{"data":{"name":"io.github.OptimNow/ai-pricing-hub","title":"OptimToken","description":"Compare LLM API and cloud compute pricing, estimate workload costs, pick a model within budget.","version":"0.4.2","websiteUrl":"https://optimtoken.optimnow.io/mcp","repositoryUrl":"https://github.com/OptimNow/ai-pricing-hub-mcp","remotes":[{"url":"https://optimtoken-mcp.optimnow.io/mcp","type":"streamable-http"}],"packages":[],"status":"active","isLatest":true,"publishedAt":"2026-10-07T21:20:44.409Z","updatedAt":"2026-10-07T21:20:44.409Z","source":"official-registry","verification":"official","confidence":100,"stars":null,"sources":[{"stars":null,"title":"OptimToken","source":"official-registry","sourceId":"io.github.OptimNow/ai-pricing-hub","updatedAt":"2026-10-07T21:20:44.409Z","confidence":100,"websiteUrl":"https://optimtoken.optimnow.io/mcp","description":"Compare LLM API and cloud compute pricing, estimate workload costs, pick a model within budget.","verification":"official","repositoryUrl":"https://github.com/OptimNow/ai-pricing-hub-mcp"}],"toolIndex":{"tools":[{"serverName":"io.github.OptimNow/ai-pricing-hub","endpointFingerprint":"6bc975b213d359f660adf536cb8cebabd52cfce6db61eb28189973d163df34ac","name":"compare-compute-pricing","title":"Compare Cloud Compute Pricing","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. Use this for 'the cheapest 8 vCPU / 32 GiB instance in Europe', and for what a commitment saves: each row gives the Linux list price in USD per hour on demand, on spot, and under a 1-year and 3-year commitment (savings plan, Google CUD, reservation) as an effective hourly rate, each with its saving against that row's on-demand rate. A row with no commitment rate says so. 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; a savings-plan or reserved rate that appears there is a static estimate, not a live quote. Prices are returned as the catalogue serves them and dated by `provenance`.","inputSchema":{"type":"object","properties":{"region":{"description":"Pricing region: us-east, us-west, europe, asia-pacific. Default: us-east","type":"string","enum":["us-east","us-west","europe","asia-pacific"]},"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"},"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"},"minVCPUs":{"description":"Minimum number of vCPUs","type":"number"},"maxVCPUs":{"description":"Maximum number of vCPUs","type":"number"},"minMemory":{"description":"Minimum memory in GiB","type":"number"},"maxMemory":{"description":"Maximum memory in GiB","type":"number"},"processor":{"description":"Processor. Matched by exact equality (case-insensitive), so a partial value like 'H100' returns nothing. Known values: Intel, AMD, Graviton, Trainium, Inferentia, Ampere, Axion, ARM, NVIDIA T4, NVIDIA V100, NVIDIA A100, NVIDIA H100, NVIDIA L4, NVIDIA A10G, NVIDIA Other. 'NVIDIA Other' is every NVIDIA GPU without a label of its own (L40S, H200, B200, RTX and older parts).","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"},"sortBy":{"description":"Sort by: price, vcpus, memory, pricePerVCPU. Default: price","type":"string","enum":["price","vcpus","memory","pricePerVCPU"]},"limit":{"description":"Max instances to return (default: 20)","type":"number","minimum":1,"maximum":50}},"$schema":"http://json-schema.org/draft-07/schema#"},"annotations":{"title":"Compare Cloud Compute Pricing","readOnlyHint":true,"destructiveHint":false,"openWorldHint":true},"definitionHash":"e00d043432b2821cceacc543f5d7cbd10b0318ef0a5dafebc107ce6dd9daf5bf","schemaStatus":"valid","origin":"official-registry","observedAt":"2026-11-19T23:46:37.758Z","metadataTrust":"untrusted"},{"serverName":"io.github.OptimNow/ai-pricing-hub","endpointFingerprint":"6bc975b213d359f660adf536cb8cebabd52cfce6db61eb28189973d163df34ac","name":"compare-llm-models","title":"Compare LLM Models","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', 'the ten cheapest models for a coding task'. The table is ordered by Arena ELO unless `sortBy` asks for efficiency, cost or price, and `limit` keeps the first rows of that order. 