# Lung injury prediction score LIPS Status: LIVE Price: $0.005 USDC `GET /api/calc/lips` HTML: https://magentlab.com/docs/lips Markdown: https://magentlab.com/docs/lips.md Not a medical device. Not a diagnosis, dose, or listing recommendation. ## What it computes Sum Gajic 2011 Table 3 lung injury prediction score items from caller-assigned flags and return the published ROC cutoff band (low <4, high ≥4). ## When to use When an agent needs the published LIPS point total and must not invent an ARDS diagnosis or additional cut-points. ## When not to use - Not a medical device. Not an ARDS diagnosis. magent does not examine the patient or read imaging; every flag is caller-assigned. - Gajic 2011 Table 3 worksheet only. At most one high-risk surgery type (orthopedic_spine, acute_abdomen, cardiac, aortic_vascular) may be true. - Emergency surgery adds 1.5 in addition to the surgery type (footnote *). Diabetes mellitus subtracts 1 only when sepsis is true (footnote †); diabetes without sepsis scores 0. - Bands are low (score <4) and high (score ≥4) from the paper ROC cutoff. No other cut-points are returned. - max_score 15.5 is the published observed range in Gajic 2011, not a theoretical sum of every Table 3 row. ## Formula ``` LIPS = shock(2) + aspiration(2) + sepsis(1) + pneumonia(1.5) + at most one of orthopedic_spine(1), acute_abdomen(2), cardiac(2.5), aortic_vascular(3.5) + emergency_surgery(1.5) + traumatic_brain_injury(2) + smoke_inhalation(2) + near_drowning(2) + lung_contusion(1.5) + multiple_fractures(1.5) + alcohol_abuse(1) + obesity_bmi_gt_30(1) + hypoalbuminemia(1) + chemotherapy(1) + fio2_gt_035(2) + tachypnea_rr_gt_30(1.5) + spo2_lt_95(1) + acidosis_ph_lt_735(1.5) + diabetes_mellitus(-1 only if sepsis); Gajic 2011 Table 3; published observed range 0-15.5; low <4, high >=4 ``` ## Citation [Early Identification of Patients at Risk of Acute Lung Injury: Evaluation of Lung Injury Prediction Score in a Multicenter Cohort Study](https://doi.org/10.1164/rccm.201004-0549OC) Gajic O, Dabbagh O, Park PK, Adesanya A, Chang SY, Hou P, Anderson H 3rd, Hoth JJ, Mikkelsen ME, Gentile NT, Gong MN, Talmor D, Bajwa E, Watkins TR, Festic E, Yilmaz M, Liendahl M, Khan NA, Sevransky JE, Malinchoc M; US Critical Illness and Injury Trials Group: Lung Injury Prevention Study Investigators (USCIITG-LIPS) Am J Respir Crit Care Med. 2011;183(4):462-470 DOI: [10.1164/rccm.201004-0549OC](https://doi.org/10.1164/rccm.201004-0549OC) ## Worked example ### Table 3 example 1: septic shock, pneumonia, alcohol, FiO2 >0.35 Given: `acidosis_ph_lt_735=false, acute_abdomen=false, alcohol_abuse=true, aortic_vascular=false, aspiration=false, cardiac=false, chemotherapy=false, diabetes_mellitus=false, emergency_surgery=false, fio2_gt_035=true, hypoalbuminemia=false, lung_contusion=false, multiple_fractures=false, near_drowning=false, obesity_bmi_gt_30=false, orthopedic_spine=false, pneumonia=true, sepsis=true, shock=true, smoke_inhalation=false, spo2_lt_95=false, tachypnea_rr_gt_30=false, traumatic_brain_injury=false` 1. sepsis → 1; shock → 2; pneumonia → 1.5; alcohol_abuse → 1; fio2_gt_035 → 2 2. score = 1+2+1.5+1+2 = 7.5; lips_band high (>=4) ### Table 3 example 2: diabetes, urosepsis, and shock Given: `acidosis_ph_lt_735=false, acute_abdomen=false, alcohol_abuse=false, aortic_vascular=false, aspiration=false, cardiac=false, chemotherapy=false, diabetes_mellitus=true, emergency_surgery=false, fio2_gt_035=false, hypoalbuminemia=false, lung_contusion=false, multiple_fractures=false, near_drowning=false, obesity_bmi_gt_30=false, orthopedic_spine=false, pneumonia=false, sepsis=true, shock=true, smoke_inhalation=false, spo2_lt_95=false, tachypnea_rr_gt_30=false, traumatic_brain_injury=false` 