Compute Screener
Free compute prices: GPU rental indices, compute futures and AI token prices, with daily history.
我该使用它吗
质量与安全性
A
发现（3）
- HIGHTool poisoning patterns detected
- MEDIUMTool description contains URL to non-standard domain在 get_gpu_prices 中
- MEDIUMTool description contains URL to non-standard domain在 get_gpu_market_prices 中
基于对工具定义和协议合规性的自动分析。
上下文开销
~6,896token 数（工具定义）
~4.2 KB典型响应大小
对注意力有显著影响（占 128k 上下文窗口的 5.39%）
这是每次将服务器的工具加载到模型上下文窗口时所消耗的大致 token 数。数值越高，可用于其他任务的注意力就越少。
安装
一键安装
将以下内容添加到你的 `claude_desktop_config.json` 文件中：
{
"mcpServers": {
"compute-screener": {
"url": "https://computescreener.com/mcp"
}
}
}远程端点
https://computescreener.com/mcpstreamable-http它能做什么
工具清单
工具（14）
🟢 只读🟡 写入🔴 删除⚪ 未知
🟢get_gpu_prices(gpu)
Today's GPU rental prices: the price index in USD per GPU-hour for each GPU (H100, H200, A100, B200, B300, RTX PRO 6000), with 1-day, 1-week and 1-month changes, the index day and a link to each GPU's page. Give one GPU to also get what its page shows: its benchmark contract, each provider's average price standardized to that contract, the posted prices of providers outside the index (AWS, Azure, Google Cloud, Oracle, Koyeb, Packet: each one's lowest, as posted) and its compute futures prices: each exchange listing a contract on its rental price, with the last price and 24-hour volume, read within the last minute (all of them: https://computescreener.com/futures). For past values use get_price_history; for providers' posted prices get_provider_prices.
输入模式
{
"type": "object",
"properties": {
"gpu": {
"type": "string",
"enum": [
"H100",
"H200",
"A100",
"B200",
"B300",
"RTX PRO 6000"
],
"description": "One GPU; omit for all listed GPUs."
}
},
"additionalProperties": false
}输出模式
{
"type": "object",
"properties": {
"unit": {
"type": [
"string",
"null"
]
},
"updated": {
"type": [
"string",
"null"
],
"description": "When the GPU prices were last calculated (ISO 8601, UTC)"
},
"gpus": {
"type": [
"array",
"null"
],
"items": {
"type": [
"object",
"null"
],
"properties": {
"gpu": {
"type": [
"string",
"null"
]
},
"price": {
"type": [
"number",
"null"
],
"description": "Latest index value, USD per GPU-hour"
},
"date": {
"type": [
"string",
"null"
],
"description": "The index day (US Central)"
},
"provisional": {
"type": [
"boolean",
"null"
],
"description": "True while the day is not over"
},
"change_1d_pct": {
"type": [
"number",
"null"
],
"description": "Percent change from the value 1 day earlier"
},
"change_1w_pct": {
"type": [
"number",
"null"
],
"description": "Percent change from the value 7 days earlier"
},
"change_1m_pct": {
"type": [
"number",
"null"
],
"description": "Percent change from the value 30 days earlier"
},
"providers": {
"type": [
"integer",
"null"
],
"description": "Providers in the index"
},
"url": {
"type": [
"string",
"null"
],
"description": "The GPU's page"
},
"note": {
"type": [
"string",
"null"
]
},
"benchmark_contract": {
"type": [
"string",
"null"
]
},
"provider_averages": {
"type": [
"array",
"null"
],
"items": {
"type": [
"object",
"null"
],
"required": [
"provider"
],
"properties": {
"provider": {
"type": [
"string",
"null"
]
},
"average_price": {
"type": [
"number",
"null"
],
"description": "Its average price, standardized to the benchmark contract"
},
"carried_from": {
"type": [
"string",
"null"
],
"description": "Not priced today: the day of its last reading"
},
"read_at": {
"type": [
"string",
"null"
],
"description": "When its prices were last read"
},
"source_url": {
"type": [
"string",
"null"
],
"description": "Where its prices were read"
}
}
}
},
"markets": {
"type": [
"array",
"null"
],
"items": {
"type": [
"object",
"null"
],
"required": [
"venue",
"contract"
],
"properties": {
"venue": {
"type": [
"string",
"null"
]
},
