Every change Wellknown observed on this MCP server, newest first, with what it was before and what it became. Tool-surface changes carry the definition diff. Nothing here is edited after the fact.
Added "gpu_rentals", "list_gpus" and "self_host_or_api" (5 tools before, 8 now)
Rental offers for one GPU, by tier — Rental offers for one GPU type: provider, price in USD per GPU per hour, number of GPUs in the published configuration, billing and region when published. One block per tier (guaranteed, community, spot), each with its own cheapest offer, also given per configuration (cheapest_by_gpu_count: the price per GPU of a single GPU and of a multi-GPU node are not comparable); tiers are never compared with each other. guaranteed: capacity the provider presents as not interrupted; community: third-party hosts; spot: interruptible capacity. Prices are as published by the provider, and dated. Get the GPU…
GPU types tracked for rental prices — GPU types whose rental price InferIndex tracks (H100, A100, L40S…), with the lowest price per GPU per hour in USD for each tier (guaranteed, community, spot) and the number of GPUs of that configuration. Prices are per GPU per hour, as published by each provider, and dated. Tiers are different products and are never compared with each other.
Self-host an open model or use the API? — Is it cheaper to host an open-weights model yourself on rented GPUs, or to use the cheapest API offer? Returns a one-sentence verdict (headline) and the numbers behind it: the break-even volume in million tokens per day, the throughput the whole configuration must deliver for self-hosting to cost less (required_tokens_per_second: compare it with what your setup does), the break-even utilization when a throughput is known, the GPU configuration and its hourly price, and what the verdict rests on (confidence). Without a volume you still get the verdict and the break-even volume. It is an estima…
Changed the definition of "cheapest", "compare_providers" and "estimate_cost"
⟨58 unchanged words⟩ per request and per month. Returns the winner in detail and one short line per following offer. A condition that is absent was not published by thefirstprovider,offers.it never means "no"; a flag not listed in signals is false.
⟨20 unchanged words⟩ "minimum":0,"type":"number"},"detail":{"description":"compact (default): the winner in detail and one short line per other offer (provider, prices, signals, training on prompts when published). full: every field of every offer (all published conditions, reliability), much longer","enum":["compact","full"],"type":"string"},"include_tiers":{"description":"Also include lower-priority service
Certificate recorded, valid to 2026-12-17
Authorization not required
Unknown → Live
First tool surface recorded: 5 tools (server version 1.0.0)
https://mcp.inferindex.dev/mcp (mcp_streamable_http) — from mcp_registry, with the record
Showing the latest 7 events. The API returns up to 500 and filters by kind: ?kind=tool_surface_changed
⟨17 unchanged words⟩ first (10 by default), with price,context,quantization,publishedsignalsconditionsand(training on prompts when published; the cheapest offer comes in detail. Pass detail: "full" for context, every published condition (data regions, sign-up) and reliability from official statuspages.pages on each offer.
⟨20 unchanged words⟩ "minimum":0,"type":"number"},"detail":{"description":"compact (default): the winner in detail and one short line per other offer (provider, prices, signals, training on prompts when published). full: every field of every offer (all published conditions, reliability), much longer","enum":["compact","full"],"type":"string"},"include_tiers":{"description":"Also include lower-priority service ⟨10 unchanged words⟩ :{"description":"Number of offers to return, cheapest included (default 10, max 50)","maximum": ⟨40 unchanged words⟩ :"Only providers with open sign-up (no waitlist, invitation orinvitationcountry restriction)","type":"boolean"},"output_tokens": ⟨102 unchanged words⟩
⟨30 unchanged words⟩ account. Offers sorted by estimated cost, cheapestfirst.first: the cheapest in detail, then one short line per offer with its estimated cost.
⟨20 unchanged words⟩ "minimum":0,"type":"number"},"detail":{"description":"compact (default): the winner in detail and one short line per other offer (provider, prices, signals, training on prompts when published). full: every field of every offer (all published conditions, reliability), much longer","enum":["compact","full"],"type":"string"},"limit":{"description":"Number of offers to return, cheapest included (default 5, max 25)","maximum" ⟨69 unchanged words⟩