GPT-5.4 Nano

import { createClient } from '@runware/sdk'

const client = await createClient({ apiKey: process.env.RUNWARE_API_KEY })
await client.connect()

const [result] = await client.run({
  model: 'openai:gpt@5.4-nano',
  settings: {
    thinkingLevel: 'high'
  },
  messages: [
    {
      role: 'user',
      content: 'Prepare a self-contained renewal-risk memo for the customer-success director using only the account evidence below. Reconcile conflicting signals, distinguish facts from reasonable inferences, and do not invent metrics or commitments.\n\nACCOUNT\nCustomer: Northstar Markets, a 46-location regional grocery chain\nProduct: ShiftPilot workforce-scheduling SaaS\nContract: $184,000 ARR, renewal on November 30\nToday: September 18\nTerm: Annual\nExecutive sponsor: Dana Ruiz, VP of Store Operations\nDay-to-day administrator: Malik Chen, Workforce Systems Manager\n\nACCOUNT EVIDENCE\n1. Product usage: 43 of 46 stores logged in during the last 30 days, down from 46 in the prior period. Weekly schedules were published through ShiftPilot at 39 stores. Mobile shift-swap usage increased 18% quarter over quarter.\n2. Support: Seven tickets were opened this quarter. Five are closed. One open ticket concerns delayed payroll exports; engineering has reproduced the issue but has not provided a fix date. One ticket about manager permissions is waiting on information from Northstar.\n3. July business review: Dana said the mobile shift-swap feature was reducing calls to store managers. She also said payroll-export reliability must improve before renewal.\n4. August administrator email: Malik wrote, “The store teams generally like it, but I am spending too much time checking exports manually.”\n5. Finance note: Northstar paid its latest invoice 12 days late. The previous four invoices were paid on time.\n6. Sales note: A payroll-software vendor offered Northstar a bundled scheduling module during an August procurement review. Pricing and product capability are unknown.\n7. Training: Two newly acquired stores have not completed administrator training. A third acquired store completed training but has not published a schedule in ShiftPilot.\n8. Relationship activity: Dana accepted an invitation to an October customer council. Malik declined because of a scheduling conflict and asked for the recording.\n9. Outcome data: Northstar has not supplied updated labor-efficiency figures since March, so the claimed annual savings cannot currently be validated.\n10. CSM note from September 15: Dana requested a one-page summary of product adoption and open issues for an internal budget meeting on October 3.\n\nWrite the memo with these exact sections:\n\n1. Executive Assessment — Assign Low, Medium, High, or Critical renewal risk and explain the rating in no more than 90 words.\n2. Evidence Table — Provide five rows with columns: Signal, Evidence, Direction (Positive/Negative/Mixed), Confidence (High/Medium/Low), and Why It Matters.\n3. Ranked Risk Drivers — List the three most important risks in priority order. Do not treat the single late payment as proof of financial distress.\n4. Protective Factors — List the three strongest reasons the account may renew.\n5. Thirty-Day Action Plan — Give five actions, each with an owner, deadline, and intended outcome. Owners may only be CSM, Support Lead, Product Manager, Account Executive, or Customer Sponsor.\n6. October 3 Talking Points — Draft four concise bullets the CSM can use in Dana’s internal budget summary.\n7. Unknowns — List the missing information that could materially change the assessment.\n\nKeep the complete response under 750 words. Use direct, professional language. Clearly label any inference, and never present an unknown competitor price, unverified savings claim, or missing engineering date as fact.'
    }
  ]
})

import asyncio
import os

from runware import Runware


async def main():
    async with Runware(api_key=os.environ["RUNWARE_API_KEY"]) as client:
        results = await client.run({
            "model": "openai:gpt@5.4-nano",
            "settings": {
                "thinkingLevel": "high"
            },
            "messages": [
                {
                    "role": "user",
                    "content": "Prepare a self-contained renewal-risk memo for the customer-success director using only the account evidence below. Reconcile conflicting signals, distinguish facts from reasonable inferences, and do not invent metrics or commitments.\n\nACCOUNT\nCustomer: Northstar Markets, a 46-location regional grocery chain\nProduct: ShiftPilot workforce-scheduling SaaS\nContract: $184,000 ARR, renewal on November 30\nToday: September 18\nTerm: Annual\nExecutive sponsor: Dana Ruiz, VP of Store Operations\nDay-to-day administrator: Malik Chen, Workforce Systems Manager\n\nACCOUNT EVIDENCE\n1. Product usage: 43 of 46 stores logged in during the last 30 days, down from 46 in the prior period. Weekly schedules were published through ShiftPilot at 39 stores. Mobile shift-swap usage increased 18% quarter over quarter.\n2. Support: Seven tickets were opened this quarter. Five are closed. One open ticket concerns delayed payroll exports; engineering has reproduced the issue but has not provided a fix date. One ticket about manager permissions is waiting on information from Northstar.\n3. July business review: Dana said the mobile shift-swap feature was reducing calls to store managers. She also said payroll-export reliability must improve before renewal.\n4. August administrator email: Malik wrote, “The store teams generally like it, but I am spending too much time checking exports manually.”\n5. Finance note: Northstar paid its latest invoice 12 days late. The previous four invoices were paid on time.\n6. Sales note: A payroll-software vendor offered Northstar a bundled scheduling module during an August procurement review. Pricing and product capability are unknown.\n7. Training: Two newly acquired stores have not completed administrator training. A third acquired store completed training but has not published a schedule in ShiftPilot.\n8. Relationship activity: Dana accepted an invitation to an October customer council. Malik declined because of a scheduling conflict and asked for the recording.\n9. Outcome data: Northstar has not supplied updated labor-efficiency figures since March, so the claimed annual savings cannot currently be validated.\n10. CSM note from September 15: Dana requested a one-page summary of product adoption and open issues for an internal budget meeting on October 3.\n\nWrite the memo with these exact sections:\n\n1. Executive Assessment — Assign Low, Medium, High, or Critical renewal risk and explain the rating in no more than 90 words.\n2. Evidence Table — Provide five rows with columns: Signal, Evidence, Direction (Positive/Negative/Mixed), Confidence (High/Medium/Low), and Why It Matters.\n3. Ranked Risk Drivers — List the three most important risks in priority order. Do not treat the single late payment as proof of financial distress.\n4. Protective Factors — List the three strongest reasons the account may renew.\n5. Thirty-Day Action Plan — Give five actions, each with an owner, deadline, and intended outcome. Owners may only be CSM, Support Lead, Product Manager, Account Executive, or Customer Sponsor.\n6. October 3 Talking Points — Draft four concise bullets the CSM can use in Dana’s internal budget summary.\n7. Unknowns — List the missing information that could materially change the assessment.\n\nKeep the complete response under 750 words. Use direct, professional language. Clearly label any inference, and never present an unknown competitor price, unverified savings claim, or missing engineering date as fact."
                }
            ]
        })


