Claude Haiku 4.5

import { createClient } from '@runware/sdk'

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

const [result] = await client.run({
  model: 'anthropic:claude@haiku-4.5',
  settings: {
    maxTokens: 1200,
    thinkingLevel: 'medium'
  },
  messages: [
    {
      role: 'user',
      content: 'Act as a procurement analyst for an independent restaurant replacing a failed walk-in cooler. Prepare a concise decision memo for the owner using only the facts below.\n\nOperating constraints:\n- Total project budget: $48,000\n- Cooler must be operational within 6 calendar days of contract award\n- Off-site refrigerated storage costs $650 per outage day\n- The city requires a mechanical permit\n\nBid A — Northstar Mechanical\n- Base price: $41,800\n- Can start 9 days after award; installation takes 4 days\n- Includes demolition, disposal, insulated 8-by-12-foot box, condensing unit, installation, permit and up to 20 feet of electrical reconnection\n- Excludes night work\n- Warranty: 2 years labor, 5 years compressor, 10 years panels\n\nBid B — Polar Service Group\n- Base price: $37,900\n- Can start 3 days after award; installation takes 5 days\n- Includes insulated box, condensing unit and installation\n- Excludes permit ($1,200), electrical work (estimated at $4,800), and demolition/disposal ($2,600)\n- Change orders carry an 18% markup\n- Warranty: 1 year labor, 5 years compressor, 10 years panels\n\nBid C — Glacier Commercial Systems\n- Fixed price: $46,700\n- Can start 2 days after award; installation takes 3 days\n- Includes demolition, disposal, box, condensing unit, permit, electrical work, a temporary refrigerated trailer during the outage and a remote temperature alarm\n- Four-hour emergency service response\n- Warranty: 3 years labor, 7 years compressor, 10 years panels\n\nDeliver exactly these sections:\n1. Recommendation — no more than 80 words\n2. Normalized Comparison — a compact table showing quoted price, known add-ons, outage-storage cost, evaluated total, completion timing and warranty\n3. Key Risks — up to three bullets\n4. Pre-Award Questions — up to four questions for the recommended vendor\n5. Negotiation Priorities — up to three bullets\n\nShow arithmetic clearly. Treat the temporary trailer as eliminating off-site storage cost for Bid C. Flag any bid that fails a stated constraint. Do not invent taxes, financing costs or equipment specifications.'
    }
  ]
})

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": "anthropic:claude@haiku-4.5",
            "settings": {
                "maxTokens": 1200,
                "thinkingLevel": "medium"
            },
            "messages": [
                {
                    "role": "user",
                    "content": "Act as a procurement analyst for an independent restaurant replacing a failed walk-in cooler. Prepare a concise decision memo for the owner using only the facts below.\n\nOperating constraints:\n- Total project budget: $48,000\n- Cooler must be operational within 6 calendar days of contract award\n- Off-site refrigerated storage costs $650 per outage day\n- The city requires a mechanical permit\n\nBid A — Northstar Mechanical\n- Base price: $41,800\n- Can start 9 days after award; installation takes 4 days\n- Includes demolition, disposal, insulated 8-by-12-foot box, condensing unit, installation, permit and up to 20 feet of electrical reconnection\n- Excludes night work\n- Warranty: 2 years labor, 5 years compressor, 10 years panels\n\nBid B — Polar Service Group\n- Base price: $37,900\n- Can start 3 days after award; installation takes 5 days\n- Includes insulated box, condensing unit and installation\n- Excludes permit ($1,200), electrical work (estimated at $4,800), and demolition/disposal ($2,600)\n- Change orders carry an 18% markup\n- Warranty: 1 year labor, 5 years compressor, 10 years panels\n\nBid C — Glacier Commercial Systems\n- Fixed price: $46,700\n- Can start 2 days after award; installation takes 3 days\n- Includes demolition, disposal, box, condensing unit, permit, electrical work, a temporary refrigerated trailer during the outage and a remote temperature alarm\n- Four-hour emergency service response\n- Warranty: 3 years labor, 7 years compressor, 10 years panels\n\nDeliver exactly these sections:\n1. Recommendation — no more than 80 words\n2. Normalized Comparison — a compact table showing quoted price, known add-ons, outage-storage cost, evaluated total, completion timing and warranty\n3. Key Risks — up to three bullets\n4. Pre-Award Questions — up to four questions for the recommended vendor\n5. Negotiation Priorities — up to three bullets\n\nShow arithmetic clearly. Treat the temporary trailer as eliminating off-site storage cost for Bid C. Flag any bid that fails a stated constraint. Do not invent taxes, financing costs or equipment specifications."
                }
            ]
        })


asyncio.run(main())

