OptimToken
What this MCP does
Compares LLM models and pricing, estimates workload costs, recommends models, and compares cloud compute prices.
Tools
Input schema
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'properties': {'limit': {'type': 'number', 'maximum': 50, 'minimum': 1, 'description': 'Max instances to return (default: 20)'}, 'region': {'enum': ['us-east', 'us-west', 'europe', 'asia-pacific'], 'type': 'string', 'description': 'Pricing region: us-east, us-west, europe, asia-pacific. Default: us-east'}, 'sortBy': {'enum': ['price', 'vcpus', 'memory', 'pricePerVCPU'], 'type': 'string', 'description': 'Sort by: price, vcpus, memory, pricePerVCPU. Default: price'}, 'useCase': {'type': 'string', 'description': 'Use case. Must be one of these exactly (case-insensitive): Web App, Database, HPC, ML & AI, Dev/Test, Big Data. Any other string returns zero matches rather than an error.'}, 'category': {'type': 'string', 'description': 'Instance category. Must be one of these exactly (case-insensitive): General Purpose, Compute Optimized, Memory Optimized, Storage Optimized, GPU / Accelerated, Burstable. Any other string returns zero matches rather than an error.'}, 'maxVCPUs': {'type': 'number', 'description': 'Maximum number of vCPUs'}, 'minVCPUs': {'type': 'number', 'description': 'Minimum number of vCPUs'}, 'provider': {'type': 'string', 'description': 'Cloud provider. Must be one of these exactly (case-insensitive): AWS, Azure, GCP, DigitalOcean, OCI, OVH, Alibaba. Any other string returns zero matches rather than an error.'}, 'maxMemory': {'type': 'number', 'description': 'Maximum memory in GiB'}, 'minMemory': {'type': 'number', 'description': 'Minimum memory in GiB'}, 'processor': {'type': 'string', 'description': "Processor. Matched by exact equality (case-insensitive), so a partial value like 'H100' returns nothing. Known values: Intel, AMD, Graviton, Ampere, NVIDIA A100, NVIDIA H100, NVIDIA L4, NVIDIA T4, NVIDIA V100, NVIDIA Other."}}}
Output schema
{'type': 'object', '$schema': 'https://json-schema.org/draft/2020-12/schema', 'required': ['instances', 'matchingCount', 'catalogSize', 'source'], 'properties': {'error': {'type': 'string'}, 'source': {'type': 'string'}, 'instances': {'type': 'array', 'items': {'type': 'object', 'required': ['provider', 'instanceType', 'os', 'vCPUs', 'memory', 'processor', 'category', 'useCases', 'onDemandHourly', 'onDemandMonthly', 'spot', 'savingsPlan1yr', 'savingsPlan3yr', 'reserved1yr', 'reserved3yr'], 'properties': {'os': {'type': 'string'}, 'spot': {'anyOf': [{'type': 'number'}, {'type': 'null'}]}, 'vCPUs': {'type': 'number'}, 'memory': {'type': 'number'}, 'category': {'type': 'string'}, 'provider': {'type': 'string'}, 'useCases': {'type': 'array', 'items': {'type': 'string'}}, 'processor': {'type': 'string'}, 'reserved1yr': {'anyOf': [{'type': 'number'}, {'type': 'null'}]}, 'reserved3yr': {'anyOf': [{'type': 'number'}, {'type': 'null'}]}, 'instanceType': {'type': 'string'}, 'onDemandHourly': {'anyOf': [{'type': 'number'}, {'type': 'null'}]}, 'savingsPlan1yr': {'anyOf': [{'type': 'number'}, {'type': 'null'}]}, 'savingsPlan3yr': {'anyOf': [{'type': 'number'}, {'type': 'null'}]}, 'onDemandMonthly': {'anyOf': [{'type': 'number'}, {'type': 'null'}]}}, 'additionalProperties': False}}, 'provenance': {'type': 'object', 'required': ['tier', 'source', 'label', 'region', 'staticPriceColumns', 'unavailablePriceColumns'], 