fix(ai): regenerate model catalog

Picks up the Claude Fable 5 thinking-off metadata (off: null in thinkingLevelMap) that 9ccfcd7c added to the generator without regenerating, fixing anthropic-thinking-disable and supports-xhigh tests. Includes upstream catalog drift; OpenRouter delisted moonshotai/kimi-k2.6:free, so the kimi compat test now pins only the listed variant.
2026-06-10 20:09:13 +02:00
parent ba93da9a93
commit 20a9b82cf9
2 changed files with 134 additions and 318 deletions
@@ -357,7 +357,7 @@ export const MODELS = {
 			provider: "amazon-bedrock",
 			baseUrl: "https://bedrock-runtime.eu-central-1.amazonaws.com",
 			reasoning: true,
-			thinkingLevelMap: {"xhigh":"xhigh"},
+			thinkingLevelMap: {"off":null,"xhigh":"xhigh"},
 			input: ["text", "image"],
 			cost: {
 				input: 11,
@@ -497,7 +497,7 @@ export const MODELS = {
 			provider: "amazon-bedrock",
 			baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
 			reasoning: true,
-			thinkingLevelMap: {"xhigh":"xhigh"},
+			thinkingLevelMap: {"off":null,"xhigh":"xhigh"},
 			input: ["text", "image"],
 			cost: {
 				input: 10,
@@ -1389,7 +1389,7 @@ export const MODELS = {
 			provider: "amazon-bedrock",
 			baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
 			reasoning: true,
-			thinkingLevelMap: {"xhigh":"xhigh"},
+			thinkingLevelMap: {"off":null,"xhigh":"xhigh"},
 			input: ["text", "image"],
 			cost: {
 				input: 10,
@@ -1878,7 +1878,7 @@ export const MODELS = {
 			baseUrl: "https://api.anthropic.com",
 			compat: {"forceAdaptiveThinking":true},
 			reasoning: true,
-			thinkingLevelMap: {"xhigh":"xhigh"},
+			thinkingLevelMap: {"off":null,"xhigh":"xhigh"},
 			input: ["text", "image"],
 			cost: {
 				input: 10,
@@ -3073,7 +3073,7 @@ export const MODELS = {
 			baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/anthropic",
 			compat: {"forceAdaptiveThinking":true},
 			reasoning: true,
-			thinkingLevelMap: {"xhigh":"xhigh"},
+			thinkingLevelMap: {"off":null,"xhigh":"xhigh"},
 			input: ["text", "image"],
 			cost: {
 				input: 10,
@@ -5022,77 +5022,9 @@ export const MODELS = {
 		} satisfies Model<"google-vertex">,
 	},
 	"groq": {
-		"deepseek-r1-distill-llama-70b": {
-			id: "deepseek-r1-distill-llama-70b",
-			name: "DeepSeek R1 Distill Llama 70B",
-			api: "openai-completions",
-			provider: "groq",
-			baseUrl: "https://api.groq.com/openai/v1",
-			reasoning: true,
-			input: ["text"],
-			cost: {
-				input: 0.75,
-				output: 0.99,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 131072,
-			maxTokens: 8192,
-		} satisfies Model<"openai-completions">,
-		"gemma2-9b-it": {
-			id: "gemma2-9b-it",
-			name: "Gemma 2 9B",
-			api: "openai-completions",
-			provider: "groq",
-			baseUrl: "https://api.groq.com/openai/v1",
-			reasoning: false,
-			input: ["text"],
-			cost: {
-				input: 0.2,
-				output: 0.2,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 8192,
-			maxTokens: 8192,
-		} satisfies Model<"openai-completions">,
-		"groq/compound": {
-			id: "groq/compound",
-			name: "Compound",
-			api: "openai-completions",
-			provider: "groq",
-			baseUrl: "https://api.groq.com/openai/v1",
-			reasoning: true,
-			input: ["text"],
-			cost: {
-				input: 0,
-				output: 0,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 131072,
-			maxTokens: 8192,
