": 0.4,
+				"output": 3.2,
+				"cacheRead": 0,
+				"cacheWrite": 0
+			},
+			"contextWindow": 262144,
+			"maxTokens": 65536,
+			"thinking": {
+				"mode": "effort",
+				"efforts": [
+					"minimal",
+					"low",
+					"medium",
+					"high"
+				]
+			}
+		},
+		"Qwen/Qwen3.5-27B": {
+			"id": "Qwen/Qwen3.5-27B",
+			"name": "Qwen3.5 27B",
+			"api": "openai-completions",
+			"provider": "huggingface",
+			"baseUrl": "https://router.huggingface.co/v1",
+			"reasoning": true,
+			"input": [
+				"text",
+				"image"
+			],
+			"cost": {
+				"input": 0.3,
+				"output": 2.4,
+				"cacheRead": 0,
+				"cacheWrite": 0
+			},
+			"contextWindow": 262144,
+			"maxTokens": 65536,
+			"thinking": {
+				"mode": "effort",
+				"efforts": [
+					"minimal",
+					"low",
+					"medium",
+					"high"
+				]
+			}
+		},
+		"Qwen/Qwen3.5-35B-A3B": {
+			"id": "Qwen/Qwen3.5-35B-A3B",
+			"name": "Qwen3.5 35B-A3B",
+			"api": "openai-completions",
+			"provider": "huggingface",
+			"baseUrl": "https://router.huggingface.co/v1",
+			"reasoning": true,
+			"input": [
+				"text",
+				"image"
+			],
+			"cost": {
+				"input": 0.25,
+				"output": 2,
+				"cacheRead": 0,
+				"cacheWrite": 0
+			},
+			"contextWindow": 262144,
+			"maxTokens": 65536,
+			"thinking": {
+				"mode": "effort",
+				"efforts": [
+					"minimal",
+					"low",
+					"medium",
+					"high"
+				]
+			}
+		},
 		"Qwen/Qwen3.5-397B-A17B": {
 			"id": "Qwen/Qwen3.5-397B-A17B",
 			"name": "Qwen3.5-397B-A17B",
@@ -21479,6 +21844,93 @@
 				]
 			}
 		},
+		"Qwen/Qwen3.5-9B": {
+			"id": "Qwen/Qwen3.5-9B",
+			"name": "Qwen3.5 9B",
+			"api": "openai-completions",
+			"provider": "huggingface",
+			"baseUrl": "https://router.huggingface.co/v1",
+			"reasoning": true,
+			"input": [
+				"text",
+				"image"
+			],
+			"cost": {
+				"input": 0.17,
+				"output": 0.25,
+				"cacheRead": 0,
+				"cacheWrite": 0
+			},
+			"contextWindow": 262144,
+			"maxTokens": 65536,
+			"thinking": {
+				"mode": "effort",
+				"efforts": [
+					"minimal",
+					"low",
+					"medium",
+					"high"
+				]
+			}
+		},
+		"Qwen/Qwen3.6-35B-A3B": {
+			"id": "Qwen/Qwen3.6-35B-A3B",
+			"name": "Qwen3.6 35B-A3B",
+			"api": "openai-completions",
+			"provider": "huggingface",
+			"baseUrl": "https://router.huggingface.co/v1",
+			"reasoning": true,
+			"input": [
+				"text",
+				"image"
+			],
+			"cost": {
+				"input": 0.15,
+				"output": 0.95,
+				"cacheRead": 0,
+				"cacheWrite": 0
+			},
+			"contextWindow": 262144,
+			"maxTokens": 65536,
+			"thinking": {
+				"mode": "effort",
+				"efforts": [
+					"minimal",
+					"low",
+					"medium",
+					"high"
+				]
+			}
+		},
+		"stepfun-ai/Step-3.5-Flash": {
+			"id": "stepfun-ai/Step-3.5-Flash",