1. sepsis → 1; shock → 2; diabetes_mellitus → -1 (footnote †, sepsis true) 2. score = 1+2-1 = 2; lips_band low (<4) ## Also searched as - lung injury prediction score - LIPS score - Gajic LIPS - ALI prediction score - lung injury prediction - LIPS Gajic 2011 - acute lung injury prediction ## Parameters - `shock` (boolean, required): Shock as assigned by the caller (Gajic 2011 Table 3). true scores 2. magent does not examine the patient. - `aspiration` (boolean, required): Aspiration as assigned by the caller (Gajic 2011 Table 3). true scores 2. magent does not examine the patient. - `sepsis` (boolean, required): Sepsis as assigned by the caller (Gajic 2011 Table 3). true scores 1. magent does not diagnose sepsis. - `pneumonia` (boolean, required): Pneumonia as assigned by the caller (Gajic 2011 Table 3). true scores 1.5. magent does not read imaging. - `orthopedic_spine` (boolean, required): High-risk orthopedic spine surgery as assigned by the caller (Gajic 2011 Table 3). true scores 1. At most one of orthopedic_spine, acute_abdomen, cardiac, and aortic_vascular may be true. - `acute_abdomen` (boolean, required): High-risk acute abdomen surgery as assigned by the caller (Gajic 2011 Table 3). true scores 2. At most one of orthopedic_spine, acute_abdomen, cardiac, and aortic_vascular may be true. - `cardiac` (boolean, required): High-risk cardiac surgery as assigned by the caller (Gajic 2011 Table 3). true scores 2.5. At most one of orthopedic_spine, acute_abdomen, cardiac, and aortic_vascular may be true. - `aortic_vascular` (boolean, required): High-risk aortic vascular surgery as assigned by the caller (Gajic 2011 Table 3). true scores 3.5. At most one of orthopedic_spine, acute_abdomen, cardiac, and aortic_vascular may be true. - `emergency_surgery` (boolean, required): Emergency surgery as assigned by the caller (Gajic 2011 Table 3 footnote *: add 1.5 points if emergency surgery). true scores 1.5 in addition to any one surgery type. - `traumatic_brain_injury` (boolean, required): Traumatic brain injury as assigned by the caller (Gajic 2011 Table 3). true scores 2. Trauma items may stack. magent does not read imaging. - `smoke_inhalation` (boolean, required): Smoke inhalation as assigned by the caller (Gajic 2011 Table 3). true scores 2. Trauma items may stack. - `near_drowning` (boolean, required): Near drowning as assigned by the caller (Gajic 2011 Table 3). true scores 2. Trauma items may stack. - `lung_contusion` (boolean, required): Lung contusion as assigned by the caller (Gajic 2011 Table 3). true scores 1.5. Trauma items may stack. magent does not read imaging. - `multiple_fractures` (boolean, required): Multiple fractures as assigned by the caller (Gajic 2011 Table 3). true scores 1.5. Trauma items may stack. - `alcohol_abuse` (boolean, required): Alcohol abuse as assigned by the caller (Gajic 2011 Table 3). true scores 1. - `obesity_bmi_gt_30` (boolean, required): Obesity (BMI >30) as assigned by the caller (Gajic 2011 Table 3). true scores 1. magent does not take height or weight. - `hypoalbuminemia` (boolean, required): Hypoalbuminemia as assigned by the caller (Gajic 2011 Table 3). true scores 1. magent does not assay albumin. - `chemotherapy` (boolean, required): Chemotherapy