fix(ai): use Xiaomi Token Plan Anthropic endpoint

closes #3912

AGENTS.md

@@ -16,6 +16,7 @@
 - Always ask before removing functionality or code that appears to be intentional
 - Do not preserve backward compatibility unless the user explicitly asks for it
 - Never hardcode key checks with, eg. `matchesKey(keyData, "ctrl+x")`. All keybindings must be configurable. Add default to matching object (`DEFAULT_EDITOR_KEYBINDINGS` or `DEFAULT_APP_KEYBINDINGS`)
+- NEVER modify `packages/ai/src/models.generated.ts` directly. Update `packages/ai/scripts/generate-models.ts` instead.
 
 ## Commands
 

packages/ai/CHANGELOG.md

@@ -16,7 +16,7 @@
 
 ### Added
 
-- Added Xiaomi MiMo provider (openai-completions compatible) with `XIAOMI_API_KEY` authentication.
+- Added Xiaomi MiMo Token Plan provider (Anthropic-compatible) with `XIAOMI_API_KEY` authentication ([#4005](https://github.com/badlogic/pi-mono/pull/4005) by [@Phoen1xCode](https://github.com/Phoen1xCode)).
 - Added `Model.thinkingLevelMap`, `getSupportedThinkingLevels()`, and `clampThinkingLevel()` so model metadata can describe supported thinking levels and provider-specific level values ([#3208](https://github.com/badlogic/pi-mono/issues/3208)).
 
 ## [0.71.1] - 2026-05-01

packages/ai/README.md

@@ -69,7 +69,7 @@ Unified LLM API with automatic model discovery, provider configuration, token an
 - **OpenCode Go**
 - **Fireworks** (uses Anthropic-compatible API)
 - **Kimi For Coding** (Moonshot AI, uses Anthropic-compatible API)
-- **Xiaomi MiMo** (uses OpenAI-compatible API)
+- **Xiaomi MiMo Token Plan** (uses Anthropic-compatible API)
 - **Any OpenAI-compatible API**: Ollama, vLLM, LM Studio, etc.
 
 ## Installation
@@ -1047,6 +1047,7 @@ In Node.js environments, you can set environment variables to avoid passing API
 | MiniMax | `MINIMAX_API_KEY` |
 | OpenCode Zen / OpenCode Go | `OPENCODE_API_KEY` |
 | Kimi For Coding | `KIMI_API_KEY` |
+| Xiaomi MiMo Token Plan | `XIAOMI_API_KEY` |
 | GitHub Copilot | `COPILOT_GITHUB_TOKEN` or `GH_TOKEN` or `GITHUB_TOKEN` |
 
 When set, the library automatically uses these keys:

packages/ai/scripts/generate-models.ts

@@ -919,9 +919,9 @@ async function loadModelsDevData(): Promise<Model<any>[]> {
 				models.push({
 					id: modelId,
 					name: m.name || modelId,
-					api: "openai-completions",
+					api: "anthropic-messages",
 					provider: "xiaomi",
-					baseUrl: "https://api.xiaomimimo.com/v1",
+					baseUrl: "https://token-plan-ams.xiaomimimo.com/anthropic",
 					reasoning: m.reasoning === true,
 					input: m.modalities?.input?.includes("image") ? ["text", "image"] : ["text"],
 					cost: {