-		} satisfies Model<"openai-completions">,
-		"groq/compound-mini": {
-			id: "groq/compound-mini",
-			name: "Compound Mini",
-			api: "openai-completions",
-			provider: "groq",
-			baseUrl: "https://api.groq.com/openai/v1",
-			reasoning: true,
-			input: ["text"],
-			cost: {
-				input: 0,
-				output: 0,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 131072,
-			maxTokens: 8192,
-		} satisfies Model<"openai-completions">,
 		"llama-3.1-8b-instant": {
 			id: "llama-3.1-8b-instant",
-			name: "Llama 3.1 8B Instant",
+			name: "Llama 3.1 8B",
 			api: "openai-completions",
 			provider: "groq",
 			baseUrl: "https://api.groq.com/openai/v1",
@@ -5109,7 +5041,7 @@ export const MODELS = {
 		} satisfies Model<"openai-completions">,
 		"llama-3.3-70b-versatile": {
 			id: "llama-3.3-70b-versatile",
-			name: "Llama 3.3 70B Versatile",
+			name: "Llama 3.3 70B",
 			api: "openai-completions",
 			provider: "groq",
 			baseUrl: "https://api.groq.com/openai/v1",
@@ -5124,60 +5056,9 @@ export const MODELS = {
 			contextWindow: 131072,
 			maxTokens: 32768,
 		} satisfies Model<"openai-completions">,
-		"llama3-70b-8192": {
-			id: "llama3-70b-8192",
-			name: "Llama 3 70B",
-			api: "openai-completions",
-			provider: "groq",
-			baseUrl: "https://api.groq.com/openai/v1",
-			reasoning: false,
-			input: ["text"],
-			cost: {
-				input: 0.59,
-				output: 0.79,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 8192,
-			maxTokens: 8192,
-		} satisfies Model<"openai-completions">,
-		"llama3-8b-8192": {
-			id: "llama3-8b-8192",
-			name: "Llama 3 8B",
-			api: "openai-completions",
-			provider: "groq",
-			baseUrl: "https://api.groq.com/openai/v1",
-			reasoning: false,
-			input: ["text"],
-			cost: {
-				input: 0.05,
-				output: 0.08,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 8192,
-			maxTokens: 8192,
-		} satisfies Model<"openai-completions">,
-		"meta-llama/llama-4-maverick-17b-128e-instruct": {
-			id: "meta-llama/llama-4-maverick-17b-128e-instruct",
-			name: "Llama 4 Maverick 17B",
-			api: "openai-completions",
-			provider: "groq",
-			baseUrl: "https://api.groq.com/openai/v1",
-			reasoning: false,
-			input: ["text", "image"],
-			cost: {
-				input: 0.2,
-				output: 0.6,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 131072,
-			maxTokens: 8192,
-		} satisfies Model<"openai-completions">,
 		"meta-llama/llama-4-scout-17b-16e-instruct": {
 			id: "meta-llama/llama-4-scout-17b-16e-instruct",
-			name: "Llama 4 Scout 17B",
+			name: "Llama 4 Scout 17B 16E",
 			api: "openai-completions",
 			provider: "groq",
 			baseUrl: "https://api.groq.com/openai/v1",
@@ -5192,57 +5073,6 @@ export const MODELS = {
 			contextWindow: 131072,
 			maxTokens: 8192,
 		} satisfies Model<"openai-completions">,
-		"mistral-saba-24b": {
-			id: "mistral-saba-24b",
-			name: "Mistral Saba 24B",
-			api: "openai-completions",
-			provider: "groq",
-			baseUrl: "https://api.groq.com/openai/v1",
-			reasoning: false,
-			input: ["text"],
-			cost: {
-				input: 0.79,
-				output: 0.79,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 32768,
-			maxTokens: 32768,
-		} satisfies Model<"openai-completions">,
-		"moonshotai/kimi-k2-instruct": {
-			id: "moonshotai/kimi-k2-instruct",
-			name: "Kimi K2 Instruct",
-			api: "openai-completions",
-			provider: "groq",