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. Prices, costs and scores are final as returned: rounded and ranked server-side, and dated by `provenance`. The text block is a numbered table of the same figures.","inputSchema":{"type":"object","properties":{"provider":{"description":"Filter by provider name (e.g. 'OpenAI', 'Anthropic', 'Google')","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"},"openness":{"description":"Filter by self-hostability, derived from the licence: Open source, Open weights, Proprietary, Unknown","type":"string","enum":["Open source","Open weights","Proprietary","Unknown"]},"capability":{"description":"Capability, matched by exact equality (case-insensitive): Text, Vision, Reasoning, Agents, Image Gen, Audio. Any other string returns zero matches. There is no Code capability: for what coding costs, use useCasePreset codingTask.","type":"string"},"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.","type":"number","exclusiveMinimum":0},"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","type":"string","enum":["supportTicket","knowledgeQA","meetingSummary","marketingContent","codingTask","invoiceProcessing","callSummary","agentWorkflow"]},"volumePreset":{"description":"Monthly request volume: 10k, 100k, or 1m. Default: 100k","type":"string","enum":["10k","100k","1m"]},"sortBy":{"description":"Order of the table, best first. elo: Arena ELO, highest first (default). efficiency: value score out of 100, highest first. cost: list-price cost per request for the use case, cheapest first. optimizedCost: the same after caching and batch. inputPrice / outputPrice: price per 1M tokens, cheapest first. A model missing the sorted figure comes last, and ties keep the ELO order. Cheapest first says nothing about quality: read the ELO beside each row.","type":"string","enum":["elo","efficiency","cost","optimizedCost","inputPrice","outputPrice"]},"limit":{"description":"Max models to return, counted after sorting (default: 15)","type":"number","minimum":1,"maximum":50}},"$schema":"http://json-schema.org/draft-07/schema#"},"annotations":{"title":"Compare LLM Models","readOnlyHint":true,"destructiveHint":false,"openWorldHint":true},"definitionHash":"2071b35434ab381869caf7658979dced3966f4c96e13da0365a007cfc9fa244f","schemaStatus":"valid","origin":"official-registry","observedAt":"2026-11-19T23:46:37.758Z","metadataTrust":"untrusted"},{"serverName":"io.github.OptimNow/ai-pricing-hub","endpointFingerprint":"6bc975b213d359f660adf536cb8cebabd52cfce6db61eb28189973d163df34ac","name":"compare-model-hosts","title":"Compare Model Hosts","description":"Who sells a model, and at what price. Most models are sold by several hosts (the model maker, a cloud platform such as Amazon Bedrock, Azure or Vertex, or an independent host) at different rates, and every other tool here quotes ONE of them. For 1-4 named models this returns how many hosts sell each, the cheapest, the dearest, the model maker's own rate, the spread between them, any promotional listing, and what a workload costs per request and per month at each. Use it for 'where is Llama 3.3 70B cheapest', 'is the price you quoted the maker's own', 'how much does the choice of host matter for this model'. To cost a workload at the quoted price with caching and batch, use estimate-llm-cost. Read the caveats it returns: the cheapest host may serve a quantized build, which is not the same product, or a promotional rate that ends. It also lists every host with its rate, cheapest first, the platforms the model is listed on (Direct API, AWS Bedrock, Azure AI Foundry, Google Vertex, OpenRouter: a hand-kept estimate for the major models) and the AWS regions where Amazon Bedrock lists it. `hostList.available` says whether that