Silicon Analysts
⚡API

Silicon Analysts Data API

Structured semiconductor data for AI agents, applications, and researchers. Free to use — no API key required for read endpoints.

Connect to AI Agents (MCP)

New

MCP (Model Context Protocol) lets AI assistants like Claude directly query Silicon Analysts data during conversations — no manual copy-paste needed. Ask about chip costs, wafer pricing, or supply chain trends and get live data in real time.

Connect to Claude Desktop

1Generate an API key below — required for MCP access. Free tier: 100 req/24h.
2Open Claude Desktop → Settings → Developer → Edit Config
3Add to claude_desktop_config.json:
{
  "mcpServers": {
    "silicon-analysts": {
      "url": "https://siliconanalysts.com/api/mcp",
      "headers": {
        "Authorization": "Bearer sa_live_YOUR_API_KEY_HERE"
      }
    }
  }
}
4Restart Claude Desktop
5Ask Claude anything about semiconductor supply chain data

Connect from Cursor, Windsurf, or any MCP client

The server speaks standard streamable-HTTP MCP at https://siliconanalysts.com/api/mcp, so any MCP-capable IDE or agent framework can query semiconductor economics in-editor. In Cursor: Settings → MCP → Add server. In Windsurf: mcp_config.json. Same config shape either way:

{
  "mcpServers": {
    "silicon-analysts": {
      "url": "https://siliconanalysts.com/api/mcp",
      "headers": { "Authorization": "Bearer sa_live_YOUR_API_KEY_HERE" }
    }
  }
}

Anonymous access also works for current data (omit the header, ~20 req/24h per IP; history needs a free key) — see /for-agents for the no-signup path. LangChain / Vercel AI SDK users can point any MCP or plain-HTTP tool adapter at the same endpoint; every response carries meta.freshness so agents know when re-fetching pays off.

Available MCP Tools

ToolWhat it answers
get_accelerator_costsAI chip specs, costs, and margins (13 chips)
calculate_chip_costDie dimensions → manufacturing cost estimate
estimate_lead_timeMask layers + utilization → manufacturing cycle time (weeks)
get_hbm_market_dataHBM pricing, market share, and forecasts
get_market_pulseCurrent supply chain signals and headlines
get_wafer_pricingWafer price ranges by process node
get_packaging_costsPackaging costs and capabilities + HBM specs
get_hbm_qualificationHBM qualification matrix + status timeline per platform
get_foundry_allocationFoundry capacity allocation snapshot by node
get_foundry_economicsQuarterly per-node wafer ASP + utilization from public IR
get_recent_changesWhat changed in the data ledger (7d/30d window)
get_market_intelligenceSourced semiconductor intelligence briefs
get_market_advantageVetted time-advantage evidence (coverage-race wins)
get_benchmark_historyHistorical benchmark observations, as-of any date
get_fab_capacityFab-level capacity snapshots over time
get_forecastsThird-party forecast vintages by original publication date
get_wfe_signalsWFE-maker order-book (ASML/AMAT/Lam/KLA/TEL) from IR
get_fab_eventsFab construction/ramp milestone log, delays included
get_policy_eventsTrade-policy timeline anchored to government documents

Example Prompts

After connecting, try asking Claude:

“What's the current wafer price range for TSMC N3?”
“Calculate chip cost for a 10x10mm die on N3 with CoWoS packaging”
“How long would a 3nm chip take to manufacture with CoWoS packaging at current utilization?”
“Compare H100 vs B200 manufacturing cost breakdown”
“What are the latest supply chain signals in advanced packaging?”
📘

Integration Guides

Building agents on the Anthropic SDK, LangChain, or the Vercel AI SDK? Step-by-step guides with working code show how to wire up these MCP tools in minutes.

Anthropic SDK →LangChain →Vercel AI SDK →All integrations →

Quick Start

# Get all AI accelerator cost breakdowns curl https://siliconanalysts.com/api/v1/accelerators # Filter by vendor curl "https://siliconanalysts.com/api/v1/accelerators?vendor=NVIDIA" # Calculate chip cost (POST) curl -X POST https://siliconanalysts.com/api/v1/calculate/chip-cost \ -H "Content-Type: application/json" \ -d '{"dieWidth": 26, "dieHeight": 33, "processNode": "5nm"}' # Get HBM market data curl https://siliconanalysts.com/api/v1/hbm # Search analysis articles curl "https://siliconanalysts.com/api/v1/articles?q=tsmc&limit=5"