as assigned by the caller (Gajic 2011 Table 3). true scores 1. - `fio2_gt_035` (boolean, required): FiO2 >0.35 or >4 L/min as assigned by the caller (Gajic 2011 Table 3). true scores 2. magent does not read the ventilator or flowmeter. - `tachypnea_rr_gt_30` (boolean, required): Tachypnea (respiratory rate >30) as assigned by the caller (Gajic 2011 Table 3). true scores 1.5. magent does not count respirations. - `spo2_lt_95` (boolean, required): SpO2 <95% as assigned by the caller (Gajic 2011 Table 3). true scores 1. magent does not measure SpO2. - `acidosis_ph_lt_735` (boolean, required): Acidosis (pH <7.35) as assigned by the caller (Gajic 2011 Table 3). true scores 1.5. magent does not assay blood gas. - `diabetes_mellitus` (boolean, required): Diabetes mellitus as assigned by the caller (Gajic 2011 Table 3 footnote dagger). Subtracts 1 only when sepsis is true. If diabetes is true and sepsis is false, 0 points (do not subtract). magent does not diagnose diabetes. ## Bulk (POST) POST the same path with a JSON items array. The first item is the GET unit; each additional item is $0.002. Invalid items return HTTP 400 before settlement. Method: `POST /api/calc/lips` Max items: 25 Price: unit_amount + extra_item_amount * (n - 1) (unit 5000 atomic, extra 2000 atomic) Status: PREVIEW - 1 to 25 items. Each item uses the same keys as the GET query parameters. - POST of 1 item costs the same as GET. Lists longer than 25: chunk into multiple POSTs. Extra items still execute; do not pad dummy rows. - The first invalid item fails the whole request (index in the 400 JSON). You are not charged. - HTTP 200 is {count, path, items}. Each items[i] is the GET 200 body for that row. - Catalog misses (empty matches, found=false) stay paid 200s inside that slot. - x402 resource URL is this path plus n and body_sha256. Browsers that prefer text/html get the same paywall as GET; Pay retries POST with the same items. Example request: ```json { "items": [ { "acidosis_ph_lt_735": "false", "acute_abdomen": "false", "alcohol_abuse": "true", "aortic_vascular": "false", "aspiration": "false", "cardiac": "false", "chemotherapy": "false", "diabetes_mellitus": "false", "emergency_surgery": "false", "fio2_gt_035": "true", "hypoalbuminemia": "false", "lung_contusion": "false", "multiple_fractures": "false", "near_drowning": "false", "obesity_bmi_gt_30": "false", "orthopedic_spine": "false", "pneumonia": "true", "sepsis": "true", "shock": "true", "smoke_inhalation": "false", "spo2_lt_95": "false", "tachypnea_rr_gt_30": "false", "traumatic_brain_injury": "false" }, { "acidosis_ph_lt_735": "false", "acute_abdomen": "false", "alcohol_abuse": "true", "aortic_vascular": "false", "aspiration": "false", "cardiac": "false", "chemotherapy": "false", "diabetes_mellitus": "false", "emergency_surgery": "false", "fio2_gt_035": "true", "hypoalbuminemia": "false", "lung_contusion": "false", "multiple_fractures": "false", "near_drowning": "false", "obesity_bmi_gt_30": "false", "orthopedic_spine": "false", "pneumonia": "true", "sepsis": "true", "shock": "true", "smoke_inhalation": "false", "spo2_lt_95": "false", "tachypnea_rr_gt_30": "false", "traumatic_brain_injury": "false" } ] } ``` Human paywall (two-item fixture): https://api.magentlab.com/paywall/bulk/lips Example 200: ```json { "count": 2, "path": "/api/calc/lips", "items": [ { "components": [ { "factor": "shock", "points": 2, "present": true }, { "factor": "aspiration", "points": 0, "present": false }, { "factor": "sepsis", "points": 1, "present": true }, { "factor": "pneumonia", "points": 1.5, "present": true }, { "factor": "emergency_surgery", "points": 0.0, "present": false }, { "factor": "traumatic_brain_injury", "points": 0, "present": false }, { "factor": "smoke_inhalation", "points": 0, "present": false }, { "factor": "near_drowning", "points": 0, "present": false }, { "factor": "lung_contusion", "points": 0.0, "present": false }, { "factor": "multiple_fractures", "points": 0.0, "present": false }, { "factor": "alcohol_abuse", "points": 1, "present": true }, { "factor": "obesity_bmi_gt_30", "points": 0, "present": false }, { "factor": "hypoalbuminemia", "points": 0, "present": false }, { "factor": "chemotherapy", "points": 0, "present": false }, { "factor": "fio2_gt_035", "points": 2, "present": true }, { "factor": "tachypnea_rr_gt_30", "points": 0.0, "present": false }, { "factor": "spo2_lt_95", "points": 0, "present": false }, { "factor": "acidosis_ph_lt_735", "points": 0.0, "present": false }, { "factor": "orthopedic_spine", "points": 0, "present": false }, { "factor": "acute_abdomen", "points": 0, "present": false }, { "factor": "cardiac", "points": 0.0, "present": false }, { "factor": "aortic_vascular", "points": 0.0, "present": false }, { "factor": "diabetes_mellitus", "points": 0, "present": false } ], "disclaimer": "Not a medical device. Deterministic published-formula or published-code output for autonomous agents. A licensed clinician remains responsible for patient care and billing submissions.", "citation": { "authors": "Gajic O, Dabbagh O, Park PK, Adesanya A, Chang SY, Hou P, Anderson H 3rd, Hoth JJ, Mikkelsen ME, Gentile NT, Gong MN, Talmor D, Bajwa E, Watkins TR, Festic E, Yilmaz M, Liendahl M, Khan NA, Sevransky JE, Malinchoc M; US Critical Illness and Injury Trials Group: Lung Injury Prevention Study Investigators (USCIITG-LIPS)", "doi": "10.1164/rccm.201004-0549OC", "id": "gajic-2011", "pmid": "20802164", "source": "Am J Respir Crit Care Med. 2011;183(4):462-470", "title": "Early Identification of Patients at Risk of Acute Lung Injury: Evaluation of Lung Injury Prediction Score in a Multicenter Cohort Study" }, "formula": "lips", "formula_expression": "LIPS = shock(2) + aspiration(2) + sepsis(1) + pneumonia(1.5) + at most one of orthopedic_spine(1), acute_abdomen(2), cardiac(2.5), aortic_vascular(3.5) + emergency_surgery(1.5) + traumatic_brain_injury(2) + smoke_inhalation(2) + near_drowning(2) + lung_contusion(1.5) + multiple_fractures(1.5) + alcohol_abuse(1) + obesity_bmi_gt_30(1) + hypoalbuminemia(1) + chemotherapy(1) + fio2_gt_035(2) + tachypnea_rr_gt_30(1.5) + spo2_lt_95(1) + acidosis_ph_lt_735(1.5) + diabetes_mellitus(-1 only if sepsis); Gajic 2011 Table 3; published observed range 0-15.5; low <4, high >=4", "max_score": 15.5, "score": 7.5, "lips_band": "high" }, { "components": [ { "factor": "shock", "points": 2, "present": true }, { "factor": "aspiration", "points": 0, "present": false }, { "factor": "sepsis", "points": 1, "present": true }, { "factor": "pneumonia", "points": 1.5, "present": true }, { "factor": "emergency_surgery", "points": 0.0, "present": false }, { "factor": "traumatic_brain_injury", "points": 0, "present": false }, { "factor": "smoke_inhalation", "points": 0, "present": false }, { "factor": "near_drowning", "points": 0, "present": false }, { "factor": "lung_contusion", "points": 0.0, "present": false }, { "factor": "multiple_fractures", "points": 