Server definition
- Hash
- sha256:cc4657b049f248cd6a6138fca39ec6167f73af6b7987470a7531e2336939070d
- What it is
- What a remote MCP server returned when asked what it offers: 5 tools
The blob, as servednamed by its sha256
{
"instructions": null,
"tools": [
{
"description": "Compare cloud compute instance pricing across AWS, Azure, GCP, DigitalOcean, OCI, OVH, and Alibaba. Filter by region, provider, vCPUs, memory, category, processor, or use case. All prices are Linux on-demand list prices in USD. Not every price column is live: `provenance.priceTypes` says which of each provider's price columns come from a live API, which are static constants, and which are unavailable, and `provenance.staticPriceColumns` lists the non-live ones outright. When you report a savings plan or reserved rate that appears there, say that it is a static estimate. IMPORTANT: Report all prices EXACTLY as returned. Do NOT add commentary or recommendations beyond the data.",
"inputSchema": {
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {
"category": {
"description": "Instance category. Must be one of these exactly (case-insensitive): General Purpose, Compute Optimized, Memory Optimized, Storage Optimized, GPU / Accelerated, Burstable. Any other string returns zero matches rather than an error.",
"type": "string"
},
"limit": {
"description": "Max instances to return (default: 20)",
"maximum": 50,
"minimum": 1,
"type": "number"
},
"maxMemory": {
"description": "Maximum memory in GiB",
"type": "number"
},
"maxVCPUs": {
"description": "Maximum number of vCPUs",
"type": "number"
},
"minMemory": {
"description": "Minimum memory in GiB",
"type": "number"
},
"minVCPUs": {
"description": "Minimum number of vCPUs",
"type": "number"
},
"processor": {
"description": "Processor. Matched by exact equality (case-insensitive), so a partial value like 'H100' returns nothing. Known values: Intel, AMD, Graviton, Ampere, NVIDIA A100, NVIDIA H100, NVIDIA L4, NVIDIA T4, NVIDIA V100, NVIDIA Other.",
"type": "string"
},
"provider": {
"description": "Cloud provider. Must be one of these exactly (case-insensitive): AWS, Azure, GCP, DigitalOcean, OCI, OVH, Alibaba. Any other string returns zero matches rather than an error.",
"type": "string"
},
"region": {
"description": "Pricing region: us-east, us-west, europe, asia-pacific. Default: us-east",
"enum": [
"us-east",
"us-west",
"europe",
"asia-pacific"
],
"type": "string"
},
"sortBy": {
"description": "Sort by: price, vcpus, memory, pricePerVCPU. Default: price",
"enum": [
"price",
"vcpus",
"memory",
"pricePerVCPU"
],
"type": "string"
},
"useCase": {
"description": "Use case. Must be one of these exactly (case-insensitive): Web App, Database, HPC, ML & AI, Dev/Test, Big Data. Any other string returns zero matches rather than an error.",
"type": "string"
}
},
"type": "object"
},
"name": "compare-compute-pricing",
"outputSchema": {
"$schema": "https://json-schema.org/draft/2020-12/schema",
"additionalProperties": false,
"properties": {
"catalogSize": {
"type": "number"
},
"error": {
"type": "string"
},
"instances": {
"items": {
"additionalProperties": false,
"properties": {
"category": {
"type": "string"
},
"instanceType": {
"type": "string"
},
"memory": {
"type": "number"
},
"onDemandHourly": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
]
},
"onDemandMonthly": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
]
},
"os": {
"type": "string"
},
"processor": {
"type": "string"
},
"provider": {
"type": "string"
},
"reserved1yr": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
]
},
"reserved3yr": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
