fix(ai): refresh Xiaomi token plan model catalogs

Use the new provider-specific Xiaomi Token Plan catalogs from models.dev instead of cloning the API-billing Xiaomi catalog into every token-plan region. This removes API-billing-only models such as mimo-v2-omni from xiaomi-token-plan-{cn,ams,sgp}.

packages/ai/CHANGELOG.md

@@ -4,6 +4,7 @@
 
 ### Fixed
 
+- Fixed Xiaomi Token Plan model metadata to follow the upstream models.dev token-plan catalogs, removing unsupported `mimo-v2-omni` variants ([#6204](https://github.com/earendil-works/pi/issues/6204)).
 - Fixed GitHub Copilot device-code login polling to wait before the first token poll, avoiding incorrect device-code failures for some users after browser authorization ([#6187](https://github.com/earendil-works/pi/issues/6187)).
 - Fixed OAuth device-code polling to honor the server-provided `slow_down` interval instead of only applying the RFC 8628 5-second increment, so GitHub Copilot login recovers instead of appearing to hang when polls arrive early (e.g. WSL/VM clock drift) ([#6187](https://github.com/earendil-works/pi/issues/6187)).
 - Fixed OpenAI Codex user-agent construction to synchronously load Node OS metadata, avoiding a startup race that could report `pi (browser)` in Node/Bun.

packages/ai/scripts/generate-models.ts

@@ -1534,38 +1534,50 @@ async function loadModelsDevData(): Promise<Model<any>[]> {
 			thinkingFormat: "deepseek",
 		};
 		const xiaomiVariants = [
-			{ provider: "xiaomi", baseUrl: "https://api.xiaomimimo.com/v1" },
+			{ source: "xiaomi", provider: "xiaomi", baseUrl: "https://api.xiaomimimo.com/v1" },
-			{ provider: "xiaomi-token-plan-cn", baseUrl: "https://token-plan-cn.xiaomimimo.com/v1" },
+			{
-			{ provider: "xiaomi-token-plan-ams", baseUrl: "https://token-plan-ams.xiaomimimo.com/v1" },
+				source: "xiaomi-token-plan-cn",
-			{ provider: "xiaomi-token-plan-sgp", baseUrl: "https://token-plan-sgp.xiaomimimo.com/v1" },
+				provider: "xiaomi-token-plan-cn",
+				baseUrl: "https://token-plan-cn.xiaomimimo.com/v1",
+			},
+			{
+				source: "xiaomi-token-plan-ams",
+				provider: "xiaomi-token-plan-ams",
+				baseUrl: "https://token-plan-ams.xiaomimimo.com/v1",
+			},
+			{
+				source: "xiaomi-token-plan-sgp",
+				provider: "xiaomi-token-plan-sgp",
+				baseUrl: "https://token-plan-sgp.xiaomimimo.com/v1",
+			},
 		] as const;
 
-		if (data.xiaomi?.models) {
+		for (const { source, provider, baseUrl } of xiaomiVariants) {
-			for (const { provider, baseUrl } of xiaomiVariants) {
+			const providerModels = data[source]?.models;
-				for (const [modelId, model] of Object.entries(data.xiaomi.models)) {
+			if (!providerModels) continue;
-					const m = model as ModelsDevModel;
-					if (m.tool_call !== true) continue;
-					if (provider.startsWith("xiaomi-token-plan-") && modelId === "mimo-v2-flash") continue;
 