asyncio.run(main())

curl https://api.runware.ai/v1 \
  -H "Authorization: Bearer $RUNWARE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '[
    {
      "taskType": "textInference",
      "taskUUID": "ef8b0510-f6ef-406f-a916-0d4e1e782d4f",
      "model": "openai:gpt@5.4-nano",
      "settings": {
        "thinkingLevel": "high"
      },
      "messages": [
        {
          "role": "user",
          "content": "Prepare a self-contained renewal-risk memo for the customer-success director using only the account evidence below. Reconcile conflicting signals, distinguish facts from reasonable inferences, and do not invent metrics or commitments.\n\nACCOUNT\nCustomer: Northstar Markets, a 46-location regional grocery chain\nProduct: ShiftPilot workforce-scheduling SaaS\nContract: $184,000 ARR, renewal on November 30\nToday: September 18\nTerm: Annual\nExecutive sponsor: Dana Ruiz, VP of Store Operations\nDay-to-day administrator: Malik Chen, Workforce Systems Manager\n\nACCOUNT EVIDENCE\n1. Product usage: 43 of 46 stores logged in during the last 30 days, down from 46 in the prior period. Weekly schedules were published through ShiftPilot at 39 stores. Mobile shift-swap usage increased 18% quarter over quarter.\n2. Support: Seven tickets were opened this quarter. Five are closed. One open ticket concerns delayed payroll exports; engineering has reproduced the issue but has not provided a fix date. One ticket about manager permissions is waiting on information from Northstar.\n3. July business review: Dana said the mobile shift-swap feature was reducing calls to store managers. She also said payroll-export reliability must improve before renewal.\n4. August administrator email: Malik wrote, “The store teams generally like it, but I am spending too much time checking exports manually.”\n5. Finance note: Northstar paid its latest invoice 12 days late. The previous four invoices were paid on time.\n6. Sales note: A payroll-software vendor offered Northstar a bundled scheduling module during an August procurement review. Pricing and product capability are unknown.\n7. Training: Two newly acquired stores have not completed administrator training. A third acquired store completed training but has not published a schedule in ShiftPilot.\n8. Relationship activity: Dana accepted an invitation to an October customer council. Malik declined because of a scheduling conflict and asked for the recording.\n9. Outcome data: Northstar has not supplied updated labor-efficiency figures since March, so the claimed annual savings cannot currently be validated.\n10. CSM note from September 15: Dana requested a one-page summary of product adoption and open issues for an internal budget meeting on October 3.\n\nWrite the memo with these exact sections:\n\n1. Executive Assessment — Assign Low, Medium, High, or Critical renewal risk and explain the rating in no more than 90 words.\n2. Evidence Table — Provide five rows with columns: Signal, Evidence, Direction (Positive/Negative/Mixed), Confidence (High/Medium/Low), and Why It Matters.\n3. Ranked Risk Drivers — List the three most important risks in priority order. Do not treat the single late payment as proof of financial distress.\n4. Protective Factors — List the three strongest reasons the account may renew.\n5. Thirty-Day Action Plan — Give five actions, each with an owner, deadline, and intended outcome. Owners may only be CSM, Support Lead, Product Manager, Account Executive, or Customer Sponsor.\n6. October 3 Talking Points — Draft four concise bullets the CSM can use in Dana’s internal budget summary.\n7. Unknowns — List the missing information that could materially change the assessment.\n\nKeep the complete response under 750 words. Use direct, professional language. Clearly label any inference, and never present an unknown competitor price, unverified savings claim, or missing engineering date as fact."
        }
      ]
    }
  ]'

runware run openai:gpt@5.4-nano \
  settings.thinkingLevel=high \
  messages.0.role=user \
  messages.0.content="Prepare a self-contained renewal-risk memo for the customer-success director using only the account evidence below. Reconcile conflicting signals, distinguish facts from reasonable inferences, and do not invent metrics or commitments.

ACCOUNT
Customer: Northstar Markets, a 46-location regional grocery chain
Product: ShiftPilot workforce-scheduling SaaS
Contract: \$184,000 ARR, renewal on November 30
Today: September 18
Term: Annual
Executive sponsor: Dana Ruiz, VP of Store Operations
Day-to-day administrator: Malik Chen, Workforce Systems Manager

ACCOUNT EVIDENCE
1. Product usage: 43 of 46 stores logged in during the last 30 days, down from 46 in the prior period. Weekly schedules were published through ShiftPilot at 39 stores. Mobile shift-swap usage increased 18% quarter over quarter.
2. Support: Seven tickets were opened this quarter. Five are closed. One open ticket concerns delayed payroll exports; engineering has reproduced the issue but has not provided a fix date. One ticket about manager permissions is waiting on information from Northstar.
3. July business review: Dana said the mobile shift-swap feature was reducing calls to store managers. She also said payroll-export reliability must improve before renewal.
4. August administrator email: Malik wrote, “The store teams generally like it, but I am spending too much time checking exports manually.”
5. Finance note: Northstar paid its latest invoice 12 days late. The previous four invoices were paid on time.
6. Sales note: A payroll-software vendor offered Northstar a bundled scheduling module during an August procurement review. Pricing and product capability are unknown.
7. Training: Two newly acquired stores have not completed administrator training. A third acquired store completed training but has not published a schedule in ShiftPilot.
8. Relationship activity: Dana accepted an invitation to an October customer council. Malik declined because of a scheduling conflict and asked for the recording.
9. Outcome data: Northstar has not supplied updated labor-efficiency figures since March, so the claimed annual savings cannot currently be validated.
10. CSM note from September 15: Dana requested a one-page summary of product adoption and open issues for an internal budget meeting on October 3.

Write the memo with these exact sections:

1. Executive Assessment — Assign Low, Medium, High, or Critical renewal risk and explain the rating in no more than 90 words.
2. Evidence Table — Provide five rows with columns: Signal, Evidence, Direction (Positive/Negative/Mixed), Confidence (High/Medium/Low), and Why It Matters.
3. Ranked Risk Drivers — List the three most important risks in priority order. Do not treat the single late payment as proof of financial distress.
4. Protective Factors — List the three strongest reasons the account may renew.
5. Thirty-Day Action Plan — Give five actions, each with an owner, deadline, and intended outcome. Owners may only be CSM, Support Lead, Product Manager, Account Executive, or Customer Sponsor.
6. October 3 Talking Points — Draft four concise bullets the CSM can use in Dana’s internal budget summary.
7. Unknowns — List the missing information that could materially change the assessment.

Keep the complete response under 750 words. Use direct, professional language. Clearly label any inference, and never present an unknown competitor price, unverified savings claim, or missing engineering date as fact."

