Feature: add new provider AIHubmix

apps/kilocode-docs/pages/ai-providers/aihubmix.md

@@ -0,0 +1,28 @@
+---
+sidebar_label: AIhubmix
+---
+
+# Using AIhubmix With Kilo Code
+
+AIhubmix is an AI gateway that provides unified access to multiple AI models from various providers through a single API. It offers competitive pricing and supports features like prompt caching.
+
+**Website:** [https://aihubmix.com/](https://aihubmix.com/)
+
+## Getting an API Key
+
+1. **Sign Up/Sign In:** Go to the [AIhubmix website](https://aihubmix.com/) and create an account or sign in.
+2. **Get API Key:** Go to the [API Keys page](https://console.aihubmix.com/token) to generate an API key.
+3. **Copy the Key:** Copy the API key.
+
+## Configuration in Kilo Code
+
+1. **Open Kilo Code Settings:** Click the gear icon ({% codicon name="gear" /%}) in the Kilo Code panel.
+2. **Select Provider:** Choose "AIhubmix" from the "API Provider" dropdown.
+3. **Enter API Key:** Paste your AIhubmix API key into the "AIhubmix API Key" field.
+4. **Select Model:** Choose your desired model from the "Model" dropdown.
+
+## Tips and Notes
+
+- **Model Selection:** AIhubmix offers a wide range of models. Models are sorted by their coding capability score.
+- **Pricing:** AIhubmix charges based on the underlying model's pricing. See the [AIhubmix Models page](https://aihubmix.com/models) for details.
+- **Prompt Caching:** Some models support prompt caching. See the AIhubmix documentation for supported models.

docs/plans/2026-01-20-apertis-provider-design.md

@@ -10,13 +10,13 @@ Apertis is a unified AI API platform providing access to 450+ models from multip
 
 ## API Endpoints
 
-| Endpoint | Format | Authentication | Use Case |
-|----------|--------|----------------|----------|
-| `/v1/chat/completions` | OpenAI Chat | `Authorization: Bearer` | General models (GPT, Gemini, etc.) |
-| `/v1/messages` | Anthropic | `x-api-key` | Claude models |
-| `/v1/responses` | OpenAI Responses | `Authorization: Bearer` | Reasoning models (o1, o3) |
-| `/api/models` | - | None required | Public model list |
-| `/v1/models` | OpenAI | `Authorization: Bearer` | Detailed model info |
+| Endpoint               | Format           | Authentication          | Use Case                           |
+| ---------------------- | ---------------- | ----------------------- | ---------------------------------- |
+| `/v1/chat/completions` | OpenAI Chat      | `Authorization: Bearer` | General models (GPT, Gemini, etc.) |
+| `/v1/messages`         | Anthropic        | `x-api-key`             | Claude models                      |
+| `/v1/responses`        | OpenAI Responses | `Authorization: Bearer` | Reasoning models (o1, o3)          |
+| `/api/models`          | -                | None required           | Public model list                  |
+| `/v1/models`           | OpenAI           | `Authorization: Bearer` | Detailed model info                |
 
 **Base URL:** `https://api.apertis.ai` (configurable for enterprise/self-hosted)
 
@@ -40,6 +40,7 @@ The ApertisHandler implements intelligent routing based on model ID:
 ```
 
 **Routing Rules:**
+
 - `claude-*` → `/v1/messages` (Anthropic format)
 - `o1-*`, `o3-*` or reasoning enabled → `/v1/responses` (Responses API)
 - Others → `/v1/chat/completions` (OpenAI Chat)
@@ -78,21 +79,21 @@ webview-ui/src/i18n/locales/*/settings.json # i18n translations
 
 ```typescript
 const apertisSchema = baseProviderSettingsSchema.extend({
-  // Authentication
-  apertisApiKey: z.string().optional(),
+	// Authentication
+	apertisApiKey: z.string().optional(),
 
-  // Model selection
-  apertisModelId: z.string().optional(),
+	// Model selection
+	apertisModelId: z.string().optional(),
 
-  // Base URL (default: https://api.apertis.ai)
-  apertisBaseUrl: z.string().optional(),
+	// Base URL (default: https://api.apertis.ai)
+	apertisBaseUrl: z.string().optional(),
 
-  // Responses API specific
-  apertisInstructions: z.string().optional(),
+	// Responses API specific
+	apertisInstructions: z.string().optional(),
 