+			"name": "Step 3.5 Flash",
+			"api": "openai-completions",
+			"provider": "huggingface",
+			"baseUrl": "https://router.huggingface.co/v1",
+			"reasoning": true,
+			"input": [
+				"text"
+			],
+			"cost": {
+				"input": 0.1,
+				"output": 0.3,
+				"cacheRead": 0,
+				"cacheWrite": 0
+			},
+			"contextWindow": 262144,
+			"maxTokens": 256000,
+			"thinking": {
+				"mode": "effort",
+				"efforts": [
+					"minimal",
+					"low",
+					"medium",
+					"high",
+					"xhigh"
+				]
+			}
+		},
 		"XiaomiMiMo/MiMo-V2-Flash": {
 			"id": "XiaomiMiMo/MiMo-V2-Flash",
 			"name": "MiMo-V2-Flash",
@@ -21506,6 +21958,123 @@
 				]
 			}
 		},
+		"zai-org/GLM-4.5": {
+			"id": "zai-org/GLM-4.5",
+			"name": "GLM-4.5",
+			"api": "openai-completions",
+			"provider": "huggingface",
+			"baseUrl": "https://router.huggingface.co/v1",
+			"reasoning": true,
+			"input": [
+				"text"
+			],
+			"cost": {
+				"input": 0.6,
+				"output": 2.2,
+				"cacheRead": 0,
+				"cacheWrite": 0
+			},
+			"contextWindow": 131072,
+			"maxTokens": 98304,
+			"thinking": {
+				"mode": "effort",
+				"efforts": [
+					"minimal",
+					"low",
+					"medium",
+					"high",
+					"xhigh"
+				]
+			}
+		},
+		"zai-org/GLM-4.5-Air": {
+			"id": "zai-org/GLM-4.5-Air",
+			"name": "GLM-4.5-Air",
+			"api": "openai-completions",
+			"provider": "huggingface",
+			"baseUrl": "https://router.huggingface.co/v1",
+			"reasoning": true,
+			"input": [
+				"text"
+			],
+			"cost": {
+				"input": 0.13,
+				"output": 0.85,
+				"cacheRead": 0,
+				"cacheWrite": 0
+			},
+			"contextWindow": 131072,
+			"maxTokens": 98304,
+			"thinking": {
+				"mode": "effort",
+				"efforts": [
+					"minimal",
+					"low",
+					"medium",
+					"high",
+					"xhigh"
+				]
+			}
+		},
+		"zai-org/GLM-4.5V": {
+			"id": "zai-org/GLM-4.5V",
+			"name": "GLM-4.5V",
+			"api": "openai-completions",
+			"provider": "huggingface",
+			"baseUrl": "https://router.huggingface.co/v1",
+			"reasoning": true,
+			"input": [
+				"text",
+				"image"
+			],
+			"cost": {
+				"input": 0.6,
+				"output": 1.8,
+				"cacheRead": 0,
+				"cacheWrite": 0
+			},
+			"contextWindow": 65536,
+			"maxTokens": 16384,
+			"thinking": {
+				"mode": "effort",
+				"efforts": [
+					"minimal",
+					"low",
+					"medium",
+					"high",
+					"xhigh"
+				]
+			}
+		},
+		"zai-org/GLM-4.6": {
+			"id": "zai-org/GLM-4.6",
+			"name": "GLM-4.6",
+			"api": "openai-completions",
+			"provider": "huggingface",
+			"baseUrl": "https://router.huggingface.co/v1",
+			"reasoning": true,
+			"input": [
+				"text"
+			],
+			"cost": {
+				"input": 0.55,
+				"output": 2.2,
+				"cacheRead": 0,
+				"cacheWrite": 0
+			},
+			"contextWindow": 204800,
+			"maxTokens": 131072,
+			"thinking": {