full list was read: without it only the cheapest, the dearest, the maker's own and promotional listings are known, and the text says so. A missing platform or region is not known, never 'not sold there'. Per-host prices are list prices read nightly and dated by `provenance.hostPricingAsOf`, and a model with no host data says so rather than reading as sold by one host.","inputSchema":{"type":"object","properties":{"models":{"minItems":1,"maxItems":4,"type":"array","items":{"type":"string"},"description":"1-4 model names, e.g. ['Llama 3.3 70B'] or ['Claude Sonnet 5', 'DeepSeek V4']"},"useCasePreset":{"description":"Workload the costs are computed for, which sets tokens per request: supportTicket (1.5k in / 500 out), knowledgeQA (2k / 800), meetingSummary (10k / 1.2k), marketingContent (2.5k / 1.8k), codingTask (3k / 2k), invoiceProcessing (1.5k / 600), callSummary (2k / 700), agentWorkflow (6k / 3k). Default: supportTicket","type":"string","enum":["supportTicket","knowledgeQA","meetingSummary","marketingContent","codingTask","invoiceProcessing","callSummary","agentWorkflow"]},"volumePreset":{"description":"Monthly request volume: 10k, 100k, or 1m. Default: 100k","type":"string","enum":["10k","100k","1m"]}},"required":["models"],"$schema":"http://json-schema.org/draft-07/schema#"},"annotations":{"title":"Compare Model Hosts","readOnlyHint":true,"destructiveHint":false,"openWorldHint":true},"definitionHash":"6422eaf21cf4f97892bb89d1d94b768ef20f676f5ae32ca6b863ebea94145abe","schemaStatus":"valid","origin":"official-registry","observedAt":"2026-11-19T23:46:37.758Z","metadataTrust":"untrusted"},{"serverName":"io.github.OptimNow/ai-pricing-hub","endpointFingerprint":"6bc975b213d359f660adf536cb8cebabd52cfce6db61eb28189973d163df34ac","name":"compare-models-side-by-side","title":"Compare Models Side by Side","description":"Compare 2-4 named LLM models against all 8 use-case profiles at a chosen monthly volume, showing list and optimized cost for each. Use when the user names specific models to weigh against each other, rather than filtering the whole catalogue. If they also supply their own token counts, or a volume outside 10k/100k/1m, use estimate-llm-cost instead. Every name is resolved against the catalogue and the outcome is reported in `resolution` and in the text: a name that matched nothing, matched several models, or duplicated an earlier pick is stated explicitly, and such a name gets no column rather than a zero cost. Prices and costs are final as returned: rounded server-side and dated by `provenance`.","inputSchema":{"type":"object","properties":{"models":{"minItems":2,"maxItems":4,"type":"array","items":{"type":"string"},"description":"2-4 model names to compare, e.g. ['GPT-4o', 'Claude Opus 5', 'Gemini 3.1 Pro']"},"volumePreset":{"description":"Monthly request volume: 10k, 100k, or 1m. Default: 100k","type":"string","enum":["10k","100k","1m"]}},"required":["models"],"$schema":"http://json-schema.org/draft-07/schema#"},"annotations":{"title":"Compare Models Side by Side","readOnlyHint":true,"destructiveHint":false,"openWorldHint":true},"definitionHash":"cfbaf9da98ba2a10ea6694af77757ed17147c510e0dfe9c75dd979e8b53cea4c","schemaStatus":"valid","origin":"official-registry","observedAt":"2026-11-19T23:46:37.758Z","metadataTrust":"untrusted"},{"serverName":"io.github.OptimNow/ai-pricing-hub","endpointFingerprint":"6bc975b213d359f660adf536cb8cebabd52cfce6db61eb28189973d163df34ac","name":"estimate-llm-cost","title":"Estimate LLM Cost","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. The presets carry their own cache-hit and batch assumptions; a custom token shape carries none unless cacheHitRate and/or batchEligible are passed with it, and each cost entry states which applied in `optimizationBasis`. Cost figures are final as returned: rounded server-side and dated by `provenance`, with the lever behind each saving, or the reason there