0.0, "present": false }, { "factor": "alcohol_abuse", "points": 1, "present": true }, { "factor": "obesity_bmi_gt_30", "points": 0, "present": false }, { "factor": "hypoalbuminemia", "points": 0, "present": false }, { "factor": "chemotherapy", "points": 0, "present": false }, { "factor": "fio2_gt_035", "points": 2, "present": true }, { "factor": "tachypnea_rr_gt_30", "points": 0.0, "present": false }, { "factor": "spo2_lt_95", "points": 0, "present": false }, { "factor": "acidosis_ph_lt_735", "points": 0.0, "present": false }, { "factor": "orthopedic_spine", "points": 0, "present": false }, { "factor": "acute_abdomen", "points": 0, "present": false }, { "factor": "cardiac", "points": 0.0, "present": false }, { "factor": "aortic_vascular", "points": 0.0, "present": false }, { "factor": "diabetes_mellitus", "points": 0, "present": false } ], "disclaimer": "Not a medical device. Deterministic published-formula or published-code output for autonomous agents. A licensed clinician remains responsible for patient care and billing submissions.", "citation": { "authors": "Gajic O, Dabbagh O, Park PK, Adesanya A, Chang SY, Hou P, Anderson H 3rd, Hoth JJ, Mikkelsen ME, Gentile NT, Gong MN, Talmor D, Bajwa E, Watkins TR, Festic E, Yilmaz M, Liendahl M, Khan NA, Sevransky JE, Malinchoc M; US Critical Illness and Injury Trials Group: Lung Injury Prevention Study Investigators (USCIITG-LIPS)", "doi": "10.1164/rccm.201004-0549OC", "id": "gajic-2011", "pmid": "20802164", "source": "Am J Respir Crit Care Med. 2011;183(4):462-470", "title": "Early Identification of Patients at Risk of Acute Lung Injury: Evaluation of Lung Injury Prediction Score in a Multicenter Cohort Study" }, "formula": "lips", "formula_expression": "LIPS = shock(2) + aspiration(2) + sepsis(1) + pneumonia(1.5) + at most one of orthopedic_spine(1), acute_abdomen(2), cardiac(2.5), aortic_vascular(3.5) + emergency_surgery(1.5) + traumatic_brain_injury(2) + smoke_inhalation(2) + near_drowning(2) + lung_contusion(1.5) + multiple_fractures(1.5) + alcohol_abuse(1) + obesity_bmi_gt_30(1) + hypoalbuminemia(1) + chemotherapy(1) + fio2_gt_035(2) + tachypnea_rr_gt_30(1.5) + spo2_lt_95(1) + acidosis_ph_lt_735(1.5) + diabetes_mellitus(-1 only if sepsis); Gajic 2011 Table 3; published observed range 0-15.5; low <4, high >=4", "max_score": 15.5, "score": 7.5, "lips_band": "high" } ] } ``` ## Response fields - `formula` (string): lips - `formula_expression` (string): Exact expression used - `score` (number): LIPS points as a number (0.0, 1.5, 7.5, …). Half-points are allowed. - `max_score` (number): 15.5 is the Gajic 2011 published observed upper range, not a sum of every Table 3 row. - `lips_band` (string): Gajic 2011 ROC cutoff: low when score <4, high when score >=4. Not an ARDS diagnosis. No other cut-points. - `components` (array): Per-factor points - `citation` (object): Gajic et al. AJRCCM 2011 citation - `disclaimer` (string): Not-a-device notice ## Example JSON Frozen fixture. Not a live lookup. ```json { "components": [ { "factor": "shock", "points": 2, "present": true }, { "factor": "aspiration", "points": 0, "present": false }, { "factor": "sepsis", "points": 1, "present": true }, { "factor": "pneumonia", "points": 1.5, "present": true }, { "factor": "emergency_surgery", "points": 0.0, "present": false }, { "factor": "traumatic_brain_injury", "points": 0, "present": false }, { "factor": "smoke_inhalation", "points": 0, "present": false }, { "factor": "near_drowning", "points": 