+				"mode": "effort",
+				"efforts": [
+					"minimal",
+					"low",
+					"medium",
+					"high",
+					"xhigh"
+				]
+			}
+		},
 		"zai-org/GLM-4.7": {
 			"id": "zai-org/GLM-4.7",
 			"name": "GLM-4.7",
@@ -21621,6 +22190,35 @@
 					"xhigh"
 				]
 			}
+		},
+		"zai-org/GLM-5.2": {
+			"id": "zai-org/GLM-5.2",
+			"name": "GLM-5.2",
+			"api": "openai-completions",
+			"provider": "huggingface",
+			"baseUrl": "https://router.huggingface.co/v1",
+			"reasoning": true,
+			"input": [
+				"text"
+			],
+			"cost": {
+				"input": 1.4,
+				"output": 4.4,
+				"cacheRead": 0,
+				"cacheWrite": 0
+			},
+			"contextWindow": 262144,
+			"maxTokens": 131072,
+			"thinking": {
+				"mode": "effort",
+				"efforts": [
+					"minimal",
+					"low",
+					"medium",
+					"high",
+					"xhigh"
+				]
+			}
 		}
 	},
 	"kilo": {
@@ -46112,11 +46710,11 @@
 		},
 		"Qwen/Qwen3-235B-A22B": {
 			"id": "Qwen/Qwen3-235B-A22B",
-			"name": "Qwen/Qwen3-235B-A22B",
+			"name": "Qwen3 235B-A22B",
 			"api": "openai-completions",
 			"provider": "nanogpt",
 			"baseUrl": "https://nano-gpt.com/api/v1",
-			"reasoning": false,
+			"reasoning": true,
 			"input": [
 				"text"
 			],
@@ -46127,7 +46725,16 @@
 				"cacheWrite": 0
 			},
 			"contextWindow": 131072,
-			"maxTokens": 8192
+			"maxTokens": 8192,
+			"thinking": {
+				"mode": "effort",
+				"efforts": [
+					"minimal",
+					"low",
+					"medium",
+					"high"
+				]
+			}
 		},
 		"qwen/Qwen3-235B-A22B-Instruct-2507": {
 			"id": "qwen/Qwen3-235B-A22B-Instruct-2507",
@@ -46647,13 +47254,14 @@
 		},
 		"Qwen/Qwen3.6-35B-A3B": {
 			"id": "Qwen/Qwen3.6-35B-A3B",
-			"name": "Qwen/Qwen3.6-35B-A3B",
+			"name": "Qwen3.6 35B-A3B",
 			"api": "openai-completions",
 			"provider": "nanogpt",
 			"baseUrl": "https://nano-gpt.com/api/v1",
 			"reasoning": true,
 			"input": [
-				"text"
+				"text",
+				"image"
 			],
 			"cost": {
 				"input": 0,
@@ -47716,6 +48324,25 @@
 			"contextWindow": null,
 			"maxTokens": null
 		},
+		"sakana/fugu-ultra": {
+			"id": "sakana/fugu-ultra",
+			"name": "sakana/fugu-ultra",
+			"api": "openai-completions",
+			"provider": "nanogpt",
+			"baseUrl": "https://nano-gpt.com/api/v1",
+			"reasoning": false,
+			"input": [
+				"text"
+			],
+			"cost": {
+				"input": 0,
+				"output": 0,
+				"cacheRead": 0,
+				"cacheWrite": 0
+			},
+			"contextWindow": 1000000,
+			"maxTokens": null
+		},
 		"Salesforce/Llama-xLAM-2-70b-fc-r": {
 			"id": "Salesforce/Llama-xLAM-2-70b-fc-r",
 			"name": "Salesforce/Llama-xLAM-2-70b-fc-r",
@@ -60466,12 +61093,12 @@
 			],
 			"cost": {
 				"input": 0.66,
-				"output": 3.5,
-				"cacheRead": 0.33,
+				"output": 3.41,
+				"cacheRead": 0.144,
 				"cacheWrite": 0
 			},
 			"contextWindow": 262144,