is none, named in the text.","inputSchema":{"type":"object","properties":{"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"},"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.","type":"string","enum":["supportTicket","knowledgeQA","meetingSummary","marketingContent","codingTask","invoiceProcessing","callSummary","agentWorkflow"]},"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 unless cacheHitRate / batchEligible say otherwise, so without them its optimized cost equals its list cost.","type":"integer","minimum":1,"maximum":10000000},"customOutputTokens":{"description":"Custom output tokens per request. Must be supplied TOGETHER with customInputTokens — either alone is ignored and the preset is used.","type":"integer","minimum":1,"maximum":10000000},"cacheHitRate":{"description":"Share of input tokens served from the prompt cache, 0 to 1: for example 0.6 for a stable system prompt and tool definitions re-sent on every call. Only valid with customInputTokens and customOutputTokens; the presets carry their own and cannot be overridden. Omitting it means no caching is assumed, not that none is achievable.","type":"number","minimum":0,"maximum":1},"batchEligible":{"description":"Whether this workload is asynchronous and can go through the batch API. Only valid with customInputTokens and customOutputTokens; the presets carry their own. Omitting it means no batch discount is assumed, not that the workload is ineligible.","type":"boolean"},"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.","type":"integer","minimum":1,"maximum":1000000000}},"$schema":"http://json-schema.org/draft-07/schema#"},"annotations":{"title":"Estimate LLM Cost","readOnlyHint":true,"destructiveHint":false,"openWorldHint":true},"definitionHash":"7ecff76951872caa63cdeb6dd301f9c2ab635780b29d4dc467eed458ef45481b","schemaStatus":"valid","origin":"official-registry","observedAt":"2026-11-19T23:46:37.758Z","metadataTrust":"untrusted"},{"serverName":"io.github.OptimNow/ai-pricing-hub","endpointFingerprint":"6bc975b213d359f660adf536cb8cebabd52cfce6db61eb28189973d163df34ac","name":"estimate-self-hosting-breakeven","title":"Estimate Self-Hosting Break-Even","description":"API or own capacity: the monthly volume at which renting GPU instances costs the same as paying a model's API per token. An API bill grows with every request, a rented instance costs the same whether it is busy or idle, so below the break-even the API is cheaper and above it the fleet is. Give a model, a workload and either an instance from the compute catalogue (instanceType) or an hourly rate of your own (hourlyRate). The answer costs the fleet at every rate the catalogue lists (on demand, spot, 1- and 3-year commitments) against the API at list price, at the optimized price with caching and batch, and at the cheapest host known, and compares them at your volume. Use it for 'at what volume does self-hosting Llama 3.3 70B on a g6e.4xlarge pay off' or 'is our 2M requests a month enough to rent our own GPUs'. It assumes neither a throughput nor an operations cost. Without outputTokensPerSecond each break-even states the output tokens per second the fleet would have to sustain around the clock; with it, the share of the fleet's capacity that volume uses, and whether it is out of reach. Without monthlyOperationsCost the fleet figures are hardware rent only: engineer time, storage, egress and failover are left out, and the text says so. It does not check that the instance can hold the model, and it reports whether the model's weights are published at all. Figures are final as returned and dated by `provenance` (API prices) and `computeProvenance` (instance rates).","inputSchema":{"type":"object","properties":{"model":{"type":"string","minLength":1,"description":"Model whose API price is the baseline, e.g. 'Llama 3.3 70B'. One name; the best match is used and other matches are reported."