{
  "taskType": "textInference",
  "taskUUID": "ef8b0510-f6ef-406f-a916-0d4e1e782d4f",
  "model": "openai:gpt@5.4-nano",
  "settings": {
    "thinkingLevel": "high"
  },
  "messages": [
    {
      "role": "user",
      "content": "Prepare a self-contained renewal-risk memo for the customer-success director using only the account evidence below. Reconcile conflicting signals, distinguish facts from reasonable inferences, and do not invent metrics or commitments.\n\nACCOUNT\nCustomer: Northstar Markets, a 46-location regional grocery chain\nProduct: ShiftPilot workforce-scheduling SaaS\nContract: $184,000 ARR, renewal on November 30\nToday: September 18\nTerm: Annual\nExecutive sponsor: Dana Ruiz, VP of Store Operations\nDay-to-day administrator: Malik Chen, Workforce Systems Manager\n\nACCOUNT EVIDENCE\n1. Product usage: 43 of 46 stores logged in during the last 30 days, down from 46 in the prior period. Weekly schedules were published through ShiftPilot at 39 stores. Mobile shift-swap usage increased 18% quarter over quarter.\n2. Support: Seven tickets were opened this quarter. Five are closed. One open ticket concerns delayed payroll exports; engineering has reproduced the issue but has not provided a fix date. One ticket about manager permissions is waiting on information from Northstar.\n3. July business review: Dana said the mobile shift-swap feature was reducing calls to store managers. She also said payroll-export reliability must improve before renewal.\n4. August administrator email: Malik wrote, “The store teams generally like it, but I am spending too much time checking exports manually.”\n5. Finance note: Northstar paid its latest invoice 12 days late. The previous four invoices were paid on time.\n6. Sales note: A payroll-software vendor offered Northstar a bundled scheduling module during an August procurement review. Pricing and product capability are unknown.\n7. Training: Two newly acquired stores have not completed administrator training. A third acquired store completed training but has not published a schedule in ShiftPilot.\n8. Relationship activity: Dana accepted an invitation to an October customer council. Malik declined because of a scheduling conflict and asked for the recording.\n9. Outcome data: Northstar has not supplied updated labor-efficiency figures since March, so the claimed annual savings cannot currently be validated.\n10. CSM note from September 15: Dana requested a one-page summary of product adoption and open issues for an internal budget meeting on October 3.\n\nWrite the memo with these exact sections:\n\n1. Executive Assessment — Assign Low, Medium, High, or Critical renewal risk and explain the rating in no more than 90 words.\n2. Evidence Table — Provide five rows with columns: Signal, Evidence, Direction (Positive/Negative/Mixed), Confidence (High/Medium/Low), and Why It Matters.\n3. Ranked Risk Drivers — List the three most important risks in priority order. Do not treat the single late payment as proof of financial distress.\n4. Protective Factors — List the three strongest reasons the account may renew.\n5. Thirty-Day Action Plan — Give five actions, each with an owner, deadline, and intended outcome. Owners may only be CSM, Support Lead, Product Manager, Account Executive, or Customer Sponsor.\n6. October 3 Talking Points — Draft four concise bullets the CSM can use in Dana’s internal budget summary.\n7. Unknowns — List the missing information that could materially change the assessment.\n\nKeep the complete response under 750 words. Use direct, professional language. Clearly label any inference, and never present an unknown competitor price, unverified savings claim, or missing engineering date as fact."
    }
  ]
}

import { createClient } from '@runware/sdk'

const client = await createClient({ apiKey: process.env.RUNWARE_API_KEY })
await client.connect()

const [result] = await client.run({
  model: 'openai:gpt@5.4-nano',
  seed: 49394,
  settings: {
    systemPrompt: 'You are a fast document-processing assistant optimized for extracting structured data from operational paperwork. Read the provided image carefully and return only valid JSON. If multiple documents are visible, process each one separately. For every document, extract: vendor_name, invoice_number, purchase_order, invoice_date, due_date, currency, subtotal, tax, total, line_item_count, and confidence. Also include a top-level summary with document_count, currencies_detected, highest_total, and any flags such as missing_field, unreadable_region, duplicate_invoice_number, or handwriting_present. Use null for missing values. Do not include markdown or explanatory text.',
    temperature: 0.1,
    topP: 0.9,
    maxTokens: 12000,
    thinkingLevel: 'medium'
  },
  inputs: {
    images: [
      'https://assets.runware.ai/assets/inputs/58747a6a-c347-4e5d-93ee-f965a0372d23.jpg'
    ]
  },
  includeUsage: true,
  messages: [
    {
      role: 'user',
      content: 'Extract all visible invoice data from this image and output strict JSON with the schema described in the system instructions. Prioritize accuracy, preserve formatting for invoice numbers and purchase orders, and include every visible document even if partial.'
    }
  ]
})

import asyncio
import os

from runware import Runware


async def main():
    async with Runware(api_key=os.environ["RUNWARE_API_KEY"]) as client:
        results = await client.run({
            "model": "openai:gpt@5.4-nano",
            "seed": 49394,
            "settings": {
                "systemPrompt": "You are a fast document-processing assistant optimized for extracting structured data from operational paperwork. Read the provided image carefully and return only valid JSON. If multiple documents are visible, process each one separately. For every document, extract: vendor_name, invoice_number, purchase_order, invoice_date, due_date, currency, subtotal, tax, total, line_item_count, and confidence. Also include a top-level summary with document_count, currencies_detected, highest_total, and any flags such as missing_field, unreadable_region, duplicate_invoice_number, or handwriting_present. Use null for missing values. Do not include markdown or explanatory text.",
                "temperature": 0.1,
                "topP": 0.9,
                "maxTokens": 12000,
                "thinkingLevel": "medium"
            },
            "inputs": {
                "images": [
                    "https://assets.runware.ai/assets/inputs/58747a6a-c347-4e5d-93ee-f965a0372d23.jpg"
                ]
            },
            "includeUsage": True,
            "messages": [
                {
                    "role": "user",
                    "content": "Extract all visible invoice data from this image and output strict JSON with the schema described in the system instructions. Prioritize accuracy, preserve formatting for invoice numbers and purchase orders, and include every visible document even if partial."
                }
            ]
        })


asyncio.run(main())

