Lemonade Server Configuration

Overview

Lemonade Server starts automatically with the OS after installation. Persistent JSON configuration is stored in Lemonade's config directory; caches and downloaded artifacts stay in the cache directory.

config.json

If you used an installer from the Lemonade release your config.json will be at these locations depending on your OS:

• Linux — apt/.deb (Debian/Ubuntu): /var/lib/lemonade/config.json

• Linux — dnf/.rpm (Fedora/Red Hat): /var/lib/lemonade/config.json

  Note: The systemd service runs as the lemonade user. Persistent config lives in /var/lib/lemonade (systemd StateDirectory), downloaded backends go to /var/cache/lemonade (CacheDirectory), and models are cached under /var/lib/lemonade/.cache/huggingface. For Debian/Ubuntu, upgrading the package automatically migrates data from the old /opt/var/lib/lemonade path to /var/lib/lemonade.

• Windows: %USERPROFILE%\.config\lemonade\config.json

• macOS: /Library/Application Support/lemonade/.config/config.json

If you are using a standalone lemond executable, the default location is ~/.config/lemonade/config.json.

On startup, Lemonade automatically migrates persistent JSON files from the legacy .cache location into the new .config location.

Note: config.json is a sparse override file. It only contains settings you explicitly customize; all unspecified settings automatically inherit default values and receive upstream improvements across updates.

Defaults Precedence & Layering

When lemond starts, effective configuration is resolved by deep-merging settings in increasing precedence:

1. Built-in Defaults: Factory defaults baked into the release (resources/defaults.json and backend descriptors).
2. Distro / System Defaults: On Linux, lemond merges /usr/share/lemonade/defaults.json if it exists, so distro packages can ship system-level defaults (e.g. backend *_bin paths pointing at system-installed binaries).
3. Environment Defaults: Set the LEMONADE_DEFAULTS_PATH environment variable to a defaults.json at any location to merge on top (for non-FHS distros like Nix/Guix that cannot write under /usr/share).
4. User Overrides (config.json): Values explicitly set in your config.json override defaults.
5. CLI Flags: Arguments passed to lemond (e.g. --port, --host).

Example config.json

{
  "_generated": "GENERATED by docs/tools/gen_backend_boilerplate.py -- do not hand-edit per-recipe sections (they come from each backend's descriptor config_defaults()). Global keys are hand-maintained in this file. Regenerate and verify with that script; CI --check fails on drift.",
  "acestep": {
    "backend": "auto",
    "cuda_bin": "builtin",
    "rocm_bin": "builtin",
    "vulkan_bin": "builtin"
  },
  "allowed_origins": "",
  "auto_check_model_updates": true,
  "auto_update_models": false,
  "broadcast": true,
  "cloud_providers": [],
  "config_version": 2,
  "ctx_size": -1,
  "default_model_source": "huggingface",
  "disable_model_filtering": false,
  "download_rate_limit": "",
  "ds4": {
    "args": ""
  },
  "enable_dgpu_gtt": false,
  "extra_models_dir": "",
  "flm": {
    "args": "",
    "prefer_system": false
  },
  "global_timeout": 600,
  "host": "localhost",
  "hrx": {
    "args": "",
    "hrx_bin": "builtin"
  },
  "inhibit_suspend": true,
  "kokoro": {
    "cpu_bin": "builtin"
  },
  "llamacpp": {
    "args": "",
    "backend": "auto",
    "cpu_args": "",
    "cpu_bin": "builtin",
    "cuda_bin": "builtin",
    "prefer_system": true,
    "rocm_args": "",
    "rocm_bin": "builtin",
    "vulkan_args": "",
    "vulkan_bin": "builtin"
  },
  "log_file": "auto",
  "log_level": "info",
  "log_max_file_size_mb": 10,
  "log_max_files": 5,
  "max_loaded_models": 1,
  "models_dir": "auto",
  "moonshine": {
    "args": "",
    "cpu_args": "",
    "cpu_bin": "builtin"
  },
  "no_fetch_executables": false,
  "offline": false,
  "onnxruntime": {
    "args": "",
    "cpu_args": "",
    "cpu_bin": "builtin"
  },
  "openmoss": {
    "backend": "auto",
    "cuda_bin": "builtin",
    "rocm_bin": "builtin",
    "vulkan_bin": "builtin"
  },
  "port": 13305,
  "rocm_channel": "stable",
  "rocm_install_method": "auto",
  "ryzenai": {
    "server_bin": "builtin"
  },
  "sdcpp": {
    "args": "",
    "backend": "auto",
    "cfg_scale": 7.0,
    "cpu_args": "",
    "cpu_bin": "builtin",
    "cuda_args": "",
    "cuda_bin": "builtin",
    "height": 512,
    "rocm_args": "",
    "rocm_bin": "builtin",
    "steps": 20,
    "vulkan_args": "",
    "vulkan_bin": "builtin",
    "width": 512
  },
  "telemetry": {
    "enabled": false,
    "hide_inputs": false,
    "hide_outputs": false,
    "hide_thinking": false,
    "max_queue_capacity": 1000,
    "otlp": {
      "batch_timeout_s": 1.0,
      "endpoint": "http://localhost:4318/v1/traces",
      "headers": {},
      "max_retries": 0,
      "protocol": "http/protobuf",
      "retry_backoff_base_s": 5.0,
      "semantics": [
        "openinference",
        "otel_genai"
      ],
      "send_batch_size": 100
    },
    "session": {
      "headers": {
        "client": [],
        "id": []
      }
    },
    "trust_incoming_trace_context": false
  },
  "thenoise": {
    "backend": "auto",
    "lora_dir": "",
    "rocm_bin": "builtin",
    "upscaler_dir": ""
  },
  "thinksound": {
    "backend": "auto",
    "cuda_bin": "builtin",
    "rocm_bin": "builtin",
    "vulkan_bin": "builtin"
  },
  "trellis": {
    "args": "",
    "backend": "auto",
    "cuda_bin": "builtin",
    "rocm_bin": "builtin",
    "vulkan_bin": "builtin"
  },
  "vllm": {
    "args": "",
    "backend": "auto"
  },
  "websocket_port": "auto",
  "whispercpp": {
    "args": "",
    "backend": "auto",
    "cpu_args": "",
    "cpu_bin": "builtin",
    "npu_args": "",
    "npu_bin": "builtin"
  }
}