'properties': {'tier': {'type': 'number'}, 'label': {'type': 'string'}, 'notice': {'type': 'string'}, 'region': {'type': 'string'}, 'source': {'type': 'string'}, 'sources': {'type': 'object', 'propertyNames': {'type': 'string'}, 'additionalProperties': {'type': 'string'}}, 'dataAsOf': {'type': 'string'}, 'priceTypes': {'type': 'object', 'propertyNames': {'type': 'string'}, 'additionalProperties': {'type': 'object', 'propertyNames': {'type': 'string'}, 'additionalProperties': {'type': 'string'}}}, 'catalogTotal': {'type': 'number'}, 'sourceRegions': {'type': 'object', 'propertyNames': {'type': 'string'}, 'additionalProperties': {'type': 'string'}}, 'fallbackReason': {'type': 'string'}, 'upstreamErrors': {'type': 'array', 'items': {'type': 'string'}}, 'unappliedFilters': {'type': 'array', 'items': {'type': 'string'}}, 'catalogueIsSubset': {'type': 'boolean'}, 'upstreamTimestamp': {'type': 'string'}, 'staticPriceColumns': {'type': 'array', 'items': {'type': 'string'}}, 'servedFromCacheAgeMs': {'type': 'number'}, 'upstreamSchemaVersion': {'type': 'string'}, 'unavailablePriceColumns': {'type': 'array', 'items': {'type': 'string'}}}, 'additionalProperties': False}, 'catalogSize': {'type': 'number'}, 'matchingCount': {'type': 'number'}}, 'additionalProperties': False}
Input schema
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'properties': {'limit': {'type': 'number', 'maximum': 50, 'minimum': 1, 'description': 'Max models to return (default: 15)'}, 'minElo': {'type': 'number', '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}, 'category': {'type': 'string', 'description': 'Price tier, matched by exact equality (case-insensitive): Frontier, Mid-tier, Budget, Image. This is cost only â\x80\x94 self-hostability is the separate `openness` axis.'}, 'openness': {'enum': ['Open source', 'Open weights', 'Proprietary', 'Unknown'], 'type': 'string', 'description': 'Filter by self-hostability, derived from the licence: Open source, Open weights, Proprietary, Unknown'}, 'provider': {'type': 'string', 'description': "Filter by provider name (e.g. 'OpenAI', 'Anthropic', 'Google')"}, 'capability': {'type': 'string', 'description': 'Capability, matched by exact equality (case-insensitive): Text, Vision, Code, Reasoning, Agents, Image Gen, Audio. Any other string returns zero matches.'}, 'volumePreset': {'enum': ['10k', '100k', '1m'], 'type': 'string', 'description': 'Monthly request volume: 10k, 100k, or 1m. Default: 100k'}, 'maxInputPrice': {'type': 'number', 'description': 'Max input price per 1M tokens in USD'}, 'useCasePreset': {'enum': ['supportTicket', 'knowledgeQA', 'meetingSummary', 'marketingContent', 'codingTask', 'invoiceProcessing', 'callSummary', 'agentWorkflow'], 'type': 'string', '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'}, 'maxOutputPrice': {'type': 'number', 'description': 'Max output price per 1M tokens in USD'}}}
Output schema