]
},
"savingsPlan1yr": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
]
},
"savingsPlan3yr": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
]
},
"spot": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
]
},
"useCases": {
"items": {
"type": "string"
},
"type": "array"
},
"vCPUs": {
"type": "number"
}
},
"required": [
"provider",
"instanceType",
"os",
"vCPUs",
"memory",
"processor",
"category",
"useCases",
"onDemandHourly",
"onDemandMonthly",
"spot",
"savingsPlan1yr",
"savingsPlan3yr",
"reserved1yr",
"reserved3yr"
],
"type": "object"
},
"type": "array"
},
"matchingCount": {
"type": "number"
},
"provenance": {
"additionalProperties": false,
"properties": {
"catalogTotal": {
"type": "number"
},
"catalogueIsSubset": {
"type": "boolean"
},
"dataAsOf": {
"type": "string"
},
"fallbackReason": {
"type": "string"
},
"label": {
"type": "string"
},
"notice": {
"type": "string"
},
"priceTypes": {
"additionalProperties": {
"additionalProperties": {
"type": "string"
},
"propertyNames": {
"type": "string"
},
"type": "object"
},
"propertyNames": {
"type": "string"
},
"type": "object"
},
"region": {
"type": "string"
},
"servedFromCacheAgeMs": {
"type": "number"
},
"source": {
"type": "string"
},
"sourceRegions": {
"additionalProperties": {
"type": "string"
},
"propertyNames": {
"type": "string"
},
"type": "object"
},
"sources": {
"additionalProperties": {
"type": "string"
},
"propertyNames": {
"type": "string"
},
"type": "object"
},
"staticPriceColumns": {
"items": {
"type": "string"
},
"type": "array"
},
"tier": {
"type": "number"
},
"unappliedFilters": {
"items": {
"type": "string"
},
"type": "array"
},
"unavailablePriceColumns": {
"items": {
"type": "string"
},
"type": "array"
},
"upstreamErrors": {
"items": {
"type": "string"
},
"type": "array"
},
"upstreamSchemaVersion": {
"type": "string"
},
"upstreamTimestamp": {
"type": "string"
}
},
"required": [
"tier",
"source",
"label",
"region",
"staticPriceColumns",
"unavailablePriceColumns"
],
"type": "object"
},
"source": {
"type": "string"
}
},
"required": [
"instances",
"matchingCount",
"catalogSize",
"source"
],
"type": "object"
}
},
{
"description": "Browse and filter the whole LLM catalogue and get back a ranked table: price, quality (ELO), efficiency and capabilities. Use this when the user wants to SEE THE FIELD — 'show me models under $1/1M', 'which providers have vision models', 'list open-weight models above ELO 1300'. For a single PICK under a budget use recommend-llm-model; to weigh 2-4 NAMED models against each other use compare-models-side-by-side. Prices come from optimtoken.optimnow.io where reachable; the response's `provenance` says which tier served them and whether they are vendor-verified. Filter by provider, price tier (category), openness, capability, price range, or minimum ELO score. Optionally enrich with business metrics for a use case. Price tier and openness are independent: a model can be Frontier-priced and open-weight at once. Reports both list-price cost and the optimized cost achievable with prompt caching and the batch API. IMPORTANT: Report all prices, costs, and scores EXACTLY as returned. Do NOT add commentary, opinions, or recommendations beyond what the data shows. Present the results as a table and let the user draw conclusions.",
"inputSchema": {
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {
"capability": {
"description": "Capability, matched by exact equality (case-insensitive): Text, Vision, Code, Reasoning, Agents, Image Gen, Audio. Any other string returns zero matches.",
"type": "string"
},