curl https://api.runware.ai/v1 \
  -H "Authorization: Bearer $RUNWARE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '[
    {
      "taskType": "textInference",
      "taskUUID": "e3e532d4-b6ea-41ee-8f15-2291b901f732",
      "model": "openai:gpt@5.4-nano",
      "seed": 49394,
      "settings": {
        "systemPrompt": "You are a fast document-processing assistant optimized for extracting structured data from operational paperwork. Read the provided image carefully and return only valid JSON. If multiple documents are visible, process each one separately. For every document, extract: vendor_name, invoice_number, purchase_order, invoice_date, due_date, currency, subtotal, tax, total, line_item_count, and confidence. Also include a top-level summary with document_count, currencies_detected, highest_total, and any flags such as missing_field, unreadable_region, duplicate_invoice_number, or handwriting_present. Use null for missing values. Do not include markdown or explanatory text.",
        "temperature": 0.1,
        "topP": 0.9,
        "maxTokens": 12000,
        "thinkingLevel": "medium"
      },
      "inputs": {
        "images": [
          "https://assets.runware.ai/assets/inputs/58747a6a-c347-4e5d-93ee-f965a0372d23.jpg"
        ]
      },
      "includeUsage": true,
      "messages": [
        {
          "role": "user",
          "content": "Extract all visible invoice data from this image and output strict JSON with the schema described in the system instructions. Prioritize accuracy, preserve formatting for invoice numbers and purchase orders, and include every visible document even if partial."
        }
      ]
    }
  ]'

runware run openai:gpt@5.4-nano \
  seed=49394 \
  settings.systemPrompt="You are a fast document-processing assistant optimized for extracting structured data from operational paperwork. Read the provided image carefully and return only valid JSON. If multiple documents are visible, process each one separately. For every document, extract: vendor_name, invoice_number, purchase_order, invoice_date, due_date, currency, subtotal, tax, total, line_item_count, and confidence. Also include a top-level summary with document_count, currencies_detected, highest_total, and any flags such as missing_field, unreadable_region, duplicate_invoice_number, or handwriting_present. Use null for missing values. Do not include markdown or explanatory text." \
  settings.temperature=0.1 \
  settings.topP=0.9 \
  settings.maxTokens=12000 \
  settings.thinkingLevel=medium \
  inputs.images.0=https://assets.runware.ai/assets/inputs/58747a6a-c347-4e5d-93ee-f965a0372d23.jpg \
  includeUsage=true \
  messages.0.role=user \
  messages.0.content="Extract all visible invoice data from this image and output strict JSON with the schema described in the system instructions. Prioritize accuracy, preserve formatting for invoice numbers and purchase orders, and include every visible document even if partial."

{
  "taskType": "textInference",
  "taskUUID": "e3e532d4-b6ea-41ee-8f15-2291b901f732",
  "model": "openai:gpt@5.4-nano",
  "seed": 49394,
  "settings": {
    "systemPrompt": "You are a fast document-processing assistant optimized for extracting structured data from operational paperwork. Read the provided image carefully and return only valid JSON. If multiple documents are visible, process each one separately. For every document, extract: vendor_name, invoice_number, purchase_order, invoice_date, due_date, currency, subtotal, tax, total, line_item_count, and confidence. Also include a top-level summary with document_count, currencies_detected, highest_total, and any flags such as missing_field, unreadable_region, duplicate_invoice_number, or handwriting_present. Use null for missing values. Do not include markdown or explanatory text.",
    "temperature": 0.1,
    "topP": 0.9,
    "maxTokens": 12000,
    "thinkingLevel": "medium"
  },
  "inputs": {
    "images": [
      "https://assets.runware.ai/assets/inputs/58747a6a-c347-4e5d-93ee-f965a0372d23.jpg"
    ]
  },
  "includeUsage": true,
  "messages": [
    {
      "role": "user",
      "content": "Extract all visible invoice data from this image and output strict JSON with the schema described in the system instructions. Prioritize accuracy, preserve formatting for invoice numbers and purchase orders, and include every visible document even if partial."
    }
  ]
}

import { createClient } from '@runware/sdk'

const client = await createClient({ apiKey: process.env.RUNWARE_API_KEY })
await client.connect()

const [result] = await client.run({
  model: 'openai:gpt@5.4-nano',
  seed: 12487,
  settings: {
    systemPrompt: 'You are a fast logistics document assistant optimized for concise extraction, classification, and operational exception detection. Read package-label images carefully. If some text is unclear, mark it as uncertain instead of inventing details. Prefer compact structured plain text.',
    temperature: 0.2,
    topP: 0.9,
    maxTokens: 12000,
    thinkingLevel: 'medium'
  },
  includeUsage: true,
  inputs: {
    images: [
      'https://assets.runware.ai/assets/inputs/ab8bb7d6-7df1-4358-9b58-a450a7edca87.jpg'
    ]
  },
  messages: [
    {
      role: 'user',
      content: 'Analyze the shipping label in this image and provide: 1) recipient name, 2) full destination address, 3) tracking number, 4) service level, 5) package weight, 6) any handwritten or sticker-based special handling notes, 7) whether the shipment should be flagged for manual review. Then add a short reason for the review decision. Format the answer as compact field-value lines.'
    }
  ]
})

import asyncio
import os

from runware import Runware


async def main():
    async with Runware(api_key=os.environ["RUNWARE_API_KEY"]) as client:
        results = await client.run({
            "model": "openai:gpt@5.4-nano",
            "seed": 12487,
            "settings": {
                "systemPrompt": "You are a fast logistics document assistant optimized for concise extraction, classification, and operational exception detection. Read package-label images carefully. If some text is unclear, mark it as uncertain instead of inventing details. Prefer compact structured plain text.",
                "temperature": 0.2,
                "topP": 0.9,
                "maxTokens": 12000,
                "thinkingLevel": "medium"
            },
            "includeUsage": True,
            "inputs": {
                "images": [
                    "https://assets.runware.ai/assets/inputs/ab8bb7d6-7df1-4358-9b58-a450a7edca87.jpg"
                ]
            },
            "messages": [
                {
                    "role": "user",
                    "content": "Analyze the shipping label in this image and provide: 1) recipient name, 2) full destination address, 3) tracking number, 4) service level, 5) package weight, 6) any handwritten or sticker-based special handling notes, 7) whether the shipment should be flagged for manual review. Then add a short reason for the review decision. Format the answer as compact field-value lines."
                }
            ]
        })


asyncio.run(main())

curl https://api.runware.ai/v1 \
  -H "Authorization: Bearer $RUNWARE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '[
    {
      "taskType": "textInference",
      "taskUUID": "cce180b7-7bb5-42df-841e-1168b9390928",
      "model": "openai:gpt@5.4-nano",
      "seed": 12487,
      "settings": {
        "systemPrompt": "You are a fast logistics document assistant optimized for concise extraction, classification, and operational exception detection. Read package-label images carefully. If some text is unclear, mark it as uncertain instead of inventing details. Prefer compact structured plain text.",
        "temperature": 0.2,
        "topP": 0.9,
        "maxTokens": 12000,
        "thinkingLevel": "medium"
      },
      "includeUsage": true,
      "inputs": {
        "images": [
          "https://assets.runware.ai/assets/inputs/ab8bb7d6-7df1-4358-9b58-a450a7edca87.jpg"
        ]
      },
      "messages": [
        {
          "role": "user",
          "content": "Analyze the shipping label in this image and provide: 1) recipient name, 2) full destination address, 3) tracking number, 4) service level, 5) package weight, 6) any handwritten or sticker-based special handling notes, 7) whether the shipment should be flagged for manual review. Then add a short reason for the review decision. Format the answer as compact field-value lines."
        }
      ]
    }
  ]'