Endpoints

MethodEndpoint
GET/api/v1
GET/api/v1/usage
GET/api/v1/accelerators
GET/api/v1/hbm
GET/api/v1/articles
GET/api/v1/market-pulse
GET/api/v1/market-data
GET/api/v1/foundry/wafer-pricing
GET/api/v1/foundry/economics
GET/api/v1/foundry/packaging-costs
GET/api/v1/allocation
POST/api/v1/calculate/chip-cost
POST/api/v1/calculate/lead-time
GET/api/v1/market-advantage
GET/api/v1/schema
GET/api/v1/snapshot
GET/api/v1/export
GET/api/v1

Lists all available endpoints, schemas, and usage terms. Start here for discovery.

Example Response

{
  "name": "Silicon Analysts Data API",
  "version": "1",
  "endpoints": [ ... ],
  "usage": { "tracking": "All requests logged" }
}
Cache: 1 hour · Rate limit: 20 req/day (no key) · 100 req/day (free key) · 10k req/hr (Pro)
GET/api/v1/usage

Your own call history across REST + MCP: timestamp, endpoint/tool, redacted params, status, latency, payload size, request_id (matches the X-Request-Id response header), and trace_id when your client sent a W3C traceparent header. We echo traceparent/tracestate on every response and store the trace-id, so your security team can join our audit trail against your own distributed traces (leaf participant — no re-spanning). Requires an API key.

Query Parameters

window24h | 7d | 30d (default 7d)?window=7d
limitMax rows after merging both surfaces (1–2000)?limit=500
beforeISO cursor: rows strictly older?before=2026-07-01T00:00:00Z

Example Response

{
  "success": true,
  "data": { "usage": [{
    "ts": "2026-07-05T10:12:03.412Z",
    "surface": "mcp",
    "target": "get_wafer_pricing",
    "status": "success",
    "latency_ms": 41, "response_bytes": 18234,
    "request_id": "7f3c…", "trace_id": "4bf92f3577b34da6a3ce929d0e0e4736"
  }] },
  "meta": { "count": 1, "window": "7d", "note": "request_id ↔ X-Request-Id; trace_id ↔ your traceparent" }
}
Cache: none (private, no-store) · Rate limit: 100 req/day (free key) · 10k req/hr (Pro)
GET/api/v1/accelerators

Manufacturing cost data for 13 AI accelerators: NVIDIA H100, H200, B100, B200, GB200, AMD MI300X, MI355X, Intel Gaudi 3, Google TPU v5p, AWS Trainium 2, Microsoft Maia 100, Meta MTIA v2. Includes logic die, HBM, packaging, and test costs.

Query Parameters

vendorFilter by vendor (case-insensitive)?vendor=NVIDIA
chipFilter by chip name (partial match, case-insensitive)?chip=H100
fieldsReturn only specified fields (comma-separated)?fields=chip,estMfgCostUsd

Example Response

{
  "success": true,
  "data": [{
    "chip": "NVIDIA H100 SXM5",
    "vendor": "NVIDIA",
    "processNode": "TSMC 4N",
    "estMfgCostUsd": 3320,
    "estSellPriceUsd": 32500,
    "chipGrossMarginPct": 87.5,
    "costBreakdown": {
      "logicDieCostUsd": 300,
      "hbmCostUsd": 1350,
      "packagingCostUsd": 750,
      "testAssemblyCostUsd": 920
    },
    ...
  }],
  "meta": {
    "count": 13,
    "source": "Silicon Analysts",
    "freshness": {
      "cadence": "Weekly — cost models recompute when inputs move (Monday refresh fleet)",
      "next_refresh": "2026-07-06T12:30:00.000Z",
      "delta_check": "https://siliconanalysts.com/api/v1/changes?window=7d — empty = nothing moved"
    }
  }
}
Cache: 1 hour · Rate limit: 20 req/day (no key) · 100 req/day (free key) · 10k req/hr (Pro)
GET/api/v1/hbm

Full HBM market dataset with 10 data tables: accelerator specs, HBM generation specs, vendor market share, spot prices, leading indicators, qualification feed, revenue forecast, supplier revenue, validation checks, and derived bit demand. bitDemand is HBM bits by SKU class + customer type (EB ranges, monthly refresh) — NOT a training-vs-inference split; dominant SKUs are dual-use, so that attribution would be dishonest. Current snapshots (specs, spot prices, market share, leading indicators) are free at full fidelity; the forward-looking series (revenueForecast, supplierRevenue, bitDemand) return a latest teaser for free/anonymous callers and the full time series for Pro — clamped with an explanatory note, never rejected.