curl https://api.runware.ai/v1 \
  -H "Authorization: Bearer $RUNWARE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '[
    {
      "taskType": "textInference",
      "taskUUID": "823d7dbd-68c5-408a-acab-02d7f7672f49",
      "model": "anthropic:claude@haiku-4.5",
      "settings": {
        "maxTokens": 1200,
        "thinkingLevel": "medium"
      },
      "messages": [
        {
          "role": "user",
          "content": "Act as a procurement analyst for an independent restaurant replacing a failed walk-in cooler. Prepare a concise decision memo for the owner using only the facts below.\n\nOperating constraints:\n- Total project budget: $48,000\n- Cooler must be operational within 6 calendar days of contract award\n- Off-site refrigerated storage costs $650 per outage day\n- The city requires a mechanical permit\n\nBid A — Northstar Mechanical\n- Base price: $41,800\n- Can start 9 days after award; installation takes 4 days\n- Includes demolition, disposal, insulated 8-by-12-foot box, condensing unit, installation, permit and up to 20 feet of electrical reconnection\n- Excludes night work\n- Warranty: 2 years labor, 5 years compressor, 10 years panels\n\nBid B — Polar Service Group\n- Base price: $37,900\n- Can start 3 days after award; installation takes 5 days\n- Includes insulated box, condensing unit and installation\n- Excludes permit ($1,200), electrical work (estimated at $4,800), and demolition/disposal ($2,600)\n- Change orders carry an 18% markup\n- Warranty: 1 year labor, 5 years compressor, 10 years panels\n\nBid C — Glacier Commercial Systems\n- Fixed price: $46,700\n- Can start 2 days after award; installation takes 3 days\n- Includes demolition, disposal, box, condensing unit, permit, electrical work, a temporary refrigerated trailer during the outage and a remote temperature alarm\n- Four-hour emergency service response\n- Warranty: 3 years labor, 7 years compressor, 10 years panels\n\nDeliver exactly these sections:\n1. Recommendation — no more than 80 words\n2. Normalized Comparison — a compact table showing quoted price, known add-ons, outage-storage cost, evaluated total, completion timing and warranty\n3. Key Risks — up to three bullets\n4. Pre-Award Questions — up to four questions for the recommended vendor\n5. Negotiation Priorities — up to three bullets\n\nShow arithmetic clearly. Treat the temporary trailer as eliminating off-site storage cost for Bid C. Flag any bid that fails a stated constraint. Do not invent taxes, financing costs or equipment specifications."
        }
      ]
    }
  ]'

runware run anthropic:claude@haiku-4.5 \
  settings.maxTokens=1200 \
  settings.thinkingLevel=medium \
  messages.0.role=user \
  messages.0.content="Act as a procurement analyst for an independent restaurant replacing a failed walk-in cooler. Prepare a concise decision memo for the owner using only the facts below.

Operating constraints:
- Total project budget: \$48,000
- Cooler must be operational within 6 calendar days of contract award
- Off-site refrigerated storage costs \$650 per outage day
- The city requires a mechanical permit

Bid A — Northstar Mechanical
- Base price: \$41,800
- Can start 9 days after award; installation takes 4 days
- Includes demolition, disposal, insulated 8-by-12-foot box, condensing unit, installation, permit and up to 20 feet of electrical reconnection
- Excludes night work
- Warranty: 2 years labor, 5 years compressor, 10 years panels

Bid B — Polar Service Group
- Base price: \$37,900
- Can start 3 days after award; installation takes 5 days
- Includes insulated box, condensing unit and installation
- Excludes permit (\$1,200), electrical work (estimated at \$4,800), and demolition/disposal (\$2,600)
- Change orders carry an 18% markup
- Warranty: 1 year labor, 5 years compressor, 10 years panels

Bid C — Glacier Commercial Systems
- Fixed price: \$46,700
- Can start 2 days after award; installation takes 3 days
- Includes demolition, disposal, box, condensing unit, permit, electrical work, a temporary refrigerated trailer during the outage and a remote temperature alarm
- Four-hour emergency service response
- Warranty: 3 years labor, 7 years compressor, 10 years panels

Deliver exactly these sections:
1. Recommendation — no more than 80 words
2. Normalized Comparison — a compact table showing quoted price, known add-ons, outage-storage cost, evaluated total, completion timing and warranty
3. Key Risks — up to three bullets
4. Pre-Award Questions — up to four questions for the recommended vendor
5. Negotiation Priorities — up to three bullets

Show arithmetic clearly. Treat the temporary trailer as eliminating off-site storage cost for Bid C. Flag any bid that fails a stated constraint. Do not invent taxes, financing costs or equipment specifications."