Settings Reference

Key	Type	Default	Description
port	int	13305	Port number for the HTTP server
host	string	"localhost"	Address to bind for connections
log_level	string	"info"	Logging level (trace, debug, info, warning, error, fatal, none)
log_file	string	"auto"	File logging mode: "auto" (console-only for direct server runs, lemonade-server.log for embedded tray app), "disabled", "enabled", or custom target file path
log_max_file_size_mb	int	10	Max active log file size in MB before triggering rotation (steady-state footprint bounded to ~log_max_file_size_mb * (log_max_files + 1))
log_max_files	int	5	Max number of rotated log backup files to retain (.1 through .N); legacy oversized files are rotated into .1 and pruned over cycles
global_timeout	int	600	Timeout in seconds for HTTP, inference, and readiness checks
max_loaded_models	int	1	Max models per type slot. Use -1 for unlimited
broadcast	bool	true	Enable or disable UDP broadcasting for server discovery
extra_models_dir	string	""	Secondary directory recursively scanned for GGUF model files. Empty disables extra discovery; existing paths must be readable by lemond. Top-level chat, embeddings, and reranking directories select how models run, see Model Management
models_dir	string	"auto"	Directory for cached model files. "auto" follows HF_HUB_CACHE / HF_HOME / platform default
ctx_size	int	-1	Default context size for LLM models. Use -1 for auto-resolution: the server computes the largest context that fits in available device memory using GGUF architecture metadata. Use a positive integer to set an explicit size.
default_model_source	string	"huggingface"	Remote registry used to pull checkpoints when a request does not name one (huggingface or modelscope). Explicit --source, a source/registry_source field, or a provider URL always overrides it.
download_rate_limit	string	""	Caps model/backend download speed. Byte rate with curl-style suffixes: 512, 100K, 10M, etc. Use "" for unlimited download speed. A non-empty value also serializes concurrent transfers.
offline	bool	false	Skip model downloads
auto_check_model_updates	bool	true	Check downloaded Hugging Face-backed models for updates during server startup. Set to false to check only with lemonade check-updates or POST /v1/models/check-updates. Manual downloads and updates remain enabled.
auto_update_models	bool	false	Automatically download model updates when available. Can be overridden per model via auto_update in model options.
no_fetch_executables	bool	false	Prevent downloading backend executable artifacts; backends must already be installed or use the system backend
disable_model_filtering	bool	false	Show all models regardless of hardware capabilities
inhibit_suspend	bool	true	Prevent the OS from suspending while inference is active. Linux only (uses systemd-logind); no-op on Windows/macOS/non-systemd environments.
enable_dgpu_gtt	bool	false	Include GTT for hardware-based model filtering
rocm_channel	string	"stable"	ROCm backend channel: "stable" (default) or "nightly". See llama.cpp Backend for details
rocm_install_method	string	"auto"	How to install the bundled ROCm runtime: "auto" (pip wheels, tarball fallback), "wheel" (wheels only), or "tarball" (no Python/pip). See llama.cpp Backend for details