},"instanceType":{"description":"Instance the model would run on, exactly as the compute catalogue names it, e.g. 'g6e.4xlarge' or 'a2-highgpu-1g'. Find one with compare-compute-pricing (category 'GPU / Accelerated'). Give this OR hourlyRate, not both.","type":"string","minLength":1},"provider":{"description":"Cloud provider of instanceType, needed only when two providers use the same instance name: AWS, Azure, GCP, DigitalOcean, OCI, OVH, Alibaba.","type":"string"},"region":{"description":"Pricing region of instanceType: us-east, us-west, europe, asia-pacific. Default: us-east","type":"string","enum":["us-east","us-west","europe","asia-pacific"]},"hourlyRate":{"description":"USD per hour for ONE instance, for hardware the catalogue does not list: a GPU cloud, a quoted rate, owned hardware amortised per hour. Give this OR instanceType, not both.","type":"number","exclusiveMinimum":0,"maximum":100000},"instanceCount":{"description":"Instances in the fleet, each billed every hour of the month. Default: 1","type":"integer","minimum":1,"maximum":10000},"outputTokensPerSecond":{"description":"MEASURED output tokens per second ONE instance generates at full load on this workload, all concurrent requests together. Omit it when it has not been measured: the tool then states the throughput each break-even requires instead of assuming one.","type":"number","exclusiveMinimum":0,"maximum":10000000},"monthlyOperationsCost":{"description":"USD per month for everything the hourly rate leaves out: the engineers who run the stack, storage, egress, failover capacity. Omitted means not included, not zero, and the answer says so.","type":"number","minimum":0,"maximum":1000000000},"useCasePreset":{"description":"Workload shape, which sets tokens per request and the caching and batch assumptions: 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. Ignored when custom token counts are given.","type":"string","enum":["supportTicket","knowledgeQA","meetingSummary","marketingContent","codingTask","invoiceProcessing","callSummary","agentWorkflow"]},"customInputTokens":{"description":"Custom input tokens per request. Must be supplied TOGETHER with customOutputTokens. A custom shape assumes no caching and no batch unless cacheHitRate / batchEligible say otherwise.","type":"integer","minimum":1,"maximum":10000000},"customOutputTokens":{"description":"Custom output tokens per request. Must be supplied TOGETHER with customInputTokens.","type":"integer","minimum":1,"maximum":10000000},"cacheHitRate":{"description":"Share of input tokens served from the prompt cache, 0 to 1. Only valid with customInputTokens and customOutputTokens; the presets carry their own.","type":"number","minimum":0,"maximum":1},"batchEligible":{"description":"Whether the workload is asynchronous and can go through the batch API. Only valid with customInputTokens and customOutputTokens; the presets carry their own.","type":"boolean"},"monthlyVolume":{"description":"Requests per month the two are compared at, any integer. Default: 100,000","type":"integer","minimum":1,"maximum":1000000000000}},"required":["model"],"$schema":"http://json-schema.org/draft-07/schema#"},"annotations":{"title":"Estimate Self-Hosting Break-Even","readOnlyHint":true,"destructiveHint":false,"openWorldHint":true},"definitionHash":"4e3c7afbc6470c09fbe0f9bcc31d43d5f3eed8b4ffbf9d29a58e8a98a4f754a2","schemaStatus":"valid","origin":"official-registry","observedAt":"2026-11-19T23:46:37.758Z","metadataTrust":"untrusted"},{"serverName":"io.github.OptimNow/ai-pricing-hub","endpointFingerprint":"6bc975b213d359f660adf536cb8cebabd52cfce6db61eb28189973d163df34ac","name":"recommend-llm-model","title":"Recommend an LLM Model","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, `recommendations` is empty, and the nearest misses are returned in `nearMisses` instead, each carrying the constraint it failed and flagged as a miss in the text. A model whose maker has announced its retirement is never recommended: it is left out, counted in `retiredExcludedCount`, and the ones that would have ranked are named in `retiredNotRecommended` with the notice. The ranking is computed server-side and is final.","inputSchema":{"type":"object","properties":{"useCasePreset":{"type":"string","enum":["supportTicket","knowledgeQA","meetingSummary","marketingContent","codingTask","invoiceProcessing","callSummary","agentWorkflow"],"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)."