-  // Reasoning settings
-  apertisReasoningEffort: z.enum(["low", "medium", "high"]).optional(),
-  apertisReasoningSummary: z.enum(["auto", "concise", "detailed"]).optional(),
+	// Reasoning settings
+	apertisReasoningEffort: z.enum(["low", "medium", "high"]).optional(),
+	apertisReasoningSummary: z.enum(["auto", "concise", "detailed"]).optional(),
 })
 ```
 
@@ -111,44 +112,44 @@ export const apertisDefaultModelId = "claude-sonnet-4-20250514"
 // src/api/providers/apertis.ts
 
 export class ApertisHandler extends BaseProvider implements SingleCompletionHandler {
-  private options: ApiHandlerOptions
-  private client: OpenAI
-  private anthropicClient: Anthropic
-
-  constructor(options: ApiHandlerOptions) {
-    const baseURL = options.apertisBaseUrl || APERTIS_DEFAULT_BASE_URL
-
-    this.client = new OpenAI({
-      baseURL: `${baseURL}/v1`,
-      apiKey: options.apertisApiKey,
-    })
-
-    this.anthropicClient = new Anthropic({
-      baseURL: `${baseURL}/v1`,
-      apiKey: options.apertisApiKey,
-    })
-  }
-
-  private getApiFormat(modelId: string): "messages" | "responses" | "chat" {
-    if (modelId.startsWith("claude-")) return "messages"
-    if (modelId.startsWith("o1-") || modelId.startsWith("o3-")) return "responses"
-    return "chat"
-  }
-
-  async *createMessage(systemPrompt, messages, metadata) {
-    const format = this.getApiFormat(this.getModel().id)
-
-    switch (format) {
-      case "messages":
-        yield* this.createAnthropicMessage(systemPrompt, messages, metadata)
-        break
-      case "responses":
-        yield* this.createResponsesMessage(systemPrompt, messages, metadata)
-        break
-      default:
-        yield* this.createChatMessage(systemPrompt, messages, metadata)
-    }
-  }
+	private options: ApiHandlerOptions
+	private client: OpenAI
+	private anthropicClient: Anthropic
+
+	constructor(options: ApiHandlerOptions) {
+		const baseURL = options.apertisBaseUrl || APERTIS_DEFAULT_BASE_URL
+
+		this.client = new OpenAI({
+			baseURL: `${baseURL}/v1`,
+			apiKey: options.apertisApiKey,
+		})
+
+		this.anthropicClient = new Anthropic({
+			baseURL: `${baseURL}/v1`,
+			apiKey: options.apertisApiKey,
+		})
+	}
+
+	private getApiFormat(modelId: string): "messages" | "responses" | "chat" {
+		if (modelId.startsWith("claude-")) return "messages"
+		if (modelId.startsWith("o1-") || modelId.startsWith("o3-")) return "responses"
+		return "chat"
+	}
+
+	async *createMessage(systemPrompt, messages, metadata) {
+		const format = this.getApiFormat(this.getModel().id)
+
+		switch (format) {
+			case "messages":
+				yield* this.createAnthropicMessage(systemPrompt, messages, metadata)
+				break
+			case "responses":
+				yield* this.createResponsesMessage(systemPrompt, messages, metadata)
+				break
+			default:
+				yield* this.createChatMessage(systemPrompt, messages, metadata)
+		}
+	}
 }
 ```
 
@@ -157,48 +158,46 @@ export class ApertisHandler extends BaseProvider implements SingleCompletionHand
 ```typescript
 // src/api/providers/fetchers/apertis.ts
 
-export async function getApertisModels(options?: {
-  apiKey?: string
-  baseUrl?: string
-}): Promise<ModelRecord> {
-  const baseUrl = options?.baseUrl || APERTIS_DEFAULT_BASE_URL
+export async function getApertisModels(options?: { apiKey?: string; baseUrl?: string }): Promise<ModelRecord> {
+	const baseUrl = options?.baseUrl || APERTIS_DEFAULT_BASE_URL
 
-  // Use public endpoint (no auth required)
-  const response = await fetch(`${baseUrl}/api/models`)
-  const data = await response.json()
+	// Use public endpoint (no auth required)
+	const response = await fetch(`${baseUrl}/api/models`)
+	const data = await response.json()
 
-  const models: ModelRecord = {}
+	const models: ModelRecord = {}
 
-  for (const modelId of data.data) {
-    models[modelId] = {
-      contextWindow: getContextWindow(modelId),
-      supportsPromptCache: modelId.startsWith("claude-"),
-      supportsImages: supportsVision(modelId),
-    }
-  }
+	for (const modelId of data.data) {
+		models[modelId] = {
+			contextWindow: getContextWindow(modelId),
+			supportsPromptCache: modelId.startsWith("claude-"),
+			supportsImages: supportsVision(modelId),
+		}
+	}
 
-  return models
+	return models
 }
 ```
 