Both models_dir and extra_models_dir can be changed at runtime through POST /internal/set. Existing extra_models_dir paths are preflighted as directories and must be enumerable by the lemond process. Nonexistent paths are accepted so the directory watcher can observe them if they are created later.

Backend Configuration

Backend-specific settings are nested under their backend name:

llamacpp — LLM inference via llama.cpp:

Key	Default	Description
backend	"auto"	Backend to use: "auto" means "choose for me"
args	""	Custom arguments to pass to llama-server (fallback, unused when backend-specific args defined)
*_args	""	Backend-specific custom arguments to pass to llama-server
device	""	Comma-separated list of devices to use for offloading. Empty is auto.
prefer_system	false	Prefer system-installed llama.cpp over bundled
*_bin	"builtin"	Backend binary selection — see Backend binary selection

whispercpp — Audio transcription:

Key	Default	Description
backend	"auto"	Backend to use: "auto" means "choose for me"
args	""	Custom arguments to pass to whisper-server (fallback, unused when backend-specific args defined)
*_args	""	Backend-specific custom arguments to pass to whisper-server
*_bin	"builtin"	Backend binary selection — see Backend binary selection

sdcpp — Image generation:

Key	Default	Description
backend	"auto"	Backend to use: "auto" means "choose for me"
args	""	Custom arguments to pass to sd-server (fallback, unused when backend-specific args defined)
*_args	""	Backend-specific custom arguments to pass to sd-server
steps	20	Number of inference steps
cfg_scale	7.0	Classifier-free guidance scale
width	512	Image width in pixels
height	512	Image height in pixels
*_bin	"builtin"	Backend binary selection — see Backend binary selection

flm — FastFlowLM NPU inference:

Key	Default	Description
args	""	Custom arguments to pass to flm serve
prefer_system	false	Prefer system-installed FLM (on PATH) over auto-installed portable binary

ryzenai — RyzenAI NPU inference:

Key	Default	Description
server_bin	"builtin"	Backend binary selection — see Backend binary selection

kokoro — Text-to-speech:

Key	Default	Description
cpu_bin	"builtin"	Backend binary selection — see Backend binary selection

cloud_providers — Cloud OpenAI-compatible providers (see Cloud Offload). Array, one object per installed provider:

Key	Description
name	Short identifier (e.g. fireworks). Used as the model-name prefix.
base_url	OpenAI-compatible base URL ending in /v1 (or equivalent).
allow_insecure_http	Whether this provider may receive its API key over http://.
auth_header_name	Header the API key is sent in. Omitted when it is the default Authorization.
auth_header_prefix	Value prefix before the key. Omitted when it is the default "Bearer ".
wire_format	openai or anthropic. Omitted when it is the default openai.

API keys for these providers are not stored in config.json — they live in LEMONADE_<PROVIDER>_API_KEY env vars (persistent) or lemond process memory via POST /v1/cloud/auth (ephemeral). Manage providers with lemonade cloud install/uninstall/auth/list rather than editing this section by hand.

telemetry — Unified telemetry and tracing configurations:

Key	Type	Default	Description
enabled	bool	false	Enable or disable telemetry tracing.
hide_inputs	bool	false	Redact prompt message content from spans.
hide_outputs	bool	false	Redact generated assistant message content from spans.
hide_thinking	bool	false	Redact reasoning/thought content from spans.
trust_incoming_trace_context	bool	false	Honor a caller-supplied W3C traceparent header so inference spans join the caller's distributed trace instead of starting a fresh root. Opt-in because span parentage then depends on client-supplied input.
max_queue_capacity	int	1000	The maximum capacity of the in-memory telemetry queue buffer. Oldest spans are dropped when full. Must be > 0.
otlp	object	(nested object)	Sub-block grouping OTLP transport details (see below).

