Skip to main content
Glama

TANDIU AI infrastructure data

GPU prices and specs

list_gpu_prices
Read-onlyIdempotent

Data-center, workstation and consumer GPUs (B300/B200/H200/H100/H20, Ascend 910B/910C/950DT (950DT figures indicative, from a circulated China Mobile test report), RTX PRO 6000/5500/5000, RTX 5090/5090D/4090D, L40S/L20): VRAM, bandwidth, FP16 compute, list price, China market price (SXM GPUs per 8-GPU node), cloud rental with 7-day change and daily median history (since 2026-10-18; few_samples flags thin markets), sources and dates. Rental comes from vast.ai; data-center GPUs include multi-GPU machines normalised per GPU; RTX 5090D/4090D have no rental (not listed on that market) and RTX 4090 is rental-only. Trend page: /en/gpu-rental.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "list_gpu_prices"
  }
}

Input Schema

NameRequiredDescriptionDefault
queryNogpu id or name substring, e.g. h20, rtx pro 6000, 910
with_cloud_rentalNo
china_available_onlyNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

B3.3/5.0
Behavior4/5

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

Annotations already declare readOnlyHint, idempotentHint and openWorldHint=false, so the safety profile is covered; the description adds genuine behavior beyond that — data provenance (vast.ai for rentals, a circulated China Mobile test report for 950DT), the indicative nature of those figures, per-GPU normalization of multi-GPU machines, thin-sample flagging, and history start date of 2026-10-18. Gaps remain around pagination and response shape, but the caveats are unusually substantive.

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

Conciseness3/5

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

The dense model-number catalog (B300/B200/H200/H100/H20, Ascend 910B/910C/950DT, RTX PRO 6000/5500/5000, etc.) is partially useful for choosing query substrings but consumes most of the text, and the definition is not front-loaded with a purpose statement. The caveats about 5090D/4090D rental coverage do earn their place; the trailing URL does not.

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

Completeness3/5

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

With three optional parameters, no output schema and low schema coverage, the description does well on data content and provenance but leaves the agent guessing on the two undocumented booleans and on result structure. For a zero-required-parameter listing tool it is close to sufficient, but not complete.

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 33% — only query is documented — so the description must compensate and does so only partially: it implies that cloud rental and China pricing are data dimensions the boolean flags likely gate, but never states defaults or what happens when they are false/omitted. The example substrings ("h20, rtx pro 6000, 910") in the schema and the model list in the description together give reasonable query semantics.

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

Purpose4/5

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

The description enumerates exactly what data the tool covers for GPUs — VRAM, bandwidth, FP16 compute, list price, China market price, cloud rental with 7-day change and median history, sources and dates — which is unambiguous about the resource. However, it never states the verb explicitly ("list/returns") and does not distinguish itself from the sibling list_llm_prices, leaving the agent to infer the CPU/LLM split from the name alone.

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

Usage Guidelines2/5

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

There is no when-to-use guidance at all: nothing says whether to call this before estimate_self_hosting or cheapest_model_for_score, nor when to set with_cloud_rental or china_available_only. The only routing hint is the trailing "/en/gpu-rental" trend page, which points away from the tool rather than explaining when to invoke it.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources