MCP-Server
GPU Economy - cloud GPU prices
io.github.laserodds21/gpu-prices
Was dieses MCP kann
Provides current cloud GPU rental prices, provider comparisons, historical price changes, and H100 price-index data.
Funktionen
Tools
16
Tools
buy_vs_rent
Buy or rent a GPU
A card's new retail price (median of 3+ sellers) against its live on-demand rental rates: months of rental, at the cheapest rate card and at the median, that equal the purchase price, at 100%, 70%, 50% and 25% of a 730-hour month. Rental fee only - power, hosting, the server around the card and resale are not counted. Without gpu, every card that has a retail median.
Nur Lesen
Eingabeschema
{'type': 'object', 'properties': {'gpu': {'type': 'string', 'description': 'GPU id or name, e.g. rtx-4090; omit for every card with a retail median.'}}, 'additionalProperties': False}
Ausgabeschema
{'type': 'object', 'required': ['data_updated_at', 'attribution', 'cite_as'], 'properties': {'gpu': {}, 'page': {}, 'cards': {}, 'gpu_id': {}, 'cite_as': {'type': 'string', 'description': 'How to cite this answer: GPU Economy, the page, the data date.'}, 'attribution': {'type': 'string'}, 'not_counted': {}, 'data_updated_at': {'type': 'string', 'description': 'Newest scrape behind the answer (ISO 8601).'}, 'hours_per_month': {}}}
commitment_savings
What a 1- or 3-year commitment saves
Committed and spot rates for one GPU (or every GPU) set against the same provider's own on-demand rate for the same card, region and price scope - the pairs behind the site's typical discount - with the median per term across every card. A commitment is paid whether the GPU runs or not.
Nur Lesen
Eingabeschema
{'type': 'object', 'properties': {'gpu': {'type': 'string', 'description': 'Optional GPU id or name; without it, every card.'}, 'term': {'enum': ['any', 'reserved_1y', 'reserved_3y', 'spot'], 'type': 'string', 'description': 'Which market to pair; default any (1-year, 3-year and spot).'}, 'limit': {'type': 'integer', 'maximum': 50, 'minimum': 1, 'description': 'Pairs to return, largest saving first; default 15.'}}, 'additionalProperties': False}
Ausgabeschema
{'type': 'object', 'required': ['data_updated_at', 'attribution', 'cite_as'], 'properties': {'gpu': {}, 'note': {}, 'page': {}, 'term': {}, 'pairs': {}, 'method': {}, 'cite_as': {'type': 'string', 'description': 'How to cite this answer: GPU Economy, the page, the data date.'}, 'attribution': {'type': 'string'}, 'pairs_found': {}, 'data_updated_at': {'type': 'string', 'description': 'Newest scrape behind the answer (ISO 8601).'}, 'typical_by_term': {}}}
compare_gpus
Compare two GPUs
Two GPU models side by side: VRAM, median rate card and panel size, cheapest on-demand rate, price per GB of VRAM, retail median where one exists, and every provider that lists both on-demand with the signed difference. Live quotes only.
Nur Lesen
Eingabeschema
{'type': 'object', 'required': ['a', 'b'], 'properties': {'a': {'type': 'string', 'description': 'First GPU id or name (h100-sxm, "H200").'}, 'b': {'type': 'string', 'description': 'Second GPU id or name.'}}, 'additionalProperties': False}
Ausgabeschema
{'type': 'object', 'required': ['data_updated_at', 'attribution', 'cite_as'], 'properties': {'a': {}, 'b': {}, 'both': {}, 'note': {}, 'cite_as': {'type': 'string', 'description': 'How to cite this answer: GPU Economy, the page, the data date.'}, 'attribution': {'type': 'string'}, 'difference_is': {}, 'data_updated_at': {'type': 'string', 'description': 'Newest scrape behind the answer (ISO 8601).'}, 'providers_listing_both': {}}}
compare_providers
Compare two providers
Two providers on every GPU both list on-demand today: each side's cheapest on-demand rate card, the difference and which is lower, and the count. Community capacity and marketplace floors are left out of the comparison. Live quotes only.
