AI Rate Card

most_expensive_models_by_task

Read-only

The n most expensive MODELS for a job (task): each model counted once at its own lowest current price, highest first - the top of the market. Same arguments as cheapest_models_by_task.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "task": "<task>"
    },
    "name": "most_expensive_models_by_task"
  }
}

Input Schema

Name	Required	Description
`n`	No	10 by default
`task`	Yes	what the buyer wants done: text (chat/LLM), vision, image, video, tts (speech from text), stt (text from speech), embedding, rerank, moderation - a job, not a model type (search_offers' category is the model type)
`scope`	No	all (default), specialized (the task's own category) or multi/universal (qualifying llm models - the two names mean the same set, WP-0086)
`component`	No	input_tokens (default), output_tokens, or the task's own unit

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedNov 5, 2026

changedInput schema / properties / task / enum

Previous value: -[
-  "embedding",
-  "image",
-  "moderation",
-  "rerank",
-  "stt",
-  "text",
-  "tts",
-  "video",
-  "vision"
-]New value: +[
+  "decision",
+  "embedding",
+  "image",
+  "moderation",
+  "rerank",
+  "stt",
+  "text",
+  "tts",
+  "video",
+  "vision"
+]

AddedNov 4, 2026

TDQS

A4.1/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Beyond readOnlyHint=true, the description discloses two non-obvious behaviors: deduplication ('each model counted once') and price basis ('its own lowest current price'), plus sort direction. It does not mention result truncation, empty-result behavior, or what fields come back, but the annotations already cover the safety profile.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, front-loaded with the core purpose and the ranking semantics, with no filler. 'The top of the market' is a cheap gloss but reinforces intent rather than wasting space.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a read-only ranked-list tool with a fully described schema and no output schema, the description covers selection logic, dedup, and ordering. Only return-format and pagination/edge-case behavior are left unstated, which is minor here.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so all four parameters are already documented, including the enum values for task, scope, and component. The description adds only the ranking meaning of n and the 'job, not model type' framing already present in the schema; baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific resource (MODELS) with a precise verb phrase ('the n most expensive ... for a job (task)') and a ranking rule ('highest first'). It also separates itself from the offers-oriented siblings by stressing that models, not offers, are returned ('each model counted once').

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Names cheapest_models_by_task as the paired alternative and states its arguments are the same, which lets an agent route between the two ends of the market. It gives no explicit exclusions or conditions beyond 'top of the market', so it stops short of full when/when-not guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All AI Rate Card tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?