"category": {
"description": "Price tier, matched by exact equality (case-insensitive): Frontier, Mid-tier, Budget, Image. This is cost only — self-hostability is the separate `openness` axis.",
"type": "string"
},
"limit": {
"description": "Max models to return (default: 15)",
"maximum": 50,
"minimum": 1,
"type": "number"
},
"maxInputPrice": {
"description": "Max input price per 1M tokens in USD",
"type": "number"
},
"maxOutputPrice": {
"description": "Max output price per 1M tokens in USD",
"type": "number"
},
"minElo": {
"description": "Minimum Chatbot Arena ELO score. Typical range 1000-1500; ~1400 is roughly frontier-class. Models with no ELO score never satisfy this.",
"exclusiveMinimum": 0,
"type": "number"
},
"openness": {
"description": "Filter by self-hostability, derived from the licence: Open source, Open weights, Proprietary, Unknown",
"enum": [
"Open source",
"Open weights",
"Proprietary",
"Unknown"
],
"type": "string"
},
"provider": {
"description": "Filter by provider name (e.g. 'OpenAI', 'Anthropic', 'Google')",
"type": "string"
},
"useCasePreset": {
"description": "Workload shape, which sets tokens per request: supportTicket (1.5k in / 500 out), knowledgeQA (2k / 800), meetingSummary (10k / 1.2k, batch-eligible), marketingContent (2.5k / 1.8k), codingTask (3k / 2k), invoiceProcessing (1.5k / 600, batch-eligible), callSummary (2k / 700, batch-eligible), agentWorkflow (6k / 3k). Default: supportTicket",
"enum": [
"supportTicket",
"knowledgeQA",
"meetingSummary",
"marketingContent",
"codingTask",
"invoiceProcessing",
"callSummary",
"agentWorkflow"
],
"type": "string"
},
"volumePreset": {
"description": "Monthly request volume: 10k, 100k, or 1m. Default: 100k",
"enum": [
"10k",
"100k",
"1m"
],
"type": "string"
}
},
"type": "object"
},
"name": "compare-llm-models",
"outputSchema": {
"$schema": "https://json-schema.org/draft/2020-12/schema",
"additionalProperties": false,
"properties": {
"catalogSize": {
"type": "number"
},
"dataAsOf": {
"type": "string"
},
"eloAsOf": {
"type": "string"
},
"error": {
"type": "string"
},
"finopsBadge": {
"additionalProperties": false,
"properties": {
"maxBlendedPrice": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
]
},
"minElo": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
]
},
"qualifying": {
"type": "number"
},
"ranked": {
"type": "number"
}
},
"required": [
"qualifying",
"ranked",
"minElo",
"maxBlendedPrice"
],
"type": "object"
},
"matchingCount": {
"type": "number"
},
"models": {
"items": {
"additionalProperties": false,
"properties": {
"batchApplied": {
"type": "boolean"
},
"batchEligible": {
"type": "boolean"
},
"batchInputPricePer1M": {
"type": "number"
},
"batchOutputPricePer1M": {
"type": "number"
},
"cacheApplied": {
"type": "boolean"
},
"cacheEligible": {
"type": "boolean"
},
"cachedInputPricePer1M": {
"type": "number"
},
"capabilities": {
"items": {
"type": "string"
},
"type": "array"
},
"category": {
"type": "string"
},
"contextWindow": {
"type": "string"
},
"efficiencyScore": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
]
},
"eloScore": {
"type": "number"
},
"inputPricePer1M": {
"type": "number"
},
"isFinOpsFriendly": {
"type": "boolean"
},
"license": {
"type": "string"
},
"model": {
"type": "string"
},
"monthlyBudget": {
"type": "number"
},
"openness": {
"type": "string"
},
"optimizedMonthlyBudget": {
"type": "number"
},
"optimizedUseCaseCost": {
"type": "number"
},
"outputPricePer1M": {
"type": "number"
},
"parameters": {
"type": "string"
},
"provider": {
"type": "string"
},
"releaseDate": {
"type": "string"
},
"useCaseCost": {
"type": "number"
},
