Add Nebius Token Factory support (merged with Xiaomi changes)

docs/concepts/model-providers.md

@@ -118,6 +118,10 @@ Moltbot ships with the pi‑ai catalog. These providers require **no**
   - OpenAI-compatible base URL: `https://api.cerebras.ai/v1`.
 - Mistral: `mistral` (`MISTRAL_API_KEY`)
 - GitHub Copilot: `github-copilot` (`COPILOT_GITHUB_TOKEN` / `GH_TOKEN` / `GITHUB_TOKEN`)
+- Nebius: `nebius` (`NEBIUS_API_KEY`)
+  - Example model: `Qwen/Qwen3-32B-fast` (recommended default)
+  - Available: Qwen, Llama, DeepSeek, GLM, and other open models
+  - OpenAI-compatible base URL: `https://api.tokenfactory.nebius.com/v1/`
 
 ## Providers via `models.providers` (custom/base URL)
 

docs/gateway/configuration.md

@@ -2608,6 +2608,56 @@ Notes:
 - Override the agent config root with `CLAWDBOT_AGENT_DIR` (or `PI_CODING_AGENT_DIR`)
   if you want `models.json` stored elsewhere (default: `~/.clawdbot/agents/main/agent`).
 
+
+### Nebius (GLM 7 / GLM 5)
+
+Use Nebius via their OpenAI-compatible endpoint:
+
+```json5
+{
+  env: {
+    NEBIUS_API_KEY: "" },
+
+  agents: {
+    defaults: {
+      model: {
+        primary: "Qwen/Qwen3-32B-fast",
+        fallbacks: ["meta-llama/Llama-3.3-70B-Instruct-fast"]
+      },
+      models: {
+        "Qwen/Qwen3-32B-fast": { alias: "Qwen3 32B Fast" },
+        "meta-llama/Llama-3.3-70B-Instruct-fast": { alias: "Llama 3.3 70B Fast" },
+        "deepseek-ai/DeepSeek-R1-0528-fast": { alias: "DeepSeek R1 Fast" },
+        "Qwen/Qwen2.5-VL-72B-Instruct": { alias: "Qwen2.5 VL 72B" }
+      }
+    }
+  },
+
+  models: {
+    mode: "merge",
+    providers: {
+      nebius: {
+        baseUrl: "https://api.tokenfactory.nebius.com/v1",
+        apiKey: "${NEBIUS_API_KEY}",
+        api: "openai-completions",
+        models: [
+          { id: "Qwen/Qwen3-32B-fast", name: "Qwen3 32B Fast" },
+          { id: "meta-llama/Meta-Llama-3.1-8B-Instruct-fast", name: "Llama 3.1 8B Fast" },
+          { id: "meta-llama/Llama-3.3-70B-Instruct", name: "Llama 3.3 70B" },
+          { id: "meta-llama/Llama-3.3-70B-Instruct-fast", name: "Llama 3.3 70B Fast" },
+          { id: "deepseek-ai/DeepSeek-V3-0324-fast", name: "DeepSeek V3 Fast" },
+          { id: "deepseek-ai/DeepSeek-R1-0528-fast", name: "DeepSeek R1 Fast", reasoning: true },
+          { id: "Qwen/Qwen2.5-VL-72B-Instruct", name: "Qwen2.5 VL 72B", input: ["text", "image"] },
+          { id: "Qwen/Qwen2.5-Coder-7B-fast", name: "Qwen2.5 Coder 7B Fast" },
+          { id: "intfloat/e5-mistral-7b-instruct", name: "e5 Mistral 7B" },
+          { id: "zai-org/GLM-4.7-FP8", name: "GLM 4.7 FP8" },
+          { id: "zai-org/GLM-4.5", name: "GLM 4.5" }
+        ]
+      }
+    }
+  }
+}
+
 ### `session`
 
 Controls session scoping, reset policy, reset triggers, and where the session store is written.

docs/providers/index.md

@@ -42,11 +42,11 @@ See [Venice AI](/providers/venice).
 - [OpenCode Zen](/providers/opencode)
 - [Amazon Bedrock](/bedrock)
 - [Z.AI](/providers/zai)
-- [Xiaomi](/providers/xiaomi)
 - [GLM models](/providers/glm)
 - [MiniMax](/providers/minimax)
 - [Venius (Venice AI, privacy-focused)](/providers/venice)
 - [Ollama (local models)](/providers/ollama)
+- [Nebius](/providers/nebius)
 
