docs: add Hugging Face provider to all documentation pages

- quickstart.md: add to provider table
- configuration.md: add to provider table, add dedicated section with
  usage examples, config.yaml snippet, routing suffixes, and token info;
  also fix pre-existing duplicate Alibaba Cloud entry
- environment-variables.md: add HF_TOKEN + HF_BASE_URL, add huggingface
  to HERMES_INFERENCE_PROVIDER values
- fallback-providers.md: add to supported providers table and
  auto-detection chain

.env.example

@@ -59,6 +59,15 @@ OPENCODE_ZEN_API_KEY=
 # OpenCode Go provides access to open models (GLM-5, Kimi K2.5, MiniMax M2.5)
 # $10/month subscription. Get your key at: https://opencode.ai/auth
 OPENCODE_GO_API_KEY=
+
+# =============================================================================
+# LLM PROVIDER (Hugging Face Inference Providers)
+# =============================================================================
+# Hugging Face routes to 20+ open models via unified OpenAI-compatible endpoint.
+# Free tier included ($0.10/month), no markup on provider rates.
+# Get your token at: https://huggingface.co/settings/tokens
+# Required permission: "Make calls to Inference Providers"
+HF_TOKEN=
 # OPENCODE_GO_BASE_URL=https://opencode.ai/zen/go/v1  # Override default base URL
 
 # =============================================================================

agent/model_metadata.py

@@ -119,6 +119,25 @@ DEFAULT_CONTEXT_LENGTHS = {
     "qwen-plus-latest": 131072,
     "qwen3.5-flash": 131072,
     "qwen-vl-max": 32768,
+    # Hugging Face Inference Providers — model IDs use org/name format
+    "Qwen/Qwen3.5-397B-A17B": 131072,
+    "Qwen/Qwen3-235B-A22B-Thinking-2507": 131072,
+    "Qwen/Qwen3-Coder-480B-A35B-Instruct": 131072,
+    "Qwen/Qwen3-Coder-Next": 131072,
+    "Qwen/Qwen3-Next-80B-A3B-Instruct": 131072,
+    "Qwen/Qwen3-Next-80B-A3B-Thinking": 131072,
+    "deepseek-ai/DeepSeek-R1-0528": 65536,
+    "deepseek-ai/DeepSeek-V3.2": 65536,
+    "moonshotai/Kimi-K2-Instruct": 262144,
+    "moonshotai/Kimi-K2-Instruct-0905": 262144,
+    "moonshotai/Kimi-K2.5": 262144,
+    "moonshotai/Kimi-K2-Thinking": 262144,
+    "MiniMaxAI/MiniMax-M2.5": 204800,
+    "MiniMaxAI/MiniMax-M2.1": 204800,
+    "XiaomiMiMo/MiMo-V2-Flash": 32768,
+    "zai-org/GLM-5": 202752,
+    "zai-org/GLM-4.7": 202752,
+    "zai-org/GLM-4.7-Flash": 202752,
 }
 
 

hermes_cli/auth.py

@@ -195,6 +195,14 @@ PROVIDER_REGISTRY: Dict[str, ProviderConfig] = {
         api_key_env_vars=("KILOCODE_API_KEY",),
         base_url_env_var="KILOCODE_BASE_URL",
     ),
+    "huggingface": ProviderConfig(
+        id="huggingface",
+        name="Hugging Face",
+        auth_type="api_key",
+        inference_base_url="https://router.huggingface.co/v1",
+        api_key_env_vars=("HF_TOKEN",),
+        base_url_env_var="HF_BASE_URL",
+    ),
 }
 
 
@@ -574,6 +582,7 @@ def resolve_provider(
         "claude": "anthropic", "claude-code": "anthropic",
         "aigateway": "ai-gateway", "vercel": "ai-gateway", "vercel-ai-gateway": "ai-gateway",
         "opencode": "opencode-zen", "zen": "opencode-zen",
+        "hf": "huggingface", "hugging-face": "huggingface", "huggingface-hub": "huggingface",
         "go": "opencode-go", "opencode-go-sub": "opencode-go",
         "kilo": "kilocode", "kilo-code": "kilocode", "kilo-gateway": "kilocode",
     }

hermes_cli/config.py

@@ -549,6 +549,21 @@ OPTIONAL_ENV_VARS = {
         "category": "provider",
         "advanced": True,
     },
+    "HF_TOKEN": {
+        "description": "Hugging Face token for Inference Providers (20+ open models via router.huggingface.co)",
+        "prompt": "Hugging Face Token",
+        "url": "https://huggingface.co/settings/tokens",
+        "password": True,
+        "category": "provider",
+    },
+    "HF_BASE_URL": {
+        "description": "Hugging Face Inference Providers base URL override",
+        "prompt": "HF base URL (leave empty for default)",
+        "url": None,
+        "password": False,
+        "category": "provider",
+        "advanced": True,
+    },
 