"contract": {
"type": [
"string",
"null"
]
},
"status": {
"type": [
"string",
"null"
]
},
"price": {
"type": [
"number",
"null"
],
"description": "The exchange's last price; none once its exchange has not refreshed it for 12 hours, as on the site"
},
"volume_24h_usd": {
"type": [
"number",
"null"
]
},
"note": {
"type": [
"string",
"null"
],
"description": "A contract not trading yet: its status, as the futures page shows it"
}
}
}
},
"other_posted_prices": {
"type": [
"array",
"null"
],
"description": "Providers outside the index (the hyperscalers): each one's lowest on-demand price per GPU-hour as posted, not standardized, and not in the index",
"items": {
"type": [
"object",
"null"
],
"required": [
"provider",
"lowest_price"
],
"properties": {
"provider": {
"type": [
"string",
"null"
]
},
"lowest_price": {
"type": [
"number",
"null"
]
},
"memory_gb": {
"type": [
"number",
"null"
]
}
}
}
}
},
"required": [
"gpu",
"price"
]
}
},
"methodology": {
"type": [
"string",
"null"
]
},
"sources": {
"type": [
"string",
"null"
]
},
"license": {
"type": [
"string",
"null"
]
}
},
"required": [
"unit",
"updated",
"gpus"
]
}🟢get_token_prices(company)
Today's AI token prices by company: each company's price index in USD per 1M tokens (3 input : 1 output blend, weighted by its models' usage), with 1-day, 1-week and 1-month changes. Give one company to also get its models' usage shares and posted input and output prices. For one model's prices use get_model_prices; for past values get_price_history.
输入模式
{
"type": "object",
"properties": {
"company": {
"type": "string",
"enum": [
"Anthropic",
"OpenAI",
"Google",
"xAI",
"Meta",
"Moonshot AI",
"Alibaba",
"DeepSeek",
"Z.ai",
"Xiaomi"
],
"description": "One company; omit for all listed companies."
}
},
"additionalProperties": false
}输出模式
{
"type": "object",
"properties": {
"unit": {
"type": [
"string",
"null"
]
},
"updated": {
"type": [
"string",
"null"
],
"description": "When the token prices were last calculated (ISO 8601, UTC)"
},
"companies": {
"type": [
"array",
"null"
],
"items": {
"type": [
"object",
"null"
],
"properties": {
"company": {
"type": [
"string",
"null"
]
},
"price": {
"type": [
"number",
"null"
],
"description": "Latest index value, USD per 1M tokens (3 input : 1 output)"
},
"date": {
"type": [
"string",
"null"
],
"description": "The index day (UTC)"
},
"change_1d_pct": {
"type": [
"number",
"null"
],
"description": "Percent change from the value 1 day earlier"
},
"change_1w_pct": {
"type": [
"number",
"null"
],
"description": "Percent change from the value 7 days earlier"
},
"change_1m_pct": {
"type": [
"number",
"null"
],
"description": "Percent change from the value 30 days earlier"
},
"url": {
"type": [
"string",
"null"
],
"description": "The company's page"
},
"note": {
"type": [
"string",
"null"
]
},
"models": {
"type": [
"array",
"null"
],
"items": {
"type": [
"object",
"null"
],
"required": [
"model"
],
"properties": {
"model": {
"type": [
"string",
"null"
]
},
"usage_share": {
"type": [
"number",
"null"
],
"description": "Share of the company's tokens that day (0 to 1)"
},
"input_price": {
"type": [
"number",
"null"
]
},
"output_price": {
"type": [
"number",
"null"
]
},
"blended_price": {
"type": [
"number",
"null"
]
}
}
}
}
},
"required": [
"company",
"price"
]
}
},
"methodology": {
"type": [
"string",
"null"
]
},
"sources": {
"type": [
"string",
"null"
]
},
"license": {
"type": [
"string",
"null"
]
}
},
"required": [
"unit",
"updated",
"companies"
]
}🟢get_price_history(name, days)
Price history of one GPU (USD per GPU-hour) or one AI company (USD per 1M tokens), oldest first. GPU history is daily from 2025-11-07 for H100 and A100 and from 2026-10-23 for the others, weekly before; token history is daily from 2025-01-01.