Query Parameters

tableNarrow to one sub-table (accelerators, specs, marketShare, spotPrices, leadingIndicators, qualificationFeed, revenueForecast, supplierRevenue, validationChecks, bitDemand)?table=bitDemand

Example Response

{
  "success": true,
  "data": {
    "accelerators": [ ... ],
    "specs": [ ... ],
    "marketShare": [ ... ],
    "spotPrices": [ ... ],
    "leadingIndicators": [ ... ],
    "qualificationFeed": [ ... ],
    "revenueForecast": [ ... ],
    "supplierRevenue": [ ... ],
    "validationChecks": [ ... ],
    "bitDemand": [{
      "metric": "hbm_bits_sku_class",
      "entity": "Blackwell",
      "period": "2026",
      "value_text": "≈1.15–1.92 EB (6–10M units × 192–384 GB/unit)",
      "value_num": 1.54, "value_min": 1.15, "value_max": 1.92, "unit": "EB",
      "observed_week": "2026-08-03", "as_of": "2026-01-01",
      "confidence": "medium", "agreement": "strong", "independent_sources": 2,
      "source_url": "https://...", "evidence": "Derived: public shipment-mix estimates × per-SKU HBM content...",
      "provenance": { "last_updated": "...", "source_type": "derived", "confidence_tier": "medium", "dataset_version": "hbmData-v1.0" }
    }]
  },
  "meta": { "source": "Silicon Analysts", "bitDemandNote": "bitDemand is NOT a workload split — ..." }
}
Cache: 5 minutes · Rate limit: 20 req/day (no key) · 100 req/day (free key) · 10k req/hr (Pro)
GET/api/v1/articles

Metadata for 30+ semiconductor industry articles. Includes title, date, description, executive insight, key takeaways, cited sources, and full URL.

Query Parameters

limitReturn only the N most recent articles?limit=5
qSearch in title and description (case-insensitive)?q=nvidia

Example Response

{
  "success": true,
  "data": [{
    "slug": "nvidia-gpu-prices-double-...",
    "title": "Nvidia GPU Prices Double as AI Demand...",
    "date": "2026-01-23",
    "description": "Analysis of Jensen Huang's comments...",
    "insight": "The spillover of AI-driven demand...",
    "keyTakeaways": ["...", "..."],
    "url": "https://siliconanalysts.com/analysis/...",
    "sources": [{ "publisher": "...", "title": "..." }]
  }],
  "meta": { "count": 30, "source": "Silicon Analysts" }
}
Cache: 1 hour · Rate limit: 20 req/day (no key) · 100 req/day (free key) · 10k req/hr (Pro)
GET/api/v1/market-pulse

Real-time semiconductor market intelligence across 6 sectors: Logic, Memory, Packaging, Connectivity, Power, Geopolitics. Each headline includes trend direction, source, and impact analysis.

Query Parameters

categoryFilter by sector (logic, memory, packaging, connectivity, power, geopolitics)?category=memory
trendFilter by trend direction (up, down, neutral)?trend=up
limitMax items to return (1-50)?limit=5

Example Response

{
  "success": true,
  "data": [{
    "category": "Memory",
    "headline": "HBM3e prices expected to increase 15-20%...",
    "trend": "up",
    "date": "Jan 2026",
    "source": "Silicon Analysts Research",
    "impact_analysis": "HBM demand continues to grow..."
  }],
  "meta": { "count": 12, "categories": ["Logic", "Memory", ...] }
}
Cache: 5 minutes · Rate limit: 20 req/day (no key) · 100 req/day (free key) · 10k req/hr (Pro)
GET/api/v1/market-data

List all semiconductor market data datasets with metadata. Covers wafer pricing, HBM/DRAM pricing, CoWoS capacity, fab utilization, NRE costs, AI chip BOM, capex, lead times, NAND pricing, and cloud GPU pricing. Individual dataset endpoints (/api/v1/market-data/{id}) require Pro for full history.