-					models.push({
+			for (const [modelId, model] of Object.entries(providerModels)) {
-						id: modelId,
+				const m = model as ModelsDevModel;
-						name: m.name || modelId,
+				if (m.tool_call !== true) continue;
-						api: "openai-completions",
+
-						provider,
+				models.push({
-						baseUrl,
+					id: modelId,
-						compat: xiaomiCompat,
+					name: m.name || modelId,
-						reasoning: m.reasoning === true,
+					api: "openai-completions",
-						input: m.modalities?.input?.includes("image") ? ["text", "image"] : ["text"],
+					provider,
-						cost: {
+					baseUrl,
-							input: m.cost?.input || 0,
+					compat: xiaomiCompat,
-							output: m.cost?.output || 0,
+					reasoning: m.reasoning === true,
-							cacheRead: m.cost?.cache_read || 0,
+					input: m.modalities?.input?.includes("image") ? ["text", "image"] : ["text"],
-							cacheWrite: m.cost?.cache_write || 0,
+					cost: {
-						},
+						input: m.cost?.input || 0,
-						contextWindow: m.limit?.context || 4096,
+						output: m.cost?.output || 0,
-						maxTokens: m.limit?.output || 4096,
+						cacheRead: m.cost?.cache_read || 0,
-					});
+						cacheWrite: m.cost?.cache_write || 0,
-				}
+					},
+					contextWindow: m.limit?.context || 4096,
+					maxTokens: m.limit?.output || 4096,
+				});
 			}
 		}
 

packages/ai/src/providers/amazon-bedrock.models.ts

@@ -749,6 +749,23 @@ export const AMAZON_BEDROCK_MODELS = {
 		contextWindow: 128000,
 		maxTokens: 4096,
 	} satisfies Model<"bedrock-converse-stream">,
+	"jp.anthropic.claude-haiku-4-5-20251001-v1:0": {
+		id: "jp.anthropic.claude-haiku-4-5-20251001-v1:0",
+		name: "Claude Haiku 4.5 (JP)",
+		api: "bedrock-converse-stream",
+		provider: "amazon-bedrock",
+		baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
+		reasoning: true,
+		input: ["text", "image"],
+		cost: {
+			input: 1,
+			output: 5,
+			cacheRead: 0.1,
+			cacheWrite: 1.25,
+		},
+		contextWindow: 200000,
+		maxTokens: 64000,
+	} satisfies Model<"bedrock-converse-stream">,
 	"jp.anthropic.claude-opus-4-7": {
 		id: "jp.anthropic.claude-opus-4-7",
 		name: "Claude Opus 4.7 (JP)",

packages/ai/src/providers/anthropic.models.ts

@@ -4,108 +4,6 @@
 import type { Model } from "../types.ts";
 