输入模式
{
"type": "object",
"properties": {
"name": {
"type": "string",
"enum": [
"H100",
"H200",
"A100",
"B200",
"B300",
"RTX PRO 6000",
"Anthropic",
"OpenAI",
"Google",
"xAI",
"Meta",
"Moonshot AI",
"Alibaba",
"DeepSeek",
"Z.ai",
"Xiaomi"
],
"description": "A GPU or an AI company."
},
"days": {
"type": "integer",
"minimum": 1,
"maximum": 1000,
"default": 30,
"description": "How many days back from the latest value."
}
},
"required": [
"name"
],
"additionalProperties": false
}输出模式
{
"type": "object",
"properties": {
"name": {
"type": [
"string",
"null"
]
},
"kind": {
"type": [
"string",
"null"
],
"enum": [
"gpu",
"company",
null
]
},
"unit": {
"type": [
"string",
"null"
]
},
"url": {
"type": [
"string",
"null"
]
},
"points": {
"type": [
"array",
"null"
],
"items": {
"type": [
"object",
"null"
],
"required": [
"date",
"price"
],
"properties": {
"date": {
"type": [
"string",
"null"
]
},
"price": {
"type": [
"number",
"null"
]
},
"provisional": {
"type": [
"boolean",
"null"
]
}
}
}
},
"sources": {
"type": [
"string",
"null"
]
},
"license": {
"type": [
"string",
"null"
]
}
},
"required": [
"name",
"kind",
"unit",
"points"
]
}🟢get_model_prices(model, company)
Each AI model's posted API prices in USD per 1M input and output tokens and their blend (the models behind the token index, each with its page), with its usage share and its 1-month change. Give a model (name or page id, e.g. "Claude Opus 5.5" or "kimi-k3") for its daily price history as its page's chart draws it, or a company to list its models.
输入模式
{
"type": "object",
"properties": {
"model": {
"type": "string",
"description": "A model's name or page id; omit to list models."
},
"company": {
"type": "string",
"enum": [
"Anthropic",
"OpenAI",
"Google",
"xAI",
"Meta",
"Moonshot AI",
"Alibaba",
"DeepSeek",
"Z.ai",
"Xiaomi"
],
"description": "List only this company's models."
}
},
"additionalProperties": false
}输出模式
{
"type": "object",
"properties": {
"unit": {
"type": [
"string",
"null"
]
},
"updated": {
"type": [
"string",
"null"
]
},
"models": {
"type": [
"array",
"null"
],
"items": {
"type": [
"object",
"null"
],
"required": [
"model",
"company"
],
"properties": {
"model": {
"type": [
"string",
"null"
]
},
"company": {
"type": [
"string",
"null"
]
},
"date": {
"type": [
"string",
"null"
]
},
"input_price": {
"type": [
"number",
"null"
],
"description": "Posted USD per 1M input tokens"
},
"output_price": {
"type": [
"number",
"null"
],
"description": "Posted USD per 1M output tokens"
},
"blended_price": {
"type": [
"number",
"null"
],
"description": "3 input : 1 output, USD per 1M tokens"
},
"usage_share": {
"type": [
"number",
"null"
],
"description": "Share of the company's tokens that day (0 to 1)"
},
"change_1m_pct": {
"type": [
"number",
"null"
],
"description": "Blended price change over 1 month, percent (its page's 1M)"
},
"url": {
"type": [
"string",
"null"
]
},
"history": {
"type": [
"array",
"null"
],
"items": {
"type": [
"object",
"null"
],
"properties": {
"date": {
"type": [
"string",
"null"
]
},
"blended_price": {
"type": [
"number",
"null"
]
}
}
}
}
}
}
},
"sources": {
"type": [
"string",
"null"
]
},
"license": {
"type": [
"string",
"null"
]
}
},
"required": [
"unit",
"models"
]
}🟢get_provider_prices(provider, gpu)
Each GPU cloud's and marketplace's posted on-demand prices per GPU, as its page on the site shows them (lowest and highest that day, as posted, with the configuration of the lowest) and its average in the index, standardized to the GPU's benchmark contract so providers compare like for like. Give a provider (e.g. "CoreWeave", "RunPod") and/or a GPU.
输入模式
{
"type": "object",
"properties": {
"provider": {
"type": "string",
"description": "A provider's name or page id; omit for all providers."