Example Response

{
  "success": true,
  "data": [{
    "id": "wafer-price-tsmc",
    "name": "TSMC Wafer Price by Node",
    "category": "Wafer Pricing",
    "unit": "USD/wafer",
    "description": "Estimated 300mm wafer prices...",
    "proOnly": false
  }, ...],
  "meta": { "count": 14 }
}
Cache: 1 hour · Rate limit: 20 req/day (no key) · 100 req/day (free key) · 10k req/hr (Pro)
GET/api/v1/foundry/wafer-pricing

Current wafer price ranges for 7 process nodes across TSMC, Samsung, and Intel. Includes defect density, NRE/mask set costs, and node maturity status with yield risk ratings.

Query Parameters

nodeFilter to a specific node (tsmc-n3, tsmc-n5, tsmc-n7, samsung-3nm, samsung-5nm, intel-16, tsmc-28)?node=tsmc-n3

Example Response

{
  "success": true,
  "data": [{
    "node": "tsmc-n3",
    "label": "TSMC 3nm (N3)",
    "waferCost": { "avg": 19500, "min": 17000, "max": 22000, "unit": "USD/wafer" },
    "defectDensity": { "mature": 0.09, "early": 0.14, "unit": "defects/cm²" },
    "nreCost": { "maskSetCost": 15000000, "totalNRE": 22000000, "unit": "USD" },
    "maturity": { "status": "Ramping", "yieldRisk": "High" },
    "source": "Analyst Reports, TrendForce, Morgan Stanley"
  }],
  "meta": { "count": 7, "updated": "2026-06-22" }
}
Cache: 1 hour · Rate limit: 20 req/day (no key) · 100 req/day (free key) · 10k req/hr (Pro)
GET/api/v1/foundry/economics

Per-foundry, per-process-node, per-fiscal-quarter wafer ASP (min/max/blended, USD per 300mm-equivalent wafer) and fab utilization (%), derived from public IR materials (earnings releases, transcripts, decks) via a documented scaling calculation (rev-mix-v1). Covers TSMC, UMC, Intel, Samsung, SMIC, GlobalFoundries. Every row carries source URLs, release dates, and a confidence tier; utilization is stated (the company said it) or derived (shipments vs capacity, capped medium) and never fabricated per node. The latest period per foundry is free; multi-period history (quarter/from/to) requires a Pro key — free callers are clamped to the latest period with an explanatory note, never rejected.

Query Parameters

foundrytsmc | umc | intel | samsung | smic | gf?foundry=tsmc
nodeCanonical node token (n3, n5, n16-20, 22-28nm, 18a, ...)?node=n3
node_groupCross-foundry bucket (leading_2nm, leading_3nm, class_5nm, class_7nm, class_10_22nm, mature_28nm_plus)?node_group=leading_3nm
quarterExact period, YYYYQn or YYYYFY (Pro)?quarter=2026Q1
from / toInclusive period range (Pro)?from=2024Q1&to=2026Q1
include_factsAlso return the underlying published IR evidence facts (verbatim quote + source per datum)?include_facts=true

Example Response

{
  "success": true,
  "data": {
    "foundries": [{
      "foundry": "tsmc",
      "fiscal_quarter": "2026Q1",
      "fiscal_note": null,
      "utilization": { "pct": 93.8, "basis": "derived", "range": { "min": null, "max": null }, "confidence": "medium" },
      "blended_asp_usd": { "value": 8500, "basis": "derived_mix", "confidence": "high" },
      "source_urls": ["https://investor.tsmc.com/english/quarterly-results/2026/q1"],
      "release_dates": ["2026-04-16"],
      "nodes": [{
        "node": "n3",
        "node_label": "3nm (N3)",
        "node_group": "leading_3nm",
        "wafer_asp_usd": { "min": 18000, "max": 22000, "blended": 20000 },
        "asp_basis": "derived_mix",
        "revenue_share_pct": 25,
        "utilization": null,
        "confidence": "medium",
        "source_urls": ["https://investor.tsmc.com/english/quarterly-results/2026/q1"],
        "release_dates": ["2026-04-16"],
        "derivation": { "method_version": "rev-mix-v1", "derived_at": "2026-07-13T14:31:02Z" },
        "provenance": { "last_updated": "2026-07-13T14:31:02Z", "source_type": "derived", "confidence_tier": "medium", "dataset_version": "foundry-economics-v1" }
      }]
    }],
    "quarters_returned": ["2026Q1"],
    "truncated": false
  },
  "meta": { "methodology": "Scaling calculation over public IR statements...", "history_access": "Latest period free; history requires Pro", "count": 1 }
}
Cache: 5 minutes (latest view); Pro history responses are private · Rate limit: 20 req/day (no key) · 100 req/day (free key) · 10k req/hr (Pro)
GET/api/v1/foundry/packaging-costs

Advanced semiconductor packaging cost benchmarks and technology capabilities for 14+ packaging types (CoWoS-S, CoWoS-L, EMIB, SoIC, InFO-PoP, FC-BGA, and the pilot-stage CoPoS panel-level entry — capabilities/notes only, no $ benchmark until public pricing exists). Also returns HBM memory specs and per-stack costs across generations.