-			baseUrl: "https://api.groq.com/openai/v1",
-			reasoning: false,
-			input: ["text"],
-			cost: {
-				input: 1,
-				output: 3,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 131072,
-			maxTokens: 16384,
-		} satisfies Model<"openai-completions">,
-		"moonshotai/kimi-k2-instruct-0905": {
-			id: "moonshotai/kimi-k2-instruct-0905",
-			name: "Kimi K2 Instruct 0905",
-			api: "openai-completions",
-			provider: "groq",
-			baseUrl: "https://api.groq.com/openai/v1",
-			reasoning: false,
-			input: ["text"],
-			cost: {
-				input: 1,
-				output: 3,
-				cacheRead: 0.5,
-				cacheWrite: 0,
-			},
-			contextWindow: 262144,
-			maxTokens: 16384,
-		} satisfies Model<"openai-completions">,
 		"openai/gpt-oss-120b": {
 			id: "openai/gpt-oss-120b",
 			name: "GPT OSS 120B",
@@ -5294,26 +5124,9 @@ export const MODELS = {
 			contextWindow: 131072,
 			maxTokens: 65536,
 		} satisfies Model<"openai-completions">,
-		"qwen-qwq-32b": {
-			id: "qwen-qwq-32b",
-			name: "Qwen QwQ 32B",
-			api: "openai-completions",
-			provider: "groq",
-			baseUrl: "https://api.groq.com/openai/v1",
-			reasoning: true,
-			input: ["text"],
-			cost: {
-				input: 0.29,
-				output: 0.39,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 131072,
-			maxTokens: 16384,
-		} satisfies Model<"openai-completions">,
 		"qwen/qwen3-32b": {
 			id: "qwen/qwen3-32b",
-			name: "Qwen3 32B",
+			name: "Qwen3-32B",
 			api: "openai-completions",
 			provider: "groq",
 			baseUrl: "https://api.groq.com/openai/v1",
@@ -6763,8 +6576,8 @@ export const MODELS = {
 			baseUrl: "https://integrate.api.nvidia.com/v1",
 			headers: {"NVCF-POLL-SECONDS":"3600"},
 			compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"supportsLongCacheRetention":false},
-			reasoning: false,
-			input: ["text"],
+			reasoning: true,
+			input: ["text", "image"],
 			cost: {
 				input: 0,
 				output: 0,
@@ -6793,44 +6606,6 @@ export const MODELS = {
 			contextWindow: 262144,
 			maxTokens: 262144,
 		} satisfies Model<"openai-completions">,
-		"nvidia/llama-3.3-nemotron-super-49b-v1": {
-			id: "nvidia/llama-3.3-nemotron-super-49b-v1",
-			name: "Llama 3.3 Nemotron Super 49B v1",
-			api: "openai-completions",
-			provider: "nvidia",
-			baseUrl: "https://integrate.api.nvidia.com/v1",
-			headers: {"NVCF-POLL-SECONDS":"3600"},
-			compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"supportsLongCacheRetention":false},
-			reasoning: true,
-			input: ["text"],
-			cost: {
-				input: 0,
-				output: 0,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 131072,
-			maxTokens: 131072,
-		} satisfies Model<"openai-completions">,
-		"nvidia/llama-3.3-nemotron-super-49b-v1.5": {
-			id: "nvidia/llama-3.3-nemotron-super-49b-v1.5",
-			name: "Llama 3.3 Nemotron Super 49B v1.5",
-			api: "openai-completions",
-			provider: "nvidia",
-			baseUrl: "https://integrate.api.nvidia.com/v1",
-			headers: {"NVCF-POLL-SECONDS":"3600"},
-			compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"supportsLongCacheRetention":false},
-			reasoning: true,
-			input: ["text"],
-			cost: {
-				input: 0,
-				output: 0,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 131072,
-			maxTokens: 131072,
-		} satisfies Model<"openai-completions">,
 		"nvidia/nemotron-3-nano-30b-a3b": {
 			id: "nvidia/nemotron-3-nano-30b-a3b",
 			name: "nemotron-3-nano-30b-a3b",