},
"gpu": {
"type": "string",
"enum": [
"H100",
"H200",
"A100",
"B200",
"B300",
"RTX PRO 6000"
],
"description": "Only this GPU."
}
},
"additionalProperties": false
}输出模式
{
"type": "object",
"properties": {
"unit": {
"type": [
"string",
"null"
]
},
"updated": {
"type": [
"string",
"null"
]
},
"providers": {
"type": [
"array",
"null"
],
"items": {
"type": [
"object",
"null"
],
"required": [
"provider"
],
"properties": {
"provider": {
"type": [
"string",
"null"
]
},
"url": {
"type": [
"string",
"null"
]
},
"gpus": {
"type": [
"array",
"null"
],
"items": {
"type": [
"object",
"null"
],
"required": [
"gpu"
],
"properties": {
"gpu": {
"type": [
"string",
"null"
]
},
"day": {
"type": [
"string",
"null"
]
},
"offers": {
"type": [
"integer",
"null"
]
},
"low_price": {
"type": [
"number",
"null"
],
"description": "Lowest posted price that day, USD per GPU-hour, as posted"
},
"high_price": {
"type": [
"number",
"null"
],
"description": "Highest posted price that day, USD per GPU-hour, as posted"
},
"variant": {
"type": [
"string",
"null"
]
},
"memory_gb": {
"type": [
"number",
"null"
]
},
"gpus_per_node": {
"type": [
"number",
"null"
]
},
"country": {
"type": [
"string",
"null"
]
},
"index_average": {
"type": [
"number",
"null"
],
"description": "This provider's average in the index, standardized to the benchmark contract"
},
"read_at": {
"type": [
"string",
"null"
],
"description": "When its prices were last read"
},
"source_url": {
"type": [
"string",
"null"
],
"description": "Where its prices were read"
}
}
}
}
}
}
},
"note": {
"type": [
"string",
"null"
]
},
"license": {
"type": [
"string",
"null"
]
}
},
"required": [
"providers"
]
}🟢get_price_changes(days)
What moved, as the site's changes show it: every listed GPU and company index's change over 1, 5, 7 or 30 days (the site's 1D, 5D, 1W and 1M), largest first, and every AI model whose price (its 3 input : 1 output blend, as its page charts it) moved over that time.
输入模式
{
"type": "object",
"properties": {
"days": {
"type": "integer",
"enum": [
1,
5,
7,
30
],
"default": 7,
"description": "How many days back: 1, 5, 7 or 30."
}
},
"additionalProperties": false
}输出模式
{
"type": "object",
"properties": {
"days": {
"type": [
"integer",
"null"
]
},
"index_moves": {
"type": [
"array",
"null"
],
"items": {
"type": [
"object",
"null"
],
"required": [
"name",
"kind"
],
"properties": {
"name": {
"type": [
"string",
"null"
]
},
"kind": {
"type": [
"string",
"null"
],
"enum": [
"gpu",
"company",
null
]
},
"change_pct": {
"type": [
"number",
"null"
]
},
"from_date": {
"type": [
"string",
"null"
]
},
"from_value": {
"type": [
"number",
"null"
]
},
"to_date": {
"type": [
"string",
"null"
]
},
"to_value": {
"type": [
"number",
"null"
]
},
"unit": {
"type": [
"string",
"null"
]
},
"url": {
"type": [
"string",
"null"
]
}
}
}
},
"model_price_changes": {
"type": [
"array",
"null"
],
"description": "Each model whose blended price (3 input : 1 output) moved, as its page's chart and changes show it",
"items": {
"type": [
"object",
"null"
],
"required": [
"model"
],
"properties": {
"model": {
"type": [
"string",
"null"
]
},
"company": {
"type": [
"string",
"null"
]
},
"change_pct": {
"type": [
"number",
"null"
]
},
"from_date": {
"type": [
"string",
"null"
]
},
"from_value": {
"type": [
"number",
"null"
]
},
"to_date": {
"type": [
"string",
"null"
]
},
"to_value": {
"type": [
"number",
"null"
]
},
"unit": {
"type": [
"string",
"null"
]
},
"url": {
"type": [
"string",
"null"
]
}
}
}
},
"license": {
"type": [
"string",
"null"
]
}
},
"required": [
"index_moves",
"model_price_changes"
]
}🟢get_gpu_market_prices(gpu)
Rental prices of every other GPU, as the site's Every GPU page lists them (https://computescreener.com/gpus): RTX 5090, RTX 4090, RTX 6000 Ada, L40, A40, L4, GH200, V100 and over 60 more, each one's lowest and median price per GPU-hour today as posted (offers that can be rented now), its offers, how many are in stock, its providers and the cheapest, from RunPod, Vast.ai, Akash, Shadeform's catalog of clouds, Lium, Vultr, AWS, Azure, Google Cloud, Oracle, Akamai, Koyeb and Packet. Not an index: configurations are not standardized (the GPUs with a price index are in get_gpu_prices).