 export const ANTHROPIC_MODELS = {
-	"claude-3-5-sonnet-20240620": {
-		id: "claude-3-5-sonnet-20240620",
-		name: "Claude Sonnet 3.5",
-		api: "anthropic-messages",
-		provider: "anthropic",
-		baseUrl: "https://api.anthropic.com",
-		reasoning: false,
-		input: ["text", "image"],
-		cost: {
-			input: 3,
-			output: 15,
-			cacheRead: 0.3,
-			cacheWrite: 3.75,
-		},
-		contextWindow: 200000,
-		maxTokens: 8192,
-	} satisfies Model<"anthropic-messages">,
-	"claude-3-5-sonnet-20241022": {
-		id: "claude-3-5-sonnet-20241022",
-		name: "Claude Sonnet 3.5 v2",
-		api: "anthropic-messages",
-		provider: "anthropic",
-		baseUrl: "https://api.anthropic.com",
-		reasoning: false,
-		input: ["text", "image"],
-		cost: {
-			input: 3,
-			output: 15,
-			cacheRead: 0.3,
-			cacheWrite: 3.75,
-		},
-		contextWindow: 200000,
-		maxTokens: 8192,
-	} satisfies Model<"anthropic-messages">,
-	"claude-3-7-sonnet-20250219": {
-		id: "claude-3-7-sonnet-20250219",
-		name: "Claude Sonnet 3.7",
-		api: "anthropic-messages",
-		provider: "anthropic",
-		baseUrl: "https://api.anthropic.com",
-		reasoning: true,
-		input: ["text", "image"],
-		cost: {
-			input: 3,
-			output: 15,
-			cacheRead: 0.3,
-			cacheWrite: 3.75,
-		},
-		contextWindow: 200000,
-		maxTokens: 64000,
-	} satisfies Model<"anthropic-messages">,
-	"claude-3-haiku-20240307": {
-		id: "claude-3-haiku-20240307",
-		name: "Claude Haiku 3",
-		api: "anthropic-messages",
-		provider: "anthropic",
-		baseUrl: "https://api.anthropic.com",
-		reasoning: false,
-		input: ["text", "image"],
-		cost: {
-			input: 0.25,
-			output: 1.25,
-			cacheRead: 0.03,
-			cacheWrite: 0.3,
-		},
-		contextWindow: 200000,
-		maxTokens: 4096,
-	} satisfies Model<"anthropic-messages">,
-	"claude-3-opus-20240229": {
-		id: "claude-3-opus-20240229",
-		name: "Claude Opus 3",
-		api: "anthropic-messages",
-		provider: "anthropic",
-		baseUrl: "https://api.anthropic.com",
-		reasoning: false,
-		input: ["text", "image"],
-		cost: {
-			input: 15,
-			output: 75,
-			cacheRead: 1.5,
-			cacheWrite: 18.75,
-		},
-		contextWindow: 200000,
-		maxTokens: 4096,
-	} satisfies Model<"anthropic-messages">,
-	"claude-3-sonnet-20240229": {
-		id: "claude-3-sonnet-20240229",
-		name: "Claude Sonnet 3",
-		api: "anthropic-messages",
-		provider: "anthropic",
-		baseUrl: "https://api.anthropic.com",
-		reasoning: false,
-		input: ["text", "image"],
-		cost: {
-			input: 3,
-			output: 15,
-			cacheRead: 0.3,
-			cacheWrite: 0.3,
-		},
-		contextWindow: 200000,
-		maxTokens: 4096,
-	} satisfies Model<"anthropic-messages">,
 	"claude-fable-5": {
 		id: "claude-fable-5",
 		name: "Claude Fable 5",
@@ -159,23 +57,6 @@ export const ANTHROPIC_MODELS = {
 		contextWindow: 200000,
 		maxTokens: 64000,
 	} satisfies Model<"anthropic-messages">,
-	"claude-opus-4-0": {
-		id: "claude-opus-4-0",
-		name: "Claude Opus 4 (latest)",
-		api: "anthropic-messages",
-		provider: "anthropic",
-		baseUrl: "https://api.anthropic.com",
-		reasoning: true,
-		input: ["text", "image"],
-		cost: {
-			input: 15,
-			output: 75,
-			cacheRead: 1.5,
-			cacheWrite: 18.75,
-		},
-		contextWindow: 200000,
-		maxTokens: 32000,
-	} satisfies Model<"anthropic-messages">,
 	"claude-opus-4-1": {
 		id: "claude-opus-4-1",
 		name: "Claude Opus 4.1 (latest)",
@@ -210,23 +91,6 @@ export const ANTHROPIC_MODELS = {
 		contextWindow: 200000,
 		maxTokens: 32000,
 	} satisfies Model<"anthropic-messages">,
-	"claude-opus-4-20250514": {
-		id: "claude-opus-4-20250514",
-		name: "Claude Opus 4",
-		api: "anthropic-messages",
-		provider: "anthropic",
-		baseUrl: "https://api.anthropic.com",
-		reasoning: true,
-		input: ["text", "image"],
-		cost: {
-			input: 15,
-			output: 75,
-			cacheRead: 1.5,
-			cacheWrite: 18.75,
-		},
-		contextWindow: 200000,
-		maxTokens: 32000,
-	} satisfies Model<"anthropic-messages">,
 	"claude-opus-4-5": {
 		id: "claude-opus-4-5",
 		name: "Claude Opus 4.5 (latest)",
@@ -318,40 +182,6 @@ export const ANTHROPIC_MODELS = {
 		contextWindow: 1000000,
 		maxTokens: 128000,
 	} satisfies Model<"anthropic-messages">,
-	"claude-sonnet-4-0": {
-		id: "claude-sonnet-4-0",
-		name: "Claude Sonnet 4 (latest)",
-		api: "anthropic-messages",
-		provider: "anthropic",
-		baseUrl: "https://api.anthropic.com",
-		reasoning: true,
-		input: ["text", "image"],
-		cost: {
-			input: 3,
-			output: 15,
-			cacheRead: 0.3,
-			cacheWrite: 3.75,
-		},
-		contextWindow: 200000,
-		maxTokens: 64000,
-	} satisfies Model<"anthropic-messages">,
-	"claude-sonnet-4-20250514": {
-		id: "claude-sonnet-4-20250514",
-		name: "Claude Sonnet 4",
-		api: "anthropic-messages",
-		provider: "anthropic",
-		baseUrl: "https://api.anthropic.com",
-		reasoning: true,
-		input: ["text", "image"],
-		cost: {
-			input: 3,
-			output: 15,
-			cacheRead: 0.3,
-			cacheWrite: 3.75,
-		},
-		contextWindow: 200000,
-		maxTokens: 64000,
-	} satisfies Model<"anthropic-messages">,
 	"claude-sonnet-4-5": {
 		id: "claude-sonnet-4-5",
 		name: "Claude Sonnet 4.5 (latest)",
@@ -366,7 +196,7 @@ export const ANTHROPIC_MODELS = {
 			cacheRead: 0.3,
 			cacheWrite: 3.75,
 		},
-		contextWindow: 200000,
+		contextWindow: 1000000,
 		maxTokens: 64000,
 	} satisfies Model<"anthropic-messages">,
 	"claude-sonnet-4-5-20250929": {
@@ -383,7 +213,7 @@ export const ANTHROPIC_MODELS = {
 			cacheRead: 0.3,
 			cacheWrite: 3.75,
 		},
-		contextWindow: 200000,
+		contextWindow: 1000000,
 		maxTokens: 64000,
 	} satisfies Model<"anthropic-messages">,
 	"claude-sonnet-4-6": {
@@ -402,7 +232,7 @@ export const ANTHROPIC_MODELS = {
 			cacheWrite: 3.75,
 		},
 		contextWindow: 1000000,
-		maxTokens: 64000,
+		maxTokens: 128000,
 	} satisfies Model<"anthropic-messages">,
 	"claude-sonnet-5": {
 		id: "claude-sonnet-5",

