diff --git a/src/agents/models-config.providers.ts b/src/agents/models-config.providers.ts
index 996f09dd0..c87bf1217 100644
--- a/src/agents/models-config.providers.ts
+++ b/src/agents/models-config.providers.ts
@@ -359,6 +359,113 @@ async function buildOllamaProvider(): Promise<ProviderConfig> {
   };
 }
 
+function buildTogetherProvider(): ProviderConfig {
+  return {
+    baseUrl: "https://api.together.xyz/v1",
+    api: "openai-completions",
+    models: [
+      {
+        id: "meta-llama/Llama-3.3-70B-Instruct-Turbo",
+        name: "Llama 3.3 70B Instruct Turbo",
+        reasoning: false,
+        input: ["text"],
+        contextWindow: 131072,
+        maxTokens: 8192,
+        cost: {
+          input: 0.88,
+          output: 0.88,
+          cacheRead: 0.88,
+          cacheWrite: 0.88,
+        },
+      },
+      {
+        id: "meta-llama/Llama-4-Scout-17B-16E-Instruct",
+        name: "Llama 4 Scout 17B 16E Instruct",
+        reasoning: false,
+        input: ["text", "image"],
+        contextWindow: 10000000,
+        maxTokens: 32768,
+        cost: {
+          input: 0.18,
+          output: 0.59,
+          cacheRead: 0.18,
+          cacheWrite: 0.18,
+        },
+      },
+      {
+        id: "meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8",
+        name: "Llama 4 Maverick 17B 128E Instruct FP8",
+        reasoning: false,
+        input: ["text", "image"],
+        contextWindow: 20000000,
+        maxTokens: 32768,
+        cost: {
+          input: 0.27,
+          output: 0.85,
+          cacheRead: 0.27,
+          cacheWrite: 0.27,
+        },
+      },
+      {
+        id: "deepseek-ai/DeepSeek-V3.1",
+        name: "DeepSeek V3.1",
+        reasoning: false,
+        input: ["text"],
+        contextWindow: 131072,
+        maxTokens: 8192,
+        cost: {
+          input: 0.6,
+          output: 1.25,
+          cacheRead: 0.6,
+          cacheWrite: 0.6,
+        },
+      },
+      {
+        id: "deepseek-ai/DeepSeek-R1",
+        name: "DeepSeek R1",
+        reasoning: true,
+        input: ["text"],
+        contextWindow: 131072,
+        maxTokens: 8192,
+        cost: {
+          input: 3.0,
+          output: 7.0,
+          cacheRead: 3.0,
+          cacheWrite: 3.0,
+        },
+      },
+      {
+        id: "Qwen/Qwen2.5-72B-Instruct-Turbo",
+        name: "Qwen 2.5 72B Instruct Turbo",
+        reasoning: false,
+        input: ["text"],
+        contextWindow: 131072,
+        maxTokens: 8192,
+        cost: {
+          input: 0.35,
+          output: 0.8,
+          cacheRead: 0.35,
+          cacheWrite: 0.35,
+        },
+      },
+      {
+        id: "mistralai/Mixtral-8x7B-Instruct-v0.1",
+        name: "Mixtral 8x7B Instruct v0.1",
+        reasoning: false,
+        input: ["text"],
+        contextWindow: 32768,
+        maxTokens: 8192,
+        cost: {
+          input: 0.6,
+          output: 0.6,
+          cacheRead: 0.6,
+          cacheWrite: 0.6,
+        },
+      },
+    ],
+  };
+}
+
 export async function resolveImplicitProviders(params: {
   agentDir: string;
 }): Promise<ModelsConfig["providers"]> {
@@ -418,6 +525,13 @@ export async function resolveImplicitProviders(params: {
     providers.ollama = { ...(await buildOllamaProvider()), apiKey: ollamaKey };
   }
 
+  const togetherKey =
+    resolveEnvApiKeyVarName("together") ??