Nur Lesen
Eingabeschema
{'type': 'object', 'required': ['a', 'b'], 'properties': {'a': {'type': 'string', 'description': 'First provider id or name (runpod, lambda, "Google Cloud").'}, 'b': {'type': 'string', 'description': 'Second provider id or name.'}}, 'additionalProperties': False}
Ausgabeschema
{'type': 'object', 'required': ['data_updated_at', 'attribution', 'cite_as'], 'properties': {'a': {}, 'b': {}, 'gpus': {}, 'note': {}, 'page': {}, 'cite_as': {'type': 'string', 'description': 'How to cite this answer: GPU Economy, the page, the data date.'}, 'lower_on': {}, 'attribution': {'type': 'string'}, 'gpus_compared': {}, 'data_updated_at': {'type': 'string', 'description': 'Newest scrape behind the answer (ISO 8601).'}}}
estimate_cost
Estimate what a workload costs
What N GPUs of one model cost for a number of hours at listed rates: at each of the cheapest rate cards and at the median rate card, with the arithmetic. Rental fee only - storage, network egress, taxes and idle time are not counted - and listed rates, not availability.
Nur Lesen
Eingabeschema
{'type': 'object', 'required': ['gpu'], 'properties': {'gpu': {'type': 'string', 'description': 'GPU id or name.'}, 'gpus': {'type': 'integer', 'maximum': 100000, 'minimum': 1, 'description': 'How many GPUs; default 1.'}, 'hours': {'type': 'number', 'maximum': 100000, 'minimum': 1, 'description': 'Hours of use; default 730 (a month around the clock).'}, 'limit': {'type': 'integer', 'maximum': 20, 'minimum': 1, 'description': 'Cheapest rate cards to price; default 5.'}, 'market': {'enum': ['on_demand', 'spot', 'community', 'shared', 'serverless', 'reserved', 'reserved_1y', 'reserved_3y'], 'type': 'string', 'description': 'Market; default on_demand.'}, 'region': {'enum': ['any', 'US', 'EU'], 'type': 'string', 'description': "Rates listed in US or EU regions, plus rates that name no region (a provider's rate everywhere); default any."}}, 'additionalProperties': False}
Ausgabeschema
{'type': 'object', 'required': ['data_updated_at', 'attribution', 'cite_as'], 'properties': {'gpu': {}, 'gpus': {}, 'page': {}, 'hours': {}, 'gpu_id': {}, 'market': {}, 'region': {}, 'cite_as': {'type': 'string', 'description': 'How to cite this answer: GPU Economy, the page, the data date.'}, 'at_median': {}, 'arithmetic': {}, 'at_cheapest': {}, 'attribution': {'type': 'string'}, 'buy_instead': {}, 'not_counted': {}, 'data_updated_at': {'type': 'string', 'description': 'Newest scrape behind the answer (ISO 8601).'}}}
fetch
Read a GPU Economy page
The text of one GPU Economy page by an id from search (gpu:h100-sxm, provider:runpod, index:h100, reserved, buy-vs-rent): its live rates with read times, as plain text, with the page URL to cite.
Nur Lesen
Eingabeschema
{'type': 'object', 'required': ['id'], 'properties': {'id': {'type': 'string', 'description': 'An id from search.'}}, 'additionalProperties': False}
Ausgabeschema
{'type': 'object', 'required': ['id', 'title', 'text', 'url'], 'properties': {'id': {'type': 'string'}, 'url': {'type': 'string'}, 'text': {'type': 'string'}, 'title': {'type': 'string'}, 'metadata': {'type': 'object'}}}
find_gpus
Find GPUs that meet a requirement
GPU models that meet a memory and price requirement, cheapest first: for each card its cheapest live on-demand rate card (provider, read time, page), its median rate card and panel size, VRAM and price per GB of VRAM. Community capacity and marketplace floors are out unless the market is set.
Nur Lesen
Eingabeschema
{'type': 'object', 'properties': {'limit': {'type': 'integer', 'maximum': 50, 'minimum': 1, 'description': 'Cards to return; default 10.'}, 'market': {'enum': ['on_demand', 'spot', 'community', 'shared', 'serverless', 'reserved', 'reserved_1y', 'reserved_3y'], 'type': 'string', 'description': 'Market of the cheapest rate; default on_demand.'}, 'region': {'enum': ['any', 'US', 'EU'], 'type': 'string', 'description': "Rates listed in US or EU regions, plus rates that name no region (a provider's rate everywhere); default any."}, 'vendor': {'enum': ['any', 'nvidia', 'amd'], 'type': 'string', 'description': 'Default any.'}, 'min_vram_gb': {'type': 'number', 'minimum': 0, 'description': 'Least memory per GPU, in GB (24, 48, 80, 141...). Default 0.'}, 'max_usd_per_gpu_hour': {'type': 'number', 'minimum': 0, 'description': "Highest acceptable rate per GPU-hour, compared with each card's cheapest rate. Optional."}}, 'additionalProperties': False}
Ausgabeschema
{'type': 'object', 'required': ['data_updated_at', 'attribution', 'cite_as'], 'properties': {'gpus': {}, 'note': {}, 'cite_as': {'type': 'string', 'description': 'How to cite this answer: GPU Economy, the page, the data date.'}, 'attribution': {'type': 'string'}, 'requirement': {}, 'cards_matching': {}, 'data_updated_at': {'type': 'string', 'description': 'Newest scrape behind the answer (ISO 8601).'}}}
gpu_prices
Current prices for one GPU
Current listed rental prices for one GPU model across providers, cheapest first, in USD per GPU-hour, each with the time it was read and the GPU Economy page that links its source. Live quotes only.