     # ── Tool API keys ──
     "PARALLEL_API_KEY": {

hermes_cli/main.py

@@ -785,6 +785,7 @@ def cmd_model(args):
         "ai-gateway": "AI Gateway",
         "kilocode": "Kilo Code",
         "alibaba": "Alibaba Cloud (DashScope)",
+        "huggingface": "Hugging Face",
         "custom": "Custom endpoint",
     }
     active_label = provider_labels.get(active, active)
@@ -809,6 +810,7 @@ def cmd_model(args):
         ("opencode-go", "OpenCode Go (open models, $10/month subscription)"),
         ("ai-gateway", "AI Gateway (Vercel — 200+ models, pay-per-use)"),
         ("alibaba", "Alibaba Cloud / DashScope (Qwen models, Anthropic-compatible)"),
+        ("huggingface", "Hugging Face Inference Providers (20+ open models)"),
     ]
 
     # Add user-defined custom providers from config.yaml
@@ -877,7 +879,7 @@ def cmd_model(args):
         _model_flow_anthropic(config, current_model)
     elif selected_provider == "kimi-coding":
         _model_flow_kimi(config, current_model)
-    elif selected_provider in ("zai", "minimax", "minimax-cn", "kilocode", "opencode-zen", "opencode-go", "ai-gateway", "alibaba"):
+    elif selected_provider in ("zai", "minimax", "minimax-cn", "kilocode", "opencode-zen", "opencode-go", "ai-gateway", "alibaba", "huggingface"):
         _model_flow_api_key_provider(config, selected_provider, current_model)
 
 
@@ -1444,6 +1446,27 @@ _PROVIDER_MODELS = {
         "google/gemini-3-pro-preview",
         "google/gemini-3-flash-preview",
     ],
+    # Curated model list sourced from https://models.dev (huggingface provider)
+    "huggingface": [
+        "Qwen/Qwen3.5-397B-A17B",
+        "Qwen/Qwen3-235B-A22B-Thinking-2507",
+        "Qwen/Qwen3-Coder-480B-A35B-Instruct",
+        "Qwen/Qwen3-Coder-Next",
+        "Qwen/Qwen3-Next-80B-A3B-Instruct",
+        "Qwen/Qwen3-Next-80B-A3B-Thinking",
+        "deepseek-ai/DeepSeek-R1-0528",
+        "deepseek-ai/DeepSeek-V3.2",
+        "moonshotai/Kimi-K2-Instruct",
+        "moonshotai/Kimi-K2-Instruct-0905",
+        "moonshotai/Kimi-K2.5",
+        "moonshotai/Kimi-K2-Thinking",
+        "MiniMaxAI/MiniMax-M2.5",
+        "MiniMaxAI/MiniMax-M2.1",
+        "XiaomiMiMo/MiMo-V2-Flash",
+        "zai-org/GLM-5",
+        "zai-org/GLM-4.7",
+        "zai-org/GLM-4.7-Flash",
+    ],
 }
 
 
@@ -2642,7 +2665,7 @@ For more help on a command:
     )
     chat_parser.add_argument(
         "--provider",
-        choices=["auto", "openrouter", "nous", "openai-codex", "anthropic", "zai", "kimi-coding", "minimax", "minimax-cn", "kilocode"],
+        choices=["auto", "openrouter", "nous", "openai-codex", "anthropic", "huggingface", "zai", "kimi-coding", "minimax", "minimax-cn", "kilocode"],
         default=None,
         help="Inference provider (default: auto)"
     )