{'type': 'object', '$schema': 'https://json-schema.org/draft/2020-12/schema', 'required': ['models', 'useCaseLabel', 'volumeLabel', 'source', 'matchingCount', 'catalogSize', 'eloAsOf'], 'properties': {'error': {'type': 'string'}, 'models': {'type': 'array', 'items': {'type': 'object', 'required': ['provider', 'model', 'inputPricePer1M', 'outputPricePer1M', 'contextWindow', 'category', 'capabilities', 'openness', 'efficiencyScore', 'useCaseCost', 'optimizedUseCaseCost', 'monthlyBudget', 'optimizedMonthlyBudget', 'volatilityRisk', 'isFinOpsFriendly', 'batchEligible', 'cacheEligible', 'batchApplied', 'cacheApplied'], 'properties': {'model': {'type': 'string'}, 'license': {'type': 'string'}, 'category': {'type': 'string'}, 'eloScore': {'type': 'number'}, 'openness': {'type': 'string'}, 'provider': {'type': 'string'}, 'parameters': {'type': 'string'}, 'releaseDate': {'type': 'string'}, 'useCaseCost': {'type': 'number'}, 'batchApplied': {'type': 'boolean'}, 'cacheApplied': {'type': 'boolean'}, 'capabilities': {'type': 'array', 'items': {'type': 'string'}}, 'batchEligible': {'type': 'boolean'}, 'cacheEligible': {'type': 'boolean'}, 'contextWindow': {'type': 'string'}, 'monthlyBudget': {'type': 'number'}, 'volatilityRisk': {'type': 'string'}, 'efficiencyScore': {'anyOf': [{'type': 'number'}, {'type': 'null'}]}, 'inputPricePer1M': {'type': 'number'}, 'isFinOpsFriendly': {'type': 'boolean'}, 'outputPricePer1M': {'type': 'number'}, 'batchInputPricePer1M': {'type': 'number'}, 'optimizedUseCaseCost': {'type': 'number'}, 'batchOutputPricePer1M': {'type': 'number'}, 'cachedInputPricePer1M': {'type': 'number'}, 'optimizedMonthlyBudget': {'type': 'number'}}, 'additionalProperties': False}}, 'source': {'type': 'string'}, 'eloAsOf': {'type': 'string'}, 'dataAsOf': {'type': 'string'}, 'provenance': {'type': 'object', 'required': ['tier', 'source', 'label', 'pricesVerified', 'eloAsOf'], 'properties': {'tier': {'type': 'number'}, 'label': {'type': 'string'}, 'notice': {'type': 'string'}, 'source': {'type': 'string'}, 'eloAsOf': {'type': 'string'}, 'dataAsOf': {'type': 'string'}, 'catalogTotal': {'type': 'number'}, 'pricesVerified': {'type': 'boolean'}, 'upstreamSource': {'type': 'string'}, 'upstreamTimestamp': {'type': 'string'}, 'upstreamSchemaVersion': {'type': 'string'}}, 'additionalProperties': False}, 'catalogSize': {'type': 'number'}, 'finopsBadge': {'type': 'object', 'required': ['qualifying', 'ranked', 'minElo', 'maxBlendedPrice'], 'properties': {'minElo': {'anyOf': [{'type': 'number'}, {'type': 'null'}]}, 'ranked': {'type': 'number'}, 'qualifying': {'type': 'number'}, 'maxBlendedPrice': {'anyOf': [{'type': 'number'}, {'type': 'null'}]}}, 'additionalProperties': False}, 'volumeLabel': {'type': 'string'}, 'useCaseLabel': {'type': 'string'}, 'matchingCount': {'type': 'number'}}, 'additionalProperties': False}
Input schema
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['models'], 'properties': {'models': {'type': 'array', 'items': {'type': 'string'}, 'maxItems': 4, 'minItems': 2, 'description': "2-4 model names to compare, e.g. ['GPT-4o', 'Claude Opus 5', 'Gemini 3.1 Pro']"}, 'volumePreset': {'enum': ['10k', '100k', '1m'], 'type': 'string', 'description': 'Monthly request volume: 10k, 100k, or 1m. Default: 100k'}}}
Output schema
{'type': 'object', '$schema': 'https://json-schema.org/draft/2020-12/schema', 'required': ['models', 'resolution', 'volume', 'volumeLabel', 'source', 'eloAsOf'], 'properties': {'error': {'type': 'string'}, 'models': {'type': 'array', 'items': {'type': 'object', 'required': ['provider', 'model', 'inputPricePer1M', 'outputPricePer1M', 'contextWindow', 'category', 'capabilities', 'useCaseCosts'], 'properties': {'model': {'type': 'string'}, 'license': {'type': 'string'}, 'category': {'type': 'string'}, 'eloScore': {'type': 'number'}, 'provider': {'type': 'string'}, 'parameters': {'type': 'string'}, 'releaseDate': {'type': 'string'}, 