 ## Transcription providers
 

docs/providers/nebius.md

@@ -0,0 +1,68 @@
+---
+summary: "Use Nebius OpenAI-compatible inference for frontier and open-source models"
+read_when:
+  - You want to use Nebius inference
+  - You want to use Qwen, Llama, DeepSeek, and other open models
+---
+# Nebius
+
+Nebius provides **OpenAI-compatible inference** for frontier and open-source models, including **Qwen**, **Llama**, **DeepSeek**, and **GLM**, via the Nebius TokenFactory API. This allows seamless drop-in usage with existing OpenAI-style clients and tooling.
+
+## CLI setup
+
+```bash
+clawdbot onboard --auth-choice nebius-api-key
+# or non-interactive
+clawdbot onboard --nebius-api-key "$NEBIUS_API_KEY"
+
+```
+
+## Config snippet
+
+```json5
+{
+  env: { NEBIUS_API_KEY: "sk-..." },
+  agents: {
+    defaults: {
+      model: {
+        primary: "Qwen/Qwen3-32B-fast",
+        fallbacks: ["meta-llama/Llama-3.3-70B-Instruct-fast"]
+      }
+    }
+  }
+}
+```
+
+## Available models
+
+### Daily Driver (Fast, Capable)
+- `Qwen/Qwen3-32B-fast` – Qwen3 32B Fast (recommended default)
+
+### Lightweight (Fast, Basic)
+- `meta-llama/Meta-Llama-3.1-8B-Instruct-fast` – Llama 3.1 8B Fast
+
+### Heavy Lifting (More Complex)
+- `meta-llama/Llama-3.3-70B-Instruct` – Llama 3.3 70B
+- `meta-llama/Llama-3.3-70B-Instruct-fast` – Llama 3.3 70B Fast
+- `deepseek-ai/DeepSeek-V3-0324-fast` – DeepSeek V3 Fast
+
+### Specialized (Reasoning)
+- `deepseek-ai/DeepSeek-R1-0528-fast` – DeepSeek R1 Fast
+
+### Vision
+- `Qwen/Qwen2.5-VL-72B-Instruct` – Qwen2.5 VL 72B
+
+### Coding
+- `Qwen/Qwen2.5-Coder-7B-fast` – Qwen2.5 Coder 7B Fast
+
+### GLM Models
+- `zai-org/GLM-4.7-FP8` – GLM 4.7 FP8
+- `zai-org/GLM-4.5` – GLM 4.5
+
+## Notes
+
+- Base URL: https://api.tokenfactory.nebius.com/v1
+- OpenAI-compatible Chat Completions API
+- Model refs use nebius/<model> format
+- Set NEBIUS_API_KEY in the environment or config
+- Works with standard OpenAI SDKs (Python, JS, etc.)

src/agents/model-auth.ts

@@ -281,11 +281,11 @@ export function resolveEnvApiKey(provider: string): EnvApiKeyResult | null {
     moonshot: "MOONSHOT_API_KEY",
     "kimi-code": "KIMICODE_API_KEY",
     minimax: "MINIMAX_API_KEY",
-    xiaomi: "XIAOMI_API_KEY",
     synthetic: "SYNTHETIC_API_KEY",
     venice: "VENICE_API_KEY",
     mistral: "MISTRAL_API_KEY",
     opencode: "OPENCODE_API_KEY",
+    nebius: "NEBIUS_API_KEY",
   };
   const envVar = envMap[normalized];
   if (!envVar) return null;

src/agents/models-config.providers.ts

@@ -30,17 +30,6 @@ const MINIMAX_API_COST = {
   cacheWrite: 10,
 };
 
-const XIAOMI_BASE_URL = "https://api.xiaomimimo.com/anthropic";
-export const XIAOMI_DEFAULT_MODEL_ID = "mimo-v2-flash";
-const XIAOMI_DEFAULT_CONTEXT_WINDOW = 262144;
-const XIAOMI_DEFAULT_MAX_TOKENS = 8192;
-const XIAOMI_DEFAULT_COST = {
-  input: 0,
-  output: 0,
-  cacheRead: 0,
-  cacheWrite: 0,
-};
-
 const MOONSHOT_BASE_URL = "https://api.moonshot.ai/v1";
 const MOONSHOT_DEFAULT_MODEL_ID = "kimi-k2.5";
 const MOONSHOT_DEFAULT_CONTEXT_WINDOW = 256000;
@@ -75,6 +64,16 @@ const QWEN_PORTAL_DEFAULT_COST = {
   cacheWrite: 0,
 };
 
+const NEBIUS_BASE_URL = "https://api.tokenfactory.nebius.com/v1";
+const NEBIUS_DEFAULT_CONTEXT_WINDOW = 128000;
+const NEBIUS_DEFAULT_MAX_TOKENS = 8192;
+const NEBIUS_DEFAULT_COST = {
+  input: 0,
+  output: 0,
+  cacheRead: 0,
+  cacheWrite: 0,
+};
+
 const OLLAMA_BASE_URL = "http://127.0.0.1:11434/v1";
 const OLLAMA_API_BASE_URL = "http://127.0.0.1:11434";
 const OLLAMA_DEFAULT_CONTEXT_WINDOW = 128000;
@@ -352,24 +351,6 @@ function buildSyntheticProvider(): ProviderConfig {
   };
 }
 