Nur Lesen
Eingabeschema
{'type': 'object', 'required': ['gpu'], 'properties': {'gpu': {'type': 'string', 'description': 'GPU id (h100-sxm, h200, b200, rtx-4090) or a name ("H100 SXM", "RTX 4090").'}, 'limit': {'type': 'integer', 'maximum': 50, 'minimum': 1, 'description': 'Rows to return, cheapest first; default 10.'}, 'market': {'enum': ['any', 'on_demand', 'spot', 'community', 'shared', 'serverless', 'reserved', 'reserved_1y', 'reserved_3y'], 'type': 'string', 'description': 'Market to keep; default on_demand. "any" keeps spot, community, serverless and reserved too.'}, 'region': {'enum': ['any', 'US', 'EU'], 'type': 'string', 'description': "Rates listed in US or EU regions, plus rates that name no region (a provider's rate everywhere); default any."}}, 'additionalProperties': False}
Ausgabeschema
{'type': 'object', 'required': ['data_updated_at', 'attribution', 'cite_as'], 'properties': {'gpu': {}, 'note': {}, 'page': {}, 'gpu_id': {}, 'market': {}, 'prices': {}, 'quotes': {}, 'region': {}, 'cite_as': {'type': 'string', 'description': 'How to cite this answer: GPU Economy, the page, the data date.'}, 'attribution': {'type': 'string'}, 'data_updated_at': {'type': 'string', 'description': 'Newest scrape behind the answer (ISO 8601).'}}}
list_gpus
List GPU models
Every GPU model tracked, with its id, VRAM, how many providers list it and the median on-demand rate card in USD per GPU-hour.
Nur Lesen
Eingabeschema
{'type': 'object', 'properties': {}, 'additionalProperties': False}
Ausgabeschema
{'type': 'object', 'required': ['data_updated_at', 'attribution', 'cite_as'], 'properties': {'gpus': {}, 'count': {}, 'cite_as': {'type': 'string', 'description': 'How to cite this answer: GPU Economy, the page, the data date.'}, 'attribution': {'type': 'string'}, 'data_updated_at': {'type': 'string', 'description': 'Newest scrape behind the answer (ISO 8601).'}}}
price_history
Weekly price history of one GPU
Weekly median and cheapest listed on-demand rate for one GPU model, newest week first, from two sources kept apart: our own hourly reads, and a series reconstructed from a public price catalog (second-hand). Each week carries its panel size; read a median against it.
Nur Lesen
Eingabeschema
{'type': 'object', 'required': ['gpu'], 'properties': {'gpu': {'type': 'string', 'description': 'GPU id or name.'}, 'weeks': {'type': 'integer', 'maximum': 120, 'minimum': 1, 'description': 'Weeks per source, newest first; default 12.'}}, 'additionalProperties': False}
Ausgabeschema
{'type': 'object', 'required': ['data_updated_at', 'attribution', 'cite_as'], 'properties': {'gpu': {}, 'note': {}, 'page': {}, 'gpu_id': {}, 'series': {}, 'cite_as': {'type': 'string', 'description': 'How to cite this answer: GPU Economy, the page, the data date.'}, 'attribution': {'type': 'string'}, 'data_updated_at': {'type': 'string', 'description': 'Newest scrape behind the answer (ISO 8601).'}}}
price_index
Cloud GPU Price Index (H100)
The Cloud GPU Price Index: median listed on-demand H100 SXM rate across providers, this week and the last eight weeks, with the base-100 index and the receipts; also the newest hourly point and the monthly averages over a fixed panel.