packages/ai/src/providers/fireworks.models.ts

@@ -71,7 +71,7 @@ export const FIREWORKS_MODELS = {
 		cost: {
 			input: 1.4,
 			output: 4.4,
-			cacheRead: 0.26,
+			cacheRead: 0.14,
 			cacheWrite: 0,
 		},
 		contextWindow: 1048575,

packages/ai/src/providers/huggingface.models.ts

@@ -670,6 +670,24 @@ export const HUGGINGFACE_MODELS = {
 		contextWindow: 131072,
 		maxTokens: 32768,
 	} satisfies Model<"openai-completions">,
+	"openai/gpt-oss-20b": {
+		id: "openai/gpt-oss-20b",
+		name: "GPT OSS 20B",
+		api: "openai-completions",
+		provider: "huggingface",
+		baseUrl: "https://router.huggingface.co/v1",
+		compat: {"supportsDeveloperRole":false},
+		reasoning: true,
+		input: ["text"],
+		cost: {
+			input: 0.1,
+			output: 0.5,
+			cacheRead: 0,
+			cacheWrite: 0,
+		},
+		contextWindow: 131072,
+		maxTokens: 32768,
+	} satisfies Model<"openai-completions">,
 	"stepfun-ai/Step-3.5-Flash": {
 		id: "stepfun-ai/Step-3.5-Flash",
 		name: "Step 3.5 Flash",

packages/ai/src/providers/mistral.models.ts

@@ -333,12 +333,12 @@ export const MISTRAL_MODELS = {
 		api: "mistral-conversations",
 		provider: "mistral",
 		baseUrl: "https://api.mistral.ai",
-		reasoning: false,
+		reasoning: true,
 		input: ["text", "image"],
 		cost: {
-			input: 0.4,
+			input: 1.5,
-			output: 2,
+			output: 7.5,
-			cacheRead: 0.04,
+			cacheRead: 0.15,
 			cacheWrite: 0,
 		},
 		contextWindow: 262144,