 ## UI Settings Component
 
 Key features:
+
 - API Key input with link to `https://apertis.ai/token`
 - Model picker with dynamic model list
 - Reasoning settings (shown only for o1/o3 models)
 - Advanced settings (collapsible) with Base URL option
 
 ## Special Features Support
 
-| Feature | API | Implementation |
-|---------|-----|----------------|
-| Extended Thinking | Messages API | `thinking.budget_tokens` parameter |
-| Reasoning Effort | Responses API | `reasoning.effort` parameter |
-| Reasoning Summary | Responses API | `reasoning.summary` parameter |
-| Instructions | Responses API | `instructions` parameter |
-| Web Search | Responses API | `tools` with web_search type |
-| Streaming | All APIs | `stream: true` parameter |
+| Feature           | API           | Implementation                     |
+| ----------------- | ------------- | ---------------------------------- |
+| Extended Thinking | Messages API  | `thinking.budget_tokens` parameter |
+| Reasoning Effort  | Responses API | `reasoning.effort` parameter       |
+| Reasoning Summary | Responses API | `reasoning.summary` parameter      |
+| Instructions      | Responses API | `instructions` parameter           |
+| Web Search        | Responses API | `tools` with web_search type       |
+| Streaming         | All APIs      | `stream: true` parameter           |
 
 ## Error Handling
 

packages/types/src/provider-settings.ts

@@ -65,6 +65,7 @@ export const dynamicProviders = [
 	"requesty",
 	"unbound",
 	"glama", // kilocode_change
+	"aihubmix", // kilocode_change
 	"roo",
 	"chutes",
 	"nano-gpt", //kilocode_change
@@ -547,6 +548,13 @@ const fireworksSchema = apiModelIdProviderModelSchema.extend({
 const syntheticSchema = apiModelIdProviderModelSchema.extend({
 	syntheticApiKey: z.string().optional(),
 })
+
+const aihubmixSchema = baseProviderSettingsSchema.extend({
+	aihubmixApiKey: z.string().optional(),
+	aihubmixBaseUrl: z.string().optional(),
+	aihubmixModelId: z.string().optional(),
+	aihubmixModelInfo: modelInfoSchema.optional(),
+})
 // kilocode_change end
 
 const featherlessSchema = apiModelIdProviderModelSchema.extend({
@@ -630,6 +638,7 @@ export const providerSettingsSchemaDiscriminated = z.discriminatedUnion("apiProv
 	virtualQuotaFallbackSchema.merge(z.object({ apiProvider: z.literal("virtual-quota-fallback") })),
 	syntheticSchema.merge(z.object({ apiProvider: z.literal("synthetic") })),
 	inceptionSchema.merge(z.object({ apiProvider: z.literal("inception") })),
+	aihubmixSchema.merge(z.object({ apiProvider: z.literal("aihubmix") })),
 	// kilocode_change end
 	groqSchema.merge(z.object({ apiProvider: z.literal("groq") })),
 	basetenSchema.merge(z.object({ apiProvider: z.literal("baseten") })),
@@ -673,6 +682,7 @@ export const providerSettingsSchema = z.object({
 	...syntheticSchema.shape,
 	...ovhcloudSchema.shape,
 	...inceptionSchema.shape,
+	...aihubmixSchema.shape,
 	// kilocode_change end
 	...openAiCodexSchema.shape,
 	...openAiNativeSchema.shape,
@@ -745,6 +755,7 @@ export const modelIdKeys = [
 	"inceptionLabsModelId", // kilocode_change
 	"sapAiCoreModelId", // kilocode_change
 	"apertisModelId", // kilocode_change
+	"aihubmixModelId", // kilocode_change
 ] as const satisfies readonly (keyof ProviderSettings)[]
 