-			"maxTokens": 65535,
+			"maxTokens": 262144,
 			"thinking": {
 				"mode": "effort",
 				"efforts": [
@@ -64132,12 +64759,12 @@
 			],
 			"cost": {
 				"input": 0.66,
-				"output": 3.5,
-				"cacheRead": 0.33,
+				"output": 3.41,
+				"cacheRead": 0.144,
 				"cacheWrite": 0
 			},
 			"contextWindow": 262144,
-			"maxTokens": 65535,
+			"maxTokens": 262144,
 			"thinking": {
 				"mode": "effort",
 				"efforts": [
@@ -69124,9 +69751,9 @@
 				"text"
 			],
 			"cost": {
-				"input": 1,
-				"output": 4,
-				"cacheRead": 0.18,
+				"input": 0.98,
+				"output": 3.08,
+				"cacheRead": 0.182,
 				"cacheWrite": 0
 			},
 			"contextWindow": 1048576,
@@ -69259,7 +69886,7 @@
 				"cacheRead": 0,
 				"cacheWrite": 0
 			},
-			"contextWindow": null,
+			"contextWindow": 1000000,
 			"maxTokens": null,
 			"thinking": {
 				"mode": "effort",
@@ -69273,7 +69900,7 @@
 			},
 			"compat": {
 				"includeEncryptedReasoning": false,
-				"streamIdleTimeoutMs": 300000
+				"streamIdleTimeoutMs": 0
 			}
 		},
 		"fugu-ultra": {
@@ -69292,7 +69919,7 @@
 				"cacheRead": 0.5,
 				"cacheWrite": 0
 			},
-			"contextWindow": null,
+			"contextWindow": 1000000,
 			"maxTokens": null,
 			"thinking": {
 				"mode": "effort",
@@ -69306,7 +69933,7 @@
 			},
 			"compat": {
 				"includeEncryptedReasoning": false,
-				"streamIdleTimeoutMs": 300000
+				"streamIdleTimeoutMs": 0
 			}
 		},
 		"fugu-ultra-20260615": {
@@ -69325,7 +69952,7 @@
 				"cacheRead": 0.5,
 				"cacheWrite": 0
 			},
-			"contextWindow": null,
+			"contextWindow": 1000000,
 			"maxTokens": null,
 			"thinking": {
 				"mode": "effort",
@@ -69339,7 +69966,7 @@
 			},
 			"compat": {
 				"includeEncryptedReasoning": false,
-				"streamIdleTimeoutMs": 300000
+				"streamIdleTimeoutMs": 0
 			}
 		}
 	},
@@ -69694,7 +70321,7 @@
 	"together": {
 		"deepseek-ai/DeepSeek-R1": {
 			"id": "deepseek-ai/DeepSeek-R1",
-			"name": "DeepSeek R1",
+			"name": "DeepSeek-R1",
 			"api": "openai-completions",
 			"provider": "together",
 			"baseUrl": "https://api.together.xyz/v1",
@@ -77765,6 +78392,36 @@
 				]
 			}
 		},
+		"sakana/fugu-ultra": {
+			"id": "sakana/fugu-ultra",
+			"name": "Fugu Ultra",
+			"api": "anthropic-messages",
+			"provider": "vercel-ai-gateway",
+			"baseUrl": "https://ai-gateway.vercel.sh",
+			"reasoning": true,
+			"input": [
+				"text",
+				"image"
+			],
+			"cost": {
+				"input": 5,
+				"output": 30,
+				"cacheRead": 0.5,
+				"cacheWrite": 0
+			},
+			"contextWindow": 1000000,
+			"maxTokens": 1000000,
+			"thinking": {
+				"mode": "budget",
+				"efforts": [
+					"minimal",
+					"low",
+					"medium",
+					"high",
+					"xhigh"
+				]
+			}
+		},
 		"stepfun/step-3.5-flash": {
 			"id": "stepfun/step-3.5-flash",