Nur Lesen
Eingabeschema
{'type': 'object', 'properties': {'window': {'enum': ['week', 'hour', 'month'], 'type': 'string', 'description': 'Which window leads the answer; default week. Every answer carries the newest value of each.'}}, 'additionalProperties': False}
Ausgabeschema
{'type': 'object', 'required': ['data_updated_at', 'attribution', 'cite_as'], 'properties': {'hour': {}, 'name': {}, 'page': {}, 'method': {}, 'months': {}, 'series': {}, 'window': {}, 'cite_as': {'type': 'string', 'description': 'How to cite this answer: GPU Economy, the page, the data date.'}, 'current': {}, 'receipts': {}, 'attribution': {'type': 'string'}, 'data_updated_at': {'type': 'string', 'description': 'Newest scrape behind the answer (ISO 8601).'}}}
provider_info
What a provider is and how it is read
One provider: its type (hyperscaler, specialist GPU cloud or marketplace), the regions or tiers it names, how GPU Economy reads its prices (pricing page, API or rendered page), how many GPU models and live quotes it has, a one-line note for a reader, and its cheapest on-demand rate per card. Links its GPU Economy page.
Nur Lesen
Eingabeschema
{'type': 'object', 'required': ['provider'], 'properties': {'provider': {'type': 'string', 'description': 'Provider id or name (runpod, "Google Cloud", vast-ai).'}}, 'additionalProperties': False}
Ausgabeschema
{'type': 'object', 'required': ['data_updated_at', 'attribution', 'cite_as'], 'properties': {'note': {}, 'page': {}, 'read': {}, 'type': {}, 'cite_as': {'type': 'string', 'description': 'How to cite this answer: GPU Economy, the page, the data date.'}, 'markets': {}, 'provider': {}, 'attribution': {'type': 'string'}, 'live_quotes': {}, 'provider_id': {}, 'data_updated_at': {'type': 'string', 'description': 'Newest scrape behind the answer (ISO 8601).'}, 'gpu_models_live': {}, 'regions_or_tiers': {}, 'cheapest_on_demand_by_gpu': {}}}
provider_prices
Current prices at one provider
Every current listed rental price at one provider (runpod, lambda, aws, vast-ai, ...), in USD per GPU-hour, each with its read time and the GPU Economy page that links its source. Live quotes only.
Nur Lesen
Eingabeschema
{'type': 'object', 'required': ['provider'], 'properties': {'provider': {'type': 'string', 'description': 'Provider id (runpod, lambda, coreweave, aws, azure, gcp, vast-ai) or its name.'}}, 'additionalProperties': False}
Ausgabeschema
{'type': 'object', 'required': ['data_updated_at', 'attribution', 'cite_as'], 'properties': {'page': {}, 'prices': {}, 'quotes': {}, 'cite_as': {'type': 'string', 'description': 'How to cite this answer: GPU Economy, the page, the data date.'}, 'provider': {}, 'attribution': {'type': 'string'}, 'provider_id': {}, 'data_updated_at': {'type': 'string', 'description': 'Newest scrape behind the answer (ISO 8601).'}}}
recent_price_changes
Recent price changes
Listed prices that changed in the last 30 days, one row per quote, newest change first: the figure before its first change in the window, the figure now, and how many times it changed. A quote back at its starting figure is left out, and so are marketplace floors unless asked for. Optionally for one GPU or one provider.
Nur Lesen
Eingabeschema
{'type': 'object', 'properties': {'gpu': {'type': 'string', 'description': 'Optional GPU id or name.'}, 'limit': {'type': 'integer', 'maximum': 50, 'minimum': 1, 'description': 'Rows; default 20.'}, 'provider': {'type': 'string', 'description': 'Optional provider id or name.'}, 'include_marketplaces': {'type': 'boolean', 'description': 'Also list marketplace floors (Vast.ai), which move with every read; default false.'}}, 'additionalProperties': False}
Ausgabeschema
{'type': 'object', 'required': ['data_updated_at', 'attribution', 'cite_as'], 'properties': {'page': {}, 'window': {}, 'changes': {}, 'cite_as': {'type': 'string', 'description': 'How to cite this answer: GPU Economy, the page, the data date.'}, 'attribution': {'type': 'string'}, 'marketplaces': {}, 'quotes_changed': {}, 'data_updated_at': {'type': 'string', 'description': 'Newest scrape behind the answer (ISO 8601).'}, 'changes_in_window': {}}}
search
Search GPU Economy pages
Find GPU Economy pages for a query - a GPU, a provider, the price index, reserved rates, buy vs rent. Returns ids for fetch, with each page's title and URL.