-export function buildXiaomiProvider(): ProviderConfig {
-  return {
-    baseUrl: XIAOMI_BASE_URL,
-    api: "anthropic-messages",
-    models: [
-      {
-        id: XIAOMI_DEFAULT_MODEL_ID,
-        name: "Xiaomi MiMo V2 Flash",
-        reasoning: false,
-        input: ["text"],
-        cost: XIAOMI_DEFAULT_COST,
-        contextWindow: XIAOMI_DEFAULT_CONTEXT_WINDOW,
-        maxTokens: XIAOMI_DEFAULT_MAX_TOKENS,
-      },
-    ],
-  };
-}
-
 async function buildVeniceProvider(): Promise<ProviderConfig> {
   const models = await discoverVeniceModels();
   return {
@@ -388,6 +369,105 @@ async function buildOllamaProvider(): Promise<ProviderConfig> {
   };
 }
 
+function buildNebiusProvider(): ProviderConfig {
+  return {
+    baseUrl: NEBIUS_BASE_URL,
+    api: "openai-completions",
+    models: [
+      {
+        id: "Qwen/Qwen3-32B-fast",
+        name: "Qwen3 32B Fast",
+        reasoning: false,
+        input: ["text"],
+        cost: NEBIUS_DEFAULT_COST,
+        contextWindow: NEBIUS_DEFAULT_CONTEXT_WINDOW,
+        maxTokens: NEBIUS_DEFAULT_MAX_TOKENS,
+      },
+      {
+        id: "meta-llama/Meta-Llama-3.1-8B-Instruct-fast",
+        name: "Llama 3.1 8B Fast",
+        reasoning: false,
+        input: ["text"],
+        cost: NEBIUS_DEFAULT_COST,
+        contextWindow: NEBIUS_DEFAULT_CONTEXT_WINDOW,
+        maxTokens: NEBIUS_DEFAULT_MAX_TOKENS,
+      },
+      {
+        id: "meta-llama/Llama-3.3-70B-Instruct",
+        name: "Llama 3.3 70B",
+        reasoning: false,
+        input: ["text"],
+        cost: NEBIUS_DEFAULT_COST,
+        contextWindow: NEBIUS_DEFAULT_CONTEXT_WINDOW,
+        maxTokens: NEBIUS_DEFAULT_MAX_TOKENS,
+      },
+      {
+        id: "meta-llama/Llama-3.3-70B-Instruct-fast",
+        name: "Llama 3.3 70B Fast",
+        reasoning: false,
+        input: ["text"],
+        cost: NEBIUS_DEFAULT_COST,
+        contextWindow: NEBIUS_DEFAULT_CONTEXT_WINDOW,
+        maxTokens: NEBIUS_DEFAULT_MAX_TOKENS,
+      },
+      {
+        id: "deepseek-ai/DeepSeek-V3-0324-fast",
+        name: "DeepSeek V3 Fast",
+        reasoning: false,
+        input: ["text"],
+        cost: NEBIUS_DEFAULT_COST,
+        contextWindow: NEBIUS_DEFAULT_CONTEXT_WINDOW,
+        maxTokens: NEBIUS_DEFAULT_MAX_TOKENS,
+      },
+      {
+        id: "deepseek-ai/DeepSeek-R1-0528-fast",
+        name: "DeepSeek R1 Fast",
+        reasoning: true,
+        input: ["text"],
+        cost: NEBIUS_DEFAULT_COST,
+        contextWindow: NEBIUS_DEFAULT_CONTEXT_WINDOW,
+        maxTokens: NEBIUS_DEFAULT_MAX_TOKENS,
+      },
+      {
+        id: "Qwen/Qwen2.5-VL-72B-Instruct",
+        name: "Qwen2.5 VL 72B",
+        reasoning: false,
+        input: ["text", "image"],
+        cost: NEBIUS_DEFAULT_COST,
+        contextWindow: NEBIUS_DEFAULT_CONTEXT_WINDOW,
+        maxTokens: NEBIUS_DEFAULT_MAX_TOKENS,
+      },
+      {
+        id: "Qwen/Qwen2.5-Coder-7B-fast",
+        name: "Qwen2.5 Coder 7B Fast",
+        reasoning: false,
+        input: ["text"],
+        cost: NEBIUS_DEFAULT_COST,
+        contextWindow: NEBIUS_DEFAULT_CONTEXT_WINDOW,
+        maxTokens: NEBIUS_DEFAULT_MAX_TOKENS,
+      },
+      {
+        id: "zai-org/GLM-4.7-FP8",
+        name: "GLM 4.7 FP8",
+        reasoning: false,
+        input: ["text"],
+        cost: NEBIUS_DEFAULT_COST,
+        contextWindow: NEBIUS_DEFAULT_CONTEXT_WINDOW,
+        maxTokens: NEBIUS_DEFAULT_MAX_TOKENS,
+      },
+      {
+        id: "zai-org/GLM-4.5",
+        name: "GLM 4.5",
+        reasoning: false,
+        input: ["text"],
+        cost: NEBIUS_DEFAULT_COST,
+        contextWindow: NEBIUS_DEFAULT_CONTEXT_WINDOW,
+        maxTokens: NEBIUS_DEFAULT_MAX_TOKENS,
+      },
+    ],
+  };
+}
+
 export async function resolveImplicitProviders(params: {
   agentDir: string;
 }): Promise<ModelsConfig["providers"]> {
@@ -439,13 +519,6 @@ export async function resolveImplicitProviders(params: {
     };
   }
 
-  const xiaomiKey =
-    resolveEnvApiKeyVarName("xiaomi") ??
-    resolveApiKeyFromProfiles({ provider: "xiaomi", store: authStore });
-  if (xiaomiKey) {
-    providers.xiaomi = { ...buildXiaomiProvider(), apiKey: xiaomiKey };
-  }
-
   // Ollama provider - only add if explicitly configured
   const ollamaKey =
     resolveEnvApiKeyVarName("ollama") ??
@@ -454,6 +527,14 @@ export async function resolveImplicitProviders(params: {
     providers.ollama = { ...(await buildOllamaProvider()), apiKey: ollamaKey };
   }
 
+  const nebiusKey =
+    resolveEnvApiKeyVarName("nebius") ??
+    resolveApiKeyFromProfiles({ provider: "nebius", store: authStore });
+
+  if (nebiusKey) {
+    providers.nebius = { ...buildNebiusProvider(), apiKey: nebiusKey };
+  }
+
   return providers;
 }
 

src/auto-reply/reply/directive-handling.model-picker.ts

@@ -25,6 +25,7 @@ const MODEL_PICK_PROVIDER_PREFERENCE = [
   "mistral",
   "xai",
   "lmstudio",
+  "nebius",
 ] as const;
 
 const PROVIDER_RANK = new Map<string, number>(

src/cli/program/register.onboard.ts

@@ -52,7 +52,7 @@ export function registerOnboardCommand(program: Command) {
     .option("--mode <mode>", "Wizard mode: local|remote")
     .option(
       "--auth-choice <choice>",
-      "Auth: setup-token|token|chutes|openai-codex|openai-api-key|openrouter-api-key|ai-gateway-api-key|moonshot-api-key|kimi-code-api-key|synthetic-api-key|venice-api-key|gemini-api-key|zai-api-key|xiaomi-api-key|apiKey|minimax-api|minimax-api-lightning|opencode-zen|skip",
+      "Auth: setup-token|token|chutes|openai-codex|openai-api-key|openrouter-api-key|ai-gateway-api-key|moonshot-api-key|kimi-code-api-key|synthetic-api-key|venice-api-key|gemini-api-key|zai-api-key|apiKey|minimax-api|minimax-api-lightning|opencode-zen|skip",
     )
     .option(
       "--token-provider <id>",
@@ -72,11 +72,11 @@ export function registerOnboardCommand(program: Command) {
     .option("--kimi-code-api-key <key>", "Kimi Code API key")
     .option("--gemini-api-key <key>", "Gemini API key")
     .option("--zai-api-key <key>", "Z.AI API key")
-    .option("--xiaomi-api-key <key>", "Xiaomi API key")
     .option("--minimax-api-key <key>", "MiniMax API key")
     .option("--synthetic-api-key <key>", "Synthetic API key")
     .option("--venice-api-key <key>", "Venice API key")
     .option("--opencode-zen-api-key <key>", "OpenCode Zen API key")
+    .option("--nebius-api-key <key>", "Nebius API key")
     .option("--gateway-port <port>", "Gateway port")
     .option("--gateway-bind <mode>", "Gateway bind: loopback|tailnet|lan|auto|custom")
     .option("--gateway-auth <mode>", "Gateway auth: token|password")
@@ -123,7 +123,6 @@ export function registerOnboardCommand(program: Command) {
             kimiCodeApiKey: opts.kimiCodeApiKey as string | undefined,
             geminiApiKey: opts.geminiApiKey as string | undefined,
             zaiApiKey: opts.zaiApiKey as string | undefined,
-            xiaomiApiKey: opts.xiaomiApiKey as string | undefined,
             minimaxApiKey: opts.minimaxApiKey as string | undefined,
             syntheticApiKey: opts.syntheticApiKey as string | undefined,
             veniceApiKey: opts.veniceApiKey as string | undefined,

src/commands/auth-choice-options.ts

@@ -16,11 +16,11 @@ export type AuthChoiceGroupId =
   | "ai-gateway"
   | "moonshot"
   | "zai"
-  | "xiaomi"
   | "opencode-zen"
   | "minimax"
   | "synthetic"
   | "venice"
+  | "nebius"
   | "qwen";
 