 			"name": "Step 3.5 Flash",

package/src/provider-models/openai-compat.ts

@@ -2527,6 +2527,7 @@ export function moonshotModelManagerOptions(
 const SAKANA_DEFAULT_BASE_URL = "https://api.sakana.ai/v1";
 const SAKANA_FREE_ROUTER_COST = { input: 0, output: 0, cacheRead: 0, cacheWrite: 0 } as const;
 const SAKANA_FUGU_ULTRA_COST = { input: 5, output: 30, cacheRead: 0.5, cacheWrite: 0 } as const;
+const SAKANA_FUGU_ULTRA_CONTEXT_WINDOW = 1_000_000;
 const SAKANA_FUGU_THINKING: ThinkingConfig = {
 	mode: "effort",
 	efforts: [Effort.High, Effort.XHigh],
@@ -2534,7 +2535,7 @@ const SAKANA_FUGU_THINKING: ThinkingConfig = {
 };
 const SAKANA_RESPONSES_COMPAT: ModelSpec<"openai-responses">["compat"] = {
 	includeEncryptedReasoning: false,
-	streamIdleTimeoutMs: 300_000,
+	streamIdleTimeoutMs: 0,
 };
 
 function normalizeSakanaBaseUrl(baseUrl: string | undefined): string {
@@ -2551,6 +2552,7 @@ function createSakanaFuguStaticModel(
 	id: string,
 	name: string,
 	cost: ModelSpec<"openai-responses">["cost"],
+	contextWindow: number | null,
 ): ModelSpec<"openai-responses"> {
 	return {
 		id,
@@ -2561,7 +2563,7 @@ function createSakanaFuguStaticModel(
 		reasoning: true,
 		input: ["text"],
 		cost: { ...cost },
-		contextWindow: null,
+		contextWindow,
 		maxTokens: null,
 		thinking: { ...SAKANA_FUGU_THINKING },
 		compat: { ...SAKANA_RESPONSES_COMPAT },
@@ -2569,12 +2571,18 @@ function createSakanaFuguStaticModel(
 }
 
 export const SAKANA_FUGU_STATIC_MODELS: readonly ModelSpec<"openai-responses">[] = [
-	createSakanaFuguStaticModel("fugu", "Fugu", SAKANA_FREE_ROUTER_COST),
-	createSakanaFuguStaticModel("fugu-ultra", "Fugu Ultra", SAKANA_FUGU_ULTRA_COST),
-	createSakanaFuguStaticModel("fugu-ultra-20260615", "Fugu Ultra 20260615", SAKANA_FUGU_ULTRA_COST),
+	createSakanaFuguStaticModel("fugu", "Fugu", SAKANA_FREE_ROUTER_COST, SAKANA_FUGU_ULTRA_CONTEXT_WINDOW),
+	createSakanaFuguStaticModel("fugu-ultra", "Fugu Ultra", SAKANA_FUGU_ULTRA_COST, SAKANA_FUGU_ULTRA_CONTEXT_WINDOW),
+	createSakanaFuguStaticModel(
+		"fugu-ultra-20260615",
+		"Fugu Ultra 20260615",
+		SAKANA_FUGU_ULTRA_COST,
+		SAKANA_FUGU_ULTRA_CONTEXT_WINDOW,
+	),
 ];
 
 const SAKANA_FUGU_STATIC_MODEL_BY_ID = new Map(SAKANA_FUGU_STATIC_MODELS.map(model => [model.id, model] as const));
+const SAKANA_FUGU_STATIC_MODEL_IDS = SAKANA_FUGU_STATIC_MODELS.map(model => model.id);
 
 export interface SakanaModelManagerConfig {
 	apiKey?: string;
@@ -2589,6 +2597,7 @@ export function sakanaModelManagerOptions(config?: SakanaModelManagerConfig): Mo
 	return {
 		providerId: "sakana",
 		dynamicModelsAuthoritative: true,
+		dropCachedModelIdsOnStaticMismatch: SAKANA_FUGU_STATIC_MODEL_IDS,
 		...(apiKey && {
 			fetchDynamicModels: () =>
 				fetchOpenAICompatibleModels({