packages/ai/src/providers/opencode.models.ts

@@ -691,6 +691,24 @@ export const OPENCODE_MODELS = {
 		contextWindow: 256000,
 		maxTokens: 256000,
 	} satisfies Model<"openai-completions">,
+	"hy3-free": {
+		id: "hy3-free",
+		name: "Hy3 Free",
+		api: "openai-completions",
+		provider: "opencode",
+		baseUrl: "https://opencode.ai/zen/v1",
+		compat: {"supportsStore":false,"supportsDeveloperRole":false,"maxTokensField":"max_tokens"},
+		reasoning: true,
+		input: ["text"],
+		cost: {
+			input: 0,
+			output: 0,
+			cacheRead: 0,
+			cacheWrite: 0,
+		},
+		contextWindow: 256000,
+		maxTokens: 64000,
+	} satisfies Model<"openai-completions">,
 	"kimi-k2.5": {
 		id: "kimi-k2.5",
 		name: "Kimi K2.5",

packages/ai/src/providers/openrouter.models.ts

@@ -22,6 +22,60 @@ export const OPENROUTER_MODELS = {
 		contextWindow: 256000,
 		maxTokens: 4096,
 	} satisfies Model<"openai-completions">,
+	"aion-labs/aion-2.0": {
+		id: "aion-labs/aion-2.0",
+		name: "AionLabs: Aion-2.0",
+		api: "openai-completions",
+		provider: "openrouter",
+		baseUrl: "https://openrouter.ai/api/v1",
+		compat: {"supportsDeveloperRole":false,"thinkingFormat":"openrouter"},
+		reasoning: true,
+		input: ["text"],
+		cost: {
+			input: 0.8,
+			output: 1.6,
+			cacheRead: 0.2,
+			cacheWrite: 0,
+		},
+		contextWindow: 131072,
+		maxTokens: 32768,
+	} satisfies Model<"openai-completions">,
+	"aion-labs/aion-3.0": {
+		id: "aion-labs/aion-3.0",
+		name: "AionLabs: Aion-3.0",
+		api: "openai-completions",
+		provider: "openrouter",
+		baseUrl: "https://openrouter.ai/api/v1",
+		compat: {"supportsDeveloperRole":false,"thinkingFormat":"openrouter"},
+		reasoning: true,
+		input: ["text"],
+		cost: {
+			input: 3,
+			output: 6,
+			cacheRead: 0.75,
+			cacheWrite: 0,
+		},
+		contextWindow: 131072,
+		maxTokens: 32768,
+	} satisfies Model<"openai-completions">,
+	"aion-labs/aion-3.0-mini": {
+		id: "aion-labs/aion-3.0-mini",
+		name: "AionLabs: Aion-3.0-Mini",
+		api: "openai-completions",
+		provider: "openrouter",
+		baseUrl: "https://openrouter.ai/api/v1",
+		compat: {"supportsDeveloperRole":false,"thinkingFormat":"openrouter"},
+		reasoning: true,
+		input: ["text"],
+		cost: {
+			input: 0.7,
+			output: 1.4,
+			cacheRead: 0.18,
+			cacheWrite: 0,
+		},
+		contextWindow: 131072,
+		maxTokens: 32768,
+	} satisfies Model<"openai-completions">,
 	"amazon/nova-2-lite-v1": {
 		id: "amazon/nova-2-lite-v1",
 		name: "Amazon: Nova 2 Lite",
@@ -746,7 +800,7 @@ export const OPENROUTER_MODELS = {
 			cacheWrite: 0,
 		},
 		contextWindow: 1048576,
-		maxTokens: 16384,
+		maxTokens: 65536,
 	} satisfies Model<"openai-completions">,
 	"deepseek/deepseek-v4-pro": {
 		id: "deepseek/deepseek-v4-pro",
@@ -1866,6 +1920,42 @@ export const OPENROUTER_MODELS = {
 		contextWindow: 262144,
 		maxTokens: 16384,
 	} satisfies Model<"openai-completions">,
+	"nex-agi/nex-n2-mini": {
+		id: "nex-agi/nex-n2-mini",
+		name: "Nex AGI: Nex-N2-Mini",
+		api: "openai-completions",
+		provider: "openrouter",
+		baseUrl: "https://openrouter.ai/api/v1",
+		compat: {"supportsDeveloperRole":false,"thinkingFormat":"openrouter"},
+		reasoning: true,
+		input: ["text", "image"],
+		cost: {
+			input: 0.025,
+			output: 0.1,
+			cacheRead: 0.0025,
+			cacheWrite: 0,
+		},
+		contextWindow: 262144,
+		maxTokens: 262144,
+	} satisfies Model<"openai-completions">,
+	"nex-agi/nex-n2-pro": {
+		id: "nex-agi/nex-n2-pro",
+		name: "Nex AGI: Nex-N2-Pro",
+		api: "openai-completions",
+		provider: "openrouter",
+		baseUrl: "https://openrouter.ai/api/v1",
+		compat: {"supportsDeveloperRole":false,"thinkingFormat":"openrouter"},
+		reasoning: true,
+		input: ["text", "image"],
+		cost: {
+			input: 0.25,
+			output: 1,
+			cacheRead: 0.025,
+			cacheWrite: 0,
+		},
+		contextWindow: 262144,
+		maxTokens: 262144,
+	} satisfies Model<"openai-completions">,
 	"nvidia/llama-3.3-nemotron-super-49b-v1.5": {
 		id: "nvidia/llama-3.3-nemotron-super-49b-v1.5",
 		name: "NVIDIA: Llama 3.3 Nemotron Super 49B V1.5",
@@ -3834,7 +3924,7 @@ export const OPENROUTER_MODELS = {
 		cost: {
 			input: 0.385,
 			output: 2.45,
-			cacheRead: 0,
+			cacheRead: 0.111,
 			cacheWrite: 0,
 		},
 		contextWindow: 256000,
@@ -4146,6 +4236,24 @@ export const OPENROUTER_MODELS = {
 		contextWindow: 256000,
 		maxTokens: 256000,
 	} satisfies Model<"openai-completions">,
+	"tencent/hy3": {
+		id: "tencent/hy3",
+		name: "Tencent: Hy3",
+		api: "openai-completions",
+		provider: "openrouter",
+		baseUrl: "https://openrouter.ai/api/v1",
+		compat: {"supportsDeveloperRole":false,"thinkingFormat":"openrouter"},
+		reasoning: true,
+		input: ["text"],
+		cost: {
+			input: 0.2,
+			output: 0.8,
+			cacheRead: 0.5,
+			cacheWrite: 0,
+		},
+		contextWindow: 262144,
+		maxTokens: 131072,
+	} satisfies Model<"openai-completions">,
 	"tencent/hy3-preview": {
 		id: "tencent/hy3-preview",
 		name: "Tencent: Hy3 preview",
@@ -4164,6 +4272,24 @@ export const OPENROUTER_MODELS = {
 		contextWindow: 262144,
 		maxTokens: 4096,
 	} satisfies Model<"openai-completions">,
+	"tencent/hy3:free": {
+		id: "tencent/hy3:free",
+		name: "Tencent: Hy3 (free)",
+		api: "openai-completions",
+		provider: "openrouter",
+		baseUrl: "https://openrouter.ai/api/v1",
+		compat: {"supportsDeveloperRole":false,"thinkingFormat":"openrouter"},
+		reasoning: true,
+		input: ["text"],
+		cost: {
+			input: 0,
+			output: 0,
+			cacheRead: 0,
+			cacheWrite: 0,
+		},
+		contextWindow: 262144,
+		maxTokens: 262144,
+	} satisfies Model<"openai-completions">,
 	"thedrummer/unslopnemo-12b": {
 		id: "thedrummer/unslopnemo-12b",
 		name: "TheDrummer: UnslopNemo 12B",
@@ -4266,7 +4392,7 @@ export const OPENROUTER_MODELS = {
 		cost: {
 			input: 0.105,
 			output: 0.28,
-			cacheRead: 0,
+			cacheRead: 0.028,
 			cacheWrite: 0,
 		},
 		contextWindow: 1048576,
@@ -4481,13 +4607,13 @@ export const OPENROUTER_MODELS = {
 		thinkingLevelMap: {"xhigh":"xhigh"},
 		input: ["text"],
 		cost: {
-			input: 0.91,
+			input: 0.93,
-			output: 2.86,
+			output: 3,
-			cacheRead: 0.169,
+			cacheRead: 0.18,
 			cacheWrite: 0,
 		},
 		contextWindow: 1048576,
-		maxTokens: 128000,
+		maxTokens: 32768,
 	} satisfies Model<"openai-completions">,
 	"z-ai/glm-5v-turbo": {
 		id: "z-ai/glm-5v-turbo",