输入模式
{
"type": "object",
"properties": {
"gpu": {
"type": "string",
"description": "A GPU model, e.g. \"RTX 5090\" or \"A40\"; omit for all."
}
},
"additionalProperties": false
}输出模式
{
"type": "object",
"properties": {
"unit": {
"type": [
"string",
"null"
]
},
"updated": {
"type": [
"string",
"null"
]
},
"gpus": {
"type": [
"array",
"null"
],
"items": {
"type": [
"object",
"null"
],
"required": [
"gpu"
],
"properties": {
"gpu": {
"type": [
"string",
"null"
]
},
"date": {
"type": [
"string",
"null"
]
},
"low": {
"type": [
"number",
"null"
],
"description": "Lowest posted price per GPU-hour today"
},
"median": {
"type": [
"number",
"null"
]
},
"offers": {
"type": [
"integer",
"null"
]
},
"in_stock": {
"type": [
"integer",
"null"
]
},
"providers": {
"type": [
"array",
"null"
],
"items": {
"type": [
"string",
"null"
]
}
},
"cheapest": {
"type": [
"string",
"null"
]
}
}
}
},
"about": {
"type": [
"string",
"null"
]
},
"license": {
"type": [
"string",
"null"
]
}
},
"required": [
"gpus"
]
}🟢get_gpu_price_at(gpu, at)
A GPU's index price at a past date or time, as its page's chart draws it: the value calculated at or just before an ISO time within the last few days (the 1D and 5D charts; prices are recalculated every minute, kept at least every 30 minutes), else the daily value of that US Central day.
输入模式
{
"type": "object",
"properties": {
"gpu": {
"type": "string",
"enum": [
"H100",
"H200",
"A100",
"B200",
"B300",
"RTX PRO 6000"
],
"description": "The GPU."
},
"at": {
"type": "string",
"pattern": "^\\d{4}-\\d{2}-\\d{2}([T ][0-9:.]+(Z|[+-]\\d{2}:?\\d{2})?)?$",
"description": "A date (2026-10-20) or an ISO time (2026-10-26T15:00:00Z)."
}
},
"required": [
"gpu",
"at"
],
"additionalProperties": false
}输出模式
{
"type": "object",
"properties": {
"gpu": {
"type": [
"string",
"null"
]
},
"requested": {
"type": [
"string",
"null"
]
},
"price": {
"type": [
"number",
"null"
]
},
"as_of": {
"type": [
"string",
"null"
]
},
"kind": {
"type": [
"string",
"null"
],
"enum": [
"intraday",
"daily",
"weekly",
null
]
},
"provisional": {
"type": [
"boolean",
"null"
]
},
"unit": {
"type": [
"string",
"null"
]
},
"note": {
"type": [
"string",
"null"
]
},
"url": {
"type": [
"string",
"null"
]
}
},
"required": [
"gpu",
"requested",
"price",
"as_of",
"kind"
]
}🟢get_workload_cost(gpu, model, company, throughput_tokens_per_second)
Break-even throughput, as each GPU's and each model's page shows it: the tokens per second one GPU must sell at a model's posted price (3 input : 1 output blend) to cover the GPU's rental price today. Give a GPU for every model on it, a model for every GPU, or a company for its models; give a throughput for what the gross margin calculator on a model's page shows: the revenue per GPU-hour and the gross margin.
输入模式
{
"type": "object",
"properties": {
"gpu": {
"type": "string",
"enum": [
"H100",
"H200",
"A100",
"B200",
"B300",
"RTX PRO 6000"
],
"description": "One GPU; omit for all listed."