{
  "taskType": "textInference",
  "taskUUID": "823d7dbd-68c5-408a-acab-02d7f7672f49",
  "model": "anthropic:claude@haiku-4.5",
  "settings": {
    "maxTokens": 1200,
    "thinkingLevel": "medium"
  },
  "messages": [
    {
      "role": "user",
      "content": "Act as a procurement analyst for an independent restaurant replacing a failed walk-in cooler. Prepare a concise decision memo for the owner using only the facts below.\n\nOperating constraints:\n- Total project budget: $48,000\n- Cooler must be operational within 6 calendar days of contract award\n- Off-site refrigerated storage costs $650 per outage day\n- The city requires a mechanical permit\n\nBid A — Northstar Mechanical\n- Base price: $41,800\n- Can start 9 days after award; installation takes 4 days\n- Includes demolition, disposal, insulated 8-by-12-foot box, condensing unit, installation, permit and up to 20 feet of electrical reconnection\n- Excludes night work\n- Warranty: 2 years labor, 5 years compressor, 10 years panels\n\nBid B — Polar Service Group\n- Base price: $37,900\n- Can start 3 days after award; installation takes 5 days\n- Includes insulated box, condensing unit and installation\n- Excludes permit ($1,200), electrical work (estimated at $4,800), and demolition/disposal ($2,600)\n- Change orders carry an 18% markup\n- Warranty: 1 year labor, 5 years compressor, 10 years panels\n\nBid C — Glacier Commercial Systems\n- Fixed price: $46,700\n- Can start 2 days after award; installation takes 3 days\n- Includes demolition, disposal, box, condensing unit, permit, electrical work, a temporary refrigerated trailer during the outage and a remote temperature alarm\n- Four-hour emergency service response\n- Warranty: 3 years labor, 7 years compressor, 10 years panels\n\nDeliver exactly these sections:\n1. Recommendation — no more than 80 words\n2. Normalized Comparison — a compact table showing quoted price, known add-ons, outage-storage cost, evaluated total, completion timing and warranty\n3. Key Risks — up to three bullets\n4. Pre-Award Questions — up to four questions for the recommended vendor\n5. Negotiation Priorities — up to three bullets\n\nShow arithmetic clearly. Treat the temporary trailer as eliminating off-site storage cost for Bid C. Flag any bid that fails a stated constraint. Do not invent taxes, financing costs or equipment specifications."
    }
  ]
}

import { createClient } from '@runware/sdk'

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

const [result] = await client.run({
  model: 'anthropic:claude@haiku-4.5',
  settings: {
    maxTokens: 1200,
    thinkingLevel: 'medium'
  },
  messages: [
    {
      role: 'user',
      content: 'Turn the raw notes below into a leadership-ready incident brief. Reconcile the chronology, distinguish confirmed facts from estimates, and do not invent missing details.\n\nRAW NOTES\n- Incident: checkout API elevated failures in EU-West\n- Deployment began 09:08 UTC\n- Alerts fired 09:12\n- Checkout failures above baseline from 09:12 to 09:37\n- Peak failure rate: 18.6% of checkout attempts at 09:19\n- Other regions unaffected\n- On-call identified database connection exhaustion at 09:17\n- Rollback initiated 09:24 and completed 09:31\n- Error rate returned to baseline at 09:37\n- No evidence of duplicate charges, lost orders, or data corruption\n- Analytics estimates 4.2% of affected shoppers abandoned checkout, but this is not directly measured\n- Support received 41 related tickets\n- Preliminary cause: release changed the checkout service connection-pool limit from 120 to 30; the lower limit became insufficient during a traffic surge\n- Release passed staging because staging load tests did not reproduce production concurrency\n- Immediate mitigation: rollback\n- Follow-ups: Priya to add a connection-pool regression test by 18 September; Mateo to add a production-concurrency scenario to load testing by 25 September; Lin to audit connection limits across payment services by 20 September\n- Still unknown: exact number of lost purchases and why the configuration review did not flag the change\n\nOUTPUT FORMAT\n1. Status — one line\n2. Executive summary — maximum 80 words\n3. Customer and business impact — bullets, labeling estimates explicitly\n4. Timeline — compact UTC table\n5. Cause and contributing factors\n6. Corrective actions — table with owner and due date\n7. Open questions\n8. Customer-facing update — maximum 60 words, plain language, no internal implementation details\n\nUse a calm, accountable, blameless tone. Keep the complete brief under 450 words.'
    }
  ]
})

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": "anthropic:claude@haiku-4.5",
            "settings": {
                "maxTokens": 1200,
                "thinkingLevel": "medium"
            },
            "messages": [
                {
                    "role": "user",
                    "content": "Turn the raw notes below into a leadership-ready incident brief. Reconcile the chronology, distinguish confirmed facts from estimates, and do not invent missing details.\n\nRAW NOTES\n- Incident: checkout API elevated failures in EU-West\n- Deployment began 09:08 UTC\n- Alerts fired 09:12\n- Checkout failures above baseline from 09:12 to 09:37\n- Peak failure rate: 18.6% of checkout attempts at 09:19\n- Other regions unaffected\n- On-call identified database connection exhaustion at 09:17\n- Rollback initiated 09:24 and completed 09:31\n- Error rate returned to baseline at 09:37\n- No evidence of duplicate charges, lost orders, or data corruption\n- Analytics estimates 4.2% of affected shoppers abandoned checkout, but this is not directly measured\n- Support received 41 related tickets\n- Preliminary cause: release changed the checkout service connection-pool limit from 120 to 30; the lower limit became insufficient during a traffic surge\n- Release passed staging because staging load tests did not reproduce production concurrency\n- Immediate mitigation: rollback\n- Follow-ups: Priya to add a connection-pool regression test by 18 September; Mateo to add a production-concurrency scenario to load testing by 25 September; Lin to audit connection limits across payment services by 20 September\n- Still unknown: exact number of lost purchases and why the configuration review did not flag the change\n\nOUTPUT FORMAT\n1. Status — one line\n2. Executive summary — maximum 80 words\n3. Customer and business impact — bullets, labeling estimates explicitly\n4. Timeline — compact UTC table\n5. Cause and contributing factors\n6. Corrective actions — table with owner and due date\n7. Open questions\n8. Customer-facing update — maximum 60 words, plain language, no internal implementation details\n\nUse a calm, accountable, blameless tone. Keep the complete brief under 450 words."
                }
            ]
        })


