# Providers > Configure Empryo's 31 built-in LLM providers across cloud, gateways, coding plans, subscriptions, local and enterprise, plus any OpenAI-compatible custom API. Empryo ships 31 built-in providers. Set one key and go. ## Cloud | Provider | Setup | Get a key | |----------|-------|-----------| | **Anthropic** | `empryo --set-key anthropic sk-ant-...` | [console.anthropic.com](https://console.anthropic.com) | | **OpenAI** | `empryo --set-key openai sk-...` | [platform.openai.com](https://platform.openai.com) | | **Google** | `empryo --set-key google ...` | [aistudio.google.com](https://aistudio.google.com) | | **xAI** | `empryo --set-key xai xai-...` | [console.x.ai](https://console.x.ai) | | **Groq** | `empryo --set-key groq gsk_...` | [console.groq.com](https://console.groq.com) | | **DeepSeek** | `empryo --set-key deepseek sk-...` | [platform.deepseek.com](https://platform.deepseek.com) | | **Mistral** | `empryo --set-key mistral ...` | [console.mistral.ai](https://console.mistral.ai) | | **NVIDIA NIM** | `empryo --set-key nim nvapi-...` | [build.nvidia.com](https://build.nvidia.com) | | **Fireworks** | `empryo --set-key fireworks ...` | [fireworks.ai](https://fireworks.ai) | | **MiniMax** | `empryo --set-key minimax ...` | [platform.minimaxi.com](https://platform.minimaxi.com) | | **Ollama Cloud** | `/login ollama-cloud` or `empryo --set-key ollama-cloud ...` | [ollama.com/settings/keys](https://ollama.com/settings/keys) | ## Gateways (one key, many models) | Provider | What you get | Get a key | |----------|--------------|-----------| | **LLM Gateway** | One key for every major model, up to 30% off frontier | [llmgateway.io](https://llmgateway.io/dashboard?ref=6tjJR2H3X4E9RmVQiQwK) | | **OpenRouter** | 200+ models | [openrouter.ai](https://openrouter.ai) | | **Vercel AI Gateway** | Unified gateway | [vercel.com/ai-gateway](https://vercel.com/ai-gateway) | ## Subscription-based | Provider | Use | Setup | |----------|-----|-------| | **[GitHub Copilot](/docs/providers/copilot)** | Your Copilot subscription | `/login copilot`, or `/login copilot-enterprise` for GHE | | **GitHub Models** | Free with any GitHub PAT | `empryo --set-key github-models ghp_...` | ## Coding plans Monthly plans that serve their own endpoint. Each one is a key and a base URL. Models, context windows and prices come from the [models.dev](https://models.dev) catalog at runtime, so a vendor shipping a model today is selectable today with no Empryo release. A row stays hidden in every picker until its key is set. | Provider | Plan | Get a key | |----------|------|-----------| | **Z.AI Coding Plan** | GLM coding plan | [z.ai](https://z.ai/manage-apikey/apikey-list) | | **Zhipu Coding Plan** | The same plan on the mainland-China host | [bigmodel.cn](https://bigmodel.cn/usercenter/apikeys) | | **Alibaba Coding Plan** | Qwen coding plan | [bailian.console.alibabacloud.com](https://bailian.console.alibabacloud.com) | | **Alibaba Token Plan** | Qwen, metered instead of flat | [bailian.console.alibabacloud.com](https://bailian.console.alibabacloud.com) | | **Xiaomi MiMo** | MiMo token plan, Singapore host | [platform.xiaomimimo.com](https://platform.xiaomimimo.com) | | **Kilo Gateway** | Many vendors behind one key | [kilo.ai](https://kilo.ai) | | **SiliconFlow** | Open-weight hosting | [cloud.siliconflow.com](https://cloud.siliconflow.com/account/ak) | | **Synthetic** | Flat-rate open-weight plan | [synthetic.new](https://synthetic.new) | Set one the same way as any other key: ```bash empryo --set-key zai-coding-plan ... empryo --set-key zhipu-coding-plan ... empryo --set-key alibaba-coding-plan ... ``` Five of these also have a sign-in lane, which is the better route when you have one: `/login` stores the key in the keychain and, for Alibaba and Xiaomi, probes the vendor's regional hosts and remembers the one that accepted it. See [Subscriptions](/docs/providers/subscriptions). The env var each vendor's own users already export works too: `ZAI_API_KEY`, `ZHIPU_API_KEY`, `ALIBABA_CODING_PLAN_API_KEY`, `ALIBABA_TOKEN_PLAN_API_KEY`, `XIAOMI_API_KEY`, `KILO_API_KEY`, `SILICONFLOW_API_KEY`, `SYNTHETIC_API_KEY`. ## Local (free) | Provider | Setup | |----------|-------| | **Ollama** | Auto-detected at `localhost:11434`. Set `OLLAMA_HOST` to override. | | **LM Studio** | Auto-detected at `localhost:1234`. Set `LM_STUDIO_URL` to override. | | **OpenCode Go** | `empryo --set-key opencode-go ...