},
"model": {
"type": "string",
"description": "A model's name or page id (e.g. \"Claude Opus 5.5\"); omit for every model."
},
"company": {
"type": "string",
"enum": [
"Anthropic",
"OpenAI",
"Google",
"xAI",
"Meta",
"Moonshot AI",
"Alibaba",
"DeepSeek",
"Z.ai",
"Xiaomi"
],
"description": "Only this company's models."
},
"throughput_tokens_per_second": {
"type": "number",
"minimum": 1,
"maximum": 10000000,
"description": "Tokens per second one GPU generates (input and output, 3 to 1)."
}
},
"additionalProperties": false
}输出模式
{
"type": "object",
"properties": {
"throughput_tokens_per_second": {
"type": [
"number",
"null"
]
},
"rows": {
"type": [
"array",
"null"
],
"items": {
"type": [
"object",
"null"
],
"required": [
"gpu",
"model"
],
"properties": {
"gpu": {
"type": [
"string",
"null"
]
},
"rental_price": {
"type": [
"number",
"null"
],
"description": "The GPU's index, USD per GPU-hour"
},
"model": {
"type": [
"string",
"null"
]
},
"company": {
"type": [
"string",
"null"
]
},
"blended_price": {
"type": [
"number",
"null"
],
"description": "The model's posted price, 3 input : 1 output, USD per 1M tokens"
},
"breakeven_tokens_per_second": {
"type": [
"number",
"null"
],
"description": "Tokens per second one GPU must sell at the blended price to cover its rental"
},
"revenue_per_gpu_hour": {
"type": [
"number",
"null"
],
"description": "At the given throughput, as the gross margin calculator"
},
"gross_margin_pct": {
"type": [
"number",
"null"
],
"description": "At the given throughput, as the gross margin calculator"
}
}
}
},
"note": {
"type": [
"string",
"null"
]
},
"methodology": {
"type": [
"string",
"null"
]
},
"license": {
"type": [
"string",
"null"
]
}
},
"required": [
"rows"
]
}🟢list_indices
Every GPU rental index and AI company token index the site lists: whether it is listed (has a price and a month of history), its latest value and day, when its history starts, its provider or model count, its benchmark contract (GPUs) and its page, and the GPUs on the Every GPU page. Use it to see what the other tools accept.
输入模式
{
"type": "object",
"properties": {},
"additionalProperties": false
}输出模式
{
"type": "object",
"properties": {
"gpus": {
"type": [
"array",
"null"
],
"items": {
"type": [
"object",
"null"
],
"required": [
"name",
"kind",
"listed"
],
"properties": {
"name": {
"type": [
"string",
"null"
]
},
"kind": {
"type": [
"string",
"null"
],
"enum": [
"gpu",
"company",
null
]
},
"listed": {
"type": [
"boolean",
"null"
],
"description": "Shown on the site and by get_gpu_prices / get_token_prices: has a price and a month of history"
},
"price": {
"type": [
"number",
"null"
]
},
"date": {
"type": [
"string",
"null"
]
},
"provisional": {
"type": [
"boolean",
"null"
]
},
"history_from": {
"type": [
"string",
"null"
],
"description": "First day with a value (the start of its page's chart)"
},
"providers": {
"type": [
"integer",
"null"
]
},
"models": {
"type": [
"integer",
"null"
]
},
"benchmark_contract": {
"type": [
"string",
"null"
]
},
"url": {
"type": [
"string",
"null"
]
},
"note": {
"type": [
"string",
"null"
]
}
}
}
},
"companies": {
"type": [
"array",
"null"
],
"items": {
"type": [
"object",
"null"
],
"required": [
"name",
"kind",
"listed"
],
"properties": {
"name": {
"type": [
"string",
"null"
]
},
"kind": {
"type": [
"string",
"null"
],
"enum": [
"gpu",
"company",
null
]
},
"listed": {
"type": [
"boolean",
"null"
],
"description": "Shown on the site and by get_gpu_prices / get_token_prices: has a price and a month of history"
},
"price": {
"type": [
"number",
"null"
]
},
"date": {
"type": [
"string",
"null"
]
},
"provisional": {
"type": [
"boolean",
"null"
]
},
"history_from": {
"type": [
"string",
"null"
],
"description": "First day with a value (the start of its page's chart)"
},
"providers": {
"type": [
"integer",
"null"
]
},
"models": {
"type": [
"integer",
"null"
]
},
"benchmark_contract": {
"type": [
"string",
"null"
]
},
"url": {
"type": [
"string",
"null"
]
},
"note": {
"type": [
"string",
"null"
]
}
}
}
},
"other_gpus": {
"type": [
"array",
"null"
],
"items": {
"type": [
"string",
"null"
]
},
"description": "The GPUs on the Every GPU page, priced as posted by get_gpu_market_prices (not indices)"
},
"units": {
"type": [
"object",
"null"
],
"properties": {
"gpu": {
"type": [
"string",
"null"
]
},
"company": {
"type": [
"string",
"null"
]
}
}
},
"methodology": {
"type": [
"string",
"null"
]
},
"license": {
"type": [
"string",
"null"
]
}
},
"required": [
"gpus",
"companies"
]
}🟢verify_price(name, date)
How a published daily value can be checked: whether it is final, and for a final day its manifest (every file it was computed from with its SHA-256, the factors in force, the calculation code's SHA-256 and the final values) and the command that recomputes it from the public files with the published code. Omit date for the latest day with a manifest.