+    resolveApiKeyFromProfiles({ provider: "together", store: authStore });
+  if (togetherKey) {
+    providers.together = { ...buildTogetherProvider(), apiKey: togetherKey };
+  }
+
   return providers;
 }
 
diff --git a/src/agents/together-models.ts b/src/agents/together-models.ts
deleted file mode 100644
index a16e96837..000000000
--- a/src/agents/together-models.ts
+++ /dev/null
@@ -1,121 +0,0 @@
-import type { ModelDefinitionConfig } from "../config/types.js";
-
-export const TOGETHER_BASE_URL = "https://api.together.xyz/v1";
-export const TOGETHER_DEFAULT_MODEL_ID = "meta-llama/Llama-3.3-70B-Instruct-Turbo";
-export const TOGETHER_DEFAULT_MODEL_REF = `together/${TOGETHER_DEFAULT_MODEL_ID}`;
-
-export const TOGETHER_MODEL_CATALOG = [
-  {
-    id: "meta-llama/Llama-3.3-70B-Instruct-Turbo",
-    name: "Llama 3.3 70B Instruct Turbo",
-    reasoning: false,
-    input: ["text"],
-    contextWindow: 131072,
-    maxTokens: 8192,
-    cost: {
-      input: 0.88,
-      output: 0.88,
-      cacheRead: 0.88,
-      cacheWrite: 0.88,
-    },
-  },
-  {
-    id: "meta-llama/Llama-4-Scout-17B-16E-Instruct",
-    name: "Llama 4 Scout 17B 16E Instruct",
-    reasoning: false,
-    input: ["text", "image"],
-    contextWindow: 10000000,
-    maxTokens: 32768,
-    cost: {
-      input: 0.18,
-      output: 0.59,
-      cacheRead: 0.18,
-      cacheWrite: 0.18,
-    },
-  },
-  {
-    id: "meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8",
-    name: "Llama 4 Maverick 17B 128E Instruct FP8",
-    reasoning: false,
-    input: ["text", "image"],
-    contextWindow: 20000000,
-    maxTokens: 32768,
-    cost: {
-      input: 0.27,
-      output: 0.85,
-      cacheRead: 0.27,
-      cacheWrite: 0.27,
-    },
-  },
-  {
-    id: "deepseek-ai/DeepSeek-V3.1",
-    name: "DeepSeek V3.1",
-    reasoning: false,
-    input: ["text"],
-    contextWindow: 131072,
-    maxTokens: 8192,
-    cost: {
-      input: 0.6,
-      output: 1.25,
-      cacheRead: 0.6,
-      cacheWrite: 0.6,
-    },
-  },
-  {
-    id: "deepseek-ai/DeepSeek-R1",
-    name: "DeepSeek R1",
-    reasoning: true,
-    input: ["text"],
-    contextWindow: 131072,
-    maxTokens: 8192,
-    cost: {
-      input: 3.0,
-      output: 7.0,
-      cacheRead: 3.0,
-      cacheWrite: 3.0,
-    },
-  },
-  {
-    id: "Qwen/Qwen2.5-72B-Instruct-Turbo",
-    name: "Qwen 2.5 72B Instruct Turbo",
-    reasoning: false,
-    input: ["text"],
-    contextWindow: 131072,
-    maxTokens: 8192,
-    cost: {
-      input: 0.35,
-      output: 0.8,
-      cacheRead: 0.35,
-      cacheWrite: 0.35,
-    },
-  },
-  {
-    id: "mistralai/Mixtral-8x7B-Instruct-v0.1",
-    name: "Mixtral 8x7B Instruct v0.1",
-    reasoning: false,
-    input: ["text"],
-    contextWindow: 32768,
-    maxTokens: 8192,
-    cost: {
-      input: 0.6,
-      output: 0.6,
-      cacheRead: 0.6,
-      cacheWrite: 0.6,
-    },
-  },
-] as const;
-
-export function buildTogetherModelDefinition(
-  model: (typeof TOGETHER_MODEL_CATALOG)[number],
-): ModelDefinitionConfig {
-  return {
-    id: model.id,
-    name: model.name,
-    api: "openai-completions",
-    reasoning: model.reasoning,
-    input: [...model.input],
-    cost: model.cost,
-    contextWindow: model.contextWindow,
-    maxTokens: model.maxTokens,
-  };
-}
diff --git a/src/commands/onboard-auth.config-core.ts b/src/commands/onboard-auth.config-core.ts
index 17ad16a2e..4c621217d 100644
--- a/src/commands/onboard-auth.config-core.ts
+++ b/src/commands/onboard-auth.config-core.ts
@@ -4,11 +4,111 @@ import {
   SYNTHETIC_DEFAULT_MODEL_REF,
   SYNTHETIC_MODEL_CATALOG,
