AICostBudget AI API Pricing
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": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| get_model_priceA | Find a model by ID or display name and return source-linked prices. |
| list_modelsB | List source-linked models, optionally filtering by provider and maximum token prices. |
| estimate_monthly_costB | Estimate monthly token cost from request volume, with optional cached-input and batch pricing. |
| compare_modelsB | Compare monthly costs for multiple models and sort them from lowest to highest total. |
| price_changesB | List up to 20 newest source-linked price-change events. |
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 5 tools
Each tool targets a distinct operation: listing models, looking up a price, estimating cost, comparing costs, and tracking price changes. compare_models and estimate_monthly_cost both compute costs, but their inputs (multiple models vs. request volume) and outputs are clearly differentiated.
Four of five names follow a verb_noun snake_case pattern (compare_models, estimate_monthly_cost, get_model_price, list_models); price_changes is a noun phrase but still readable and consistent in casing.
5 tools is well-scoped for a pricing data server; each tool covers a distinct capability (list, get, estimate, compare, change history) without redundancy.
Core lifecycle for pricing data (list, get, estimate, compare, change history) is covered. Minor gaps include no batch estimation across different request volumes or provider-specific metadata beyond price filtering.