telemetry.otlp — Nested OTLP settings:

Key	Type	Default	Description
endpoint	string	"http://localhost:4318/v1/traces"	The OTLP endpoint to send traces to.
protocol	string	"http/protobuf"	Supported OTLP trace protocol: "http/protobuf" or "http/json".
semantics	array of strings	["openinference", "otel_genai"]	Active trace semantics. Supported values: "openinference" and "otel_genai".
headers	object	{}	Map of custom HTTP headers to pass to the OTLP receiver.
max_retries	int	0	Maximum number of retry attempts for failed exports. Set to 0 to disable retries and discard failed spans immediately. Must be >= 0.
retry_backoff_base_s	double	5.0	Base delay in seconds for exponential backoff retries. Must be >= 0.
send_batch_size	int	100	Target maximum number of spans to group in a single batched OTLP request. Must be >= 1.
batch_timeout_s	double	1.0	Maximum time to wait in seconds before exporting a partially filled batch of spans. Must be > 0.

Telemetry and Tracing Details

Lemonade uses a unified telemetry subsystem to trace requests and capture critical execution spans. The following technical behaviors apply:

• Multi-Standard Semantic Conventions: Supports exporting traces using two co-existing semantics:
  • OpenInference: Uses Arize Phoenix-compatible properties (always prefixed with openinference.span.kind, llm.model_name, llm.token_count.*).
  • OpenTelemetry GenAI: Uses standard OpenTelemetry GenAI properties (gen_ai.system, gen_ai.request.model, gen_ai.usage.input_tokens, gen_ai.input.messages, gen_ai.output.messages). When both semantics are specified in telemetry.otlp.semantics, trace spans carry attributes for both conventions in a single network payload. This allows the collector to parse either convention without duplicate network requests.
• Dynamic Attribute Prefixing: Span attributes are dynamically prefixed based on the query type to simplify filtering:
  • llm.* for standard chat and completion spans.
  • embedding.* for text embedding generation spans.
  • reranker.* for document reranking spans.
• Token Tracking: Captures and reports token usage metrics using semantic attributes depending on the enabled semantics:
  • For OpenInference: Token count is prefixed with llm.token_count across all span kinds (llm.token_count.prompt, llm.token_count.completion, llm.token_count.total) alongside legacy keys like llm.usage.prompt_tokens.
  • For OpenTelemetry GenAI: Token count uses standard fields like gen_ai.usage.input_tokens and gen_ai.usage.output_tokens.
• Calculated Performance Metrics: In streaming mode, the server automatically computes and records throughput (llm.performance.tokens_per_second / gen_ai.usage.tokens_per_second depending on semantic conventions) and prefill latency (llm.performance.time_to_first_token / gen_ai.performance.time_to_first_token) if not natively returned by the backend (e.g., for vLLM and Cloud models).
• vLLM Engine Telemetry: For the vLLM backend, the server queries the local /metrics endpoint on completion to attach scheduler queue metrics (llm.vllm.num_requests_waiting, llm.vllm.num_requests_running, llm.vllm.num_requests_swapped) and KV cache utilization (llm.vllm.gpu_cache_usage_factor, llm.vllm.cpu_cache_usage_factor) directly to the trace spans.
• Reasoning Model Support: For reasoning models (e.g., DeepSeek models), the server extracts and records reasoning_content from the assistant's generation. Any variant thought-termination tags (e.g., </think|>) are automatically standardized to the canonical </think> tag.
• Exporter Retry Backoff: When retries are enabled (i.e., max_retries > 0), the exporter uses an exponential backoff strategy combined with randomized jitter for failed posts. The base retry interval starts at retry_backoff_base_s seconds (defaulting to 5), doubling on each subsequent failure (e.g., 5s, 10s, 20s, 40s), up to a maximum cap of 60 seconds. A randomized jitter factor between 0.5 and 1.5 is applied to each calculated delay to prevent a "thundering herd" when the collector recovers. Permanent client errors (4xx HTTP status codes, excluding 429 Too Many Requests) are classified as non-retryable and cause the batch to be dropped immediately to save resources.
• OTLP Trace Batching: Spans are aggregated in an in-memory queue buffer and exported in batches to minimize network overhead and maximize compression efficiency. Batching operates on a dual-trigger system: a batch is immediately serialized and dispatched if it reaches send_batch_size (default: 100), or if batch_timeout_s (default: 1.0 second) has elapsed since the oldest span in the batch arrived. All remaining traces are flushed cleanly to the OTel collector upon server shutdown. Users can also trigger a manual flush at any time via the POST /internal/telemetry/flush endpoint.
• Request Failure Tracing: Captures request failures directly on the telemetry spans. If a model fails to load, a request is rejected by the router, or a streaming connection encounters an exception or a non-200 HTTP status code from the backend, the span is ended with Error status and the specific error message is attached.
• Queue Blocking & Thundering Herd Prevention: To prevent client requests from hanging and to avoid exhausting resources when the telemetry receiver endpoint is down, Lemonade employs a fail-fast mechanism. The exporter memory buffer is strictly bounded to a capacity of max_queue_capacity spans (default: 1000). When full, a head-drop (FIFO) eviction policy is applied to drop the oldest telemetry spans to make room for newer ones, prioritizing current application state. If a telemetry transmission task fails all of its retries and is dropped, the endpoint is marked as unreachable. While in this unreachable state, subsequent spans in the transmission queue are attempted only once and immediately dropped without backoff delay if they fail, preventing the telemetry queue from blocking server operations. A single successful span delivery to the endpoint automatically resets the unreachable state and restores normal retry behavior.