runware run openai:gpt@5.4-nano \
  seed=12487 \
  settings.systemPrompt="You are a fast logistics document assistant optimized for concise extraction, classification, and operational exception detection. Read package-label images carefully. If some text is unclear, mark it as uncertain instead of inventing details. Prefer compact structured plain text." \
  settings.temperature=0.2 \
  settings.topP=0.9 \
  settings.maxTokens=12000 \
  settings.thinkingLevel=medium \
  includeUsage=true \
  inputs.images.0=https://assets.runware.ai/assets/inputs/ab8bb7d6-7df1-4358-9b58-a450a7edca87.jpg \
  messages.0.role=user \
  messages.0.content="Analyze the shipping label in this image and provide: 1) recipient name, 2) full destination address, 3) tracking number, 4) service level, 5) package weight, 6) any handwritten or sticker-based special handling notes, 7) whether the shipment should be flagged for manual review. Then add a short reason for the review decision. Format the answer as compact field-value lines."

{
  "taskType": "textInference",
  "taskUUID": "cce180b7-7bb5-42df-841e-1168b9390928",
  "model": "openai:gpt@5.4-nano",
  "seed": 12487,
  "settings": {
    "systemPrompt": "You are a fast logistics document assistant optimized for concise extraction, classification, and operational exception detection. Read package-label images carefully. If some text is unclear, mark it as uncertain instead of inventing details. Prefer compact structured plain text.",
    "temperature": 0.2,
    "topP": 0.9,
    "maxTokens": 12000,
    "thinkingLevel": "medium"
  },
  "includeUsage": true,
  "inputs": {
    "images": [
      "https://assets.runware.ai/assets/inputs/ab8bb7d6-7df1-4358-9b58-a450a7edca87.jpg"
    ]
  },
  "messages": [
    {
      "role": "user",
      "content": "Analyze the shipping label in this image and provide: 1) recipient name, 2) full destination address, 3) tracking number, 4) service level, 5) package weight, 6) any handwritten or sticker-based special handling notes, 7) whether the shipment should be flagged for manual review. Then add a short reason for the review decision. Format the answer as compact field-value lines."
    }
  ]
}

import { createClient } from '@runware/sdk'

const client = await createClient({ apiKey: process.env.RUNWARE_API_KEY })
await client.connect()

const [result] = await client.run({
  model: 'openai:gpt@5.4-nano',
  seed: 72273,
  settings: {
    systemPrompt: 'You are a fast municipal records assistant. Extract visible plaque text from the provided image with best-effort OCR, then organize the results clearly. If text is uncertain, preserve the uncertain characters with [?]. Do not invent details not supported by the image. Return concise but structured output with one item per bench or plaque region.',
    temperature: 0.2,
    topP: 0.9,
    maxTokens: 12000,
    thinkingLevel: 'low'
  },
  includeUsage: true,
  inputs: {
    images: [
      'https://assets.runware.ai/assets/inputs/a173496f-73bd-4736-9df0-53d3230eba93.jpg'
    ]
  },
  messages: [
    {
      role: 'user',
      content: 'Analyze the uploaded park image. Identify every bench plaque you can find. For each plaque, provide: 1) plaque index, 2) approximate location in the image, 3) transcribed text, 4) confidence level as high/medium/low, and 5) a short normalization of the dedication name if present. Then add a final section listing plaques that may require a manual recheck because of glare, angle, distance, or occlusion.'
    }
  ]
})

import asyncio
import os

from runware import Runware


async def main():
    async with Runware(api_key=os.environ["RUNWARE_API_KEY"]) as client:
        results = await client.run({
            "model": "openai:gpt@5.4-nano",
            "seed": 72273,
            "settings": {
                "systemPrompt": "You are a fast municipal records assistant. Extract visible plaque text from the provided image with best-effort OCR, then organize the results clearly. If text is uncertain, preserve the uncertain characters with [?]. Do not invent details not supported by the image. Return concise but structured output with one item per bench or plaque region.",
                "temperature": 0.2,
                "topP": 0.9,
                "maxTokens": 12000,
                "thinkingLevel": "low"
            },
            "includeUsage": True,
            "inputs": {
                "images": [
                    "https://assets.runware.ai/assets/inputs/a173496f-73bd-4736-9df0-53d3230eba93.jpg"
                ]
            },
            "messages": [
                {
                    "role": "user",
                    "content": "Analyze the uploaded park image. Identify every bench plaque you can find. For each plaque, provide: 1) plaque index, 2) approximate location in the image, 3) transcribed text, 4) confidence level as high/medium/low, and 5) a short normalization of the dedication name if present. Then add a final section listing plaques that may require a manual recheck because of glare, angle, distance, or occlusion."
                }
            ]
        })


asyncio.run(main())

curl https://api.runware.ai/v1 \
  -H "Authorization: Bearer $RUNWARE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '[
    {
      "taskType": "textInference",
      "taskUUID": "df039aa4-d093-499d-bdf8-0a93f64a9c93",
      "model": "openai:gpt@5.4-nano",
      "seed": 72273,
      "settings": {
        "systemPrompt": "You are a fast municipal records assistant. Extract visible plaque text from the provided image with best-effort OCR, then organize the results clearly. If text is uncertain, preserve the uncertain characters with [?]. Do not invent details not supported by the image. Return concise but structured output with one item per bench or plaque region.",
        "temperature": 0.2,
        "topP": 0.9,
        "maxTokens": 12000,
        "thinkingLevel": "low"
      },
      "includeUsage": true,
      "inputs": {
        "images": [
          "https://assets.runware.ai/assets/inputs/a173496f-73bd-4736-9df0-53d3230eba93.jpg"
        ]
      },
      "messages": [
        {
          "role": "user",
          "content": "Analyze the uploaded park image. Identify every bench plaque you can find. For each plaque, provide: 1) plaque index, 2) approximate location in the image, 3) transcribed text, 4) confidence level as high/medium/low, and 5) a short normalization of the dedication name if present. Then add a final section listing plaques that may require a manual recheck because of glare, angle, distance, or occlusion."
        }
      ]
    }
  ]'

runware run openai:gpt@5.4-nano \
  seed=72273 \
  settings.systemPrompt="You are a fast municipal records assistant. Extract visible plaque text from the provided image with best-effort OCR, then organize the results clearly. If text is uncertain, preserve the uncertain characters with [?]. Do not invent details not supported by the image. Return concise but structured output with one item per bench or plaque region." \
  settings.temperature=0.2 \
  settings.topP=0.9 \
  settings.maxTokens=12000 \
  settings.thinkingLevel=low \
  includeUsage=true \
  inputs.images.0=https://assets.runware.ai/assets/inputs/a173496f-73bd-4736-9df0-53d3230eba93.jpg \
  messages.0.role=user \
  messages.0.content="Analyze the uploaded park image. Identify every bench plaque you can find. For each plaque, provide: 1) plaque index, 2) approximate location in the image, 3) transcribed text, 4) confidence level as high/medium/low, and 5) a short normalization of the dedication name if present. Then add a final section listing plaques that may require a manual recheck because of glare, angle, distance, or occlusion."

