cheaplane
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| DELEGATE_LOG | No | Where the savings ledger lives | ~/.cheaplane/usage.jsonl |
| DELEGATE_NO_LOG | No | Set to 1 to disable the ledger entirely | |
| DELEGATE_API_KEY | No | Key for that endpoint | sk-litellm |
| DELEGATE_TIMEOUT | No | Per-call timeout (seconds) | 120 |
| DELEGATE_BASE_URL | No | OpenAI-compatible endpoint (your proxy) | http://localhost:4000 |
| DELEGATE_MODEL_MAP | No | JSON remapping aliases, e.g. {"deepseek":"deepseek-v4-flash"} — overrides defaults, no code edit |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| delegateA | Offload a self-contained subtask to a cheaper model and return its output. WHEN TO USE: hand off replaceable grunt work to save your premium tokens — boilerplate code, small bug fixes, formatting, translation, reading/summarizing long documents, drafting routine copy. Do NOT delegate judgment work (planning, architecture, final review, talking to the user) — keep that for yourself. The delegated model sees ONLY the Args: task: Complete, self-contained instruction for the cheap model. model: "auto" (default) routes by task — code→deepseek, long docs→kimi, Chinese→qwen, multi-step→mimo, quick chores→flash. Or force an alias (deepseek/mimo/flash/kimi/qwen) or a raw proxy model_name. max_tokens: Output cap. Default 4000 (kept large so reasoning models that spend budget on hidden thinking still return non-empty text). Note: a call typically takes ~10-60s (longer for big inputs) and blocks until the cheap model returns, so prefer one focused task per call. Returns: The model's text output, or a string starting with "[delegate-error]" on failure. |
| savingsA | Show what delegating has kept off your premium quota (estimates, list prices). |
| list_modelsA | List the model aliases available to delegate(), with their best use. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 3 tools
Each tool covers a distinct function: performing a delegation, viewing accumulated savings, and listing available models. There is no overlap or ambiguity between them.
delegate and list_models are imperative verbs, but savings is a noun and doesn't follow a verb_noun pattern. The mixed conventions are still readable.
Three tools is lean but well-scoped for a delegation utility: one core action, one supporting reference, and one feedback metric. Each earns its place.
The core delegation workflow is covered: choose a model, delegate, and review savings. A minor gap is the lack of pre-delegation cost estimation or detailed history, but it does not create a dead end.