Backend binary selection

Every *_bin key (e.g. llamacpp.vulkan_bin, whispercpp.cpu_bin, sdcpp.rocm_bin) accepts the same set of values:

Value	Meaning
"builtin" (default)	Use the version of the upstream backend that lemonade pins in its release. Recommended for most users — these versions are tested with this lemonade build.
""	Same as "builtin".
"latest"	Resolve to the most-recent upstream GitHub release on first install or first status query for that backend, then install on demand. The resolved tag is recorded in <lemonade-home>/bin/<recipe>/<backend>/version.txt.
"b8664" / "v1.8.2" / etc.	A specific upstream release tag. Lemonade downloads that exact version from GitHub.
"/path/to/bin"	A directory you populated yourself (e.g. a local build). Lemonade uses the executable inside this directory and never downloads. The path must exist when set.

Note: the latest setting is experimental.

Note: llamacpp.rocm_bin version tags are channel-specific. Each ROCm channel downloads from a different GitHub repository, so you must set the correct rocm_channel before pinning rocm_bin to a specific tag. See Pinning to a Specific Version Tag for details.

Examples:

# Track upstream llama.cpp Vulkan releases (auto-resolve at lemond start)
lemonade config set llamacpp.vulkan_bin=latest

# Pin to a specific llama.cpp build
lemonade config set llamacpp.vulkan_bin=b8664

# Use your own llama.cpp build
lemonade config set llamacpp.vulkan_bin=/home/me/llama.cpp/build/bin

# Revert to the version lemonade ships
lemonade config set llamacpp.vulkan_bin=builtin

Behavior when *_bin changes

Changing a *_bin value applies live: lemonade unloads any model currently using that backend, downloads the new binary if needed, and reloads the model on the new binary. No lemond restart is required.

latest re-resolution

"latest" is resolved once per lemond process. The first install or status query for a latest-pinned backend hits the GitHub API; the resolved tag is then cached in memory for the rest of the process lifetime. Subsequent installs and status queries (including manual lemonade backends install) reuse the cached tag and do not re-query GitHub. Restart lemond to pick up a newer upstream release.

Upgrade signals in lemonade backends

The lemonade backends listing surfaces two upgrade signals for backends pinned to "latest":

• update_available — A newer upstream release exists than what's installed. The backend keeps running on the installed version; the listed action is the install command to apply the upgrade when you're ready.
• update_required — The installed version is older than the version lemonade ships in this release. This forces an upgrade prompt because running below the lemonade-shipped baseline is not supported.

Backends pinned to a specific tag (e.g. b8664) do not get either signal — they're treated as an explicit user choice.

Interactions with other config

• offline: true blocks the GitHub call for "latest". If a previously-installed version.txt exists in the install directory, lemonade reuses that version with a warning. Otherwise the install fails.
• no_fetch_executables: true blocks all downloads, including resolving and installing "latest" and any version-tag pin. Existing installs continue to work.

Editing Configuration

lemonade config (recommended)

Use the lemonade config CLI to view and modify settings while the server is running. Changes are applied immediately and persisted to config.json.