{
  "taskType": "textInference",
  "taskUUID": "df039aa4-d093-499d-bdf8-0a93f64a9c93",
  "model": "openai:gpt@5.4-nano",
  "seed": 72273,
  "settings": {
    "systemPrompt": "You are a fast municipal records assistant. Extract visible plaque text from the provided image with best-effort OCR, then organize the results clearly. If text is uncertain, preserve the uncertain characters with [?]. Do not invent details not supported by the image. Return concise but structured output with one item per bench or plaque region.",
    "temperature": 0.2,
    "topP": 0.9,
    "maxTokens": 12000,
    "thinkingLevel": "low"
  },
  "includeUsage": true,
  "inputs": {
    "images": [
      "https://assets.runware.ai/assets/inputs/a173496f-73bd-4736-9df0-53d3230eba93.jpg"
    ]
  },
  "messages": [
    {
      "role": "user",
      "content": "Analyze the uploaded park image. Identify every bench plaque you can find. For each plaque, provide: 1) plaque index, 2) approximate location in the image, 3) transcribed text, 4) confidence level as high/medium/low, and 5) a short normalization of the dedication name if present. Then add a final section listing plaques that may require a manual recheck because of glare, angle, distance, or occlusion."
    }
  ]
}

import { createClient } from '@runware/sdk'

const client = await createClient({ apiKey: process.env.RUNWARE_API_KEY })
await client.connect()

const [result] = await client.run({
  model: 'openai:gpt@5.4-nano',
  seed: 83712,
  settings: {
    systemPrompt: 'You are a fast, precise operations-document parser. Analyze the provided image and extract all readable operational information. Prioritize accuracy, concise wording, and complete coverage. If text is unclear, mark it as uncertain instead of guessing. Organize the response into these sections: 1) Document types present, 2) Key identifiers and dates, 3) Warnings or urgent issues, 4) Handwritten edits and overrides, 5) Missing, conflicting, or suspicious details, 6) A final 5-bullet action summary.',
    temperature: 0.2,
    topP: 0.9,
    maxTokens: 12000,
    thinkingLevel: 'medium'
  },
  includeUsage: true,
  inputs: {
    images: [
      'https://assets.runware.ai/assets/inputs/9788b2f9-5c0a-4cd0-b184-191b7b1ccc83.jpg'
    ]
  },
  messages: [
    {
      role: 'user',
      content: 'Review this noticeboard image from a metalworking floor. Extract the readable information, identify any contradictions between printed sheets and handwritten edits, flag overdue inspections, and summarize the top operational risks. Keep the answer structured under the six requested headings.'
    }
  ]
})

import asyncio
import os

from runware import Runware


async def main():
    async with Runware(api_key=os.environ["RUNWARE_API_KEY"]) as client:
        results = await client.run({
            "model": "openai:gpt@5.4-nano",
            "seed": 83712,
            "settings": {
                "systemPrompt": "You are a fast, precise operations-document parser. Analyze the provided image and extract all readable operational information. Prioritize accuracy, concise wording, and complete coverage. If text is unclear, mark it as uncertain instead of guessing. Organize the response into these sections: 1) Document types present, 2) Key identifiers and dates, 3) Warnings or urgent issues, 4) Handwritten edits and overrides, 5) Missing, conflicting, or suspicious details, 6) A final 5-bullet action summary.",
                "temperature": 0.2,
                "topP": 0.9,
                "maxTokens": 12000,
                "thinkingLevel": "medium"
            },
            "includeUsage": True,
            "inputs": {
                "images": [
                    "https://assets.runware.ai/assets/inputs/9788b2f9-5c0a-4cd0-b184-191b7b1ccc83.jpg"
                ]
            },
            "messages": [
                {
                    "role": "user",
                    "content": "Review this noticeboard image from a metalworking floor. Extract the readable information, identify any contradictions between printed sheets and handwritten edits, flag overdue inspections, and summarize the top operational risks. Keep the answer structured under the six requested headings."
                }
            ]
        })


asyncio.run(main())

curl https://api.runware.ai/v1 \
  -H "Authorization: Bearer $RUNWARE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '[
    {
      "taskType": "textInference",
      "taskUUID": "595dcbb6-ed9a-4197-940f-4233947715e6",
      "model": "openai:gpt@5.4-nano",
      "seed": 83712,
      "settings": {
        "systemPrompt": "You are a fast, precise operations-document parser. Analyze the provided image and extract all readable operational information. Prioritize accuracy, concise wording, and complete coverage. If text is unclear, mark it as uncertain instead of guessing. Organize the response into these sections: 1) Document types present, 2) Key identifiers and dates, 3) Warnings or urgent issues, 4) Handwritten edits and overrides, 5) Missing, conflicting, or suspicious details, 6) A final 5-bullet action summary.",
        "temperature": 0.2,
        "topP": 0.9,
        "maxTokens": 12000,
        "thinkingLevel": "medium"
      },
      "includeUsage": true,
      "inputs": {
        "images": [
          "https://assets.runware.ai/assets/inputs/9788b2f9-5c0a-4cd0-b184-191b7b1ccc83.jpg"
        ]
      },
      "messages": [
        {
          "role": "user",
          "content": "Review this noticeboard image from a metalworking floor. Extract the readable information, identify any contradictions between printed sheets and handwritten edits, flag overdue inspections, and summarize the top operational risks. Keep the answer structured under the six requested headings."
        }
      ]
    }
  ]'

runware run openai:gpt@5.4-nano \
  seed=83712 \
  settings.systemPrompt="You are a fast, precise operations-document parser. Analyze the provided image and extract all readable operational information. Prioritize accuracy, concise wording, and complete coverage. If text is unclear, mark it as uncertain instead of guessing. Organize the response into these sections: 1) Document types present, 2) Key identifiers and dates, 3) Warnings or urgent issues, 4) Handwritten edits and overrides, 5) Missing, conflicting, or suspicious details, 6) A final 5-bullet action summary." \
  settings.temperature=0.2 \
  settings.topP=0.9 \
  settings.maxTokens=12000 \
  settings.thinkingLevel=medium \
  includeUsage=true \
  inputs.images.0=https://assets.runware.ai/assets/inputs/9788b2f9-5c0a-4cd0-b184-191b7b1ccc83.jpg \
  messages.0.role=user \
  messages.0.content="Review this noticeboard image from a metalworking floor. Extract the readable information, identify any contradictions between printed sheets and handwritten edits, flag overdue inspections, and summarize the top operational risks. Keep the answer structured under the six requested headings."

