diff --git a/crates/goose/src/providers/declarative/auxen.json b/crates/goose/src/providers/declarative/auxen.json
new file mode 100644
index 000000000000..5354d6d3c302
--- /dev/null
+++ b/crates/goose/src/providers/declarative/auxen.json
@@ -0,0 +1,39 @@
+{
+  "name": "auxen",
+  "engine": "openai",
+  "display_name": "Auxen",
+  "description": "Per-customer dedicated LLM endpoints (Llama, Qwen, Mistral, Gemma, Mixtral, Phi, Command R) with OpenAI-compatible API",
+  "api_key_env": "AUXEN_API_KEY",
+  "base_url": "${AUXEN_API_BASE}/chat/completions",
+  "env_vars": [
+    {
+      "name": "AUXEN_API_BASE",
+      "required": true,
+      "secret": false,
+      "primary": true,
+      "description": "Auxen instance base URL issued by the Auxen dashboard, e.g. https://api.auxen.ai/v1/inst_xxx/v1"
+    },
+    {
+      "name": "AUXEN_API_KEY",
+      "required": true,
+      "secret": true,
+      "description": "Auxen instance API key (auxk_*) issued by the Auxen dashboard"
+    }
+  ],
+  "models": [
+    { "name": "llama-3.1-8b",     "context_limit": 131072, "max_tokens": 8192 },
+    { "name": "llama-3.1-70b",    "context_limit": 131072, "max_tokens": 8192 },
+    { "name": "llama-3.2-3b",     "context_limit": 131072, "max_tokens": 8192 },
+    { "name": "qwen2.5-7b",       "context_limit": 131072, "max_tokens": 8192 },
+    { "name": "qwen2.5-14b",      "context_limit": 131072, "max_tokens": 8192 },
+    { "name": "qwen2.5-32b",      "context_limit": 131072, "max_tokens": 8192 },
+    { "name": "mistral-7b",       "context_limit": 32768,  "max_tokens": 8192 },
+    { "name": "mistral-nemo-12b", "context_limit": 131072, "max_tokens": 8192 },
+    { "name": "mixtral-8x7b",     "context_limit": 32768,  "max_tokens": 8192 },
+    { "name": "gemma2-9b",        "context_limit": 8192,   "max_tokens": 8192 },
+    { "name": "phi-3-mini",       "context_limit": 131072, "max_tokens": 4096 },
+    { "name": "command-r-7b",     "context_limit": 131072, "max_tokens": 4096 }
+  ],
+  "supports_streaming": true,
+  "requires_auth": true
+}
diff --git a/documentation/docs/getting-started/providers.md b/documentation/docs/getting-started/providers.md
index 90367355c743..80220a035f2d 100644
--- a/documentation/docs/getting-started/providers.md
+++ b/documentation/docs/getting-started/providers.md
@@ -26,6 +26,7 @@ goose is compatible with a wide range of LLM providers, allowing you to choose a
 | [Amazon SageMaker TGI](https://docs.aws.amazon.com/sagemaker/latest/dg/realtime-endpoints.html) | Run Text Generation Inference models through Amazon SageMaker endpoints. **AWS credentials must be configured in advance.** | `SAGEMAKER_ENDPOINT_NAME`, `AWS_REGION` (optional), `AWS_PROFILE` (optional)  |
 | [Anthropic](https://www.anthropic.com/)                                     | Offers Claude, an advanced AI model for natural language tasks.                                                                                                                                                           | `ANTHROPIC_API_KEY`, `ANTHROPIC_HOST` (optional)                                                                                                                                                                 |
 | [Atomic Chat](https://github.com/AtomicBot-ai/Atomic-Chat)                | Run local models with Atomic Chat's OpenAI-compatible server. **Because this provider runs locally, you must first [download a model](#local-llms).** | None required. Connects to local server at `localhost:1337` by default. |
+| [Auxen](https://auxen.ai/)                                                  | Per-customer **dedicated** LLM endpoints (Llama, Qwen, Mistral, Gemma, Mixtral, Phi, Command R) with OpenAI-compatible API. Each instance is a dedicated GPU billed per-minute of runtime, not per-token. | `AUXEN_API_BASE`, `AUXEN_API_KEY` |
 | [Avian](https://avian.io/)                                                   | Cost-effective inference API with DeepSeek, Kimi, GLM, and MiniMax models. OpenAI-compatible with streaming and function calling support.                                                                                  | `AVIAN_API_KEY`, `AVIAN_HOST` (optional)                                                                                                                                            |
 | [Azure OpenAI](https://learn.microsoft.com/en-us/azure/ai-services/openai/) | Access Azure-hosted OpenAI models, including GPT-4 and GPT-3.5. Supports both API key and Azure credential chain authentication.                                                                                          | `AZURE_OPENAI_ENDPOINT`, `AZURE_OPENAI_DEPLOYMENT_NAME`, `AZURE_OPENAI_API_KEY` (optional)                                                                                           |
 | [ChatGPT Codex](https://chatgpt.com/codex) | Access GPT-5 Codex models optimized for code generation and understanding. **Requires a ChatGPT Plus/Pro subscription.** | No manual key. Uses browser-based OAuth authentication for both CLI and Desktop. |