},"volumePreset":{"description":"Monthly request volume: 10k, 100k, or 1m. Default: 100k","type":"string","enum":["10k","100k","1m"]},"maxMonthlyBudget":{"description":"Maximum monthly budget in USD at the given volume. Tested against the LIST-price monthly cost, not the caching/batch-optimized cost.","type":"number","exclusiveMinimum":0},"minElo":{"description":"Minimum Chatbot Arena ELO score. Typical range 1000-1500; ~1400 is roughly frontier-class. Models with no ELO score never satisfy this.","type":"number","exclusiveMinimum":0},"requiredCapability":{"description":"Capability the model must have: Text, Vision, Reasoning, Agents, Image Gen, Audio. There is no Code capability: for coding, pass useCasePreset codingTask.","type":"string"},"openness":{"description":"Require a self-hostability bucket, derived from the licence: Open source, Open weights, Proprietary, Unknown","type":"string","enum":["Open source","Open weights","Proprietary","Unknown"]}},"required":["useCasePreset"],"$schema":"http://json-schema.org/draft-07/schema#"},"annotations":{"title":"Recommend an LLM Model","readOnlyHint":true,"destructiveHint":false,"openWorldHint":true},"definitionHash":"18e65ef22f2e4ba013ce09fddd3d39bf105d2fb2f279f96c0c64c4c7634d63ea","schemaStatus":"valid","origin":"official-registry","observedAt":"2026-11-19T23:46:37.758Z","metadataTrust":"untrusted"},{"serverName":"io.github.OptimNow/ai-pricing-hub","endpointFingerprint":"6bc975b213d359f660adf536cb8cebabd52cfce6db61eb28189973d163df34ac","name":"track-llm-price-changes","title":"Track LLM Price Changes","description":"What moved. Every other tool here quotes today's price; this one says whether it has just changed, from the price archive optimtoken.optimnow.io keeps (its first day is `provenance.trackingStart`). Without `models` it returns the moves of the last 7 days across the catalogue: each model whose quoted price moved by 1% or more, with the price before and after and what the move does to a workload's monthly bill. With `models` (1-4 names) it returns each model's quoted price since tracking began, change by change. Use it for 'did any LLM price change this week', 'which models got cheaper', 'has the price of X moved since the summer', 'is this price stable enough to budget on'. Read the flags: most models are sold by several hosts and one of them is quoted, so a move flagged `hostSwitch` is a change of the host quoted, not a repricing, and `outlierHost` is an outlier listing. The moves with no flag are returned apart, as `priceChanges`; no flag means none was established, which is not proof that the model maker repriced. There is no fallback for this data: when the archive cannot be read the tool returns an error, never an empty list that would read as 'nothing moved'.","inputSchema":{"type":"object","properties":{"models":{"description":"1-4 model names, for each one's price history since tracking began, e.g. ['Llama 3.3 70B']. Leave out for the week's moves across the catalogue.","minItems":1,"maxItems":4,"type":"array","items":{"type":"string"}},"direction":{"description":"Week's moves only: keep the rises (up) or the falls (down). Not accepted with `models`.","type":"string","enum":["up","down"]},"provider":{"description":"Week's moves only: keep one provider's models, by exact name (case-insensitive), e.g. OpenAI, Anthropic, Meta. Not accepted with `models`.","type":"string"},"includeFlagged":{"description":"Week's moves only: false leaves out the moves flagged as a change of quoted host or an outlier listing. Default: true, returned apart in `flaggedMoves`. Not accepted with `models`.","type":"boolean"},"limit":{"description":"Week's moves: max moves returned in each of the two groups, largest first. History: max changes printed per model, the most recent (structuredContent carries all). Default: 15","type":"number","minimum":1,"maximum":50},"useCasePreset":{"description":"Workload the monthly figures are computed for, which sets tokens per request: supportTicket (1.5k in / 500 out), knowledgeQA (2k / 800), meetingSummary (10k / 1.2k), marketingContent (2.5k / 1.8k), codingTask (3k / 2k), invoiceProcessing (1.5k / 600), callSummary (2k / 700), agentWorkflow (6k / 3k). Default: supportTicket","type":"string","enum":["supportTicket","knowledgeQA","meetingSummary","marketingContent","codingTask","invoiceProcessing","callSummary","agentWorkflow"]},"volumePreset":{"description":"Monthly request volume: 10k, 100k, or 1m. Default: 100k","type":"string","enum":["10k","100k","1m"]}},"$schema":"http://json-schema.org/draft-07/schema#"},"annotations":{"title":"Track LLM Price Changes","readOnlyHint":true,"destructiveHint":false,"openWorldHint":true},"definitionHash":"6397635e7b8fd4e6f8906035553900f36f84a7d202059e7e2cbb85d1c263f008","schemaStatus":"valid","origin":"official-registry","observedAt":"2026-11-19T23:46:37.758Z","metadataTrust":"untrusted"}],"endpoints":[{"endpointFingerprint":"6bc975b213d359f660adf536cb8cebabd52cfce6db61eb28189973d163df34ac","protocol":"streamable-http","status":"indexed","toolCount":8,"observedAt":"2026-11-19T23:46:37.758Z"}],"authentication":"unknown"},"connectionConfigurations":{"status":"ready","authentication":"not embedded","clients":{"Claude Desktop":{"mcpServers":{"io.github.OptimNow/ai-pricing-hub":{"url":"https://optimtoken-mcp.optimnow.io/mcp"}}},"Cursor":{"mcpServers":{"io.github.OptimNow/ai-pricing-hub":{"url":"https://optimtoken-mcp.optimnow.io/mcp"}}},"VS Code":{"servers":{"io.github.OptimNow/ai-pricing-hub":{"type":"http","url":"https://optimtoken-mcp.optimnow.io/mcp"}}}}},"resourceType":"mcp-server","callable":true,"runtime":{"callable":true,"protocols":["mcp"]},"interfaces":[{"protocol":"mcp","transport":"streamable-http","url":"https://optimtoken-mcp.optimnow.io/mcp"}],"profile":{"apiVersion":"1","schemaVersion":"1","id":"mcp-server:io.github.OptimNow%2Fai-pricing-hub","resourceType":"mcp-server","canonicalUrl":"https://www.agentsjunction.com/api/v1/servers/io.github.OptimNow%2Fai-pricing-hub","name":"io.github.OptimNow/ai-pricing-hub","description":"Compare LLM API and cloud compute pricing, estimate workload costs, pick a model within budget.","interfaces":[{"protocol":"mcp","transport":"streamable-http","url":"https://optimtoken-mcp.optimnow.io/mcp"}],"capabilities":[],"identity":{"source":"official-registry","websiteUrl":"https://optimtoken.optimnow.io/mcp","repositoryUrl":"https://github.com/OptimNow/ai-pricing-hub-mcp","version":"0.4.2"},"verification":{"state":"official","confidence":100},"operations":{"resourceType":"mcp-server","name":"io.github.OptimNow/ai-pricing-hub","status":"online","lastCheckedAt":"2026-11-20T05:17:56.537Z","lastSuccessfulCheck":"2026-11-20T05:17:56.537Z","latencyMs":203,"consecutiveFailures":0,"isStale":false,"checks":{"endpointReachable":true,"protocolValid":true,"agentCardValid":null,"mcpHandshakeValid":true},"lastSeen":null,"lastSuccessfulInteraction":null,"lastHealthCheck":"2026-11-20T05:17:56.537Z","source":{"type":"health-check","url":null},"observedAt":"2026-11-20T05:17:56.537Z"},"security":null,"timestamps":{"createdAt":"2026-10-07T21:20:44.409Z","updatedAt":"2026-10-07T21:20:44.409Z","observedAt":"2026-11-20T05:17:56.537Z"},"compatibility":{"serverVersion":"0.4.2","protocolVersions":[{"protocol":"mcp","version":null}]}}}}