hermes_cli/models.py

@@ -155,6 +155,28 @@ _PROVIDER_MODELS: dict[str, list[str]] = {
         "qwen3.5-flash",
         "qwen-vl-max",
     ],
+    # Curated model list for Hugging Face Inference Providers
+    # sourced from https://models.dev (huggingface provider)
+    "huggingface": [
+        "Qwen/Qwen3.5-397B-A17B",
+        "Qwen/Qwen3-235B-A22B-Thinking-2507",
+        "Qwen/Qwen3-Coder-480B-A35B-Instruct",
+        "Qwen/Qwen3-Coder-Next",
+        "Qwen/Qwen3-Next-80B-A3B-Instruct",
+        "Qwen/Qwen3-Next-80B-A3B-Thinking",
+        "deepseek-ai/DeepSeek-R1-0528",
+        "deepseek-ai/DeepSeek-V3.2",
+        "moonshotai/Kimi-K2-Instruct",
+        "moonshotai/Kimi-K2-Instruct-0905",
+        "moonshotai/Kimi-K2.5",
+        "moonshotai/Kimi-K2-Thinking",
+        "MiniMaxAI/MiniMax-M2.5",
+        "MiniMaxAI/MiniMax-M2.1",
+        "XiaomiMiMo/MiMo-V2-Flash",
+        "zai-org/GLM-5",
+        "zai-org/GLM-4.7",
+        "zai-org/GLM-4.7-Flash",
+    ],
 }
 
 _PROVIDER_LABELS = {
@@ -172,6 +194,7 @@ _PROVIDER_LABELS = {
     "ai-gateway": "AI Gateway",
     "kilocode": "Kilo Code",
     "alibaba": "Alibaba Cloud (DashScope)",
+    "huggingface": "Hugging Face",
     "custom": "Custom endpoint",
 }
 
@@ -201,6 +224,9 @@ _PROVIDER_ALIASES = {
     "aliyun": "alibaba",
     "qwen": "alibaba",
     "alibaba-cloud": "alibaba",
+    "hf": "huggingface",
+    "hugging-face": "huggingface",
+    "huggingface-hub": "huggingface",
 }
 
 
@@ -234,7 +260,7 @@ def list_available_providers() -> list[dict[str, str]]:
     # Canonical providers in display order
     _PROVIDER_ORDER = [
         "openrouter", "nous", "openai-codex",
-        "zai", "kimi-coding", "minimax", "minimax-cn", "kilocode", "anthropic", "alibaba",
+        "huggingface", "zai", "kimi-coding", "minimax", "minimax-cn", "kilocode", "anthropic", "alibaba",
         "opencode-zen", "opencode-go",
         "ai-gateway", "deepseek", "custom",
     ]

hermes_cli/setup.py

@@ -61,6 +61,11 @@ _DEFAULT_PROVIDER_MODELS = {
     "minimax-cn": ["MiniMax-M2.5", "MiniMax-M2.5-highspeed", "MiniMax-M2.1"],
     "ai-gateway": ["anthropic/claude-opus-4.6", "anthropic/claude-sonnet-4.6", "openai/gpt-5", "google/gemini-3-flash"],
     "kilocode": ["anthropic/claude-opus-4.6", "anthropic/claude-sonnet-4.6", "openai/gpt-5.4", "google/gemini-3-pro-preview", "google/gemini-3-flash-preview"],
+    "huggingface": [
+        "Qwen/Qwen3.5-397B-A17B", "Qwen/Qwen3-235B-A22B-Thinking-2507",
+        "Qwen/Qwen3-Coder-480B-A35B-Instruct", "deepseek-ai/DeepSeek-R1-0528",
+        "deepseek-ai/DeepSeek-V3.2", "moonshotai/Kimi-K2.5",
+    ],
 }
 
 
@@ -741,6 +746,7 @@ def setup_model_provider(config: dict):
         "Alibaba Cloud / DashScope (Qwen models via Anthropic-compatible API)",
         "OpenCode Zen (35+ curated models, pay-as-you-go)",
         "OpenCode Go (open models, $10/month subscription)",
+        "Hugging Face Inference Providers (20+ open models)",
     ]
     if keep_label:
         provider_choices.append(keep_label)
@@ -1412,7 +1418,29 @@ def setup_model_provider(config: dict):
         _set_model_provider(config, "opencode-go", pconfig.inference_base_url)
         selected_base_url = pconfig.inference_base_url
 
