Configuration

Authentication

The gateway requires an Authorization: Bearer <token> header on all requests (except /health). For full details on how gateway auth and provider auth work, see the Authentication guide.

Environment Variables

Server

Variable	Default	Description
`LLMG_PORT`	`8080`	Server port
`LLMG_HOST`	`0.0.0.0`	Bind address
`LLMG_LOG_LEVEL`	`info`	Log level (`error`, `warn`, `info`, `debug`, `trace`)
`LLMG_CORS`	`false`	Enable CORS headers for browser clients

Provider API Keys

Set the API key environment variable for each provider you want to use. The gateway auto-discovers providers based on which keys are present.

Variable	Provider
`OPENAI_API_KEY`	OpenAI
`ANTHROPIC_API_KEY`	Anthropic
`GROQ_API_KEY`	Groq
`MISTRAL_API_KEY`	Mistral
`COHERE_API_KEY`	Cohere
`DEEPSEEK_API_KEY`	DeepSeek
`OPENROUTER_API_KEY`	OpenRouter
`XAI_API_KEY`	xAI (Grok)
`AZURE_OPENAI_API_KEY`	Azure OpenAI
`Z_AI_API_KEY`	Z.AI (GLM)

See the full provider list for all supported environment variables.

Config File

You can optionally create an llmg.toml:

[server]
port = 8080
host = "0.0.0.0"
timeout = 60
cors = true

[providers.openai]
enabled = true
api_key = "${OPENAI_API_KEY}"
default_model = "gpt-4"

[aliases]
gpt-4 = "openai/gpt-4"
claude = "anthropic/claude-sonnet-4-20250514"

Model Aliases

The gateway supports short aliases that map to full provider/model paths. Built-in aliases include:

Alias	Maps To
`gpt-4`	`openai/gpt-4`
`claude`	`anthropic/claude-sonnet-4-20250514`
`gemini`	`antigravity/gemini-2.0-flash`
`llama`	`meta_llama/llama-3.1-70b-instruct`
`mistral`	`mistral/mistral-large`
`deepseek`	`deepseek/deepseek-chat`
`groq`	`groq/llama3-70b-8192`