# View all current settings
lemonade config

# Set one or more values
lemonade config set key=value [key=value ...]

Top-level settings use their JSON key name directly. Nested backend settings use dot notation (section.key=value):

# Change the server port and log level
lemonade config set port=9000 log_level=debug

# Change a backend setting
lemonade config set llamacpp.backend=rocm

# Set multiple values at once
lemonade config set port=9000 llamacpp.backend=rocm sdcpp.steps=30

# Set complex types like JSON arrays and objects (use single quotes to prevent shell expansion)
lemonade config set telemetry.otlp.semantics='["openinference"]'
lemonade config set telemetry.otlp.headers='{"Authorization":"Bearer key"}'

lemond CLI arguments (runtime overrides)

lemond accepts --port and --host as CLI arguments to provide ephemeral runtime overrides for that specific server process without modifying config.json:

lemond --port 9000 --host 0.0.0.0

Because CLI overrides are ephemeral and do not mutate config.json on disk, if the server cannot start due to an invalid port or host setting in config.json:

1. Start lemond using the CLI override: lemond --port 9000
2. Run lemonade config set port=9000 against the running server to persist the fix for subsequent restarts.
3. Alternatively, edit config.json directly as shown below.

Edit config.json manually (last resort)

If the server won't start and CLI tools aren't sufficient, you can edit config.json directly. Restart the server after making changes:

# Linux (Debian/Ubuntu and Fedora/Red Hat)
sudo nano /var/lib/lemonade/config.json

sudo systemctl restart lemond

# Windows — edit with your preferred text editor:
# %USERPROFILE%\.config\lemonade\config.json
# Then quit and relaunch from the Start Menu

lemond CLI

lemond [cache_dir] [config_dir] [--port PORT] [--host HOST] [--broadcast] [--no-broadcast]

• cache_dir — Path to the lemonade cache/data directory. Optional; defaults to the platform-specific cache location.
• config_dir — Path to the lemonade config directory for persistent JSON state. Optional; defaults to the platform-specific config location.
• --port — Port to serve on (runtime override, does not mutate config.json).
• --host — Address to bind (runtime override, does not mutate config.json).
• --broadcast / --no-broadcast — Enable or disable UDP broadcasting for server discovery (non-persistent override).

API Key and Security

Regular API Key

The LEMONADE_API_KEY environment variable sets an API key for authentication on regular API endpoints (/api/*, /v0/*, /v1/*). On Linux with systemd, set it in the service environment (e.g., via a systemd override or drop-in file). On Windows, set it as a system environment variable.

When LEMONADE_API_KEY is set, the inference and model-management endpoints reject any request that does not present a matching Bearer token. This is the only credential that gates those endpoints, so it controls whether unauthenticated clients can reach the server at all. When it is unset, those endpoints are reachable without authentication.

Admin API Key

The LEMONADE_ADMIN_API_KEY environment variable provides elevated access to both regular API endpoints and internal endpoints (/internal/*). When set, it takes precedence over LEMONADE_API_KEY for client authentication.

LEMONADE_ADMIN_API_KEY enables privilege separation between two classes of authenticated clients. Holders of LEMONADE_API_KEY can reach the regular API endpoints, while only holders of LEMONADE_ADMIN_API_KEY can reach the internal control endpoints (/internal/*, e.g. shutdown and configuration). A client presenting only LEMONADE_API_KEY cannot reach /internal/* if LEMONADE_ADMIN_API_KEY is set to a distinct value. If LEMONADE_ADMIN_API_KEY is not set, it defaults to the value of LEMONADE_API_KEY, so the regular key then also authenticates against /internal/* and no privilege separation exists.

Authentication Hierarchy:

Scenario	LEMONADE_API_KEY	LEMONADE_ADMIN_API_KEY	Internal Endpoints	Regular API Endpoints
No keys set	(not set)	(not set)	No auth required	No auth required
Only API key	"secret"	(not set)	Requires key	Requires key
Only admin key	(not set)	"admin"	Requires admin key	No auth required
Both keys different	"regular"	"admin"	Requires admin key	Either key accepted

Client Behavior: Clients (CLI, tray app) automatically prefer LEMONADE_ADMIN_API_KEY if set, otherwise fall back to LEMONADE_API_KEY.

Allowed Origins

The allowed_origins setting (in config.json or configured via lemonade config set allowed_origins="...") controls which remote web origins are authorized to connect to the server (specifically for CORS headers on HTTP endpoints and origin validation on WebSocket connections).