-    # else: provider_idx == 14 (Keep current) — only shown when a provider already exists
+    elif provider_idx == 14:  # Hugging Face Inference Providers
+        selected_provider = "huggingface"
+        print()
+        print_header("Hugging Face API Token")
+        pconfig = PROVIDER_REGISTRY["huggingface"]
+        print_info(f"Provider: {pconfig.name}")
+        print_info("Get your token at: https://huggingface.co/settings/tokens")
+        print_info("Required permission: 'Make calls to Inference Providers'")
+        print()
+
+        api_key = prompt_fn(
+            "  HF_TOKEN: ",
+            is_password=True,
+        ).strip()
+        if api_key:
+            save_env_value("HF_TOKEN", api_key)
+            # Clear OpenRouter env vars to prevent routing confusion
+            save_env_value("OPENAI_BASE_URL", "")
+            save_env_value("OPENAI_API_KEY", "")
+        _set_model_provider(config, "huggingface", pconfig.inference_base_url)
+        selected_base_url = pconfig.inference_base_url
+
+    # else: provider_idx == 15 (Keep current) — only shown when a provider already exists
     # Normalize "keep current" to an explicit provider so downstream logic
     # doesn't fall back to the generic OpenRouter/static-model path.
     if selected_provider is None:

website/docs/getting-started/quickstart.md

@@ -50,6 +50,7 @@ hermes setup       # Or configure everything at once
 | **MiniMax** | International MiniMax endpoint | Set `MINIMAX_API_KEY` |
 | **MiniMax China** | China-region MiniMax endpoint | Set `MINIMAX_CN_API_KEY` |
 | **Alibaba Cloud** | Qwen models via DashScope | Set `DASHSCOPE_API_KEY` |
+| **Hugging Face** | 20+ open models via unified router (Qwen, DeepSeek, Kimi, etc.) | Set `HF_TOKEN` |
 | **Kilo Code** | KiloCode-hosted models | Set `KILOCODE_API_KEY` |
 | **Vercel AI Gateway** | Vercel AI Gateway routing | Set `AI_GATEWAY_API_KEY` |
 | **Custom Endpoint** | VLLM, SGLang, or any OpenAI-compatible API | Set base URL + API key |

website/docs/reference/environment-variables.md

@@ -30,6 +30,8 @@ All variables go in `~/.hermes/.env`. You can also set them with `hermes config
 | `MINIMAX_CN_BASE_URL` | Override MiniMax China base URL (default: `https://api.minimaxi.com/v1`) |
 | `KILOCODE_API_KEY` | Kilo Code API key ([kilo.ai](https://kilo.ai)) |
 | `KILOCODE_BASE_URL` | Override Kilo Code base URL (default: `https://api.kilo.ai/api/gateway`) |
+| `HF_TOKEN` | Hugging Face token for Inference Providers ([huggingface.co/settings/tokens](https://huggingface.co/settings/tokens)) |
+| `HF_BASE_URL` | Override Hugging Face base URL (default: `https://router.huggingface.co/v1`) |
 | `ANTHROPIC_API_KEY` | Anthropic Console API key ([console.anthropic.com](https://console.anthropic.com/)) |
 | `ANTHROPIC_TOKEN` | Manual or legacy Anthropic OAuth/setup-token override |
 | `DASHSCOPE_API_KEY` | Alibaba Cloud DashScope API key for Qwen models ([modelstudio.console.alibabacloud.com](https://modelstudio.console.alibabacloud.com/)) |
@@ -48,7 +50,7 @@ For native Anthropic auth, Hermes prefers Claude Code's own credential files whe
 
 | Variable | Description |
 |----------|-------------|
-| `HERMES_INFERENCE_PROVIDER` | Override provider selection: `auto`, `openrouter`, `nous`, `openai-codex`, `anthropic`, `zai`, `kimi-coding`, `minimax`, `minimax-cn`, `kilocode`, `alibaba` (default: `auto`) |
+| `HERMES_INFERENCE_PROVIDER` | Override provider selection: `auto`, `openrouter`, `nous`, `openai-codex`, `anthropic`, `huggingface`, `zai`, `kimi-coding`, `minimax`, `minimax-cn`, `kilocode`, `alibaba` (default: `auto`) |
 | `HERMES_PORTAL_BASE_URL` | Override Nous Portal URL (for development/testing) |
 | `NOUS_INFERENCE_BASE_URL` | Override Nous inference API URL |
 | `HERMES_NOUS_MIN_KEY_TTL_SECONDS` | Min agent key TTL before re-mint (default: 1800 = 30min) |