@@ -6926,6 +6701,25 @@ export const MODELS = {
 			contextWindow: 131072,
 			maxTokens: 131072,
 		} satisfies Model<"openai-completions">,
+		"openai/gpt-oss-120b": {
+			id: "openai/gpt-oss-120b",
+			name: "GPT-OSS-120B",
+			api: "openai-completions",
+			provider: "nvidia",
+			baseUrl: "https://integrate.api.nvidia.com/v1",
+			headers: {"NVCF-POLL-SECONDS":"3600"},
+			compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"supportsLongCacheRetention":false},
+			reasoning: true,
+			input: ["text"],
+			cost: {
+				input: 0,
+				output: 0,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 128000,
+			maxTokens: 8192,
+		} satisfies Model<"openai-completions">,
 		"openai/gpt-oss-20b": {
 			id: "openai/gpt-oss-20b",
 			name: "GPT OSS 20B",
@@ -7882,7 +7676,7 @@ export const MODELS = {
 			baseUrl: "https://opencode.ai/zen",
 			compat: {"forceAdaptiveThinking":true},
 			reasoning: true,
-			thinkingLevelMap: {"xhigh":"xhigh"},
+			thinkingLevelMap: {"off":null,"xhigh":"xhigh"},
 			input: ["text", "image"],
 			cost: {
 				input: 10,
@@ -8066,7 +7860,7 @@ export const MODELS = {
 			cost: {
 				input: 0.14,
 				output: 0.28,
-				cacheRead: 0.03,
+				cacheRead: 0.028,
 				cacheWrite: 0,
 			},
 			contextWindow: 1000000,
@@ -8091,6 +7885,25 @@ export const MODELS = {
 			contextWindow: 200000,
 			maxTokens: 128000,
 		} satisfies Model<"openai-completions">,
+		"deepseek-v4-pro": {
+			id: "deepseek-v4-pro",
+			name: "DeepSeek V4 Pro",
+			api: "openai-completions",
+			provider: "opencode",
+			baseUrl: "https://opencode.ai/zen/v1",
+			compat: {"maxTokensField":"max_tokens","requiresReasoningContentOnAssistantMessages":true,"thinkingFormat":"deepseek"},
+			reasoning: true,
+			thinkingLevelMap: {"minimal":null,"low":null,"medium":null,"high":"high","xhigh":"max"},
+			input: ["text"],
+			cost: {
+				input: 1.74,
+				output: 3.84,
+				cacheRead: 0.145,
+				cacheWrite: 0,
+			},
+			contextWindow: 1000000,
+			maxTokens: 384000,
+		} satisfies Model<"openai-completions">,
 		"gemini-3-flash": {
 			id: "gemini-3-flash",
 			name: "Gemini 3 Flash",
@@ -9484,7 +9297,7 @@ export const MODELS = {
 				cacheRead: 0.135,
 				cacheWrite: 0,
 			},
-			contextWindow: 163840,
+			contextWindow: 131072,
 			maxTokens: 16384,
 		} satisfies Model<"openai-completions">,
 		"deepseek/deepseek-chat-v3.1": {
@@ -10632,24 +10445,6 @@ export const MODELS = {
 			contextWindow: 262144,
 			maxTokens: 262142,
 		} satisfies Model<"openai-completions">,
-		"moonshotai/kimi-k2.6:free": {
-			id: "moonshotai/kimi-k2.6:free",
-			name: "MoonshotAI: Kimi K2.6 (free)",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			compat: {"supportsDeveloperRole":false,"requiresReasoningContentOnAssistantMessages":true},
-			reasoning: true,
-			input: ["text", "image"],
-			cost: {
-				input: 0,
-				output: 0,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 262144,
-			maxTokens: 4096,
-		} satisfies Model<"openai-completions">,
 		"nex-agi/nex-n2-pro:free": {
 			id: "nex-agi/nex-n2-pro:free",
 			name: "Nex AGI: Nex-N2-Pro (free)",
@@ -12923,23 +12718,6 @@ export const MODELS = {
 			contextWindow: 1048576,
 			maxTokens: 131072,
 		} satisfies Model<"openai-completions">,
-		"z-ai/glm-4-32b": {
-			id: "z-ai/glm-4-32b",