"volatilityRisk": {
"type": "string"
}
},
"required": [
"provider",
"model",
"inputPricePer1M",
"outputPricePer1M",
"contextWindow",
"category",
"capabilities",
"openness",
"efficiencyScore",
"useCaseCost",
"optimizedUseCaseCost",
"monthlyBudget",
"optimizedMonthlyBudget",
"volatilityRisk",
"isFinOpsFriendly",
"batchEligible",
"cacheEligible",
"batchApplied",
"cacheApplied"
],
"type": "object"
},
"type": "array"
},
"provenance": {
"additionalProperties": false,
"properties": {
"catalogTotal": {
"type": "number"
},
"dataAsOf": {
"type": "string"
},
"eloAsOf": {
"type": "string"
},
"label": {
"type": "string"
},
"notice": {
"type": "string"
},
"pricesVerified": {
"type": "boolean"
},
"source": {
"type": "string"
},
"tier": {
"type": "number"
},
"upstreamSchemaVersion": {
"type": "string"
},
"upstreamSource": {
"type": "string"
},
"upstreamTimestamp": {
"type": "string"
}
},
"required": [
"tier",
"source",
"label",
"pricesVerified",
"eloAsOf"
],
"type": "object"
},
"source": {
"type": "string"
},
"useCaseLabel": {
"type": "string"
},
"volumeLabel": {
"type": "string"
}
},
"required": [
"models",
"useCaseLabel",
"volumeLabel",
"source",
"matchingCount",
"catalogSize",
"eloAsOf"
],
"type": "object"
}
},
{
"description": "Compare 2-4 named LLM models against all 8 use-case profiles at a chosen monthly volume, showing list and optimized cost for each. Use when the user names specific models to weigh against each other, rather than filtering the whole catalogue. If they also supply their own token counts, or a volume outside 10k/100k/1m, use estimate-llm-cost instead. Every name is resolved against the catalogue and the result is reported: a name that matched nothing, matched several models, or duplicated an earlier pick is stated explicitly. IMPORTANT: Report all prices and costs EXACTLY as returned, and repeat any name-resolution warning to the user — a missing column is not the same as a model that costs nothing.",
"inputSchema": {
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {
"models": {
"description": "2-4 model names to compare, e.g. ['GPT-4o', 'Claude Opus 5', 'Gemini 3.1 Pro']",
"items": {
"type": "string"
},
"maxItems": 4,
"minItems": 2,
"type": "array"
},
"volumePreset": {
"description": "Monthly request volume: 10k, 100k, or 1m. Default: 100k",
"enum": [
"10k",
"100k",
"1m"
],
"type": "string"
}
},
"required": [
"models"
],
"type": "object"
},
"name": "compare-models-side-by-side",
"outputSchema": {
"$schema": "https://json-schema.org/draft/2020-12/schema",
"additionalProperties": false,
"properties": {
"dataAsOf": {
"type": "string"
},
"eloAsOf": {
"type": "string"
},
"error": {
"type": "string"
},
"models": {
"items": {
"additionalProperties": false,
"properties": {
"batchInputPricePer1M": {
"type": "number"
},
"batchOutputPricePer1M": {
"type": "number"
},
"cachedInputPricePer1M": {
"type": "number"
},
"capabilities": {
"items": {
"type": "string"
},
"type": "array"
},
"category": {
"type": "string"
},
"contextWindow": {
"type": "string"
},
"eloScore": {
"type": "number"
},
"inputPricePer1M": {
"type": "number"
},
"license": {
"type": "string"
},
"model": {
"type": "string"
},
"outputPricePer1M": {
"type": "number"
},
"parameters": {
"type": "string"
},
"provider": {
"type": "string"
},
"releaseDate": {
"type": "string"
},
"useCaseCosts": {
"items": {
"additionalProperties": false,
"properties": {
"batchApplied": {
"type": "boolean"
},
"batchEligible": {
"type": "boolean"
},
"cacheApplied": {
"type": "boolean"
},
"cacheEligible": {
"type": "boolean"
},
"inputTokens": {
"type": "number"
},
"key": {
"type": "string"
},