输入模式
{
"type": "object",
"properties": {
"name": {
"type": "string",
"enum": [
"H100",
"H200",
"A100",
"B200",
"B300",
"RTX PRO 6000",
"Anthropic",
"OpenAI",
"Google",
"xAI",
"Meta",
"Moonshot AI",
"Alibaba",
"DeepSeek",
"Z.ai",
"Xiaomi"
],
"description": "A GPU or an AI company."
},
"date": {
"type": "string",
"pattern": "^\\d{4}-\\d{2}-\\d{2}$",
"description": "The index day, YYYY-MM-DD (US Central for GPUs, UTC for companies)."
}
},
"required": [
"name"
],
"additionalProperties": false
}输出模式
{
"type": "object",
"properties": {
"name": {
"type": [
"string",
"null"
]
},
"kind": {
"type": [
"string",
"null"
],
"enum": [
"gpu",
"company",
null
]
},
"date": {
"type": [
"string",
"null"
]
},
"unit": {
"type": [
"string",
"null"
]
},
"published": {
"type": [
"number",
"null"
],
"description": "The value as published for that day"
},
"status": {
"type": [
"string",
"null"
],
"enum": [
"verifiable",
"provisional",
"pending",
"rebuilt_history",
"no_value",
null
],
"description": "verifiable: final, with a manifest; provisional: the day is not over; pending: final, its manifest comes with the next update; rebuilt_history: before manifests began; no_value: nothing published that day"
},
"explanation": {
"type": [
"string",
"null"
]
},
"manifest": {
"type": [
"object",
"null"
],
"properties": {
"id": {
"type": [
"string",
"null"
],
"description": "SHA-256 of the manifest's contents"
},
"url": {
"type": [
"string",
"null"
]
},
"created": {
"type": [
"string",
"null"
]
},
"value": {
"type": [
"number",
"null"
]
},
"matches_published": {
"type": [
"boolean",
"null"
]
},
"methodology_version": {
"type": [
"string",
"null"
]
},
"files": {
"type": [
"array",
"null"
],
"items": {
"type": [
"object",
"null"
],
"required": [
"path",
"sha256"
],
"properties": {
"path": {
"type": [
"string",
"null"
]
},
"role": {
"type": [
"string",
"null"
]
},
"sha256": {
"type": [
"string",
"null"
]
},
"url": {
"type": [
"string",
"null"
]
}
}
}
},
"factors": {
"type": [
"object",
"null"
],
"properties": {
"calibrated_on": {
"type": [
"string",
"null"
]
},
"sha256": {
"type": [
"string",
"null"
]
}
}
},
"code_files": {
"type": [
"object",
"null"
],
"additionalProperties": {
"type": [
"string",
"null"
]
},
"description": "SHA-256 of each calculation file"
}
}
},
"recompute": {
"type": [
"object",
"null"
],
"properties": {
"command": {
"type": [
"string",
"null"
]
},
"verifier": {
"type": [
"string",
"null"
]
},
"daily_results": {
"type": [
"string",
"null"
]
}
}
},
"methodology": {
"type": [
"string",
"null"
]
}
},
"required": [
"name",
"kind",
"date",
"status",
"explanation"
]
}🟢get_data_status
How fresh the data is, as the status page shows it: when the GPU and token indices were last calculated, today's index day, each GPU price source's status and last read, each GPU index's status, provider count and imputed share, and the latest days with a manifest.