 export type ModelIdKey = (typeof modelIdKeys)[number]
@@ -792,6 +803,7 @@ export const modelIdKeysByProvider: Record<TypicalProvider, ModelIdKey> = {
 	ovhcloud: "ovhCloudAiEndpointsModelId",
 	inception: "inceptionLabsModelId",
 	"sap-ai-core": "sapAiCoreModelId",
+	aihubmix: "aihubmixModelId",
 	apertis: "apertisModelId",
 	zenmux: "zenmuxModelId", // kilocode_change
 	// kilocode_change end
@@ -968,6 +980,7 @@ export const MODELS_BY_PROVIDER: Record<
 	inception: { id: "inception", label: "Inception", models: [] },
 	kilocode: { id: "kilocode", label: "Kilocode", models: [] },
 	"virtual-quota-fallback": { id: "virtual-quota-fallback", label: "Virtual Quota Fallback", models: [] },
+	aihubmix: { id: "aihubmix", label: "AIhubmix", models: [] },
 	apertis: { id: "apertis", label: "Apertis", models: [] },
 	zenmux: { id: "zenmux", label: "ZenMux", models: [] }, // kilocode_change
 	// kilocode_change end

packages/types/src/providers/aihubmix.ts

@@ -0,0 +1,19 @@
+// kilocode_change - new file
+// AIhubmix is a dynamic provider, models are fetched from API
+// Only fallback types are defined here
+
+export type AihubmixModelId = string
+
+export const aihubmixDefaultModelId = "claude-opus-4-5"
+
+export const aihubmixDefaultModelInfo = {
+	maxTokens: 8192,
+	contextWindow: 128000,
+	supportsImages: true,
+	supportsPromptCache: false,
+	supportsNativeTools: true,
+	defaultToolProtocol: "native" as const,
+	inputPrice: 3,
+	outputPrice: 15,
+	description: "AIhubmix unified model provider",
+}

packages/types/src/providers/fireworks.ts

@@ -207,7 +207,7 @@ export const fireworksModels = {
 		supportsImages: false,
 		supportsPromptCache: false,
 		supportsNativeTools: true,
-    defaultToolProtocol: "native",
+		defaultToolProtocol: "native",
 		inputPrice: 0.22,
 		outputPrice: 0.88,
 		displayName: "GLM-4.5 Air",
@@ -243,7 +243,7 @@ export const fireworksModels = {
 		supportsImages: false,
 		supportsPromptCache: true,
 		supportsNativeTools: true,
-    defaultToolProtocol: "native",
+		defaultToolProtocol: "native",
 		inputPrice: 0.05,
 		outputPrice: 0.2,
 		cacheReadsPrice: 0.04,

packages/types/src/providers/index.ts

@@ -16,6 +16,7 @@ export * from "./synthetic.js"
 export * from "./inception.js"
 export * from "./minimax.js"
 export * from "./glama.js"
+export * from "./aihubmix.js"
 export * from "./apertis.js"
 export * from "./zenmux.js"
 // kilocode_change end
@@ -58,6 +59,7 @@ import { featherlessDefaultModelId } from "./featherless.js"
 import { fireworksDefaultModelId } from "./fireworks.js"
 import { geminiDefaultModelId } from "./gemini.js"
 import { glamaDefaultModelId } from "./glama.js" // kilocode_change
+import { aihubmixDefaultModelId } from "./aihubmix.js" // kilocode_change
 import { apertisDefaultModelId } from "./apertis.js" // kilocode_change
 import { zenmuxDefaultModelId } from "./zenmux.js" // kilocode_change
 import { groqDefaultModelId } from "./groq.js"
@@ -102,6 +104,8 @@ export function getProviderDefaultModelId(
 		// kilocode_change start
 		case "glama":
 			return glamaDefaultModelId
+		case "aihubmix":
+			return aihubmixDefaultModelId
 		case "apertis":
 			return apertisDefaultModelId
 		// kilocode_change end

src/api/index.ts

@@ -38,6 +38,7 @@ import {
 	SyntheticHandler,
 	OVHcloudAIEndpointsHandler,
 	SapAiCoreHandler,
+	AihubmixHandler,
 	ApertisHandler,
 	// kilocode_change end
 	ClaudeCodeHandler,
@@ -265,6 +266,8 @@ export function buildApiHandler(configuration: ProviderSettings): ApiHandler {
 			return new OVHcloudAIEndpointsHandler(options)
 		case "sap-ai-core":
 			return new SapAiCoreHandler(options)
+		case "aihubmix":
+			return new AihubmixHandler(options)
 		case "apertis":
 			return new ApertisHandler(options)
 		// kilocode_change end

src/api/providers/__tests__/moonshot.spec.ts

@@ -335,7 +335,9 @@ describe("MoonshotHandler", () => {
 				}),
 			})
 
-			for await (const _chunk of strictHandler.createMessage(systemPrompt, messages, { taskId: "task-cache-2" })) {
+			for await (const _chunk of strictHandler.createMessage(systemPrompt, messages, {
+				taskId: "task-cache-2",
+			})) {
 				// Drain stream
 			}