"label": {
"type": "string"
},
"monthly": {
"type": "number"
},
"monthlyOptimized": {
"type": "number"
},
"outputTokens": {
"type": "number"
},
"perRequest": {
"type": "number"
},
"perRequestOptimized": {
"type": "number"
},
"savingsPct": {
"type": "number"
}
},
"required": [
"key",
"label",
"inputTokens",
"outputTokens",
"perRequest",
"perRequestOptimized",
"monthly",
"monthlyOptimized",
"savingsPct",
"batchEligible",
"cacheEligible",
"batchApplied",
"cacheApplied"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"provider",
"model",
"inputPricePer1M",
"outputPricePer1M",
"contextWindow",
"category",
"capabilities",
"useCaseCosts"
],
"type": "object"
},
"type": "array"
},
"provenance": {
"additionalProperties": false,
"properties": {
"catalogTotal": {
"type": "number"
},
"dataAsOf": {
"type": "string"
},
"eloAsOf": {
"type": "string"
},
"label": {
"type": "string"
},
"notice": {
"type": "string"
},
"pricesVerified": {
"type": "boolean"
},
"source": {
"type": "string"
},
"tier": {
"type": "number"
},
"upstreamSchemaVersion": {
"type": "string"
},
"upstreamSource": {
"type": "string"
},
"upstreamTimestamp": {
"type": "string"
}
},
"required": [
"tier",
"source",
"label",
"pricesVerified",
"eloAsOf"
],
"type": "object"
},
"resolution": {
"items": {
"additionalProperties": false,
"properties": {
"alternatives": {
"items": {
"type": "string"
},
"type": "array"
},
"query": {
"type": "string"
},
"resolved": {
"type": "string"
},
"status": {
"enum": [
"exact",
"unique",
"ambiguous",
"not-found",
"duplicate"
],
"type": "string"
},
"totalMatches": {
"type": "number"
}
},
"required": [
"query",
"status",
"alternatives",
"totalMatches"
],
"type": "object"
},
"type": "array"
},
"source": {
"type": "string"
},
"volume": {
"type": "number"
},
"volumeLabel": {
"type": "string"
}
},
"required": [
"models",
"resolution",
"volume",
"volumeLabel",
"source",
"eloAsOf"
],
"type": "object"
}
},
{
"description": "Cost a workload with EXACT numbers the caller supplies: arbitrary token counts per request and any monthly volume, not just the 10k/100k/1m presets the other cost tools use. Use this for 'about 800 in and 200 out, 4 million calls a month', or to price one named model across every use-case profile. To compare 2-4 named models like for like at a preset volume, use compare-models-side-by-side instead. Provide a model name to get detailed cost breakdowns, or compare costs across all use case presets. Each figure comes twice: list price, and the optimized price achievable with prompt caching and the batch API. IMPORTANT: Report all cost figures EXACTLY as returned. Do NOT add commentary or recommendations beyond the data.",
"inputSchema": {
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {
"customInputTokens": {
"description": "Custom input tokens per request. Must be supplied TOGETHER with customOutputTokens — either alone is ignored and the preset is used. A custom shape assumes no cacheable prefix and no batch eligibility, so its optimized cost equals its list cost.",
"maximum": 10000000,
"minimum": 1,
"type": "integer"
},
"customOutputTokens": {
"description": "Custom output tokens per request. Must be supplied TOGETHER with customInputTokens — either alone is ignored and the preset is used.",
"maximum": 10000000,
"minimum": 1,
"type": "integer"
},
"modelName": {
"description": "Model name, e.g. 'GPT-4o'. A partial name matches up to 5 models and ALL of them are costed. If omitted, the first 8 catalogue entries are used — that is catalogue order, not a quality ranking.",
"type": "string"
},
"monthlyVolume": {