asyncio.run(main())

curl https://api.runware.ai/v1 \
  -H "Authorization: Bearer $RUNWARE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '[
    {
      "taskType": "textInference",
      "taskUUID": "65d6f55b-cefd-4c6b-abef-9a44bbb7d715",
      "model": "anthropic:claude@haiku-4.5",
      "settings": {
        "maxTokens": 1200,
        "thinkingLevel": "medium"
      },
      "messages": [
        {
          "role": "user",
          "content": "Turn the raw notes below into a leadership-ready incident brief. Reconcile the chronology, distinguish confirmed facts from estimates, and do not invent missing details.\n\nRAW NOTES\n- Incident: checkout API elevated failures in EU-West\n- Deployment began 09:08 UTC\n- Alerts fired 09:12\n- Checkout failures above baseline from 09:12 to 09:37\n- Peak failure rate: 18.6% of checkout attempts at 09:19\n- Other regions unaffected\n- On-call identified database connection exhaustion at 09:17\n- Rollback initiated 09:24 and completed 09:31\n- Error rate returned to baseline at 09:37\n- No evidence of duplicate charges, lost orders, or data corruption\n- Analytics estimates 4.2% of affected shoppers abandoned checkout, but this is not directly measured\n- Support received 41 related tickets\n- Preliminary cause: release changed the checkout service connection-pool limit from 120 to 30; the lower limit became insufficient during a traffic surge\n- Release passed staging because staging load tests did not reproduce production concurrency\n- Immediate mitigation: rollback\n- Follow-ups: Priya to add a connection-pool regression test by 18 September; Mateo to add a production-concurrency scenario to load testing by 25 September; Lin to audit connection limits across payment services by 20 September\n- Still unknown: exact number of lost purchases and why the configuration review did not flag the change\n\nOUTPUT FORMAT\n1. Status — one line\n2. Executive summary — maximum 80 words\n3. Customer and business impact — bullets, labeling estimates explicitly\n4. Timeline — compact UTC table\n5. Cause and contributing factors\n6. Corrective actions — table with owner and due date\n7. Open questions\n8. Customer-facing update — maximum 60 words, plain language, no internal implementation details\n\nUse a calm, accountable, blameless tone. Keep the complete brief under 450 words."
        }
      ]
    }
  ]'

runware run anthropic:claude@haiku-4.5 \
  settings.maxTokens=1200 \
  settings.thinkingLevel=medium \
  messages.0.role=user \
  messages.0.content="Turn the raw notes below into a leadership-ready incident brief. Reconcile the chronology, distinguish confirmed facts from estimates, and do not invent missing details.

RAW NOTES
- Incident: checkout API elevated failures in EU-West
- Deployment began 09:08 UTC
- Alerts fired 09:12
- Checkout failures above baseline from 09:12 to 09:37
- Peak failure rate: 18.6% of checkout attempts at 09:19
- Other regions unaffected
- On-call identified database connection exhaustion at 09:17
- Rollback initiated 09:24 and completed 09:31
- Error rate returned to baseline at 09:37
- No evidence of duplicate charges, lost orders, or data corruption
- Analytics estimates 4.2% of affected shoppers abandoned checkout, but this is not directly measured
- Support received 41 related tickets
- Preliminary cause: release changed the checkout service connection-pool limit from 120 to 30; the lower limit became insufficient during a traffic surge
- Release passed staging because staging load tests did not reproduce production concurrency
- Immediate mitigation: rollback
- Follow-ups: Priya to add a connection-pool regression test by 18 September; Mateo to add a production-concurrency scenario to load testing by 25 September; Lin to audit connection limits across payment services by 20 September
- Still unknown: exact number of lost purchases and why the configuration review did not flag the change

OUTPUT FORMAT
1. Status — one line
2. Executive summary — maximum 80 words
3. Customer and business impact — bullets, labeling estimates explicitly
4. Timeline — compact UTC table
5. Cause and contributing factors
6. Corrective actions — table with owner and due date
7. Open questions
8. Customer-facing update — maximum 60 words, plain language, no internal implementation details

Use a calm, accountable, blameless tone. Keep the complete brief under 450 words."