packages/ai/src/models.generated.ts

@@ -9316,7 +9316,7 @@ export const MODELS = {
 				cacheRead: 0.024999999999999998,
 				cacheWrite: 0.08333333333333334,
 			},
-			contextWindow: 1000000,
+			contextWindow: 1048576,
 			maxTokens: 8192,
 		} satisfies Model<"openai-completions">,
 		"google/gemini-2.0-flash-lite-001": {
@@ -16392,9 +16392,9 @@ export const MODELS = {
 		"mimo-v2-flash": {
 			id: "mimo-v2-flash",
 			name: "MiMo-V2-Flash",
-			api: "openai-completions",
+			api: "anthropic-messages",
 			provider: "xiaomi",
-			baseUrl: "https://api.xiaomimimo.com/v1",
+			baseUrl: "https://token-plan-ams.xiaomimimo.com/anthropic",
 			reasoning: true,
 			input: ["text"],
 			cost: {
@@ -16405,13 +16405,13 @@ export const MODELS = {
 			},
 			contextWindow: 256000,
 			maxTokens: 64000,
-		} satisfies Model<"openai-completions">,
+		} satisfies Model<"anthropic-messages">,
 		"mimo-v2-omni": {
 			id: "mimo-v2-omni",
 			name: "MiMo-V2-Omni",
-			api: "openai-completions",
+			api: "anthropic-messages",
 			provider: "xiaomi",
-			baseUrl: "https://api.xiaomimimo.com/v1",
+			baseUrl: "https://token-plan-ams.xiaomimimo.com/anthropic",
 			reasoning: true,
 			input: ["text", "image"],
 			cost: {
@@ -16422,13 +16422,13 @@ export const MODELS = {
 			},
 			contextWindow: 256000,
 			maxTokens: 128000,
-		} satisfies Model<"openai-completions">,
+		} satisfies Model<"anthropic-messages">,
 		"mimo-v2-pro": {
 			id: "mimo-v2-pro",
 			name: "MiMo-V2-Pro",
-			api: "openai-completions",
+			api: "anthropic-messages",
 			provider: "xiaomi",
-			baseUrl: "https://api.xiaomimimo.com/v1",
+			baseUrl: "https://token-plan-ams.xiaomimimo.com/anthropic",
 			reasoning: true,
 			input: ["text"],
 			cost: {
@@ -16439,13 +16439,13 @@ export const MODELS = {
 			},
 			contextWindow: 1000000,
 			maxTokens: 128000,
-		} satisfies Model<"openai-completions">,
+		} satisfies Model<"anthropic-messages">,
 		"mimo-v2.5": {
 			id: "mimo-v2.5",
 			name: "MiMo-V2.5",
-			api: "openai-completions",
+			api: "anthropic-messages",
 			provider: "xiaomi",
-			baseUrl: "https://api.xiaomimimo.com/v1",
+			baseUrl: "https://token-plan-ams.xiaomimimo.com/anthropic",
 			reasoning: true,
 			input: ["text"],
 			cost: {
@@ -16456,13 +16456,13 @@ export const MODELS = {
 			},
 			contextWindow: 1048576,
 			maxTokens: 131072,
-		} satisfies Model<"openai-completions">,
+		} satisfies Model<"anthropic-messages">,
 		"mimo-v2.5-pro": {
 			id: "mimo-v2.5-pro",
 			name: "MiMo-V2.5-Pro",
-			api: "openai-completions",
+			api: "anthropic-messages",
 			provider: "xiaomi",
-			baseUrl: "https://api.xiaomimimo.com/v1",
+			baseUrl: "https://token-plan-ams.xiaomimimo.com/anthropic",
 			reasoning: true,
 			input: ["text", "image"],
 			cost: {
@@ -16473,7 +16473,7 @@ export const MODELS = {
 			},
 			contextWindow: 1048576,
 			maxTokens: 131072,
-		} satisfies Model<"openai-completions">,
+		} satisfies Model<"anthropic-messages">,
 	},
 	"zai": {
 		"glm-4.5-air": {

packages/ai/test/stream.test.ts

@@ -994,9 +994,13 @@ describe("Generate E2E Tests", () => {
 	);
 
 	describe.skipIf(!process.env.XIAOMI_API_KEY)(
-		"Xiaomi MiMo Provider (Xiaomi MiMo-V2.5-Pro via OpenAI Completions)",
+		"Xiaomi MiMo Token Plan Provider (Xiaomi MiMo-V2.5-Pro via Anthropic Messages)",
 		() => {
 			const llm = getModel("xiaomi", "mimo-v2.5-pro");
+			const thinkingOptions = {
+				thinkingEnabled: true,
+				reasoningEffort: "high",
+			} satisfies StreamOptionsWithExtras;
 
