ai-api-prices
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.
Read-only AI API standard list prices in USD from AISelect.online, updated daily (caching, batch, and volume discounts excluded; providers without published prices are omitted). Use find_models to look up names, model_prices for every provider of one model, estimate_monthly_cost for a monthly workload bill, compare_models for two models side by side, and cheapest_models for category lows.
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 |
|---|---|
| find_modelsA | Search AI API models by name across text (LLMs), image, video, transcription, tts, search, and embedding categories, returning up to 10 matches with each model's cheapest USD price and provider. Exact slug or prefix matches rank first, then widely sold models. Use model_prices to list every provider for a matched model, or cheapest_models to browse lowest prices in a category. |
| model_pricesA | List standard USD list prices for one AI model at every priced provider, ordered cheapest first (including size or quality variants for media). Returns input, output, and cached token prices for text LLMs (unit rate otherwise) plus each provider's pricing page URL; unpriced providers are omitted. Use find_models if unsure of the name, compare_models for two models, or estimate_monthly_cost for a monthly bill. |
| estimate_monthly_costA | Estimate a monthly workload bill in USD across every priced provider for one model, ordered cheapest first (standard list prices only; excludes caching, batch, and volume discounts; unpriced providers are omitted). For text LLMs pass input_million_tokens and/or output_million_tokens; for all other categories pass units. Use model_prices for raw per-unit rates or compare_models for a two-model headline comparison. |
| compare_modelsA | Compare two AI models in USD by each model's cheapest priced provider (3 input : 1 output blended per 1M tokens for text LLMs, unit rate otherwise) and provider counts. Optional category scopes both model lookups; cross-category pairs display both prices without a price ratio. Use model_prices for every provider of one model or cheapest_models for category lows. |
| cheapest_modelsA | List the cheapest AI models in a category in USD ranked by lowest provider price, returning up to limit models (default 10). Only priced models appear; text LLMs require at least two priced providers so one-off listings do not crowd the ranking. Use find_models to search by name or model_prices to inspect every provider for one model. |
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 has a distinct output shape: name search, per-model provider price list, monthly bill estimate, two-model comparison, and category-wide cheapest ranking. The main potential confusion is between model_prices and cheapest_models since both list prices, but the descriptions clearly delineate per-model vs. per-category and explicitly cross-reference alternatives.
find_models, estimate_monthly_cost, and compare_models follow a verb_noun pattern, while model_prices and cheapest_models are noun phrases. The deviation is minor and all names are readable and domain-appropriate, so an agent can still infer behavior from the name alone.
Five tools is a tight, well-scoped set for a price-discovery server, with search, detail, comparison, ranking, and estimation each earning its place. It is slightly thin (no provider or category listing tool), but not problematically so.
The surface covers the core price-research lifecycle: discover a model, inspect all provider prices, compare two models, find category lows, and project a monthly bill. Minor gaps exist, such as no tool to enumerate provider names or categories directly, but agents can work around this via search results.