{
  "taskType": "textInference",
  "taskUUID": "65d6f55b-cefd-4c6b-abef-9a44bbb7d715",
  "model": "anthropic:claude@haiku-4.5",
  "settings": {
    "maxTokens": 1200,
    "thinkingLevel": "medium"
  },
  "messages": [
    {
      "role": "user",
      "content": "Turn the raw notes below into a leadership-ready incident brief. Reconcile the chronology, distinguish confirmed facts from estimates, and do not invent missing details.\n\nRAW NOTES\n- Incident: checkout API elevated failures in EU-West\n- Deployment began 09:08 UTC\n- Alerts fired 09:12\n- Checkout failures above baseline from 09:12 to 09:37\n- Peak failure rate: 18.6% of checkout attempts at 09:19\n- Other regions unaffected\n- On-call identified database connection exhaustion at 09:17\n- Rollback initiated 09:24 and completed 09:31\n- Error rate returned to baseline at 09:37\n- No evidence of duplicate charges, lost orders, or data corruption\n- Analytics estimates 4.2% of affected shoppers abandoned checkout, but this is not directly measured\n- Support received 41 related tickets\n- Preliminary cause: release changed the checkout service connection-pool limit from 120 to 30; the lower limit became insufficient during a traffic surge\n- Release passed staging because staging load tests did not reproduce production concurrency\n- Immediate mitigation: rollback\n- Follow-ups: Priya to add a connection-pool regression test by 18 September; Mateo to add a production-concurrency scenario to load testing by 25 September; Lin to audit connection limits across payment services by 20 September\n- Still unknown: exact number of lost purchases and why the configuration review did not flag the change\n\nOUTPUT FORMAT\n1. Status — one line\n2. Executive summary — maximum 80 words\n3. Customer and business impact — bullets, labeling estimates explicitly\n4. Timeline — compact UTC table\n5. Cause and contributing factors\n6. Corrective actions — table with owner and due date\n7. Open questions\n8. Customer-facing update — maximum 60 words, plain language, no internal implementation details\n\nUse a calm, accountable, blameless tone. Keep the complete brief under 450 words."
    }
  ]
}

import { createClient } from '@runware/sdk'

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

const [result] = await client.run({
  model: 'anthropic:claude@haiku-4.5',
  settings: {
    thinkingLevel: 'low'
  },
  inputs: {
    images: [
      'https://assets.runware.ai/assets/inputs/45358bd1-e67c-4e7c-9eb4-40162bdd4628.jpg'
    ]
  },
  messages: [
    {
      role: 'user',
      content: 'Act as the owner\'s quality-control representative for a hotel renovation. Inspect the attached guest-room photograph and prepare a contractor-ready visual punch list based only on evidence visible in the image.\n\nStart with a 2–3 sentence readiness summary. Then provide a markdown table with these columns: Item, Visible issue, Exact image location, Category/trade, Priority, Recommended corrective action, Confidence.\n\nUse these priorities: P1 = safety or room-blocking, P2 = must correct before guest turnover, P3 = cosmetic closeout. Use High, Medium, or Low confidence. Identify up to 12 distinct issues, ordered by priority and then confidence. Describe each location with an unambiguous spatial anchor such as furniture, wall, fixture, or image edge so a contractor can find it quickly.\n\nDo not invent measurements, hidden damage, code violations, causes, or defects outside the frame. Distinguish probable defects from normal shadows, reflections, styling choices, and temporary housekeeping conditions. If something is uncertain, label it \'verify on site\' and explain the visual cue. Finish with a short \'Photo limitations and next checks\' section listing areas that require closer inspection.'
    }
  ]
})

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": "anthropic:claude@haiku-4.5",
            "settings": {
                "thinkingLevel": "low"
            },
            "inputs": {
                "images": [
                    "https://assets.runware.ai/assets/inputs/45358bd1-e67c-4e7c-9eb4-40162bdd4628.jpg"
                ]
            },
            "messages": [
                {
                    "role": "user",
                    "content": "Act as the owner's quality-control representative for a hotel renovation. Inspect the attached guest-room photograph and prepare a contractor-ready visual punch list based only on evidence visible in the image.\n\nStart with a 2–3 sentence readiness summary. Then provide a markdown table with these columns: Item, Visible issue, Exact image location, Category/trade, Priority, Recommended corrective action, Confidence.\n\nUse these priorities: P1 = safety or room-blocking, P2 = must correct before guest turnover, P3 = cosmetic closeout. Use High, Medium, or Low confidence. Identify up to 12 distinct issues, ordered by priority and then confidence. Describe each location with an unambiguous spatial anchor such as furniture, wall, fixture, or image edge so a contractor can find it quickly.\n\nDo not invent measurements, hidden damage, code violations, causes, or defects outside the frame. Distinguish probable defects from normal shadows, reflections, styling choices, and temporary housekeeping conditions. If something is uncertain, label it 'verify on site' and explain the visual cue. Finish with a short 'Photo limitations and next checks' section listing areas that require closer inspection."
                }
            ]
        })


asyncio.run(main())