-			name: "Z.ai: GLM 4 32B ",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: false,
-			input: ["text"],
-			cost: {
-				input: 0.09999999999999999,
-				output: 0.09999999999999999,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 128000,
-			maxTokens: 4096,
-		} satisfies Model<"openai-completions">,
 		"z-ai/glm-4.5": {
 			id: "z-ai/glm-4.5",
 			name: "Z.ai: GLM 4.5",
@@ -12974,23 +12752,6 @@ export const MODELS = {
 			contextWindow: 131072,
 			maxTokens: 131070,
 		} satisfies Model<"openai-completions">,
-		"z-ai/glm-4.5-air:free": {
-			id: "z-ai/glm-4.5-air:free",
-			name: "Z.ai: GLM 4.5 Air (free)",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: true,
-			input: ["text"],
-			cost: {
-				input: 0,
-				output: 0,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 131072,
-			maxTokens: 96000,
-		} satisfies Model<"openai-completions">,
 		"z-ai/glm-4.5v": {
 			id: "z-ai/glm-4.5v",
 			name: "Z.ai: GLM 4.5V",
@@ -13036,11 +12797,11 @@ export const MODELS = {
 			cost: {
 				input: 0.3,
 				output: 0.8999999999999999,
-				cacheRead: 0.049999999999999996,
+				cacheRead: 0.055,
 				cacheWrite: 0,
 			},
 			contextWindow: 131072,
-			maxTokens: 24000,
+			maxTokens: 32768,
 		} satisfies Model<"openai-completions">,
 		"z-ai/glm-4.7": {
 			id: "z-ai/glm-4.7",
@@ -13107,7 +12868,7 @@ export const MODELS = {
 				cacheRead: 0.24,
 				cacheWrite: 0,
 			},
-			contextWindow: 202752,
+			contextWindow: 262144,
 			maxTokens: 131072,
 		} satisfies Model<"openai-completions">,
 		"z-ai/glm-5.1": {
@@ -13127,23 +12888,6 @@ export const MODELS = {
 			contextWindow: 202752,
 			maxTokens: 4096,
 		} satisfies Model<"openai-completions">,
-		"z-ai/glm-5v-turbo": {
-			id: "z-ai/glm-5v-turbo",
-			name: "Z.ai: GLM 5V Turbo",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: true,
-			input: ["text", "image"],
-			cost: {
-				input: 1.2,
-				output: 4,
-				cacheRead: 0.24,
-				cacheWrite: 0,
-			},
-			contextWindow: 202752,
-			maxTokens: 131072,
-		} satisfies Model<"openai-completions">,
 		"~anthropic/claude-fable-latest": {
 			id: "~anthropic/claude-fable-latest",
 			name: "Anthropic: Claude Fable Latest",
@@ -14075,7 +13819,7 @@ export const MODELS = {
 			baseUrl: "https://ai-gateway.vercel.sh",
 			compat: {"forceAdaptiveThinking":true},
 			reasoning: true,
-			thinkingLevelMap: {"xhigh":"xhigh"},
+			thinkingLevelMap: {"off":null,"xhigh":"xhigh"},
 			input: ["text", "image"],
 			cost: {
 				input: 10,
@@ -16749,6 +16493,24 @@ export const MODELS = {
 			contextWindow: 1048576,
 			maxTokens: 131072,
 		} satisfies Model<"openai-completions">,
+		"mimo-v2.5-pro-ultraspeed": {
+			id: "mimo-v2.5-pro-ultraspeed",
+			name: "MiMo-V2.5-Pro-UltraSpeed",
+			api: "openai-completions",
+			provider: "xiaomi",
+			baseUrl: "https://api.xiaomimimo.com/v1",
+			compat: {"requiresReasoningContentOnAssistantMessages":true,"thinkingFormat":"deepseek"},
+			reasoning: true,
+			input: ["text"],
+			cost: {
+				input: 1.305,
+				output: 2.61,
+				cacheRead: 0.0108,
+				cacheWrite: 0,
+			},
+			contextWindow: 1048576,
+			maxTokens: 131072,
+		} satisfies Model<"openai-completions">,
 	},
 	"xiaomi-token-plan-ams": {
 		"mimo-v2-omni": {
@@ -16823,6 +16585,24 @@ export const MODELS = {
 			contextWindow: 1048576,
 			maxTokens: 131072,
 		} satisfies Model<"openai-completions">,