• Configuration:
  • In config.json: "allowed_origins": "https://app.lemonade.dev,http://localhost:3000"
  • Via CLI: lemonade config set allowed_origins="https://app.lemonade.dev,http://localhost:3000"
• Format: A comma-separated list of complete origins including the scheme and optional port (e.g., https://app.lemonade.dev,http://localhost:3000).

  Warning

  Allowing a non-local plain-HTTP origin (e.g., http://app.example.com) is vulnerable to on-path modification (man-in-the-middle) and interception. It is highly recommended to use HTTPS (https://) for all remote/non-local allowed origins.

• Wildcard (*): Setting allowed_origins to * allows any origin to connect.
• Security Implications of *:

  Warning

  Using allowed_origins=* permits any website running in a user's browser to make requests to your local Lemonade server. In particular, if LEMONADE_API_KEY is not configured, this exposes the server to unauthenticated remote access and cross-origin attacks from malicious websites. Use wildcards only for development or in secure, isolated environments.

• Local/Loopback, Desktop & Same-Origin Access (Zero-Configuration):
  • Loopback & Subdomains: Loopback addresses (localhost, 127.0.0.1, [::1], *.localhost) are permitted automatically.
  • Native Desktop Apps: Native desktop application schemes (lemonade://, file://, app://., vscode-webview://, jan://, etc.) are permitted for client connections.
  • Same-Origin LAN & mDNS Web App Access: Direct browser requests to Lemonade's built-in web interface over active network interfaces (e.g. http://192.168.1.50:13305/app, http://100.100.x.x:13305/app) and local mDNS hostnames (http://<hostname>.local:13305/app) are dynamically permitted without manual configuration because they are same-origin to the server's own interfaces.
• When Allowed Origins Must Be Configured:
  • Cross-Origin Web Applications: Any external or third-party web application hosted on a different domain or port connecting to Lemonade in the browser (e.g. a web UI hosted at https://app.lemonade.dev or http://localhost:3000 calling Lemonade on http://192.168.1.50:13305).
  • Reverse Proxies & TLS Frontends: Reverse proxies, tunnels, or frontends terminating TLS (e.g., https://lemonade.example.com or Tailscale Serve at https://mybox.tailnet.ts.net). Because proxies forward HTTPS requests to an HTTP server and present external hostnames not belonging to local network interfaces, their external origins must be explicitly allowlisted. (By contrast, direct access via a local Tailscale interface IP http://100.x.y.z:13305 is zero-config).
  • Sandboxed Frames: Opaque null origins (e.g. from sandboxed browser iframes) are rejected unless explicitly listed in allowed_origins to prevent CSWSH attacks.

  Note

  When an explicit allowed_origins list is configured, it is authoritative: zero-configuration fallback for unlisted non-loopback LAN origins is disabled. If you access the server through both a reverse proxy and direct LAN IP in a browser, include both in allowed_origins.

Model Synchronization & Auto-Updates

Lemonade supports manual model synchronization via lemonade update-models as well as automatic background updates.

Configuration

• Global Config: Set auto_update_models: true in server configuration or via lemonade config set auto_update_models=true.
• Per-Model Override: Include "auto_update": true or "auto_update": false in custom model recipes (user.*) to override the global default on a per-model basis.
• Administrative Authorization: Because model synchronization endpoints are administrative (/internal/*), manual synchronization via the CLI or direct API requests requires the appropriate admin credentials (LEMONADE_ADMIN_API_KEY, falling back to LEMONADE_API_KEY if the admin key is not explicitly configured) when server-side authentication is enabled.

Risks of Automatic Model Updates

Remote Server Connection

To make Lemonade Server accessible from other machines on your network, set the host to 0.0.0.0:

lemonade config set host=0.0.0.0

Warning: Using host: "0.0.0.0" allows connections from any machine on the network — including to the internal control endpoints (/internal/*, e.g. shutdown and config). Only do this on trusted networks, and set an API key to manage access. LEMONADE_API_KEY secures all endpoints; LEMONADE_ADMIN_API_KEY on its own secures only /internal/* and leaves the inference and model-management endpoints (/api, /v0, /v1) open, so set LEMONADE_API_KEY to protect those too. The server logs a warning at startup when bound to a non-loopback host without the regular key.

Next Steps

The Server Specification provides more information about how to integrate Lemonade Server into an application.