Query Parameters

typeFilter by packaging type (cowos, cowos-l, emib, soic, info-pop, fc-bga, fc-csp, etc.)?type=cowos

Example Response

{
  "success": true,
  "data": {
    "packaging": [{
      "id": "cowos",
      "name": "CoWoS-S (2.5D)",
      "description": "Silicon Interposer. Standard for high-end chips.",
      "category": "hpc-ai",
      "costBenchmark": { "cost": 600, "unit": "USD/package", "costRange": { "min": 600, "max": 900 } },
      "capabilities": { "interposerActive": true, "stacking": false, ... }
    }],
    "hbmSpecs": [{
      "type": "HBM3e",
      "bandwidth": "1.2 TB/s",
      "capacity": "36 GB",
      "costPerStack": 300,
      "unit": "USD/stack"
    }]
  },
  "meta": { "packagingCount": 14, "hbmSpecCount": 5 }
}
Cache: 1 hour · Rate limit: 20 req/day (no key) · 100 req/day (free key) · 10k req/hr (Pro)
GET/api/v1/allocation

Current allocation snapshot + optional time-series history for foundry nodes and advanced packaging (TSMC, Samsung, Intel × N2, N3, CoWoS-S, CoWoS-L, SoIC). Shows what is booked vs available, lead-time weeks, utilization, price trend, geo risk, and publicly-reported customer allocation shares. Every record carries provenance (source type, confidence tier, last updated). Sourced public estimates, human-reviewed. The current snapshot is free; the time-series history (include_history=true) requires a Pro key — free/anonymous callers get the snapshot only, with an explanatory note, never rejected.

Query Parameters

foundryFilter by foundry (case-insensitive)?foundry=TSMC
nodeFilter by node/technology (substring: n2, n3, cowos-l, soic, …)?node=cowos-l
categoryleading_edge | advanced | mature | packaging | hbm?category=packaging
customerFilter to nodes/readings involving a customer (substring)?customer=NVIDIA
include_historyInclude the time-series history array?include_history=true
history_metricNarrow history (lead_time, pct_locked, customer_allocation, cowos_capacity, foundry_utilization)?history_metric=lead_time

Example Response

{
  "success": true,
  "data": {
    "current": [{
      "id": "tsmc-n2",
      "foundry": "TSMC",
      "node": "N2 / A16",
      "allocation_status": "fully_booked",
      "lead_time_weeks_min": 78,
      "lead_time_weeks_max": 156,
      "lead_time_trend": "stable",
      "price_trend": "rising",
      "customers": ["Apple", "AMD", "MediaTek", "Qualcomm"],
      "customer_shares": [{ "customer": "Lead mobile customer (public est.)", "share": 50 }],
      "latest_signal": {
        "metric": "pct_locked",
        "value_text": "production schedule largely booked through late 2026",
        "as_of": "2026-06-01", "observed_week": "2026-06-29", "confidence": "medium"
      },
      "provenance": {
        "last_updated": "2026-06-15",
        "source_type": "research",
        "confidence_tier": "medium",
        "dataset_version": "allocation-v1"
      }
    }],
    "history": [{
      "metric": "pct_locked", "entity": "TSMC CoWoS", "node": "CoWoS-L",
      "value_text": ">85%", "value_num": 85, "unit": "%",
      "observed_week": "2026-06-15", "agreement": "strong",
      "independent_sources": 2,
      "provenance": { "confidence_tier": "medium", "dataset_version": "allocation-v1" }
    }]
  },
  "meta": { "snapshot_source": "table", "current_count": 13, "history_count": 11, "signals_current_through": "2026-06-29" }
}
Cache: 5 minutes · Rate limit: 20 req/day (no key) · 100 req/day (free key) · 10k req/hr (Pro)
POST/api/v1/calculate/chip-cost

Calculate manufacturing cost breakdown for a custom chip design. Provide die dimensions and process node to get yield analysis, cost per die, packaging, and ASP estimates.