curl https://api.runware.ai/v1 \
  -H "Authorization: Bearer $RUNWARE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '[
    {
      "taskType": "textInference",
      "taskUUID": "fc96b1ca-5173-44b9-aa38-2d29f10af218",
      "model": "anthropic:claude@haiku-4.5",
      "settings": {
        "thinkingLevel": "low"
      },
      "inputs": {
        "images": [
          "https://assets.runware.ai/assets/inputs/45358bd1-e67c-4e7c-9eb4-40162bdd4628.jpg"
        ]
      },
      "messages": [
        {
          "role": "user",
          "content": "Act as the owner's quality-control representative for a hotel renovation. Inspect the attached guest-room photograph and prepare a contractor-ready visual punch list based only on evidence visible in the image.\n\nStart with a 2–3 sentence readiness summary. Then provide a markdown table with these columns: Item, Visible issue, Exact image location, Category/trade, Priority, Recommended corrective action, Confidence.\n\nUse these priorities: P1 = safety or room-blocking, P2 = must correct before guest turnover, P3 = cosmetic closeout. Use High, Medium, or Low confidence. Identify up to 12 distinct issues, ordered by priority and then confidence. Describe each location with an unambiguous spatial anchor such as furniture, wall, fixture, or image edge so a contractor can find it quickly.\n\nDo not invent measurements, hidden damage, code violations, causes, or defects outside the frame. Distinguish probable defects from normal shadows, reflections, styling choices, and temporary housekeeping conditions. If something is uncertain, label it 'verify on site' and explain the visual cue. Finish with a short 'Photo limitations and next checks' section listing areas that require closer inspection."
        }
      ]
    }
  ]'

runware run anthropic:claude@haiku-4.5 \
  settings.thinkingLevel=low \
  inputs.images.0=https://assets.runware.ai/assets/inputs/45358bd1-e67c-4e7c-9eb4-40162bdd4628.jpg \
  messages.0.role=user \
  messages.0.content="Act as the owner's quality-control representative for a hotel renovation. Inspect the attached guest-room photograph and prepare a contractor-ready visual punch list based only on evidence visible in the image.

Start with a 2–3 sentence readiness summary. Then provide a markdown table with these columns: Item, Visible issue, Exact image location, Category/trade, Priority, Recommended corrective action, Confidence.

Use these priorities: P1 = safety or room-blocking, P2 = must correct before guest turnover, P3 = cosmetic closeout. Use High, Medium, or Low confidence. Identify up to 12 distinct issues, ordered by priority and then confidence. Describe each location with an unambiguous spatial anchor such as furniture, wall, fixture, or image edge so a contractor can find it quickly.

Do not invent measurements, hidden damage, code violations, causes, or defects outside the frame. Distinguish probable defects from normal shadows, reflections, styling choices, and temporary housekeeping conditions. If something is uncertain, label it 'verify on site' and explain the visual cue. Finish with a short 'Photo limitations and next checks' section listing areas that require closer inspection."

{
  "taskType": "textInference",
  "taskUUID": "fc96b1ca-5173-44b9-aa38-2d29f10af218",
  "model": "anthropic:claude@haiku-4.5",
  "settings": {
    "thinkingLevel": "low"
  },
  "inputs": {
    "images": [
      "https://assets.runware.ai/assets/inputs/45358bd1-e67c-4e7c-9eb4-40162bdd4628.jpg"
    ]
  },
  "messages": [
    {
      "role": "user",
      "content": "Act as the owner's quality-control representative for a hotel renovation. Inspect the attached guest-room photograph and prepare a contractor-ready visual punch list based only on evidence visible in the image.\n\nStart with a 2–3 sentence readiness summary. Then provide a markdown table with these columns: Item, Visible issue, Exact image location, Category/trade, Priority, Recommended corrective action, Confidence.\n\nUse these priorities: P1 = safety or room-blocking, P2 = must correct before guest turnover, P3 = cosmetic closeout. Use High, Medium, or Low confidence. Identify up to 12 distinct issues, ordered by priority and then confidence. Describe each location with an unambiguous spatial anchor such as furniture, wall, fixture, or image edge so a contractor can find it quickly.\n\nDo not invent measurements, hidden damage, code violations, causes, or defects outside the frame. Distinguish probable defects from normal shadows, reflections, styling choices, and temporary housekeeping conditions. If something is uncertain, label it 'verify on site' and explain the visual cue. Finish with a short 'Photo limitations and next checks' section listing areas that require closer inspection."
    }
  ]
}

import { createClient } from '@runware/sdk'

