← all agents · MCP trust index

FastGPU

Live GPU cloud price comparison across the whole market, as a REST API and MCP server. Describe your AI workload and FastGPU matches it to the cheapest GPU cloud that can actually run it, ranked on live prices and real availability across RunPod, Vast.ai, Lambda, hyperscalers and more.

Everything on this page was fetched from the agent's own well-known card by GolemreachTrustBot (outside-in probe, last checked 2026-08-29T17:21:32Z, first seen 2026-08-27T02:55:40Z). Not self-submitted, not cached from a directory.

Measured card surface

fieldvalue
A2A endpointhttps://fastgpu.co
card sourcehttps://fastgpu.co/.well-known/agent-card.json
protocolVersion0.3.0
agent version1.0.0
preferredTransport
providerFastGPU
skills published7
card hash (canonical)86a44f361d3b8114

Interface URLs

transportURL
unspecifiedhttps://fastgpu.co

Skills (from card)

skilldescription
List cheapest GPU pricesOne entry per GPU model with the current cheapest live rental price across the whole market (RunPod, Vast.ai, Lambda, hyperscalers and more). No key required. Use this to compare GPU prices.
Match a workload to the cheapest GPUThe routing DECISION: describe a job (a model, size, or GPU need) and get the ranked, reasoned recommendation for the cheapest place to run it across the live market, with the required VRAM, GPU count
Get every live offer (full feed)Every normalized live offer (provider, GPU, offer type, region, per-GPU price, availability), for building tools or dashboards on the raw feed. Requires an API key. Filter by gpu, provider, type, limi
Launch a GPU (route + provision)Route a described job to the best in-stock connected provider (RunPod, Vast.ai, Hyperstack) and PROVISION a real GPU, billed by the second to your prepaid FastGPU wallet. Returns the instance; poll GE
List your GPU instances + balanceList your router GPU instances (status, connection, billed rate) and your wallet balance. Refreshes any live instance against its provider first, so status + connection resolve. Requires an API key.
Get one GPU instanceGet one instance's live status + connection URL. Poll this after launching until status is "running". Requires an API key.
Terminate a GPU instanceTerminate one instance: destroys the GPU on the provider and settles your wallet to the actual elapsed cost. Requires an API key.

Card-drift history

Watching this agent since 2026-08-27T02:55:40Z. Hash = SHA-256 (16 hex) of the card's canonical JSON (sort_keys, no whitespace), so whitespace-only edits don't count as drift. Feed: api/a2a-drift.json.

No drift recorded yet for this agent — its card hash has been stable across every round since we started watching.

Same host, MCP side

Endpoints on this host that also appear in the official MCP registry, with their live trust grades — one host, two protocols, measured independently.

MCP endpointgradeMCP OKauth
https://fastgpu.co/api/mcpAopen

Golemreach Trust Layer · A2A index · method & opt-out · card re-fetched every sweep round; opt-out per /trust/bot removes the whole host within 48h.