 export type AuthChoiceGroup = {
@@ -109,10 +109,10 @@ const AUTH_CHOICE_GROUP_DEFS: {
     choices: ["zai-api-key"],
   },
   {
-    value: "xiaomi",
+    value: "nebius",
-    label: "Xiaomi",
+    label: "Nebius",
-    hint: "API key",
+    hint: "Nebius Token Factory",
-    choices: ["xiaomi-api-key"],
+    choices: ["nebius-api-key"],
   },
   {
     value: "opencode-zen",
@@ -171,10 +171,6 @@ export function buildAuthChoiceOptions(params: {
     hint: "Uses the bundled Gemini CLI auth plugin",
   });
   options.push({ value: "zai-api-key", label: "Z.AI (GLM 4.7) API key" });
-  options.push({
-    value: "xiaomi-api-key",
-    label: "Xiaomi API key",
-  });
   options.push({ value: "qwen-portal", label: "Qwen OAuth" });
   options.push({
     value: "copilot-proxy",
@@ -189,6 +185,11 @@ export function buildAuthChoiceOptions(params: {
     hint: "Claude, GPT, Gemini via opencode.ai/zen",
   });
   options.push({ value: "minimax-api", label: "MiniMax M2.1" });
+  options.push({
+    value: "nebius-api-key",
+    label: "Nebius API key",
+    hint: "Nebius Token Factory)",
+  });
   options.push({
     value: "minimax-api-lightning",
     label: "MiniMax M2.1 Lightning",

src/commands/auth-choice.apply.api-providers.ts

@@ -17,6 +17,8 @@ import {
   applyKimiCodeProviderConfig,
   applyMoonshotConfig,
   applyMoonshotProviderConfig,
+  applyNebiusConfig,
+  applyNebiusProviderConfig,
   applyOpencodeZenConfig,
   applyOpencodeZenProviderConfig,
   applyOpenrouterConfig,
@@ -27,25 +29,23 @@ import {
   applyVeniceProviderConfig,
   applyVercelAiGatewayConfig,
   applyVercelAiGatewayProviderConfig,
-  applyXiaomiConfig,
-  applyXiaomiProviderConfig,
   applyZaiConfig,
   KIMI_CODE_MODEL_REF,
   MOONSHOT_DEFAULT_MODEL_REF,
+  NEBIUS_DEFAULT_MODEL_REF,
   OPENROUTER_DEFAULT_MODEL_REF,
   SYNTHETIC_DEFAULT_MODEL_REF,
   VENICE_DEFAULT_MODEL_REF,
   VERCEL_AI_GATEWAY_DEFAULT_MODEL_REF,
-  XIAOMI_DEFAULT_MODEL_REF,
   setGeminiApiKey,
   setKimiCodeApiKey,
   setMoonshotApiKey,
+  setNebiusApiKey,
   setOpencodeZenApiKey,
   setOpenrouterApiKey,
   setSyntheticApiKey,
   setVeniceApiKey,
   setVercelAiGatewayApiKey,
-  setXiaomiApiKey,
   setZaiApiKey,
   ZAI_DEFAULT_MODEL_REF,
 } from "./onboard-auth.js";
@@ -83,12 +83,12 @@ export async function applyAuthChoiceApiProviders(
       authChoice = "gemini-api-key";
     } else if (params.opts.tokenProvider === "zai") {
       authChoice = "zai-api-key";
-    } else if (params.opts.tokenProvider === "xiaomi") {
-      authChoice = "xiaomi-api-key";
     } else if (params.opts.tokenProvider === "synthetic") {
       authChoice = "synthetic-api-key";
     } else if (params.opts.tokenProvider === "venice") {
       authChoice = "venice-api-key";
+    } else if (params.opts.tokenProvider === "nebius") {
+      authChoice = "nebius-api-key";
     } else if (params.opts.tokenProvider === "opencode") {
       authChoice = "opencode-zen";
     }
@@ -437,54 +437,6 @@ export async function applyAuthChoiceApiProviders(
     return { config: nextConfig, agentModelOverride };
   }
 
-  if (authChoice === "xiaomi-api-key") {
-    let hasCredential = false;
-
-    if (!hasCredential && params.opts?.token && params.opts?.tokenProvider === "xiaomi") {
-      await setXiaomiApiKey(normalizeApiKeyInput(params.opts.token), params.agentDir);
-      hasCredential = true;
-    }
-
-    const envKey = resolveEnvApiKey("xiaomi");
-    if (envKey) {
-      const useExisting = await params.prompter.confirm({
-        message: `Use existing XIAOMI_API_KEY (${envKey.source}, ${formatApiKeyPreview(envKey.apiKey)})?`,
-        initialValue: true,
-      });
-      if (useExisting) {
-        await setXiaomiApiKey(envKey.apiKey, params.agentDir);
-        hasCredential = true;
-      }
-    }
-    if (!hasCredential) {
-      const key = await params.prompter.text({
-        message: "Enter Xiaomi API key",
-        validate: validateApiKeyInput,
-      });
-      await setXiaomiApiKey(normalizeApiKeyInput(String(key)), params.agentDir);
-    }
-    nextConfig = applyAuthProfileConfig(nextConfig, {
-      profileId: "xiaomi:default",
-      provider: "xiaomi",
-      mode: "api_key",
-    });
-    {
-      const applied = await applyDefaultModelChoice({
-        config: nextConfig,
-        setDefaultModel: params.setDefaultModel,
-        defaultModel: XIAOMI_DEFAULT_MODEL_REF,
-        applyDefaultConfig: applyXiaomiConfig,
-        applyProviderConfig: applyXiaomiProviderConfig,
-        noteDefault: XIAOMI_DEFAULT_MODEL_REF,
-        noteAgentModel,
-        prompter: params.prompter,
-      });
-      nextConfig = applied.config;
-      agentModelOverride = applied.agentModelOverride ?? agentModelOverride;
-    }
-    return { config: nextConfig, agentModelOverride };
-  }
-
   if (authChoice === "synthetic-api-key") {
     if (params.opts?.token && params.opts?.tokenProvider === "synthetic") {
       await setSyntheticApiKey(String(params.opts.token).trim(), params.agentDir);
@@ -576,6 +528,69 @@ export async function applyAuthChoiceApiProviders(
     return { config: nextConfig, agentModelOverride };
   }
 