"description": "Exact monthly request count, any integer (default 100,000). This tool does not take the 10k/100k/1m presets the other cost tools use.",
"maximum": 1000000000,
"minimum": 1,
"type": "integer"
},
"useCasePreset": {
"description": "Workload shape, which sets tokens per request: supportTicket (1.5k in / 500 out), knowledgeQA (2k / 800), meetingSummary (10k / 1.2k, batch-eligible), marketingContent (2.5k / 1.8k), codingTask (3k / 2k), invoiceProcessing (1.5k / 600, batch-eligible), callSummary (2k / 700, batch-eligible), agentWorkflow (6k / 3k). Default: every preset.",
"enum": [
"supportTicket",
"knowledgeQA",
"meetingSummary",
"marketingContent",
"codingTask",
"invoiceProcessing",
"callSummary",
"agentWorkflow"
],
"type": "string"
}
},
"type": "object"
},
"name": "estimate-llm-cost",
"outputSchema": {
"$schema": "https://json-schema.org/draft/2020-12/schema",
"additionalProperties": false,
"properties": {
"dataAsOf": {
"type": "string"
},
"eloAsOf": {
"type": "string"
},
"error": {
"type": "string"
},
"modelCosts": {
"items": {
"additionalProperties": false,
"properties": {
"costs": {
"items": {
"additionalProperties": false,
"properties": {
"batchApplied": {
"type": "boolean"
},
"batchEligible": {
"type": "boolean"
},
"cacheApplied": {
"type": "boolean"
},
"cacheEligible": {
"type": "boolean"
},
"inputTokens": {
"type": "number"
},
"monthly": {
"type": "number"
},
"monthlyOptimized": {
"type": "number"
},
"outputTokens": {
"type": "number"
},
"perRequest": {
"type": "number"
},
"perRequestOptimized": {
"type": "number"
},
"savingsPct": {
"type": "number"
},
"useCase": {
"type": "string"
}
},
"required": [
"useCase",
"inputTokens",
"outputTokens",
"perRequest",
"monthly",
"perRequestOptimized",
"monthlyOptimized",
"savingsPct",
"batchEligible",
"cacheEligible",
"batchApplied",
"cacheApplied"
],
"type": "object"
},
"type": "array"
},
"model": {
"additionalProperties": false,
"properties": {
"batchInputPricePer1M": {
"type": "number"
},
"batchOutputPricePer1M": {
"type": "number"
},
"cachedInputPricePer1M": {
"type": "number"
},
"capabilities": {
"items": {
"type": "string"
},
"type": "array"
},
"category": {
"type": "string"
},
"contextWindow": {
"type": "string"
},
"eloScore": {
"type": "number"
},
"inputPricePer1M": {
"type": "number"
},
"license": {
"type": "string"
},
"model": {
"type": "string"
},
"outputPricePer1M": {
"type": "number"
},
"parameters": {
"type": "string"
},
"provider": {
"type": "string"
},
"releaseDate": {
"type": "string"
}
},
"required": [
"provider",
"model",
"inputPricePer1M",
"outputPricePer1M",
"contextWindow",
"category",
"capabilities"
],
"type": "object"
}
},
"required": [
"model",
"costs"
],
"type": "object"
},
"type": "array"
},
"provenance": {
"additionalProperties": false,
"properties": {
"catalogTotal": {
"type": "number"
},
"dataAsOf": {
"type": "string"
},
"eloAsOf": {
"type": "string"
},
"label": {
"type": "string"
},
"notice": {
"type": "string"
},
"pricesVerified": {
"type": "boolean"
},
"source": {
"type": "string"
},
"tier": {
"type": "number"
},
"upstreamSchemaVersion": {
"type": "string"
},
"upstreamSource": {
"type": "string"
},
"upstreamTimestamp": {
"type": "string"
}
},
"required": [
"tier",
"source",
"label",
"pricesVerified",
"eloAsOf"
],
"type": "object"
},
"source": {
"type": "string"
},
"volume": {
"type": "number"
}
},
"required": [
"modelCosts",
"volume",
"source",
"eloAsOf"
],
"type": "object"
}
},
{
