{ "landing.description": "One OpenAI-compatible endpoint in front of self-hosted models.", "landing.open_warning": "This gateway has no API keys configured, so it serves anyone\nwho can reach it. That is a deployment choice, and only safe on a trusted network.", "landing.sub": "One OpenAI-compatible endpoint in front of your own GPUs.", "landing.lede": "Point any OpenAI client at this address. The API is the one you\n already have a client for — only the base URL changes.", "landing.create_account": "Create an account", "landing.sign_in": "Sign in", "landing.schematic": "Clients reach one endpoint, which places work on GPU nodes across separate fabrics.", "landing.schematic.client": "your client", "landing.schematic.editor": "editor agent", "landing.schematic.script": "a script", "landing.schematic.address": "one address", "landing.schematic.fabric": "fabric", "landing.schematic_caption": "Clients see one address. Work is placed on GPUs that\n can actually run it — and a model split across machines never straddles two fabrics.", "landing.base_url": "Base URL", "landing.three_steps": "Three steps", "landing.step1": "Get a key", "landing.step1_signup": "Create an account. Someone approves it, and then you issue\n your own keys from your profile — as many as you need,\n revoking them yourself when a laptop is retired or a script is done.", "landing.step1_contact": "Ask %s\n for one.", "landing.step1_contact_signin": " If you already have an account,\n sign in.", "landing.step1_nobody": "Keys are issued by whoever operates this gateway. If you do not know who that\n is, the address you reached this page at is the place to start asking.", "landing.step1_shown_once": "A key is shown once and never again — only its hash is kept here —\n so put it in a password manager straight away.", "landing.step2": "Point your client at it", "landing.step2_text": "Set the base URL above and your key. Every OpenAI SDK, and every tool built on\n one, takes both as configuration.", "landing.step3": "Pick a model", "landing.step3_keyed": "GET /v1/models lists what is available to your key. It needs the\n key, which is why this page does not list them: this page is served to anyone who\n can reach the address.", "landing.step3_open": "GET /v1/models lists what is available.", "landing.step3_placeholder": "Sending the placeholder <model-name> unchanged is\n answered with the list of models you may use, rather than with an error.", "landing.connect": "Connect your client", "landing.anything_works": "Anything that speaks the chat-completions API works, whether or not it\nis listed here — there is nothing llmgw-specific to install.", "landing.once_you_have_key": "Once you have a key", "landing.models_endpoint": "what your key may use", "landing.me_endpoint": "its limits, and what it has spent", "landing.client_guide": "The client guide has more: streaming, tools, embeddings and the Anthropic SDK." }