+  if (authChoice === "nebius-api-key") {
+    let hasCredential = false;
+
+    if (!hasCredential && params.opts?.token && params.opts?.tokenProvider === "nebius") {
+      await setNebiusApiKey(normalizeApiKeyInput(params.opts.token), params.agentDir);
+      hasCredential = true;
+    }
+
+    if (!hasCredential) {
+      await params.prompter.note(
+        [
+          "Nebius provides OpenAI-compatible inference for frontier and open models.",
+          "Get your API key at: https://tokenfactory.nebius.com/",
+          "Available models: zai-glm-7, zai-glm-5",
+        ].join("\n"),
+        "Nebius",
+      );
+    }
+
+    const envKey = resolveEnvApiKey("nebius");
+    if (envKey) {
+      const useExisting = await params.prompter.confirm({
+        message: `Use existing NEBIUS_API_KEY (${envKey.source}, ${formatApiKeyPreview(envKey.apiKey)})?`,
+        initialValue: true,
+      });
+      if (useExisting) {
+        await setNebiusApiKey(envKey.apiKey, params.agentDir);
+        hasCredential = true;
+      }
+    }
+
+    if (!hasCredential) {
+      const key = await params.prompter.text({
+        message: "Enter Nebius API key",
+        validate: validateApiKeyInput,
+      });
+      await setNebiusApiKey(normalizeApiKeyInput(String(key)), params.agentDir);
+    }
+
+    nextConfig = applyAuthProfileConfig(nextConfig, {
+      profileId: "nebius:default",
+      provider: "nebius",
+      mode: "api_key",
+    });
+
+    {
+      const applied = await applyDefaultModelChoice({
+        config: nextConfig,
+        setDefaultModel: params.setDefaultModel,
+        defaultModel: NEBIUS_DEFAULT_MODEL_REF,
+        applyDefaultConfig: applyNebiusConfig,
+        applyProviderConfig: applyNebiusProviderConfig,
+        noteDefault: NEBIUS_DEFAULT_MODEL_REF,
+        noteAgentModel,
+        prompter: params.prompter,
+      });
+      nextConfig = applied.config;
+      agentModelOverride = applied.agentModelOverride ?? agentModelOverride;
+    }
+
+    return { config: nextConfig, agentModelOverride };
+  }
+
   if (authChoice === "opencode-zen") {
     let hasCredential = false;
     if (!hasCredential && params.opts?.token && params.opts?.tokenProvider === "opencode") {

src/commands/models/list.status-command.ts

@@ -134,6 +134,7 @@ export async function modelsStatusCommand(
     "zai",
     "mistral",
     "synthetic",
+    "nebius",
   ];
   for (const provider of envProbeProviders) {
     if (resolveEnvApiKey(provider)) providersFromEnv.add(provider);

src/commands/onboard-auth.config-core.ts

@@ -1,4 +1,3 @@
-import { buildXiaomiProvider, XIAOMI_DEFAULT_MODEL_ID } from "../agents/models-config.providers.js";
 import {
   buildSyntheticModelDefinition,
   SYNTHETIC_BASE_URL,
@@ -15,7 +14,6 @@ import type { MoltbotConfig } from "../config/config.js";
 import {
   OPENROUTER_DEFAULT_MODEL_REF,
   VERCEL_AI_GATEWAY_DEFAULT_MODEL_REF,
-  XIAOMI_DEFAULT_MODEL_REF,
   ZAI_DEFAULT_MODEL_REF,
 } from "./onboard-auth.credentials.js";
 import {
@@ -338,37 +336,17 @@ export function applySyntheticConfig(cfg: MoltbotConfig): MoltbotConfig {
   };
 }
 
-export function applyXiaomiProviderConfig(cfg: MoltbotConfig): MoltbotConfig {
+export function applyNebiusProviderConfig(cfg: MoltbotConfig): MoltbotConfig {
   const models = { ...cfg.agents?.defaults?.models };
-  models[XIAOMI_DEFAULT_MODEL_REF] = {
+
-    ...models[XIAOMI_DEFAULT_MODEL_REF],
+  models["zai-org/GLM-4.7-FP8"] = {
-    alias: models[XIAOMI_DEFAULT_MODEL_REF]?.alias ?? "Xiaomi",
+    ...models["zai-org/GLM-4.7-FP8"],
+    alias: models["zai-org/GLM-4.7-FP8"]?.alias ?? "GLM 7",
   };
 
