FX Reference Rates

by dev.workers.regnotes.fx-reference-rates

ai_llm_prices

Read-only

LLM API pricing lookup: USD per 1M input, output and cached-input tokens plus context window for ~3,300 models (OpenAI GPT, Anthropic Claude, Google Gemini, DeepSeek, Llama, Mistral, Qwen, xAI ...) across providers (direct, Azure, Bedrock, Vertex, Together, Fireworks ...). Filter by model and provider; sorted by input price. Price: $0.005 USDC per request (fixed; one paid HTTP GET = one charge; x402 exact on Base or MPP on Tempo; 4xx errors are not charged).

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": {
      "model": "<model>"
    },
    "name": "ai_llm_prices"
  }
}

Input Schema

Name	Required	Description
`limit`	No	1-100, default 25
`model`	Yes	Model name substring, e.g. gpt-5, claude-sonnet, gemini-2.5
`provider`	No	Provider substring, e.g. openai, anthropic, bedrock

Schema Changelog

Changes observed during successful MCP inspections.

AddedOct 25, 2026

TDQS

A4.4/5.0

Behavior5/5

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

Beyond the readOnlyHint annotation, the description discloses the paid-call model in detail: $0.005 USDC per request, one paid HTTP GET equals one charge, x402 on Base or MPP on Tempo, and 4xx errors are not charged. It also discloses result ordering, which is behavior an agent needs to interpret a limited result set.

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?

Front-loaded with the purpose and return fields, with the cost/transport details relegated to a trailing parenthetical. The provider and model enumeration is long but earns its place by signaling coverage; slightly denser than necessary but no filler sentences.

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

Completeness5/5

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

There is no output schema, and the description compensates by naming the returned fields (input, output, cached-input prices plus context window) and the sort order. Combined with the explicit payment terms and error-charging rule, an agent has everything needed to call it correctly and predict the cost.

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 description coverage is 100%, so model substring, provider substring, and the limit range are already fully documented, which sets the baseline at 3. The description adds only the sort key (input price) and reinforces that model and provider act as filters; it adds no new per-parameter syntax or defaults beyond the schema.

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 verb and resource ("LLM API pricing lookup") plus exactly what is returned (USD per 1M input, output and cached-input tokens, context window) over a quantified corpus (~3,300 models). The scope is unmistakably distinct from the sibling ai_gpu_prices and the rates/macro tools, so an agent can route without opening the schema.

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?

"Filter by model and provider; sorted by input price" tells the agent how to drive the tool, and the enumerated model/provider families clarify the domain of applicability. It never explicitly names ai_gpu_prices as the alternative for GPU pricing or states exclusions, 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 FX Reference Rates 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?