0, "present": false }, { "factor": "lung_contusion", "points": 0.0, "present": false }, { "factor": "multiple_fractures", "points": 0.0, "present": false }, { "factor": "alcohol_abuse", "points": 1, "present": true }, { "factor": "obesity_bmi_gt_30", "points": 0, "present": false }, { "factor": "hypoalbuminemia", "points": 0, "present": false }, { "factor": "chemotherapy", "points": 0, "present": false }, { "factor": "fio2_gt_035", "points": 2, "present": true }, { "factor": "tachypnea_rr_gt_30", "points": 0.0, "present": false }, { "factor": "spo2_lt_95", "points": 0, "present": false }, { "factor": "acidosis_ph_lt_735", "points": 0.0, "present": false }, { "factor": "orthopedic_spine", "points": 0, "present": false }, { "factor": "acute_abdomen", "points": 0, "present": false }, { "factor": "cardiac", "points": 0.0, "present": false }, { "factor": "aortic_vascular", "points": 0.0, "present": false }, { "factor": "diabetes_mellitus", "points": 0, "present": false } ], "disclaimer": "Not a medical device. Deterministic published-formula or published-code output for autonomous agents. A licensed clinician remains responsible for patient care and billing submissions.", "citation": { "authors": "Gajic O, Dabbagh O, Park PK, Adesanya A, Chang SY, Hou P, Anderson H 3rd, Hoth JJ, Mikkelsen ME, Gentile NT, Gong MN, Talmor D, Bajwa E, Watkins TR, Festic E, Yilmaz M, Liendahl M, Khan NA, Sevransky JE, Malinchoc M; US Critical Illness and Injury Trials Group: Lung Injury Prevention Study Investigators (USCIITG-LIPS)", "doi": "10.1164/rccm.201004-0549OC", "id": "gajic-2011", "pmid": "20802164", "source": "Am J Respir Crit Care Med. 2011;183(4):462-470", "title": "Early Identification of Patients at Risk of Acute Lung Injury: Evaluation of Lung Injury Prediction Score in a Multicenter Cohort Study" }, "formula": "lips", "formula_expression": "LIPS = shock(2) + aspiration(2) + sepsis(1) + pneumonia(1.5) + at most one of orthopedic_spine(1), acute_abdomen(2), cardiac(2.5), aortic_vascular(3.5) + emergency_surgery(1.5) + traumatic_brain_injury(2) + smoke_inhalation(2) + near_drowning(2) + lung_contusion(1.5) + multiple_fractures(1.5) + alcohol_abuse(1) + obesity_bmi_gt_30(1) + hypoalbuminemia(1) + chemotherapy(1) + fio2_gt_035(2) + tachypnea_rr_gt_30(1.5) + spo2_lt_95(1) + acidosis_ph_lt_735(1.5) + diabetes_mellitus(-1 only if sepsis); Gajic 2011 Table 3; published observed range 0-15.5; low <4, high >=4", "max_score": 15.5, "score": 7.5, "lips_band": "high" } ``` ## Errors - HTTP 400 `invalid_flag`: boolean clinical flags must be true or false Returned before settlement; you are not charged. - HTTP 400 `invalid_lips_surgery`: at most one high-risk surgery type may be true: orthopedic_spine, acute_abdomen, cardiac, or aortic_vascular (Gajic 2011 Table 3). Returned before settlement; you are not charged. - HTTP 400 `invalid_items`: POST body must be a JSON object with only an items array Returned before settlement; you are not charged. - HTTP 400 `invalid_item_count`: items must be an array of 1 to 25 objects Returned before settlement; you are not charged. - HTTP 400 `invalid_item`: each items entry must be a JSON object Returned before settlement; you are not charged. Shared HTTP 402 and 503: https://magentlab.com/docs/payments ## Related tools - [Berlin Definition of ARDS](https://magentlab.com/docs/berlin-ards) — Apply the 2012 Berlin Definition of ARDS and return whether the clinical box holds, severity (none, mild, moderate, or