-  const providers = { ...cfg.models?.providers };
+  models["zai-org/GLM-4.5"] = {
-  const existingProvider = providers.xiaomi;
+    ...models["zai-org/GLM-4.5"],
-  const defaultProvider = buildXiaomiProvider();
+    alias: models["zai-org/GLM-4.5"]?.alias ?? "GLM 5",
-  const existingModels = Array.isArray(existingProvider?.models) ? existingProvider.models : [];
-  const defaultModels = defaultProvider.models ?? [];
-  const hasDefaultModel = existingModels.some((model) => model.id === XIAOMI_DEFAULT_MODEL_ID);
-  const mergedModels =
-    existingModels.length > 0
-      ? hasDefaultModel
-        ? existingModels
-        : [...existingModels, ...defaultModels]
-      : defaultModels;
-  const { apiKey: existingApiKey, ...existingProviderRest } = (existingProvider ?? {}) as Record<
-    string,
-    unknown
-  > as { apiKey?: string };
-  const resolvedApiKey = typeof existingApiKey === "string" ? existingApiKey : undefined;
-  const normalizedApiKey = resolvedApiKey?.trim();
-  providers.xiaomi = {
-    ...existingProviderRest,
-    baseUrl: defaultProvider.baseUrl,
-    api: defaultProvider.api,
-    ...(normalizedApiKey ? { apiKey: normalizedApiKey } : {}),
-    models: mergedModels.length > 0 ? mergedModels : defaultProvider.models,
   };
 
   return {
@@ -380,16 +358,13 @@ export function applyXiaomiProviderConfig(cfg: MoltbotConfig): MoltbotConfig {
         models,
       },
     },
-    models: {
-      mode: cfg.models?.mode ?? "merge",
-      providers,
-    },
   };
 }
 
-export function applyXiaomiConfig(cfg: MoltbotConfig): MoltbotConfig {
+export function applyNebiusConfig(cfg: MoltbotConfig): MoltbotConfig {
-  const next = applyXiaomiProviderConfig(cfg);
+  const next = applyNebiusProviderConfig(cfg);
   const existingModel = next.agents?.defaults?.model;
+
   return {
     ...next,
     agents: {
@@ -402,7 +377,7 @@ export function applyXiaomiConfig(cfg: MoltbotConfig): MoltbotConfig {
                 fallbacks: (existingModel as { fallbacks?: string[] }).fallbacks,
               }
             : undefined),
-          primary: XIAOMI_DEFAULT_MODEL_REF,
+          primary: "zai-org/GLM-4.7-FP8",
         },
       },
     },

src/commands/onboard-auth.credentials.ts

@@ -113,9 +113,9 @@ export async function setVeniceApiKey(key: string, agentDir?: string) {
 }
 
 export const ZAI_DEFAULT_MODEL_REF = "zai/glm-4.7";
-export const XIAOMI_DEFAULT_MODEL_REF = "xiaomi/mimo-v2-flash";
 export const OPENROUTER_DEFAULT_MODEL_REF = "openrouter/auto";
 export const VERCEL_AI_GATEWAY_DEFAULT_MODEL_REF = "vercel-ai-gateway/anthropic/claude-opus-4.5";
+export const NEBIUS_DEFAULT_MODEL_REF = "Qwen/Qwen3-32B-fast";
 
 export async function setZaiApiKey(key: string, agentDir?: string) {
   // Write to resolved agent dir so gateway finds credentials on startup.
@@ -130,18 +130,6 @@ export async function setZaiApiKey(key: string, agentDir?: string) {
   });
 }
 
-export async function setXiaomiApiKey(key: string, agentDir?: string) {
-  upsertAuthProfile({
-    profileId: "xiaomi:default",
-    credential: {
-      type: "api_key",
-      provider: "xiaomi",
-      key,
-    },
-    agentDir: resolveAuthAgentDir(agentDir),
-  });
-}
-
 export async function setOpenrouterApiKey(key: string, agentDir?: string) {
   upsertAuthProfile({
     profileId: "openrouter:default",
@@ -177,3 +165,15 @@ export async function setOpencodeZenApiKey(key: string, agentDir?: string) {
     agentDir: resolveAuthAgentDir(agentDir),
   });
 }
+
+export async function setNebiusApiKey(key: string, agentDir?: string) {
+  upsertAuthProfile({
+    profileId: "nebius:default",
+    credential: {
+      type: "api_key",
+      provider: "nebius",
+      key,
+    },
+    agentDir: resolveAuthAgentDir(agentDir),
+  });
+}