Request Body (JSON)

dieWidthnumber *Die width in mm
dieHeightnumber *Die height in mm
processNodestring *Process node (e.g., "7nm", "5nm", "28nm")
waferCostnumberOverride wafer cost in USD
packagingTypestringPackaging type (e.g., "Flip-Chip BGA")
packagingCostnumberOverride packaging cost in USD
hbmStacksnumberNumber of HBM stacks (0-8)
hbmCostnumberOverride per-stack HBM cost in USD
testCostnumberOverride test cost in USD
volumenumberAnnual production volume
marginTargetnumberTarget gross margin (0-1)
energyRegionstringOpt-in manufacturing-energy adder: fab region for electricity pricing (texas, ohio, arizona, china, korea, taiwan, germany). Adds a conditional `energy` block — SA estimate, scenario delta (wafer price already embeds foundry energy)
energyFacilityOverheadbooleanApply the ~1.75× facility-overhead multiplier to the energy adder (default true; only meaningful with energyRegion)
substratestringPackaging substrate SCENARIO (default no-op): wafer-300mm | panel-310x310. Panel applies the midpoint of Yole's realistic 20–30% CoPoS savings band to the packaging cost only — silicon GDPW unchanged. SA scenario; TSMC CoPoS pilot ~Jun 2026, MP 2028–29.
kgdTestCoveragenumberKnown-Good-Die pre-bond test coverage % (0–100). Returns a kgdScenario block: per-die test cost at this coverage vs. the packaged-defect waste it avoids, effective KGD quality, and the cost-minimizing coverage. Informational — never changes the headline cost. SA scenario.

Example Response

{
  "success": true,
  "data": {
    "estimatedChipCost": 1004.57,
    "dieArea": 806,
    "grossDiesPerWafer": 67,
    "frontendYield": 56.32,
    "totalYield": 55.19,
    "costBreakdown": {
      "waferCostPerGoodDie": 500.28,
      "packagingAndTestCost": 2,
      "hbmCost": 0,
      "marginCost": 502.28
    },
    "inputs": {
      "dieWidth": 26,
      "dieHeight": 31,
      "processNode": "tsmc-n5",
      "waferCost": 18500,
      "packagingType": "flip-chip",
      "hbmStacks": 0,
      "marginTarget": 50
    }
  },
  "meta": { "source": "Silicon Analysts", "apiVersion": "1" }
}
Cache: No cache · Rate limit: 20 req/day (no key) · 20 req/day (free key) · 10k req/hr (Pro)
POST/api/v1/calculate/lead-time

Heuristic chip manufacturing lead-time estimation: MANUFACTURING CYCLE TIME (wafer fab + packaging assembly/test) as a min/max band in weeks. Mask layers × utilization-scaled days-per-mask-layer (FabTime operating-curve shape) + a packaging-class adder. EXCLUDES allocation/booking queue time — use /api/v1/allocation for booking windows.

Request Body (JSON)

maskLayersnumberTotal mask layers, integer 10–200. Required unless processNode is set (then defaults to the node-typical mask count)
processNodestringNode ID for node-aware defaults: tsmc-n3 | tsmc-n5 | tsmc-n7 | tsmc-28 | samsung-3nm | samsung-5nm | intel-16. Supplies typical mask count + a DPML factor
utilizationnumberFoundry utilization % (0–100). Omitted: defaults from live foundry-allocation data for the node (else a documented constant); the fired default is echoed in assumptions. ≤80% → best-case band; ≥95% → worst-case bound
packagingTypestringCoarse class conventional | flip-chip | cowos (default flip-chip), or any platform packaging id (fc-bga, wirebond-bga, cowos-l, copos, qfn, fowpl, 3d-stacking, ...)

Example Response

{
  "success": true,
  "data": {
    "fabDays": { "min": 104, "max": 137 },
    "fabWeeks": { "min": 14.8, "max": 19.5 },
    "packagingWeeks": { "min": 8, "max": 14 },
    "totalWeeks": { "min": 22.8, "max": 33.5 },
    "effectiveDpml": { "min": 1.092, "max": 1.438 },
    "utilizationWeight": 1,
    "inputs": {
      "maskLayers": 95, "utilization": 98, "utilizationSource": "allocation_live",
      "packagingType": "cowos", "packagingClass": "cowos",
      "processNode": "tsmc-n3", "nodeDpmlFactor": 1.15
    },
    "assumptions": ["maskLayers defaulted to 95 (typical for TSMC 3nm (N3) ...)", "..."],
    "methodology": "fabDays = maskLayers × effective DPML (days per mask layer). ...",
    "sources": [{ "name": "Utilization operating curve", "citation": "FabTime Cycle Time Tutorial & Queueing Formulas (INFICON), 2023 ..." }],
    "provenance": { "source_type": "computed", "confidence_tier": "low", "dataset_version": "leadTimeData-v1.0" }
  },
  "meta": { "source": "Silicon Analysts", "allocationCaveat": "Manufacturing cycle time only. Booking/allocation queue time is EXCLUDED ..." }
}
Cache: No cache · Rate limit: 20 req/day (no key) · 20 req/day (free key) · 10k req/hr (Pro) — shared calc bucket
GET/api/v1/market-advantage