severe), and berlin_ards. - [Murray lung injury score](https://magentlab.com/docs/murray) — Mean the four Murray 1988 lung injury score components (chest radiograph quadrants, PaO2/FiO2, PEEP, and compliance), each 0–4, and return LIS and injury_band. - [PaO2/FiO2 ratio](https://magentlab.com/docs/pf-ratio) — Compute the PaO2/FiO2 ratio as arterial PO2 in mm Hg divided by inspired oxygen fraction. ## Payment Unpaid requests return HTTP 402 even if query parameters or POST items are missing or invalid, so CDP and agents can index the path. After a PAYMENT-SIGNATURE, invalid params return HTTP 400 JSON before settlement. magent does not charge. Fix the params, then request a new 402 quote for that complete URL. Catalog misses (empty matches, found=false) are valid paid 200s. - GET the tool with Accept: application/json (do not send Accept: text/html unless you want the human paywall). - HTTP 402 means you have not paid. Decode the base64 PAYMENT-REQUIRED header. HTTP 503 is not a new quote. - Sign accepts[0] (exact, EIP-3009) with validBefore = now + maxTimeoutSeconds (600 seconds), or accepts[1] (batch-settlement deposit/voucher) on product GET. Ping and POST {items} stay exact. Magent retries transient facilitator 429/5xx before answering. - Retry the same URL with PAYMENT-SIGNATURE (base64 JSON of accepted and payload). Magent attaches canonical extensions.bazaar on CDP verify/settle; echoing 402 bazaar is optional. - Success is HTTP 200 JSON plus PAYMENT-RESPONSE. exact settles before the tool. batch-settlement verifies (and deposit-settles) before the tool and commits the charge after HTTP 2xx. HTTP 503: retry the same PAYMENT-SIGNATURE. Mint a new exact nonce only after a new HTTP 402. - offered `exact` on eip155:8453: Fixed-price USDC on Base. The buyer authorizes the advertised amount (EIP-3009). magent settles before the tool runs (paymentFlow upfront). extra.assetTransferMethod=eip3009 extra.paymentFlow=upfront. - offered `batch-settlement` on eip155:8453: Payment-channel vouchers claimed later in batches. Exact stays accepts[0]. Same-path POST {items} is still exact. extra.assetTransferMethod=eip3009 extra.paymentFlow=authorization. - not offered `upto`: Not offered. Usage-based: buyer authorizes a ceiling, seller settles the actual amount after work. Reserved for a future metered tool. Not for current calculators or code search. Same-path POST {items} is still scheme exact: one EIP-3009 authorization for GET unit plus $0.002 per extra item. That is not x402 batch-settlement (payment channels / vouchers). Shared HTTP 402 and 503 table: https://magentlab.com/docs/payments Stdio MCP (one process per host): https://magentlab.com/docs/mcp ## Guarantees - HTTP 402 is unpaid, including a missing query. After PAYMENT-SIGNATURE, invalid parameters return HTTP 400 before settlement. You are not charged. HTTP 402 never includes the tool JSON. - exact: settlement finishes before the tool (paymentFlow upfront). batch-settlement: verify/deposit before the tool; chargedCumulativeAmount commits after HTTP 2xx. Uncertain or failed settlement fails closed (HTTP 503). Retry the same PAYMENT-SIGNATURE. - HTTP 402 is unpaid only. Do not sign a second authorization because of a 503. - Execution is timeout-bounded and concurrency-capped. - Calculator inputs are stored encrypted for allowlisted operators (Magent Console). They are not in public logs, SSH lookups, catalog, or rollups. Request logs store path without query.