'capabilities': {'type': 'array', 'items': {'type': 'string'}}, 'useCaseCosts': {'type': 'array', 'items': {'type': 'object', 'required': ['key', 'label', 'inputTokens', 'outputTokens', 'perRequest', 'perRequestOptimized', 'monthly', 'monthlyOptimized', 'savingsPct', 'batchEligible', 'cacheEligible', 'batchApplied', 'cacheApplied'], 'properties': {'key': {'type': 'string'}, 'label': {'type': 'string'}, 'monthly': {'type': 'number'}, 'perRequest': {'type': 'number'}, 'savingsPct': {'type': 'number'}, 'inputTokens': {'type': 'number'}, 'batchApplied': {'type': 'boolean'}, 'cacheApplied': {'type': 'boolean'}, 'outputTokens': {'type': 'number'}, 'batchEligible': {'type': 'boolean'}, 'cacheEligible': {'type': 'boolean'}, 'monthlyOptimized': {'type': 'number'}, 'perRequestOptimized': {'type': 'number'}}, 'additionalProperties': False}}, 'contextWindow': {'type': 'string'}, 'inputPricePer1M': {'type': 'number'}, 'outputPricePer1M': {'type': 'number'}, 'batchInputPricePer1M': {'type': 'number'}, 'batchOutputPricePer1M': {'type': 'number'}, 'cachedInputPricePer1M': {'type': 'number'}}, 'additionalProperties': False}}, 'source': {'type': 'string'}, 'volume': {'type': 'number'}, 'eloAsOf': {'type': 'string'}, 'dataAsOf': {'type': 'string'}, 'provenance': {'type': 'object', 'required': ['tier', 'source', 'label', 'pricesVerified', 'eloAsOf'], 'properties': {'tier': {'type': 'number'}, 'label': {'type': 'string'}, 'notice': {'type': 'string'}, 'source': {'type': 'string'}, 'eloAsOf': {'type': 'string'}, 'dataAsOf': {'type': 'string'}, 'catalogTotal': {'type': 'number'}, 'pricesVerified': {'type': 'boolean'}, 'upstreamSource': {'type': 'string'}, 'upstreamTimestamp': {'type': 'string'}, 'upstreamSchemaVersion': {'type': 'string'}}, 'additionalProperties': False}, 'resolution': {'type': 'array', 'items': {'type': 'object', 'required': ['query', 'status', 'alternatives', 'totalMatches'], 'properties': {'query': {'type': 'string'}, 'status': {'enum': ['exact', 'unique', 'ambiguous', 'not-found', 'duplicate'], 'type': 'string'}, 'resolved': {'type': 'string'}, 'alternatives': {'type': 'array', 'items': {'type': 'string'}}, 'totalMatches': {'type': 'number'}}, 'additionalProperties': False}}, 'volumeLabel': {'type': 'string'}}, 'additionalProperties': False}
Input schema
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'properties': {'modelName': {'type': 'string', 'description': "Model name, e.g. 'GPT-4o'. A partial name matches up to 5 models and ALL of them are costed. If omitted, the first 8 catalogue entries are used â\x80\x94 that is catalogue order, not a quality ranking."}, 'monthlyVolume': {'type': 'integer', 'maximum': 1000000000, 'minimum': 1, 'description': 'Exact monthly request count, any integer (default 100,000). This tool does not take the 10k/100k/1m presets the other cost tools use.'}, 'useCasePreset': {'enum': ['supportTicket', 'knowledgeQA', 'meetingSummary', 'marketingContent', 'codingTask', 'invoiceProcessing', 'callSummary', 'agentWorkflow'], 'type': 'string', 'description': 'Workload shape, which sets tokens per request: supportTicket (1.5k in / 500 out), knowledgeQA (2k / 800), meetingSummary (10k / 1.2k, batch-eligible), marketingContent (2.5k / 1.8k), codingTask (3k / 2k), invoiceProcessing (1.5k / 600, batch-eligible), callSummary (2k / 700, batch-eligible), agentWorkflow (6k / 3k). Default: every preset.'