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

const [result] = await client.run({
  model: 'anthropic:claude@haiku-4.5',
  settings: {
    maxTokens: 1200,
    thinkingLevel: 'medium'
  },
  messages: [
    {
      role: 'user',
      content: 'Act as a senior support agent for an outdoor equipment retailer. Resolve the ticket using only the policy and order facts below. Do not reveal private chain-of-thought. Provide a concise policy rationale and calculate the exact refund.\n\nREFUND POLICY\n- Fulfillment errors must be reported within 14 calendar days of delivery.\n- A verified wrong-item shipment qualifies for a refund of the merchandise price and standard outbound shipping.\n- An expedited shipping upgrade is refundable only when the carrier misses its delivery guarantee.\n- If the customer requests a refund rather than a replacement, honor that choice.\n- A verified incorrect item with a resale value below $75 does not need to be returned; tell the customer to keep or donate it.\n- Agents may issue up to $15 in store credit when a verified warehouse error causes the customer to miss a fixed-date event and the customer requests additional compensation.\n\nORDER FACTS\n- Order: TR-48219\n- Ordered: SummitSafe climbing helmet, slate, size M/L\n- Merchandise price: $64.00\n- Standard shipping: $6.00\n- Expedited upgrade: $18.00\n- Delivered on the carrier\'s promised date: September 12, 2026\n- Customer contacted support: September 16, 2026\n- Warehouse audit confirms the parcel contained a TrailLite cycling helmet, white, size S\n- Resale value of the incorrect item: $64.00\n- SummitSafe size M/L is currently in stock\n\nCUSTOMER MESSAGE\n"I ordered this helmet for a climbing certification course on September 14, but you sent the wrong model and size. I had to borrow one at the last minute. I don\'t want a replacement now—please refund the order, including shipping. I also think some compensation is fair because this could have kept me out of the course. Do I need to send the wrong helmet back?"\n\nReturn exactly these sections:\n1. Decision — approved or denied, refund amount, payment destination, store credit, and return requirement.\n2. Policy Rationale — no more than four bullets, citing the relevant facts.\n3. Customer Reply — a polished email under 140 words with an empathetic but non-defensive tone.\n4. Internal Tags — 3 to 5 short comma-separated tags.'
    }
  ]
})

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": "anthropic:claude@haiku-4.5",
            "settings": {
                "maxTokens": 1200,
                "thinkingLevel": "medium"
            },
            "messages": [
                {
                    "role": "user",
                    "content": "Act as a senior support agent for an outdoor equipment retailer. Resolve the ticket using only the policy and order facts below. Do not reveal private chain-of-thought. Provide a concise policy rationale and calculate the exact refund.\n\nREFUND POLICY\n- Fulfillment errors must be reported within 14 calendar days of delivery.\n- A verified wrong-item shipment qualifies for a refund of the merchandise price and standard outbound shipping.\n- An expedited shipping upgrade is refundable only when the carrier misses its delivery guarantee.\n- If the customer requests a refund rather than a replacement, honor that choice.\n- A verified incorrect item with a resale value below $75 does not need to be returned; tell the customer to keep or donate it.\n- Agents may issue up to $15 in store credit when a verified warehouse error causes the customer to miss a fixed-date event and the customer requests additional compensation.\n\nORDER FACTS\n- Order: TR-48219\n- Ordered: SummitSafe climbing helmet, slate, size M/L\n- Merchandise price: $64.00\n- Standard shipping: $6.00\n- Expedited upgrade: $18.00\n- Delivered on the carrier's promised date: September 12, 2026\n- Customer contacted support: September 16, 2026\n- Warehouse audit confirms the parcel contained a TrailLite cycling helmet, white, size S\n- Resale value of the incorrect item: $64.00\n- SummitSafe size M/L is currently in stock\n\nCUSTOMER MESSAGE\n\"I ordered this helmet for a climbing certification course on September 14, but you sent the wrong model and size. I had to borrow one at the last minute. I don't want a replacement now—please refund the order, including shipping. I also think some compensation is fair because this could have kept me out of the course. Do I need to send the wrong helmet back?\"\n\nReturn exactly these sections:\n1. Decision — approved or denied, refund amount, payment destination, store credit, and return requirement.\n2. Policy Rationale — no more than four bullets, citing the relevant facts.\n3. Customer Reply — a polished email under 140 words with an empathetic but non-defensive tone.\n4. Internal Tags — 3 to 5 short comma-separated tags."
                }
            ]
        })


asyncio.run(main())