packages/ai/src/providers/xiaomi-token-plan-ams.models.ts

@@ -4,24 +4,6 @@
 import type { Model } from "../types.ts";
 
 export const XIAOMI_TOKEN_PLAN_AMS_MODELS = {
-	"mimo-v2-omni": {
-		id: "mimo-v2-omni",
-		name: "MiMo-V2-Omni",
-		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", "image"],
-		cost: {
-			input: 0.14,
-			output: 0.28,
-			cacheRead: 0.0028,
-			cacheWrite: 0,
-		},
-		contextWindow: 262144,
-		maxTokens: 131072,
-	} satisfies Model<"openai-completions">,
 	"mimo-v2-pro": {
 		id: "mimo-v2-pro",
 		name: "MiMo-V2-Pro",
@@ -32,9 +14,9 @@ export const XIAOMI_TOKEN_PLAN_AMS_MODELS = {
 		reasoning: true,
 		input: ["text"],
 		cost: {
-			input: 0.435,
+			input: 0,
-			output: 0.87,
+			output: 0,
-			cacheRead: 0.0036,
+			cacheRead: 0,
 			cacheWrite: 0,
 		},
 		contextWindow: 1048576,
@@ -50,9 +32,9 @@ export const XIAOMI_TOKEN_PLAN_AMS_MODELS = {
 		reasoning: true,
 		input: ["text", "image"],
 		cost: {
-			input: 0.14,
+			input: 0,
-			output: 0.28,
+			output: 0,
-			cacheRead: 0.0028,
+			cacheRead: 0,
 			cacheWrite: 0,
 		},
 		contextWindow: 1048576,
@@ -68,27 +50,9 @@ export const XIAOMI_TOKEN_PLAN_AMS_MODELS = {
 		reasoning: true,
 		input: ["text"],
 		cost: {
-			input: 0.435,
+			input: 0,
-			output: 0.87,
+			output: 0,
-			cacheRead: 0.0036,
+			cacheRead: 0,
-			cacheWrite: 0,
-		},
-		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,

packages/ai/src/providers/xiaomi-token-plan-cn.models.ts

@@ -4,24 +4,6 @@
 import type { Model } from "../types.ts";
 
 export const XIAOMI_TOKEN_PLAN_CN_MODELS = {
-	"mimo-v2-omni": {
-		id: "mimo-v2-omni",
-		name: "MiMo-V2-Omni",
-		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", "image"],
-		cost: {
-			input: 0.14,
-			output: 0.28,
-			cacheRead: 0.0028,
-			cacheWrite: 0,
-		},
-		contextWindow: 262144,
-		maxTokens: 131072,
-	} satisfies Model<"openai-completions">,
 	"mimo-v2-pro": {
 		id: "mimo-v2-pro",
 		name: "MiMo-V2-Pro",
@@ -32,9 +14,9 @@ export const XIAOMI_TOKEN_PLAN_CN_MODELS = {
 		reasoning: true,
 		input: ["text"],
 		cost: {
-			input: 0.435,
+			input: 0,
-			output: 0.87,
+			output: 0,
-			cacheRead: 0.0036,
+			cacheRead: 0,
 			cacheWrite: 0,
 		},
 		contextWindow: 1048576,
@@ -50,9 +32,9 @@ export const XIAOMI_TOKEN_PLAN_CN_MODELS = {
 		reasoning: true,
 		input: ["text", "image"],
 		cost: {
-			input: 0.14,
+			input: 0,
-			output: 0.28,
+			output: 0,
-			cacheRead: 0.0028,
+			cacheRead: 0,
 			cacheWrite: 0,
 		},
 		contextWindow: 1048576,
@@ -68,27 +50,9 @@ export const XIAOMI_TOKEN_PLAN_CN_MODELS = {
 		reasoning: true,
 		input: ["text"],
 		cost: {
-			input: 0.435,
+			input: 0,
-			output: 0.87,
+			output: 0,
-			cacheRead: 0.0036,
+			cacheRead: 0,
-			cacheWrite: 0,
-		},
-		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,