}, 'customInputTokens': {'type': 'integer', 'maximum': 10000000, 'minimum': 1, 'description': 'Custom input tokens per request. Must be supplied TOGETHER with customOutputTokens â\x80\x94 either alone is ignored and the preset is used. A custom shape assumes no cacheable prefix and no batch eligibility, so its optimized cost equals its list cost.'}, 'customOutputTokens': {'type': 'integer', 'maximum': 10000000, 'minimum': 1, 'description': 'Custom output tokens per request. Must be supplied TOGETHER with customInputTokens â\x80\x94 either alone is ignored and the preset is used.'}}}
Output schema
{'type': 'object', '$schema': 'https://json-schema.org/draft/2020-12/schema', 'required': ['modelCosts', 'volume', 'source', 'eloAsOf'], 'properties': {'error': {'type': 'string'}, 'source': {'type': 'string'}, 'volume': {'type': 'number'}, 'eloAsOf': {'type': 'string'}, 'dataAsOf': {'type': 'string'}, 'modelCosts': {'type': 'array', 'items': {'type': 'object', 'required': ['model', 'costs'], 'properties': {'costs': {'type': 'array', 'items': {'type': 'object', 'required': ['useCase', 'inputTokens', 'outputTokens', 'perRequest', 'monthly', 'perRequestOptimized', 'monthlyOptimized', 'savingsPct', 'batchEligible', 'cacheEligible', 'batchApplied', 'cacheApplied'], 'properties': {'monthly': {'type': 'number'}, 'useCase': {'type': 'string'}, 'perRequest': {'type': 'number'}, 'savingsPct': {'type': 'number'}, 'inputTokens': {'type': 'number'}, 'batchApplied': {'type': 'boolean'}, 'cacheApplied': {'type': 'boolean'}, 'outputTokens': {'type': 'number'}, 'batchEligible': {'type': 'boolean'}, 'cacheEligible': {'type': 'boolean'}, 'monthlyOptimized': {'type': 'number'}, 'perRequestOptimized': {'type': 'number'}}, 'additionalProperties': False}}, 'model': {'type': 'object', 'required': ['provider', 'model', 'inputPricePer1M', 'outputPricePer1M', 'contextWindow', 'category', 'capabilities'], 'properties': {'model': {'type': 'string'}, 'license': {'type': 'string'}, 'category': {'type': 'string'}, 'eloScore': {'type': 'number'}, 'provider': {'type': 'string'}, 'parameters': {'type': 'string'}, 'releaseDate': {'type': 'string'}, 'capabilities': {'type': 'array', 'items': {'type': 'string'}}, 'contextWindow': {'type': 'string'}, 'inputPricePer1M': {'type': 'number'}, 'outputPricePer1M': {'type': 'number'}, 'batchInputPricePer1M': {'type': 'number'}, 'batchOutputPricePer1M': {'type': 'number'}, 'cachedInputPricePer1M': {'type': 'number'}}, 'additionalProperties': False}}, 'additionalProperties': False}}, 'provenance': {'type': 'object', 'required': ['tier', 'source', 'label', 'pricesVerified', 'eloAsOf'], 'properties': {'tier': {'type': 'number'}, 'label': {'type': 'string'}, 'notice': {'type': 'string'}, 'source': {'type': 'string'}, 'eloAsOf': {'type': 'string'}, 'dataAsOf': {'type': 'string'}, 'catalogTotal': {'type': 'number'}, 'pricesVerified': {'type': 'boolean'}, 'upstreamSource': {'type': 'string'}, 'upstreamTimestamp': {'type': 'string'}, 'upstreamSchemaVersion': {'type': 'string'}}, 'additionalProperties': False}}, 'additionalProperties': False}
Input schema