Human-vetted proof that Silicon Analysts recorded a semiconductor supply-chain event before the first English-language coverage of it. Per win: our immutable first-seen timestamp, the cited source's publication time, the first English coverage's time + public URL/publisher, and the lead in hours. Only wins a human has confirmed for citation are returned — facts, not claims; empty until a win is confirmed.

Query Parameters

limitMax wins (1–100)?limit=25
order_bylead_time (default) | recent?order_by=lead_time
event_kindhbm_qual | capacity_signal | market_intelligence?event_kind=hbm_qual

Example Response

{
  "success": true,
  "data": {
    "wins": [{
      "event_kind": "hbm_qual",
      "event_ref": "SK Hynix|NVIDIA|HBM4|12-Hi",
      "our_first_seen_at": "2026-07-01T09:12:00Z",
      "english_first_seen_at": "2026-07-01T14:30:00Z",
      "english_publisher": "Reuters",
      "english_url": "https://...",
      "lead_time_hours_vs_detection": 5.3,
      "provenance": { "source_type": "derived", "confidence_tier": "high", "dataset_version": "market-advantage-v1" }
    }],
    "count": 1
  },
  "meta": { "citeAs": "Silicon Analysts — Market Advantage", "methodology": "https://siliconanalysts.com/data-quality#immutability" }
}
Cache: 5 minutes · Rate limit: 20 req/day (no key) · 100 req/day (free key) · 10k req/hr (Pro)
GET/api/v1/schema

Machine-readable data dictionary: per-dataset point-in-time semantics — which timestamp is our first-seen vs the data's vintage, what mutates vs what is frozen, and how corrections work (append-only events, daily ledger, trigger-written history tables, archive + re-insert). Plus field docs, refresh cadences, and the endpoints/MCP tools serving each dataset. Built for data-engineering and DDQ reviewers.

Example Response

{
  "success": true,
  "data": {
    "version": "data-dictionary-v1",
    "pit_classes": { "append_only_event": "Rows never change; the table is its own complete history.", ... },
    "sourcing_policy": "Public sources only — no insider data. ...",
    "datasets": [{
      "id": "hbm_qualification_events",
      "pit_class": "append_only_event",
      "first_seen_field": "detected_at",
      "vintage_field": "as_of",
      "correction_policy": "Append-only; a wrong event is superseded by a later event...",
      "fields": [ ... ]
    }]
  }
}
Cache: 1 hour · Rate limit: 20 req/day (no key) · 100 req/day (free key) · 10k req/hr (Pro)
GET/api/v1/snapshot

The full frozen state of every published metric on a given day — "what did the feed say on date D?" Serves the newest ledger day at/before the requested date and reports both dates honestly. The ledger is append-only from 2026-06-06: days are never edited or backfilled, which is exactly what makes it backtest-grade. Requires a Pro API key or Pro session.

Query Parameters

dateYYYY-MM-DD (default today). Served day = newest snapshot at/before this date.?date=2026-06-20
domainFilter to one ledger domain (wafer_pricing, chip_cost, margin_benchmark, foundry_capacity, defect_density, nre_cost, hbm_spot_price, hbm_leading_indicator, hbm_market_share, hbm_revenue_forecast, hbm_supplier_revenue)?domain=wafer_pricing
limitMax rows (1–2000; truncated flag reports overflow)?limit=500

Example Response

{
  "success": true,
  "data": {
    "date_requested": "2026-06-20",
    "date_served": "2026-06-20",
    "ledger_start": "2026-06-06",
    "domain": "wafer_pricing",
    "rows": [{
      "domain": "wafer_pricing", "entity_id": "tsmc-n3", "metric": "avg",
      "value_num": 19500, "unit": "usd_per_wafer",
      "captured_at": "2026-06-20T08:00:12.412Z"
    }],
    "count": 45, "truncated": false
  }
}
Cache: 5 minutes (private) · Rate limit: Pro subscription required · 10k req/hr
GET/api/v1/export

Download the dated append-only history of a series as JSONL (default) or CSV — one HTTP call, no pagination gymnastics. Datasets: any daily-ledger domain, the HBM qualification event timeline, or the published capacity-signal series. Bounded at 10,000 rows with an explicit truncated flag (X-Truncated header + JSONL _meta line); narrow with from/to to page longer histories. Requires a Pro API key or Pro session.