packages/ai/src/providers/xiaomi-token-plan-sgp.models.ts

@@ -4,24 +4,6 @@
 import type { Model } from "../types.ts";
 
 export const XIAOMI_TOKEN_PLAN_SGP_MODELS = {
-	"mimo-v2-omni": {
-		id: "mimo-v2-omni",
-		name: "MiMo-V2-Omni",
-		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", "image"],
-		cost: {
-			input: 0.14,
-			output: 0.28,
-			cacheRead: 0.0028,
-			cacheWrite: 0,
-		},
-		contextWindow: 262144,
-		maxTokens: 131072,
-	} satisfies Model<"openai-completions">,
 	"mimo-v2-pro": {
 		id: "mimo-v2-pro",
 		name: "MiMo-V2-Pro",
@@ -32,9 +14,9 @@ export const XIAOMI_TOKEN_PLAN_SGP_MODELS = {
 		reasoning: true,
 		input: ["text"],
 		cost: {
-			input: 0.435,
+			input: 0,
-			output: 0.87,
+			output: 0,
-			cacheRead: 0.0036,
+			cacheRead: 0,
 			cacheWrite: 0,
 		},
 		contextWindow: 1048576,
@@ -50,9 +32,9 @@ export const XIAOMI_TOKEN_PLAN_SGP_MODELS = {
 		reasoning: true,
 		input: ["text", "image"],
 		cost: {
-			input: 0.14,
+			input: 0,
-			output: 0.28,
+			output: 0,
-			cacheRead: 0.0028,
+			cacheRead: 0,
 			cacheWrite: 0,
 		},
 		contextWindow: 1048576,
@@ -68,27 +50,9 @@ export const XIAOMI_TOKEN_PLAN_SGP_MODELS = {
 		reasoning: true,
 		input: ["text"],
 		cost: {
-			input: 0.435,
+			input: 0,
-			output: 0.87,
+			output: 0,
-			cacheRead: 0.0036,
+			cacheRead: 0,
-			cacheWrite: 0,
-		},
-		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,

packages/ai/test/xiaomi-models.test.ts

@@ -2,14 +2,16 @@ import { describe, expect, it } from "vitest";
 import { getModel, getModels } from "../src/compat.ts";
 
 describe("Xiaomi MiMo models", () => {
-	it("keeps mimo-v2-flash on the API billing provider", () => {
+	it.each(["mimo-v2-flash", "mimo-v2-omni"] as const)("keeps %s on the API billing provider", (modelId) => {
-		expect(getModel("xiaomi", "mimo-v2-flash")).toBeDefined();
+		expect(getModel("xiaomi", modelId)).toBeDefined();
 	});
 
 	it.each(["xiaomi-token-plan-cn", "xiaomi-token-plan-ams", "xiaomi-token-plan-sgp"] as const)(
-		"omits mimo-v2-flash from %s",
+		"omits API-billing-only models from %s",
 		(provider) => {
-			expect(getModels(provider).some((model) => model.id === "mimo-v2-flash")).toBe(false);
+			const modelIds = getModels(provider).map((model) => model.id);
+			expect(modelIds).not.toContain("mimo-v2-flash");
+			expect(modelIds).not.toContain("mimo-v2-omni");
 		},
 	);
 });

packages/coding-agent/CHANGELOG.md

@@ -9,6 +9,7 @@
 
 ### Fixed
 
+- Fixed Xiaomi Token Plan model metadata to follow the upstream models.dev token-plan catalogs, removing unsupported `mimo-v2-omni` variants ([#6204](https://github.com/earendil-works/pi/issues/6204)).
 - Fixed startup model selection to skip unauthenticated saved defaults so configured local custom models can be selected instead ([#6231](https://github.com/earendil-works/pi/issues/6231)).
 - Fixed the question extension example to run question tool calls sequentially so multiple questions in one assistant turn remain answerable ([#6189](https://github.com/earendil-works/pi/issues/6189)).
 - Fixed `/login` to report auth storage persistence failures instead of claiming credentials were saved when `auth.json` is locked ([#6223](https://github.com/earendil-works/pi/issues/6223)).