website/docs/user-guide/configuration.md

@@ -72,7 +72,7 @@ You need at least one way to connect to an LLM. Use `hermes model` to switch pro
 | **MiniMax China** | `MINIMAX_CN_API_KEY` in `~/.hermes/.env` (provider: `minimax-cn`) |
 | **Alibaba Cloud** | `DASHSCOPE_API_KEY` in `~/.hermes/.env` (provider: `alibaba`, aliases: `dashscope`, `qwen`) |
 | **Kilo Code** | `KILOCODE_API_KEY` in `~/.hermes/.env` (provider: `kilocode`) |
-| **Alibaba Cloud** | `DASHSCOPE_API_KEY` in `~/.hermes/.env` (provider: `alibaba`) |
+| **Hugging Face** | `HF_TOKEN` in `~/.hermes/.env` (provider: `huggingface`, aliases: `hf`) |
 | **Custom Endpoint** | `hermes model` (saved in `config.yaml`) or `OPENAI_BASE_URL` + `OPENAI_API_KEY` in `~/.hermes/.env` |
 
 :::info Codex Note
@@ -152,6 +152,32 @@ model:
 
 Base URLs can be overridden with `GLM_BASE_URL`, `KIMI_BASE_URL`, `MINIMAX_BASE_URL`, `MINIMAX_CN_BASE_URL`, or `DASHSCOPE_BASE_URL` environment variables.
 
+### Hugging Face Inference Providers
+
+[Hugging Face Inference Providers](https://huggingface.co/docs/inference-providers) routes to 20+ open models through a unified OpenAI-compatible endpoint (`router.huggingface.co/v1`). Requests are automatically routed to the fastest available backend (Groq, Together, SambaNova, etc.) with automatic failover.
+
+```bash
+# Use any available model
+hermes chat --provider huggingface --model Qwen/Qwen3-235B-A22B-Thinking-2507
+# Requires: HF_TOKEN in ~/.hermes/.env
+
+# Short alias
+hermes chat --provider hf --model deepseek-ai/DeepSeek-V3.2
+```
+
+Or set it permanently in `config.yaml`:
+```yaml
+model:
+  provider: "huggingface"
+  default: "Qwen/Qwen3-235B-A22B-Thinking-2507"
+```
+
+Get your token at [huggingface.co/settings/tokens](https://huggingface.co/settings/tokens) — make sure to enable the "Make calls to Inference Providers" permission. Free tier included ($0.10/month credit, no markup on provider rates).
+
+You can append routing suffixes to model names: `:fastest` (default), `:cheapest`, or `:provider_name` to force a specific backend.
+
+The base URL can be overridden with `HF_BASE_URL`.
+
 ## Custom & Self-Hosted LLM Providers
 
 Hermes Agent works with **any OpenAI-compatible API endpoint**. If a server implements `/v1/chat/completions`, you can point Hermes at it. This means you can use local models, GPU inference servers, multi-provider routers, or any third-party API.
@@ -443,7 +469,7 @@ fallback_model:
 
 When activated, the fallback swaps the model and provider mid-session without losing your conversation. It fires **at most once** per session.
 
-Supported providers: `openrouter`, `nous`, `openai-codex`, `anthropic`, `zai`, `kimi-coding`, `minimax`, `minimax-cn`, `custom`.
+Supported providers: `openrouter`, `nous`, `openai-codex`, `anthropic`, `huggingface`, `zai`, `kimi-coding`, `minimax`, `minimax-cn`, `custom`.
 
 :::tip
 Fallback is configured exclusively through `config.yaml` — there are no environment variables for it. For full details on when it triggers, supported providers, and how it interacts with auxiliary tasks and delegation, see [Fallback Providers](/docs/user-guide/features/fallback-providers).

website/docs/user-guide/features/fallback-providers.md

@@ -44,6 +44,7 @@ Both `provider` and `model` are **required**. If either is missing, the fallback
 | MiniMax | `minimax` | `MINIMAX_API_KEY` |
 | MiniMax (China) | `minimax-cn` | `MINIMAX_CN_API_KEY` |
 | Kilo Code | `kilocode` | `KILOCODE_API_KEY` |
+| Hugging Face | `huggingface` | `HF_TOKEN` |
 | Custom endpoint | `custom` | `base_url` + `api_key_env` (see below) |
 
 ### Custom Endpoint Fallback
@@ -161,7 +162,7 @@ When a task's provider is set to `"auto"` (the default), Hermes tries providers
 
 ```text
 OpenRouter → Nous Portal → Custom endpoint → Codex OAuth →
-API-key providers (z.ai, Kimi, MiniMax, Anthropic) → give up
+API-key providers (z.ai, Kimi, MiniMax, Hugging Face, Anthropic) → give up
 ```
 
 **For vision tasks:**