src/commands/onboard-auth.ts

@@ -9,6 +9,8 @@ export {
   applyKimiCodeProviderConfig,
   applyMoonshotConfig,
   applyMoonshotProviderConfig,
+  applyNebiusConfig,
+  applyNebiusProviderConfig,
   applyOpenrouterConfig,
   applyOpenrouterProviderConfig,
   applySyntheticConfig,
@@ -17,8 +19,6 @@ export {
   applyVeniceProviderConfig,
   applyVercelAiGatewayConfig,
   applyVercelAiGatewayProviderConfig,
-  applyXiaomiConfig,
-  applyXiaomiProviderConfig,
   applyZaiConfig,
 } from "./onboard-auth.config-core.js";
 export {
@@ -36,21 +36,21 @@ export {
 } from "./onboard-auth.config-opencode.js";
 export {
   OPENROUTER_DEFAULT_MODEL_REF,
+  NEBIUS_DEFAULT_MODEL_REF,
   setAnthropicApiKey,
   setGeminiApiKey,
   setKimiCodeApiKey,
   setMinimaxApiKey,
   setMoonshotApiKey,
+  setNebiusApiKey,
   setOpencodeZenApiKey,
   setOpenrouterApiKey,
   setSyntheticApiKey,
   setVeniceApiKey,
   setVercelAiGatewayApiKey,
-  setXiaomiApiKey,
   setZaiApiKey,
   writeOAuthCredentials,
   VERCEL_AI_GATEWAY_DEFAULT_MODEL_REF,
-  XIAOMI_DEFAULT_MODEL_REF,
   ZAI_DEFAULT_MODEL_REF,
 } from "./onboard-auth.credentials.js";
 export {

src/commands/onboard-non-interactive/local/auth-choice.ts

@@ -12,24 +12,24 @@ import {
   applyMinimaxApiConfig,
   applyMinimaxConfig,
   applyMoonshotConfig,
+  applyNebiusConfig,
   applyOpencodeZenConfig,
   applyOpenrouterConfig,
   applySyntheticConfig,
   applyVeniceConfig,
   applyVercelAiGatewayConfig,
-  applyXiaomiConfig,
   applyZaiConfig,
   setAnthropicApiKey,
   setGeminiApiKey,
   setKimiCodeApiKey,
   setMinimaxApiKey,
   setMoonshotApiKey,
+  setNebiusApiKey,
   setOpencodeZenApiKey,
   setOpenrouterApiKey,
   setSyntheticApiKey,
   setVeniceApiKey,
   setVercelAiGatewayApiKey,
-  setXiaomiApiKey,
   setZaiApiKey,
 } from "../../onboard-auth.js";
 import type { AuthChoice, OnboardOptions } from "../../onboard-types.js";
@@ -179,25 +179,6 @@ export async function applyNonInteractiveAuthChoice(params: {
     return applyZaiConfig(nextConfig);
   }
 
-  if (authChoice === "xiaomi-api-key") {
-    const resolved = await resolveNonInteractiveApiKey({
-      provider: "xiaomi",
-      cfg: baseConfig,
-      flagValue: opts.xiaomiApiKey,
-      flagName: "--xiaomi-api-key",
-      envVar: "XIAOMI_API_KEY",
-      runtime,
-    });
-    if (!resolved) return null;
-    if (resolved.source !== "profile") await setXiaomiApiKey(resolved.key);
-    nextConfig = applyAuthProfileConfig(nextConfig, {
-      profileId: "xiaomi:default",
-      provider: "xiaomi",
-      mode: "api_key",
-    });
-    return applyXiaomiConfig(nextConfig);
-  }
-
   if (authChoice === "openai-api-key") {
     const resolved = await resolveNonInteractiveApiKey({
       provider: "openai",
@@ -357,6 +338,25 @@ export async function applyNonInteractiveAuthChoice(params: {
 
   if (authChoice === "minimax") return applyMinimaxConfig(nextConfig);
 
+  if (authChoice === "nebius-api-key") {
+    const resolved = await resolveNonInteractiveApiKey({
+      provider: "nebius",
+      cfg: baseConfig,
+      flagValue: opts.nebiusApiKey,
+      flagName: "--nebius-api-key",
+      envVar: "NEBIUS_API_KEY",
+      runtime,
+    });
+    if (!resolved) return null;
+    if (resolved.source !== "profile") await setNebiusApiKey(resolved.key);
+    nextConfig = applyAuthProfileConfig(nextConfig, {
+      profileId: "nebius:default",
+      provider: "nebius",
+      mode: "api_key",
+    });
+    return applyNebiusConfig(nextConfig);
+  }
+
   if (authChoice === "opencode-zen") {
     const resolved = await resolveNonInteractiveApiKey({
       provider: "opencode",

src/commands/onboard-types.ts

@@ -23,11 +23,11 @@ export type AuthChoice =
   | "google-antigravity"
   | "google-gemini-cli"
   | "zai-api-key"
-  | "xiaomi-api-key"
   | "minimax-cloud"
   | "minimax"
   | "minimax-api"
   | "minimax-api-lightning"
+  | "nebius-api-key"
   | "opencode-zen"
   | "github-copilot"
   | "copilot-proxy"
@@ -68,8 +68,8 @@ export type OnboardOptions = {
   kimiCodeApiKey?: string;
   geminiApiKey?: string;
   zaiApiKey?: string;
-  xiaomiApiKey?: string;
   minimaxApiKey?: string;
+  nebiusApiKey?: string;
   syntheticApiKey?: string;
   veniceApiKey?: string;
   opencodeZenApiKey?: string;