Query Parameters

datasetRequired: a ledger domain (e.g. wafer_pricing, chip_cost) or hbm_qualification_events | capacity_signals?dataset=hbm_qualification_events
fromInclusive start date (YYYY-MM-DD)&from=2026-06-06
toInclusive end date (YYYY-MM-DD)&to=2026-07-01
formatjsonl (default) | csv&format=csv

Example Response

{"_meta":{"dataset":"hbm_qualification_events","count":214,"truncated":false,"time_axis":"detected_at","note":"Append-only history export."}}
{"detected_at":"2026-06-14T09:02:11.000Z","relationship":"SK Hynix|NVIDIA|HBM4|12-Hi","new_status":"qualified","as_of":"2026-06-13","source_url":"https://...","confidence":"high"}
{"detected_at":"2026-06-16T09:01:47.000Z","relationship":"Samsung|NVIDIA|HBM4|12-Hi","new_status":"in_qualification"}
Cache: 5 minutes (private) · Rate limit: Pro subscription required · 10k req/hr

Authentication & Rate Limits

All endpoints accept API keys for higher rate limits and authenticated usage tracking. Anonymous IP-based access works for real use of current data (20 GET req/day, 10 POST calculate req/day). Historical / time-series data requires a free API key — a key raises limits, unlocks a history preview, and attributes usage to your account.

Generate a free API key below for higher rate limits (100 req/day) and a history preview. Pro keys unlock 10,000 req/hr and the full time series. Include your key in requests via header:

# API key via X-API-Key header curl -H "X-API-Key: sa_live_abc123..." https://siliconanalysts.com/api/v1/accelerators # Or via Authorization header curl -H "Authorization: Bearer sa_live_abc123..." https://siliconanalysts.com/api/v1/hbm
TierGET EndpointsPOST CalculateHistory depthAuth
Anonymous (no key)20 req/day10 req/dayCurrent onlyNone required
Free API key100 req/day20 req/dayPreview (latest ~3 pts / 30d)X-API-Key header
Pro API key10,000 req/hr10,000 req/hrFull series + exportX-API-Key header

Your API Keys

Sign in to generate API keys for higher rate limits and usage tracking.

API Playground

Try any endpoint live. No authentication required for read endpoints.

Try endpoints with live data — no API key required for public endpoints.

Need higher rate limits, webhook alerts, or bulk data access?

Pro API access is coming soon — higher rate limits, webhook alerts for price movements, and priority support. Join the waitlist and we'll reach out before launch.

AI Agent Discovery

Silicon Analysts is optimized for discovery by AI agents and LLM-powered search.

/llms.txt — Machine-readable site description for LLM agents
/api/v1 — JSON API manifest for programmatic endpoint discovery
JSON-LD structured data on every page (Dataset, SoftwareApplication, Article)
/sitemap.xml — Full sitemap with all tools and articles

Trust & Reliability

Provenance
Data Quality & Provenance
Per-record provenance taxonomy, source-type and confidence-tier reference, update cadence per dataset.
Status
System Status ↗
Live uptime + 90-day history for /api/v1, /api/mcp, web. Hosted on Better Stack.

Data Sources

Cost estimates are derived from Epoch AI Monte Carlo models, Raymond James semiconductor research, TrendForce quarterly reports, and SemiAnalysis teardown data.

HBM market data is sourced from SK Hynix, Samsung, and Micron investor relations, TrendForce, and proprietary supply chain tracking models.

Estimates are directional and may vary ±15-20% from actual manufacturing costs. Per-record provenance, source-type taxonomy, and confidence tiers are documented at /data-quality. For full terms see Terms & Data Provenance.

Explore Interactive Tools

Use our interactive tools to model chip costs, compare accelerators, and analyze markets

Cost Bridge ChartChip Price CalculatorHBM Market Analysis