 } from "../agents/synthetic-models.js";
-import {
-  buildTogetherModelDefinition,
-  TOGETHER_BASE_URL,
-  TOGETHER_MODEL_CATALOG,
-} from "../agents/together-models.js";
+
+// Together AI constants and models - inline to avoid separate models file
+const TOGETHER_BASE_URL = "https://api.together.xyz/v1";
+const TOGETHER_MODEL_CATALOG = [
+  {
+    id: "meta-llama/Llama-3.3-70B-Instruct-Turbo",
+    name: "Llama 3.3 70B Instruct Turbo",
+    reasoning: false,
+    input: ["text"],
+    contextWindow: 131072,
+    maxTokens: 8192,
+    cost: {
+      input: 0.88,
+      output: 0.88,
+      cacheRead: 0.88,
+      cacheWrite: 0.88,
+    },
+  },
+  {
+    id: "meta-llama/Llama-4-Scout-17B-16E-Instruct",
+    name: "Llama 4 Scout 17B 16E Instruct",
+    reasoning: false,
+    input: ["text", "image"],
+    contextWindow: 10000000,
+    maxTokens: 32768,
+    cost: {
+      input: 0.18,
+      output: 0.59,
+      cacheRead: 0.18,
+      cacheWrite: 0.18,
+    },
+  },
+  {
+    id: "meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8",
+    name: "Llama 4 Maverick 17B 128E Instruct FP8",
+    reasoning: false,
+    input: ["text", "image"],
+    contextWindow: 20000000,
+    maxTokens: 32768,
+    cost: {
+      input: 0.27,
+      output: 0.85,
+      cacheRead: 0.27,
+      cacheWrite: 0.27,
+    },
+  },
+  {
+    id: "deepseek-ai/DeepSeek-V3.1",
+    name: "DeepSeek V3.1",
+    reasoning: false,
+    input: ["text"],
+    contextWindow: 131072,
+    maxTokens: 8192,
+    cost: {
+      input: 0.6,
+      output: 1.25,
+      cacheRead: 0.6,
+      cacheWrite: 0.6,
+    },
+  },
+  {
+    id: "deepseek-ai/DeepSeek-R1",
+    name: "DeepSeek R1",
+    reasoning: true,
+    input: ["text"],
+    contextWindow: 131072,
+    maxTokens: 8192,
+    cost: {
+      input: 3.0,
+      output: 7.0,
+      cacheRead: 3.0,
+      cacheWrite: 3.0,
+    },
+  },
+  {
+    id: "Qwen/Qwen2.5-72B-Instruct-Turbo",
+    name: "Qwen 2.5 72B Instruct Turbo",
+    reasoning: false,
+    input: ["text"],
+    contextWindow: 131072,
+    maxTokens: 8192,
+    cost: {
+      input: 0.35,
+      output: 0.8,
+      cacheRead: 0.35,
+      cacheWrite: 0.35,
+    },
+  },
+];
+
+function buildTogetherModelDefinition(
+  model: (typeof TOGETHER_MODEL_CATALOG)[number],
+): ModelDefinitionConfig {
+  return {
+    id: model.id,
+    name: model.name,
+    api: "openai-completions",
+    reasoning: model.reasoning,
+    input: model.input as ("text" | "image")[],
+    cost: model.cost,
+    contextWindow: model.contextWindow,
+    maxTokens: model.maxTokens,
+  };
+}
+
 import {
   buildVeniceModelDefinition,
   VENICE_BASE_URL,
@@ -16,6 +116,7 @@ import {
   VENICE_MODEL_CATALOG,
 } from "../agents/venice-models.js";
 import type { ClawdbotConfig } from "../config/config.js";
+import type { ModelDefinitionConfig } from "../config/types.models.js";
 import {
   OPENROUTER_DEFAULT_MODEL_REF,
   TOGETHER_DEFAULT_MODEL_REF,
diff --git a/src/commands/onboard-auth.ts b/src/commands/onboard-auth.ts
index 555093765..b970457bf 100644
--- a/src/commands/onboard-auth.ts
+++ b/src/commands/onboard-auth.ts
@@ -68,10 +68,5 @@ export {
   MOONSHOT_DEFAULT_MODEL_ID,
   MOONSHOT_DEFAULT_MODEL_REF,
 } from "./onboard-auth.models.js";
-export {
-  buildTogetherModelDefinition,
-  TOGETHER_BASE_URL,
-  TOGETHER_DEFAULT_MODEL_ID,
-  TOGETHER_DEFAULT_MODEL_REF,
-  TOGETHER_MODEL_CATALOG,
-} from "../agents/together-models.js";
+// Together AI constants are now defined inline in onboard-auth.config-core.ts
+export { TOGETHER_DEFAULT_MODEL_REF } from "./onboard-auth.credentials.js";