 			it("should complete basic text generation", { retry: 3 }, async () => {
 				await basicTextGeneration(llm);
@@ -1009,6 +1013,14 @@ describe("Generate E2E Tests", () => {
 			it("should handle streaming", { retry: 3 }, async () => {
 				await handleStreaming(llm);
 			});
+
+			it("should handle thinking mode", { retry: 3 }, async () => {
+				await handleThinking(llm, thinkingOptions);
+			});
+
+			it("should handle multi-turn with thinking and tools", { retry: 3 }, async () => {
+				await multiTurn(llm, thinkingOptions);
+			});
 		},
 	);
 	// =========================================================================

packages/coding-agent/CHANGELOG.md

@@ -8,6 +8,7 @@
 
 ### Added
 
+- Added Xiaomi MiMo Token Plan provider support with `XIAOMI_API_KEY`, default model resolution, `/login` display support, and provider documentation ([#4005](https://github.com/badlogic/pi-mono/pull/4005) by [@Phoen1xCode](https://github.com/Phoen1xCode)).
 - Added model-level `thinkingLevelMap` support in `models.json` and `pi.registerProvider()`, allowing models to expose only the thinking levels they actually support ([#3208](https://github.com/badlogic/pi-mono/issues/3208)).
 
 ### Fixed

packages/coding-agent/README.md

@@ -128,7 +128,7 @@ For each built-in provider, pi maintains a list of tool-capable models, updated
 - Fireworks
 - Kimi For Coding
 - MiniMax
-- Xiaomi MiMo
+- Xiaomi MiMo Token Plan
 
 See [docs/providers.md](docs/providers.md) for detailed setup instructions.
 

packages/coding-agent/docs/providers.md

@@ -69,7 +69,9 @@ pi
 | Kimi For Coding | `KIMI_API_KEY` | `kimi-coding` |
 | MiniMax | `MINIMAX_API_KEY` | `minimax` |
 | MiniMax (China) | `MINIMAX_CN_API_KEY` | `minimax-cn` |
-| Xiaomi MiMo | `XIAOMI_API_KEY` | `xiaomi` |
+| Xiaomi MiMo Token Plan | `XIAOMI_API_KEY` | `xiaomi` |
+
+The Xiaomi MiMo provider targets the Xiaomi MiMo Token Plan Anthropic-compatible endpoint.
 
 Reference for environment variables and `auth.json` keys: [`const envMap`](https://github.com/badlogic/pi-mono/blob/main/packages/ai/src/env-api-keys.ts) in [`packages/ai/src/env-api-keys.ts`](https://github.com/badlogic/pi-mono/blob/main/packages/ai/src/env-api-keys.ts).
 

packages/coding-agent/src/cli/args.ts

@@ -320,7 +320,7 @@ ${chalk.bold("Environment Variables:")}
   CLOUDFLARE_API_KEY               - Cloudflare API token (Workers AI and AI Gateway)
   CLOUDFLARE_ACCOUNT_ID            - Cloudflare account id (required for both)
   CLOUDFLARE_GATEWAY_ID            - Cloudflare AI Gateway slug (required for AI Gateway)
-  XIAOMI_API_KEY                   - Xiaomi MiMo API key
+  XIAOMI_API_KEY                   - Xiaomi MiMo Token Plan API key
   AWS_PROFILE                      - AWS profile for Amazon Bedrock
   AWS_ACCESS_KEY_ID                - AWS access key for Amazon Bedrock
   AWS_SECRET_ACCESS_KEY            - AWS secret key for Amazon Bedrock

packages/coding-agent/src/core/provider-display-names.ts

@@ -24,5 +24,5 @@ export const BUILT_IN_PROVIDER_DISPLAY_NAMES: Record<string, string> = {
 	"vercel-ai-gateway": "Vercel AI Gateway",
 	xai: "xAI",
 	zai: "ZAI",
-	xiaomi: "Xiaomi MiMo",
+	xiaomi: "Xiaomi MiMo Token Plan",
 };