+		"mimo-v2.5-pro-ultraspeed": {
+			id: "mimo-v2.5-pro-ultraspeed",
+			name: "MiMo-V2.5-Pro-UltraSpeed",
+			api: "openai-completions",
+			provider: "xiaomi-token-plan-ams",
+			baseUrl: "https://token-plan-ams.xiaomimimo.com/v1",
+			compat: {"requiresReasoningContentOnAssistantMessages":true,"thinkingFormat":"deepseek"},
+			reasoning: true,
+			input: ["text"],
+			cost: {
+				input: 1.305,
+				output: 2.61,
+				cacheRead: 0.0108,
+				cacheWrite: 0,
+			},
+			contextWindow: 1048576,
+			maxTokens: 131072,
+		} satisfies Model<"openai-completions">,
 	},
 	"xiaomi-token-plan-cn": {
 		"mimo-v2-omni": {
@@ -16897,6 +16677,24 @@ export const MODELS = {
 			contextWindow: 1048576,
 			maxTokens: 131072,
 		} satisfies Model<"openai-completions">,
+		"mimo-v2.5-pro-ultraspeed": {
+			id: "mimo-v2.5-pro-ultraspeed",
+			name: "MiMo-V2.5-Pro-UltraSpeed",
+			api: "openai-completions",
+			provider: "xiaomi-token-plan-cn",
+			baseUrl: "https://token-plan-cn.xiaomimimo.com/v1",
+			compat: {"requiresReasoningContentOnAssistantMessages":true,"thinkingFormat":"deepseek"},
+			reasoning: true,
+			input: ["text"],
+			cost: {
+				input: 1.305,
+				output: 2.61,
+				cacheRead: 0.0108,
+				cacheWrite: 0,
+			},
+			contextWindow: 1048576,
+			maxTokens: 131072,
+		} satisfies Model<"openai-completions">,
 	},
 	"xiaomi-token-plan-sgp": {
 		"mimo-v2-omni": {
@@ -16971,6 +16769,24 @@ export const MODELS = {
 			contextWindow: 1048576,
 			maxTokens: 131072,
 		} satisfies Model<"openai-completions">,
+		"mimo-v2.5-pro-ultraspeed": {
+			id: "mimo-v2.5-pro-ultraspeed",
+			name: "MiMo-V2.5-Pro-UltraSpeed",
+			api: "openai-completions",
+			provider: "xiaomi-token-plan-sgp",
+			baseUrl: "https://token-plan-sgp.xiaomimimo.com/v1",
+			compat: {"requiresReasoningContentOnAssistantMessages":true,"thinkingFormat":"deepseek"},
+			reasoning: true,
+			input: ["text"],
+			cost: {
+				input: 1.305,
+				output: 2.61,
+				cacheRead: 0.0108,
+				cacheWrite: 0,
+			},
+			contextWindow: 1048576,
+			maxTokens: 131072,
+		} satisfies Model<"openai-completions">,
 	},
 	"zai": {
 		"glm-4.5-air": {
@@ -1,7 +1,7 @@
 import { Type } from "typebox";
 import { beforeEach, describe, expect, it, vi } from "vitest";
+import { convertMessages } from "../src/api/openai-completions.ts";
 import { getModel } from "../src/models.ts";
-import { convertMessages } from "../src/providers/openai-completions.ts";
 import { stream, streamSimple } from "../src/stream.ts";
 import type { AssistantMessage, Model, Tool, ToolResultMessage } from "../src/types.ts";

@@ -890,11 +890,11 @@ describe("openai-completions tool_choice", () => {
 	});

 	it("stores OpenRouter Kimi K2.6 reasoning replay compat in built-in metadata", () => {
-		for (const modelId of ["moonshotai/kimi-k2.6", "moonshotai/kimi-k2.6:free"] as const) {
-			const model = getModel("openrouter", modelId)!;
+		// `:free` variant delisted from the OpenRouter API; the generator override
+		// matches any `moonshotai/kimi-k2.6*` variant that is listed.
+		const model = getModel("openrouter", "moonshotai/kimi-k2.6")!;
 		expect(model.compat?.supportsDeveloperRole).toBe(false);
 		expect(model.compat?.requiresReasoningContentOnAssistantMessages).toBe(true);
-		}
 	});

 	it("stores Xiaomi MiMo reasoning replay compat in built-in metadata", () => {