输入模式
{
"type": "object",
"properties": {},
"additionalProperties": false
}输出模式
{
"type": "object",
"properties": {
"gpu_index": {
"type": [
"object",
"null"
],
"properties": {
"updated": {
"type": [
"string",
"null"
]
},
"age_minutes": {
"type": [
"number",
"null"
]
},
"live": {
"type": [
"boolean",
"null"
],
"description": "Recalculated every minute"
},
"day": {
"type": [
"string",
"null"
]
},
"provisional": {
"type": [
"boolean",
"null"
]
},
"sources_ok": {
"type": [
"integer",
"null"
]
},
"sources_total": {
"type": [
"integer",
"null"
]
},
"sources": {
"type": [
"array",
"null"
],
"items": {
"type": [
"object",
"null"
],
"required": [
"source"
],
"properties": {
"source": {
"type": [
"string",
"null"
]
},
"ok": {
"type": [
"boolean",
"null"
]
},
"last_read": {
"type": [
"string",
"null"
]
},
"every_minutes": {
"type": [
"number",
"null"
]
},
"prices": {
"type": [
"number",
"null"
]
},
"error": {
"type": [
"string",
"null"
]
}
}
}
},
"gpus": {
"type": [
"array",
"null"
],
"items": {
"type": [
"object",
"null"
],
"required": [
"gpu"
],
"properties": {
"gpu": {
"type": [
"string",
"null"
]
},
"status": {
"type": [
"string",
"null"
]
},
"providers": {
"type": [
"integer",
"null"
]
},
"imputed_share": {
"type": [
"number",
"null"
]
}
}
}
}
}
},
"token_index": {
"type": [
"object",
"null"
],
"properties": {
"updated": {
"type": [
"string",
"null"
]
},
"age_hours": {
"type": [
"number",
"null"
]
},
"day": {
"type": [
"string",
"null"
]
},
"rankings_as_of": {
"type": [
"string",
"null"
]
}
}
},
"manifests": {
"type": [
"object",
"null"
],
"properties": {
"gpu_latest": {
"type": [
"string",
"null"
]
},
"tokens_latest": {
"type": [
"string",
"null"
]
},
"url": {
"type": [
"string",
"null"
]
}
}
},
"verifier": {
"type": [
"string",
"null"
]
},
"methodology": {
"type": [
"string",
"null"
]
}
},
"required": [
"gpu_index",
"token_index"
]
}🟢search(query)
Search Compute Screener's GPUs, AI companies, AI models, GPU providers and methodology by keyword (e.g. "H100", "Claude Opus", "CoreWeave", "benchmark contract"). Returns ids for fetch.
输入模式
{
"type": "object",
"properties": {
"query": {
"type": "string",
"description": "Keywords."
}
},
"required": [
"query"
],
"additionalProperties": false
}输出模式
{
"type": "object",
"properties": {
"results": {
"type": [
"array",
"null"
],
"items": {
"type": [
"object",
"null"
],
"required": [
"id",
"title",
"url"
],
"properties": {
"id": {
"type": [
"string",
"null"
]
},
"title": {
"type": [
"string",
"null"
]
},
"url": {
"type": [
"string",
"null"
]
}
}
}
}
},
"required": [
"results"
]
}🟢fetch(id)
The full text of a result from search, by its id (gpu:H100, company:OpenAI, model:<page>, provider:<page>, page:methodology, page:futures, page:verification): prices, changes, history, providers or models, as on the site.
输入模式
{
"type": "object",
"properties": {
"id": {
"type": "string",
"description": "An id from search."
}
},
"required": [
"id"
],
"additionalProperties": false
}输出模式
{
"type": "object",
"properties": {
"id": {
"type": [
"string",
"null"
]
},
"title": {
"type": [
"string",
"null"
]
},
"text": {
"type": [
"string",
"null"
]
},
"url": {
"type": [
"string",
"null"
]
},
"metadata": {
"type": [
"object",
"null"
]
}
},
"required": [
"id",
"title",
"text",
"url"
]
}社区
证据
最近观测
已验证未记录版本14 个工具