{
  "taskType": "textInference",
  "taskUUID": "595dcbb6-ed9a-4197-940f-4233947715e6",
  "model": "openai:gpt@5.4-nano",
  "seed": 83712,
  "settings": {
    "systemPrompt": "You are a fast, precise operations-document parser. Analyze the provided image and extract all readable operational information. Prioritize accuracy, concise wording, and complete coverage. If text is unclear, mark it as uncertain instead of guessing. Organize the response into these sections: 1) Document types present, 2) Key identifiers and dates, 3) Warnings or urgent issues, 4) Handwritten edits and overrides, 5) Missing, conflicting, or suspicious details, 6) A final 5-bullet action summary.",
    "temperature": 0.2,
    "topP": 0.9,
    "maxTokens": 12000,
    "thinkingLevel": "medium"
  },
  "includeUsage": true,
  "inputs": {
    "images": [
      "https://assets.runware.ai/assets/inputs/9788b2f9-5c0a-4cd0-b184-191b7b1ccc83.jpg"
    ]
  },
  "messages": [
    {
      "role": "user",
      "content": "Review this noticeboard image from a metalworking floor. Extract the readable information, identify any contradictions between printed sheets and handwritten edits, flag overdue inspections, and summarize the top operational risks. Keep the answer structured under the six requested headings."
    }
  ]
}

import { createClient } from '@runware/sdk'

const client = await createClient({ apiKey: process.env.RUNWARE_API_KEY })
await client.connect()

const [result] = await client.run({
  model: 'openai:gpt@5.4-nano',
  inputs: {
    images: [
      'https://assets.runware.ai/assets/inputs/a93c611e-7a04-4791-ab9e-07c0f528165c.jpg',
      'https://assets.runware.ai/assets/inputs/99f05b63-b8dc-4de8-a76a-23d38554580b.jpg'
    ]
  },
  messages: [
    {
      role: 'user',
      content: 'Prepare one listing-ready catalog record for this secondhand jacket using both images. Image 1 is the garment overview; Image 2 shows its interior labels. Reconcile the visual features with the label information and return:\n\n1. A factual listing title of no more than 12 words.\n2. Structured fields for brand, style or model, garment type, tagged size, color, shell material, lining material, country of manufacture, closure, collar, pockets, and care instructions.\n3. A concise condition summary naming only wear or defects clearly visible in Image 1.\n4. Any conflict or uncertainty between the two images.\n5. A 60–90 word marketplace description.\n\nTranscribe label facts exactly when legible. Do not infer measurements, gender category, age, authenticity, fit, price, or unseen condition. Use “Not visible” when evidence is missing, and clearly distinguish label-derived facts from visual observations.'
    }
  ]
})

import asyncio
import os

from runware import Runware


async def main():
    async with Runware(api_key=os.environ["RUNWARE_API_KEY"]) as client:
        results = await client.run({
            "model": "openai:gpt@5.4-nano",
            "inputs": {
                "images": [
                    "https://assets.runware.ai/assets/inputs/a93c611e-7a04-4791-ab9e-07c0f528165c.jpg",
                    "https://assets.runware.ai/assets/inputs/99f05b63-b8dc-4de8-a76a-23d38554580b.jpg"
                ]
            },
            "messages": [
                {
                    "role": "user",
                    "content": "Prepare one listing-ready catalog record for this secondhand jacket using both images. Image 1 is the garment overview; Image 2 shows its interior labels. Reconcile the visual features with the label information and return:\n\n1. A factual listing title of no more than 12 words.\n2. Structured fields for brand, style or model, garment type, tagged size, color, shell material, lining material, country of manufacture, closure, collar, pockets, and care instructions.\n3. A concise condition summary naming only wear or defects clearly visible in Image 1.\n4. Any conflict or uncertainty between the two images.\n5. A 60–90 word marketplace description.\n\nTranscribe label facts exactly when legible. Do not infer measurements, gender category, age, authenticity, fit, price, or unseen condition. Use “Not visible” when evidence is missing, and clearly distinguish label-derived facts from visual observations."
                }
            ]
        })


asyncio.run(main())

curl https://api.runware.ai/v1 \
  -H "Authorization: Bearer $RUNWARE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '[
    {
      "taskType": "textInference",
      "taskUUID": "03d14b02-84d2-4e22-b2ec-7a8e8ba443b6",
      "model": "openai:gpt@5.4-nano",
      "inputs": {
        "images": [
          "https://assets.runware.ai/assets/inputs/a93c611e-7a04-4791-ab9e-07c0f528165c.jpg",
          "https://assets.runware.ai/assets/inputs/99f05b63-b8dc-4de8-a76a-23d38554580b.jpg"
        ]
      },
      "messages": [
        {
          "role": "user",
          "content": "Prepare one listing-ready catalog record for this secondhand jacket using both images. Image 1 is the garment overview; Image 2 shows its interior labels. Reconcile the visual features with the label information and return:\n\n1. A factual listing title of no more than 12 words.\n2. Structured fields for brand, style or model, garment type, tagged size, color, shell material, lining material, country of manufacture, closure, collar, pockets, and care instructions.\n3. A concise condition summary naming only wear or defects clearly visible in Image 1.\n4. Any conflict or uncertainty between the two images.\n5. A 60–90 word marketplace description.\n\nTranscribe label facts exactly when legible. Do not infer measurements, gender category, age, authenticity, fit, price, or unseen condition. Use “Not visible” when evidence is missing, and clearly distinguish label-derived facts from visual observations."
        }
      ]
    }
  ]'

runware run openai:gpt@5.4-nano \
  inputs.images.0=https://assets.runware.ai/assets/inputs/a93c611e-7a04-4791-ab9e-07c0f528165c.jpg \
  inputs.images.1=https://assets.runware.ai/assets/inputs/99f05b63-b8dc-4de8-a76a-23d38554580b.jpg \
  messages.0.role=user \
  messages.0.content="Prepare one listing-ready catalog record for this secondhand jacket using both images. Image 1 is the garment overview; Image 2 shows its interior labels. Reconcile the visual features with the label information and return:

1. A factual listing title of no more than 12 words.
2. Structured fields for brand, style or model, garment type, tagged size, color, shell material, lining material, country of manufacture, closure, collar, pockets, and care instructions.
3. A concise condition summary naming only wear or defects clearly visible in Image 1.
4. Any conflict or uncertainty between the two images.
5. A 60–90 word marketplace description.

Transcribe label facts exactly when legible. Do not infer measurements, gender category, age, authenticity, fit, price, or unseen condition. Use “Not visible” when evidence is missing, and clearly distinguish label-derived facts from visual observations."