` | | **OpenCode Zen** | `empryo --set-key opencode-zen ...` | ## Enterprise | Provider | Setup | |----------|-------| | **Bedrock** | `export AWS_ACCESS_KEY_ID=... AWS_SECRET_ACCESS_KEY=... AWS_REGION=us-east-1` | | **Subscriptions** | 22 sign-in lanes: Claude, ChatGPT Codex, Grok, Cursor, Devin, Copilot, Gemini CLI, Antigravity, Kimi Code, Fire Pass, OpenRouter, Ollama Cloud, LLM Gateway, Kilo, Z.AI, Alibaba (coding and token plans), Xiaomi. `/login`, no addon. Use at your own risk. See [Subscriptions](/docs/providers/subscriptions). | | **Proxy** | Local CLIProxyAPI relay - routes Claude, GPT, Gemini, Grok via your existing chat subscriptions. Install the addon (`empryo addon install proxy`), then `/proxy login`. Use at your own risk. See [addons](/docs/tools/addons) and [Proxy](/docs/providers/proxy). Claude and ChatGPT no longer need it: see [Subscriptions](/docs/providers/subscriptions). | ## LLM Gateway One key for 200+ models with built-in cost tracking, Claude, GPT, Gemini, Grok, Llama, Qwen, and more. Or DevPass: a fixed-price monthly subscription with 3× the value. 1. Get a key at [llmgateway.io](https://llmgateway.io/dashboard?ref=6tjJR2H3X4E9RmVQiQwK), or just type `/login` inside Empryo, the browser mints one and hands it back over a local loopback. 2. Or save a key manually: ```bash empryo --set-key llmgateway sk-... ``` 3. Launch Empryo, press `Ctrl+L`, pick any model. The picker's gateway header says which lane is paying, **Pay-as-you-go · account credits** or **DevPass · subscription**, so a model pick is never a billing surprise. Switching lanes happens in `/keys` (it's a credential, not a toggle). ### Pick who serves your model (upstream routing) The gateway resells many models from **several upstream vendors at different prices and output caps**, the same `deepseek-v4-pro` costs $0.435/M input on DeepSeek and $2.40/M on Alibaba, and its output cap ranges from 64K to 393K depending on the route. By default the id is sent bare and the gateway auto-routes. On the pay-as-you-go lane you can pin the route per model: - **Terminal**, in the model picker, rows with more than one route show `⇌ N`. Press `Ctrl+R` on one to open the route chooser: `Auto — gateway decides` first, then every upstream **cheapest-first with that route's own price and output cap**. Picking a route picks the model pinned to it. The active row then reads `via DeepSeek`. - **Desktop**, gateway rows carry a `⇌` button that swaps the picker to the same route list. - **Headless**, pin in the id itself: ```bash empryo --headless "fix the tests" --model llmgateway/anthropic/claude-opus-5 empryo --headless "fix the tests" --model llmgateway/deepinfra/deepseek-v4-pro ``` `llmgateway//` routes through that vendor. `llmgateway/` lets the gateway decide. Either way it is the same model: favourites, Recents, pricing and the context window all follow it, and the route you pin belongs to the tab, so two tabs can run one model on different routes. Pinning a Claude id to Anthropic also turns on Empryo's own tool-deferral path. Pinning works on pay-as-you-go keys only, because a DevPass plan routes on the gateway's side. ## OpenRouter 200+ models behind a single key, including frontier and open-weight. Sign in with your browser and there is no key to paste: ```bash empryo # then: /login openrouter ``` Or save a key yourself: 1. Get one at [openrouter.ai/keys](https://openrouter.ai/keys). 2. Save it: ```bash empryo --set-key openrouter sk-or-... ``` 3. Launch Empryo, press `Ctrl+L`, pick any model. Either way the credit balance on the account shows up as a meter in `/usage` and the desktop Usage drawer, next to the dollar spend. ## Anything else Any OpenAI-compatible API works via [custom providers](/docs/providers/custom) - one block of config, no code. The key goes in the same way, under the `id` you gave the provider: ```bash empryo --set-key together sk-... # `id` from your providers[] entry ``` Run it again with a second key and both are kept. An account that runs out hands the turn to the next one. See [several accounts on one provider](/docs/providers/custom#several-accounts-on-one-provider). ## Switching models Inside Empryo, press `Ctrl+L` to pick a provider and model. Assign different models to different tasks with `/router` (cheap model for search, strong for code). ```bash empryo --list-providers # see what's configured empryo --list-models anthropic # see available models for one provider ```