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['useCasePreset'], 'properties': {'minElo': {'type': 'number', 'description': 'Minimum Chatbot Arena ELO score. Typical range 1000-1500; ~1400 is roughly frontier-class. Models with no ELO score never satisfy this.', 'exclusiveMinimum': 0}, 'openness': {'enum': ['Open source', 'Open weights', 'Proprietary', 'Unknown'], 'type': 'string', 'description': 'Require a self-hostability bucket, derived from the licence: Open source, Open weights, Proprietary, Unknown'}, 'volumePreset': {'enum': ['10k', '100k', '1m'], 'type': 'string', 'description': 'Monthly request volume: 10k, 100k, or 1m. Default: 100k'}, 'useCasePreset': {'enum': ['supportTicket', 'knowledgeQA', 'meetingSummary', 'marketingContent', 'codingTask', 'invoiceProcessing', 'callSummary', 'agentWorkflow'], 'type': 'string', 'description': 'Workload shape, which sets tokens per request: supportTicket (1.5k in / 500 out), knowledgeQA (2k / 800), meetingSummary (10k / 1.2k, batch-eligible), marketingContent (2.5k / 1.8k), codingTask (3k / 2k), invoiceProcessing (1.5k / 600, batch-eligible), callSummary (2k / 700, batch-eligible), agentWorkflow (6k / 3k).'}, 'maxMonthlyBudget': {'type': 'number', 'description': 'Maximum monthly budget in USD at the given volume. Tested against the LIST-price monthly cost, not the caching/batch-optimized cost.', 'exclusiveMinimum': 0}, 'requiredCapability': {'type': 'string', 'description': 'Capability the model must have: Text, Vision, Code, Reasoning, Agents, Image Gen, Audio'}}}
Output schema
{'type': 'object', '$schema': 'https://json-schema.org/draft/2020-12/schema', 'required': ['recommendations', 'nearMisses', 'overConstrained', 'useCaseLabel', 'volumeLabel', 'volume', 'candidateCount', 'rankedCount', 'catalogSize', 'roiCalculatorUrl', 'source', 'eloAsOf'], 'properties': {'error': {'type': 'string'}, 'source': {'type': 'string'}, 'volume': {'type': 'number'}, 'eloAsOf': {'type': 'string'}, 'dataAsOf': {'type': 'string'}, 'nearMisses': {'type': 'array', 'items': {'type': 'object', 'required': ['rank', 'provider', 'model', 'category', 'openness', 'contextWindow', 'capabilities', 'eloScore', 'efficiencyScore', 'efficiencyRank', 'rankedOutOf', 'perRequest', 'perRequestOptimized', 'monthlyBudget', 'monthlyOptimizedBudget', 'savingsPct', 'isFinOpsFriendly', 'volatilityRisk', 'costDeltaVsTopPct', 'constraints'], 'properties': {'rank': {'type': 'number'}, 'model': {'type': 'string'}, 'license': {'type': 'string'}, 'category': {'type': 'string'}, 'eloScore': {'anyOf': [{'type': 'number'}, {'type': 'null'}]}, 'openness': {'type': 'string'}, 'provider': {'type': 'string'}, 'perRequest': {'type': 'number'}, 'savingsPct': {'type': 'number'}, 'constraints': {'type': 'array', 'items': {'type': 'object', 'required': ['constraint', 'required', 'actual', 'satisfied'], 'properties': {'actual': {'type': 'string'}, 'required': {'type': 'string'}, 'satisfied': {'type': 'boolean'}, 'constraint': {'type': 'string'}}, 'additionalProperties': False}}, 'rankedOutOf': {'type': 'number'}, 'capabilities': {'type': 'array', 'items': {'type': 'string'}}, 'contextWindow': {'type': 'string'}, 'monthlyBudget': {'type': 'number'}, 'efficiencyRank': {'anyOf': [{'type': 'number'}, {'type': 'null'}]}, 'volatilityRisk': {'type': 'string'}, 'efficiencyScore': {'anyOf': [{'type': 'number'}, {'type': 'null'}]}, 'isFinOpsFriendly': {'type': 'boolean'}, 'costDeltaVsTopPct': {'type': 'number'}, 'perRequestOptimized': {'type': 'number'}, 'monthlyOptimizedBudget': {'type': 'number'}}, 'additionalProperties': False}}, 'provenance': {'type': 'object', 'required': ['tier', 'source', 'label', 'pricesVerified', 'eloAsOf'], 'properties': {'tier': {'type': 'number'}, 'label': {'type': 'string'}, 