{
  "taskType": "textInference",
  "taskUUID": "03d14b02-84d2-4e22-b2ec-7a8e8ba443b6",
  "model": "openai:gpt@5.4-nano",
  "inputs": {
    "images": [
      "https://assets.runware.ai/assets/inputs/a93c611e-7a04-4791-ab9e-07c0f528165c.jpg",
      "https://assets.runware.ai/assets/inputs/99f05b63-b8dc-4de8-a76a-23d38554580b.jpg"
    ]
  },
  "messages": [
    {
      "role": "user",
      "content": "Prepare one listing-ready catalog record for this secondhand jacket using both images. Image 1 is the garment overview; Image 2 shows its interior labels. Reconcile the visual features with the label information and return:\n\n1. A factual listing title of no more than 12 words.\n2. Structured fields for brand, style or model, garment type, tagged size, color, shell material, lining material, country of manufacture, closure, collar, pockets, and care instructions.\n3. A concise condition summary naming only wear or defects clearly visible in Image 1.\n4. Any conflict or uncertainty between the two images.\n5. A 60–90 word marketplace description.\n\nTranscribe label facts exactly when legible. Do not infer measurements, gender category, age, authenticity, fit, price, or unseen condition. Use “Not visible” when evidence is missing, and clearly distinguish label-derived facts from visual observations."
    }
  ]
}

import { createClient } from '@runware/sdk'

const client = await createClient({ apiKey: process.env.RUNWARE_API_KEY })
await client.connect()

const [result] = await client.run({
  model: 'openai:gpt@5.4-nano',
  inputs: {
    images: [
      'https://assets.runware.ai/assets/inputs/acbcc752-da7e-4cfc-a7e9-b7934e439dfa.jpg',
      'https://assets.runware.ai/assets/inputs/bbd047d0-d6ab-4ffe-a962-95ea483e31d1.jpg'
    ]
  },
  messages: [
    {
      role: 'user',
      content: 'Image 1 is the move-in baseline and Image 2 is the move-out inspection. Compare both images and write a concise property-condition report for the manager. Include: (1) an overall finding; (2) a table with area or fixture, baseline condition, move-out condition, visible change, likely category—damage, ordinary wear, cleanliness or unchanged—severity, and confidence; and (3) recommended follow-up evidence or action. Mention only differences supported by the images. Distinguish physical damage from removable dirt, avoid estimating repair costs, and state when angle, lighting or visibility prevents a reliable conclusion.'
    }
  ]
})

import asyncio
import os

from runware import Runware


async def main():
    async with Runware(api_key=os.environ["RUNWARE_API_KEY"]) as client:
        results = await client.run({
            "model": "openai:gpt@5.4-nano",
            "inputs": {
                "images": [
                    "https://assets.runware.ai/assets/inputs/acbcc752-da7e-4cfc-a7e9-b7934e439dfa.jpg",
                    "https://assets.runware.ai/assets/inputs/bbd047d0-d6ab-4ffe-a962-95ea483e31d1.jpg"
                ]
            },
            "messages": [
                {
                    "role": "user",
                    "content": "Image 1 is the move-in baseline and Image 2 is the move-out inspection. Compare both images and write a concise property-condition report for the manager. Include: (1) an overall finding; (2) a table with area or fixture, baseline condition, move-out condition, visible change, likely category—damage, ordinary wear, cleanliness or unchanged—severity, and confidence; and (3) recommended follow-up evidence or action. Mention only differences supported by the images. Distinguish physical damage from removable dirt, avoid estimating repair costs, and state when angle, lighting or visibility prevents a reliable conclusion."
                }
            ]
        })


asyncio.run(main())

curl https://api.runware.ai/v1 \
  -H "Authorization: Bearer $RUNWARE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '[
    {
      "taskType": "textInference",
      "taskUUID": "5c9cb0be-3bef-4c88-b14e-f0fbbf5f0d27",
      "model": "openai:gpt@5.4-nano",
      "inputs": {
        "images": [
          "https://assets.runware.ai/assets/inputs/acbcc752-da7e-4cfc-a7e9-b7934e439dfa.jpg",
          "https://assets.runware.ai/assets/inputs/bbd047d0-d6ab-4ffe-a962-95ea483e31d1.jpg"
        ]
      },
      "messages": [
        {
          "role": "user",
          "content": "Image 1 is the move-in baseline and Image 2 is the move-out inspection. Compare both images and write a concise property-condition report for the manager. Include: (1) an overall finding; (2) a table with area or fixture, baseline condition, move-out condition, visible change, likely category—damage, ordinary wear, cleanliness or unchanged—severity, and confidence; and (3) recommended follow-up evidence or action. Mention only differences supported by the images. Distinguish physical damage from removable dirt, avoid estimating repair costs, and state when angle, lighting or visibility prevents a reliable conclusion."
        }
      ]
    }
  ]'

runware run openai:gpt@5.4-nano \
  inputs.images.0=https://assets.runware.ai/assets/inputs/acbcc752-da7e-4cfc-a7e9-b7934e439dfa.jpg \
  inputs.images.1=https://assets.runware.ai/assets/inputs/bbd047d0-d6ab-4ffe-a962-95ea483e31d1.jpg \
  messages.0.role=user \
  messages.0.content="Image 1 is the move-in baseline and Image 2 is the move-out inspection. Compare both images and write a concise property-condition report for the manager. Include: (1) an overall finding; (2) a table with area or fixture, baseline condition, move-out condition, visible change, likely category—damage, ordinary wear, cleanliness or unchanged—severity, and confidence; and (3) recommended follow-up evidence or action. Mention only differences supported by the images. Distinguish physical damage from removable dirt, avoid estimating repair costs, and state when angle, lighting or visibility prevents a reliable conclusion."

{
  "taskType": "textInference",
  "taskUUID": "5c9cb0be-3bef-4c88-b14e-f0fbbf5f0d27",
  "model": "openai:gpt@5.4-nano",
  "inputs": {
    "images": [
      "https://assets.runware.ai/assets/inputs/acbcc752-da7e-4cfc-a7e9-b7934e439dfa.jpg",
      "https://assets.runware.ai/assets/inputs/bbd047d0-d6ab-4ffe-a962-95ea483e31d1.jpg"
    ]
  },
  "messages": [
    {
      "role": "user",
      "content": "Image 1 is the move-in baseline and Image 2 is the move-out inspection. Compare both images and write a concise property-condition report for the manager. Include: (1) an overall finding; (2) a table with area or fixture, baseline condition, move-out condition, visible change, likely category—damage, ordinary wear, cleanliness or unchanged—severity, and confidence; and (3) recommended follow-up evidence or action. Mention only differences supported by the images. Distinguish physical damage from removable dirt, avoid estimating repair costs, and state when angle, lighting or visibility prevents a reliable conclusion."
    }
  ]
}