"description": "Pick a model. Returns a ranked top 3 for one workload under optional constraints, each with a per-constraint satisfied/violated breakdown as the evidence. Use this when the user wants an ANSWER rather than a table — 'what should I use for support tickets under $500 a month'. To browse or filter the whole catalogue instead, use compare-llm-models. Constraints: (monthly budget, minimum ELO, required capability, self-hostability). Returns a top 3 as structured facts — efficiency rank, ELO, list and optimized cost, FinOps flag, volatility, and a per-constraint satisfied/violated breakdown. When nothing satisfies every constraint the query is reported as over-constrained and the nearest misses are returned instead, each carrying the constraint it failed. IMPORTANT: Report the returned facts EXACTLY. The ranking is already computed — do not re-rank, and do not present a near miss as if it satisfied the constraints.",
"inputSchema": {
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {
"maxMonthlyBudget": {
"description": "Maximum monthly budget in USD at the given volume. Tested against the LIST-price monthly cost, not the caching/batch-optimized cost.",
"exclusiveMinimum": 0,
"type": "number"
},
"minElo": {
"description": "Minimum Chatbot Arena ELO score. Typical range 1000-1500; ~1400 is roughly frontier-class. Models with no ELO score never satisfy this.",
"exclusiveMinimum": 0,
"type": "number"
},
"openness": {
"description": "Require a self-hostability bucket, derived from the licence: Open source, Open weights, Proprietary, Unknown",
"enum": [
"Open source",
"Open weights",
"Proprietary",
"Unknown"
],
"type": "string"
},
"requiredCapability": {
"description": "Capability the model must have: Text, Vision, Code, Reasoning, Agents, Image Gen, Audio",
"type": "string"
},
"useCasePreset": {
"description": "Workload shape, which sets tokens per request: supportTicket (1.5k in / 500 out), knowledgeQA (2k / 800), meetingSummary (10k / 1.2k, batch-eligible), marketingContent (2.5k / 1.8k), codingTask (3k / 2k), invoiceProcessing (1.5k / 600, batch-eligible), callSummary (2k / 700, batch-eligible), agentWorkflow (6k / 3k).",
"enum": [
"supportTicket",
"knowledgeQA",
"meetingSummary",
"marketingContent",
"codingTask",
"invoiceProcessing",
"callSummary",
"agentWorkflow"
],
"type": "string"
},
"volumePreset": {
"description": "Monthly request volume: 10k, 100k, or 1m. Default: 100k",
"enum": [
"10k",
"100k",
"1m"
],
"type": "string"
}
},
"required": [
"useCasePreset"
],
"type": "object"
},
"name": "recommend-llm-model",
"outputSchema": {
"$schema": "https://json-schema.org/draft/2020-12/schema",
"additionalProperties": false,
"properties": {
"candidateCount": {
"type": "number"
},
"catalogSize": {
"type": "number"
},
"dataAsOf": {
"type": "string"
},
"eloAsOf": {
"type": "string"
},
"error": {
"type": "string"
},
"nearMisses": {
"items": {
"additionalProperties": false,
"properties": {
"capabilities": {
"items": {
"type": "string"
},
"type": "array"
},
"category": {
"type": "string"
},
"constraints": {
"items": {
"additionalProperties": false,
"properties": {
"actual": {
"type": "string"
},
"constraint": {
"type": "string"
},
"required": {
"type": "string"
},
"satisfied": {
"type": "boolean"
}
},
"required": [
"constraint",
"required",
"actual",
"satisfied"
],
"type": "object"
},
"type": "array"
},
"contextWindow": {
"type": "string"
},
"costDeltaVsTopPct": {
"type": "number"
},
"efficiencyRank": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
]
},
"efficiencyScore": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
]
},
"eloScore": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
]
},
"isFinOpsFriendly": {
"type": "boolean"
},
"license": {
"type": "string"
},
"model": {
"type": "string"
},
"monthlyBudget": {
