model-price-radar
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
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 |
|---|---|
| find_modelsA | Search OpenRouter's live catalog by name, capabilities, price ceilings and context size. 'cheapest' ranks by blended price (3 input : 1 output tokens). |
| estimate_costA | Cost of a workload on several models at today's prices, cheapest first. |
| model_price_historyA | Monthly price history of one model since it appeared on OpenRouter (archived copies since 2023) plus today's price. Shows every price change with its % and the overall change. |
| price_changesB | What changed in LLM pricing since a month: biggest price drops and increases, newly free models, and how many models were added or removed. |
| compare_providersA | Same model, different providers: price, context, max output, quantization and recent uptime for every provider that serves it on OpenRouter, cheapest first. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| cheapest_model_for | Pick the cheapest model that can do a job, with cost estimates. |
| monthly_price_report | What changed in LLM pricing recently. |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 5 tools
Each tool targets a distinct question: catalog search, workload cost estimation, per-model price history, market-wide price changes, and provider-level comparison. The descriptions clarify scope, especially between model_price_history (single model over time) and price_changes (market-wide since a month), so misselection is unlikely.
All tool names use snake_case and are descriptive. Three follow a verb_noun pattern (find_models, estimate_cost, compare_providers) while two are noun phrases (model_price_history, price_changes), a minor deviation but still readable and predictable overall.
Five tools is well-scoped for an LLM pricing radar: search, cost estimation, historical tracking, market change detection, and provider comparison. Each tool earns its place without redundancy or thin coverage.
The surface covers the core lifecycle of price discovery: finding models, estimating workload costs, tracking per-model price history, detecting market-wide changes, and comparing providers. No obvious dead ends exist for the stated domain of OpenRouter price monitoring.