Nur Lesen
Eingabeschema
{'type': 'object', 'required': ['query'], 'properties': {'query': {'type': 'string', 'description': 'What to look for, e.g. "H100 SXM", "runpod", "reserved H200", "price index".'}}, 'additionalProperties': False}
Ausgabeschema
{'type': 'object', 'required': ['results'], 'properties': {'results': {'type': 'array', 'items': {'type': 'object', 'required': ['id', 'title', 'url'], 'properties': {'id': {'type': 'string'}, 'url': {'type': 'string'}, 'title': {'type': 'string'}}}}}}
token_cost
Cost per million output tokens (modelled)
Modelled, not measured: a listed GPU-hour rate divided by the output throughput NVIDIA published for that card and model, per million output tokens, at the cheapest live on-demand rate card and at the median, with NVIDIA's run (model, framework, precision, sequence, concurrency, date). Cards are not comparable on it - NVIDIA runs each card differently - and an idle GPU costs the same and produces nothing: a floor, never a bill.
Nur Lesen
Eingabeschema
{'type': 'object', 'required': ['gpu'], 'properties': {'gpu': {'type': 'string', 'description': 'GPU id or name; NVIDIA publishes runs for B200, B300, H100 SXM, H200 and RTX PRO 6000.'}, 'model': {'type': 'string', 'description': 'Optional model name to keep (gpt-oss-120b, "Qwen 3.5"); default every model NVIDIA ran on the card.'}}, 'additionalProperties': False}
Ausgabeschema
{'type': 'object', 'required': ['data_updated_at', 'attribution', 'cite_as'], 'properties': {'gpu': {}, 'page': {}, 'runs': {}, 'rates': {}, 'caveat': {}, 'gpu_id': {}, 'cite_as': {'type': 'string', 'description': 'How to cite this answer: GPU Economy, the page, the data date.'}, 'formula': {}, 'modelled': {}, 'attribution': {'type': 'string'}, 'data_updated_at': {'type': 'string', 'description': 'Newest scrape behind the answer (ISO 8601).'}, 'throughput_source': {}}}
Verlauf
Letzte Tool-Änderungen
Hinzugefügt
fetch
2. October 2026 02:40
Hinzugefügt
search
2. October 2026 02:40
Hinzugefügt
buy_vs_rent
2. October 2026 02:40
Hinzugefügt
token_cost
2. October 2026 02:40
Hinzugefügt
provider_info
2. October 2026 02:40
Hinzugefügt
commitment_savings
2. October 2026 02:40
Hinzugefügt
price_history
2. October 2026 02:40
Hinzugefügt
estimate_cost
2. October 2026 02:40
Hinzugefügt
compare_providers
2. October 2026 02:40
Hinzugefügt
compare_gpus
2. October 2026 02:40
Hinzugefügt
find_gpus
2. October 2026 02:40
Geändert
recent_price_changes
2. October 2026 02:40
Geändert
price_index
2. October 2026 02:40
Geändert
provider_prices
2. October 2026 02:40
Geändert
gpu_prices
2. October 2026 02:40
Geändert
list_gpus
2. October 2026 02:40
Hinzugefügt
recent_price_changes
30. September 2026 02:40
Hinzugefügt
price_index
30. September 2026 02:40
Hinzugefügt
provider_prices
30. September 2026 02:40
Hinzugefügt
gpu_prices
30. September 2026 02:40
Hinzugefügt
list_gpus
30. September 2026 02:40
Entdecken
Ähnliche MCP-Server
Algenta MCP Server
io.github.thyn-ai/algenta
Provides governed data onboarding, connector browsing, deterministic simulations, agent-run lifecycles, capability routing, deplo…
Scalix Cloud
world.scalix/cloud
Provides managed databases, SQL tools, container builds, persistent Linux machines, domains, scheduled functions, storage, and pr…
RationalBloks
io.github.rationalbloks/rationalbloks-mcp
Creates, deploys, manages, and searches schema-based REST API projects and Neo4j knowledge graphs across staging and production e…
RationalBloks
com.rationalbloks/mcp
Creates, deploys, manages, and queries REST API and Neo4j graph projects from JSON schemas, including graph data modeling, versio…
Cloudflare Radar
io.github.pipeworx-io/cloudflare-radar
Provides Cloudflare Radar internet observatory data on DDoS attacks, BGP leaks, domain popularity, internet quality, and traffic …
Peeringdb
io.github.pipeworx-io/peeringdb
Provides lookup and identity data for internet peering facilities, networks, and exchange infrastructure from PeeringDB.
Supabase
io.github.mcp-dir/supabase-mcp
Manages Supabase projects, PostgreSQL databases, migrations, branches, storage-related infrastructure, Edge Functions, logs, keys…
corpusAI Cloud Pricing
io.github.JTraversa/corpus-cloud-pricing-mcp
Provides historical and current cloud instance, GPU rental, spot, on-demand, reserved-price, capacity, and pricing-index data.