"type": "number"
},
"monthlyOptimizedBudget": {
"type": "number"
},
"openness": {
"type": "string"
},
"perRequest": {
"type": "number"
},
"perRequestOptimized": {
"type": "number"
},
"provider": {
"type": "string"
},
"rank": {
"type": "number"
},
"rankedOutOf": {
"type": "number"
},
"savingsPct": {
"type": "number"
},
"volatilityRisk": {
"type": "string"
}
},
"required": [
"rank",
"provider",
"model",
"category",
"openness",
"contextWindow",
"capabilities",
"eloScore",
"efficiencyScore",
"efficiencyRank",
"rankedOutOf",
"perRequest",
"perRequestOptimized",
"monthlyBudget",
"monthlyOptimizedBudget",
"savingsPct",
"isFinOpsFriendly",
"volatilityRisk",
"costDeltaVsTopPct",
"constraints"
],
"type": "object"
},
"type": "array"
},
"overConstrained": {
"type": "boolean"
},
"provenance": {
"additionalProperties": false,
"properties": {
"catalogTotal": {
"type": "number"
},
"dataAsOf": {
"type": "string"
},
"eloAsOf": {
"type": "string"
},
"label": {
"type": "string"
},
"notice": {
"type": "string"
},
"pricesVerified": {
"type": "boolean"
},
"source": {
"type": "string"
},
"tier": {
"type": "number"
},
"upstreamSchemaVersion": {
"type": "string"
},
"upstreamSource": {
"type": "string"
},
"upstreamTimestamp": {
"type": "string"
}
},
"required": [
"tier",
"source",
"label",
"pricesVerified",
"eloAsOf"
],
"type": "object"
},
"rankedCount": {
"type": "number"
},
"recommendations": {
"items": {
"additionalProperties": false,
"properties": {
"capabilities": {
"items": {
"type": "string"
},
"type": "array"
},
"category": {
"type": "string"
},
"constraints": {
"items": {
"additionalProperties": false,
"properties": {
"actual": {
"type": "string"
},
"constraint": {
"type": "string"
},
"required": {
"type": "string"
},
"satisfied": {
"type": "boolean"
}
},
"required": [
"constraint",
"required",
"actual",
"satisfied"
],
"type": "object"
},
"type": "array"
},
"contextWindow": {
"type": "string"
},
"costDeltaVsTopPct": {
"type": "number"
},
"efficiencyRank": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
]
},
"efficiencyScore": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
]
},
"eloScore": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
]
},
"isFinOpsFriendly": {
"type": "boolean"
},
"license": {
"type": "string"
},
"model": {
"type": "string"
},
"monthlyBudget": {
"type": "number"
},
"monthlyOptimizedBudget": {
"type": "number"
},
"openness": {
"type": "string"
},
"perRequest": {
"type": "number"
},
"perRequestOptimized": {
"type": "number"
},
"provider": {
"type": "string"
},
"rank": {
"type": "number"
},
"rankedOutOf": {
"type": "number"
},
"savingsPct": {
"type": "number"
},
"volatilityRisk": {
"type": "string"
}
},
"required": [
"rank",
"provider",
"model",
"category",
"openness",
"contextWindow",
"capabilities",
"eloScore",
"efficiencyScore",
"efficiencyRank",
"rankedOutOf",
"perRequest",
"perRequestOptimized",
"monthlyBudget",
"monthlyOptimizedBudget",
"savingsPct",
"isFinOpsFriendly",
"volatilityRisk",
"costDeltaVsTopPct",
"constraints"
],
"type": "object"
},
"type": "array"
},
"roiCalculatorUrl": {
"type": "string"
},
"source": {
"type": "string"
},
"useCaseLabel": {
"type": "string"
},
"volume": {
"type": "number"
},
"volumeLabel": {
"type": "string"
}
},
"required": [
"recommendations",
"nearMisses",
"overConstrained",
"useCaseLabel",
"volumeLabel",
"volume",
"candidateCount",
"rankedCount",
"catalogSize",
"roiCalculatorUrl",
"source",
"eloAsOf"
],
"type": "object"
}
}
]
}Verify it yourself
curl -s https://api.teppi.xyz/v1/evidence/sha256:cc4657b049f248cd6a6138fca39ec6167f73af6b7987470a7531e2336939070d | sha256sum