'notice': {'type': 'string'}, 'source': {'type': 'string'}, 'eloAsOf': {'type': 'string'}, 'dataAsOf': {'type': 'string'}, 'catalogTotal': {'type': 'number'}, 'pricesVerified': {'type': 'boolean'}, 'upstreamSource': {'type': 'string'}, 'upstreamTimestamp': {'type': 'string'}, 'upstreamSchemaVersion': {'type': 'string'}}, 'additionalProperties': False}, 'catalogSize': {'type': 'number'}, 'rankedCount': {'type': 'number'}, 'volumeLabel': {'type': 'string'}, 'useCaseLabel': {'type': 'string'}, 'candidateCount': {'type': 'number'}, 'overConstrained': {'type': 'boolean'}, 'recommendations': {'type': 'array', 'items': {'type': 'object', 'required': ['rank', 'provider', 'model', 'category', 'openness', 'contextWindow', 'capabilities', 'eloScore', 'efficiencyScore', 'efficiencyRank', 'rankedOutOf', 'perRequest', 'perRequestOptimized', 'monthlyBudget', 'monthlyOptimizedBudget', 'savingsPct', 'isFinOpsFriendly', 'volatilityRisk', 'costDeltaVsTopPct', 'constraints'], 'properties': {'rank': {'type': 'number'}, 'model': {'type': 'string'}, 'license': {'type': 'string'}, 'category': {'type': 'string'}, 'eloScore': {'anyOf': [{'type': 'number'}, {'type': 'null'}]}, 'openness': {'type': 'string'}, 'provider': {'type': 'string'}, 'perRequest': {'type': 'number'}, 'savingsPct': {'type': 'number'}, 'constraints': {'type': 'array', 'items': {'type': 'object', 'required': ['constraint', 'required', 'actual', 'satisfied'], 'properties': {'actual': {'type': 'string'}, 'required': {'type': 'string'}, 'satisfied': {'type': 'boolean'}, 'constraint': {'type': 'string'}}, 'additionalProperties': False}}, 'rankedOutOf': {'type': 'number'}, 'capabilities': {'type': 'array', 'items': {'type': 'string'}}, 'contextWindow': {'type': 'string'}, 'monthlyBudget': {'type': 'number'}, 'efficiencyRank': {'anyOf': [{'type': 'number'}, {'type': 'null'}]}, 'volatilityRisk': {'type': 'string'}, 'efficiencyScore': {'anyOf': [{'type': 'number'}, {'type': 'null'}]}, 'isFinOpsFriendly': {'type': 'boolean'}, 'costDeltaVsTopPct': {'type': 'number'}, 'perRequestOptimized': {'type': 'number'}, 'monthlyOptimizedBudget': {'type': 'number'}}, 'additionalProperties': False}}, 'roiCalculatorUrl': {'type': 'string'}}, 'additionalProperties': False}
Recent tool changes
Similar MCP servers
AI Compute Radar
Evaluates which tracked AI models fit specific GPUs or Macs and provides model trends, GPU rental prices, and weekly recommendati…
Algenta MCP Server
Provides governed data onboarding, connector browsing, deterministic simulations, agent-run lifecycles, capability routing, deplo…
Replicate
Provides access to Replicate models, versions, collections, hardware, predictions, and deployments for running and managing hoste…
Scalix Cloud
Provides managed databases, SQL tools, container builds, persistent Linux machines, domains, scheduled functions, storage, and pr…
RationalBloks
Creates, deploys, manages, and searches schema-based REST API projects and Neo4j knowledge graphs across staging and production e…
RationalBloks
Creates, deploys, manages, and queries REST API and Neo4j graph projects from JSON schemas, including graph data modeling, versio…
Huggingface
Provides access to Hugging Face model, dataset, and Space metadata, alongside broader structured research and data-routing tools.
Ai Model Experiments
Runs prompts across multiple AI models and compares their outputs, costs, latency, token usage, and errors.