curl https://api.runware.ai/v1 \
  -H "Authorization: Bearer $RUNWARE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '[
    {
      "taskType": "textInference",
      "taskUUID": "f660ea6e-e5e9-4e1b-9e11-17b03e28fee6",
      "model": "anthropic:claude@haiku-4.5",
      "settings": {
        "maxTokens": 1200,
        "thinkingLevel": "medium"
      },
      "messages": [
        {
          "role": "user",
          "content": "Act as a senior support agent for an outdoor equipment retailer. Resolve the ticket using only the policy and order facts below. Do not reveal private chain-of-thought. Provide a concise policy rationale and calculate the exact refund.\n\nREFUND POLICY\n- Fulfillment errors must be reported within 14 calendar days of delivery.\n- A verified wrong-item shipment qualifies for a refund of the merchandise price and standard outbound shipping.\n- An expedited shipping upgrade is refundable only when the carrier misses its delivery guarantee.\n- If the customer requests a refund rather than a replacement, honor that choice.\n- A verified incorrect item with a resale value below $75 does not need to be returned; tell the customer to keep or donate it.\n- Agents may issue up to $15 in store credit when a verified warehouse error causes the customer to miss a fixed-date event and the customer requests additional compensation.\n\nORDER FACTS\n- Order: TR-48219\n- Ordered: SummitSafe climbing helmet, slate, size M/L\n- Merchandise price: $64.00\n- Standard shipping: $6.00\n- Expedited upgrade: $18.00\n- Delivered on the carrier's promised date: September 12, 2026\n- Customer contacted support: September 16, 2026\n- Warehouse audit confirms the parcel contained a TrailLite cycling helmet, white, size S\n- Resale value of the incorrect item: $64.00\n- SummitSafe size M/L is currently in stock\n\nCUSTOMER MESSAGE\n\"I ordered this helmet for a climbing certification course on September 14, but you sent the wrong model and size. I had to borrow one at the last minute. I don't want a replacement now—please refund the order, including shipping. I also think some compensation is fair because this could have kept me out of the course. Do I need to send the wrong helmet back?\"\n\nReturn exactly these sections:\n1. Decision — approved or denied, refund amount, payment destination, store credit, and return requirement.\n2. Policy Rationale — no more than four bullets, citing the relevant facts.\n3. Customer Reply — a polished email under 140 words with an empathetic but non-defensive tone.\n4. Internal Tags — 3 to 5 short comma-separated tags."
        }
      ]
    }
  ]'

runware run anthropic:claude@haiku-4.5 \
  settings.maxTokens=1200 \
  settings.thinkingLevel=medium \
  messages.0.role=user \
  messages.0.content="Act as a senior support agent for an outdoor equipment retailer. Resolve the ticket using only the policy and order facts below. Do not reveal private chain-of-thought. Provide a concise policy rationale and calculate the exact refund.

REFUND POLICY
- Fulfillment errors must be reported within 14 calendar days of delivery.
- A verified wrong-item shipment qualifies for a refund of the merchandise price and standard outbound shipping.
- An expedited shipping upgrade is refundable only when the carrier misses its delivery guarantee.
- If the customer requests a refund rather than a replacement, honor that choice.
- A verified incorrect item with a resale value below \$75 does not need to be returned; tell the customer to keep or donate it.
- Agents may issue up to \$15 in store credit when a verified warehouse error causes the customer to miss a fixed-date event and the customer requests additional compensation.

ORDER FACTS
- Order: TR-48219
- Ordered: SummitSafe climbing helmet, slate, size M/L
- Merchandise price: \$64.00
- Standard shipping: \$6.00
- Expedited upgrade: \$18.00
- Delivered on the carrier's promised date: September 12, 2026
- Customer contacted support: September 16, 2026
- Warehouse audit confirms the parcel contained a TrailLite cycling helmet, white, size S
- Resale value of the incorrect item: \$64.00
- SummitSafe size M/L is currently in stock

CUSTOMER MESSAGE
\"I ordered this helmet for a climbing certification course on September 14, but you sent the wrong model and size. I had to borrow one at the last minute. I don't want a replacement now—please refund the order, including shipping. I also think some compensation is fair because this could have kept me out of the course. Do I need to send the wrong helmet back?\"

Return exactly these sections:
1. Decision — approved or denied, refund amount, payment destination, store credit, and return requirement.
2. Policy Rationale — no more than four bullets, citing the relevant facts.
3. Customer Reply — a polished email under 140 words with an empathetic but non-defensive tone.
4. Internal Tags — 3 to 5 short comma-separated tags."

{
  "taskType": "textInference",
  "taskUUID": "f660ea6e-e5e9-4e1b-9e11-17b03e28fee6",
  "model": "anthropic:claude@haiku-4.5",
  "settings": {
    "maxTokens": 1200,
    "thinkingLevel": "medium"
  },
  "messages": [
    {
      "role": "user",
      "content": "Act as a senior support agent for an outdoor equipment retailer. Resolve the ticket using only the policy and order facts below. Do not reveal private chain-of-thought. Provide a concise policy rationale and calculate the exact refund.\n\nREFUND POLICY\n- Fulfillment errors must be reported within 14 calendar days of delivery.\n- A verified wrong-item shipment qualifies for a refund of the merchandise price and standard outbound shipping.\n- An expedited shipping upgrade is refundable only when the carrier misses its delivery guarantee.\n- If the customer requests a refund rather than a replacement, honor that choice.\n- A verified incorrect item with a resale value below $75 does not need to be returned; tell the customer to keep or donate it.\n- Agents may issue up to $15 in store credit when a verified warehouse error causes the customer to miss a fixed-date event and the customer requests additional compensation.\n\nORDER FACTS\n- Order: TR-48219\n- Ordered: SummitSafe climbing helmet, slate, size M/L\n- Merchandise price: $64.00\n- Standard shipping: $6.00\n- Expedited upgrade: $18.00\n- Delivered on the carrier's promised date: September 12, 2026\n- Customer contacted support: September 16, 2026\n- Warehouse audit confirms the parcel contained a TrailLite cycling helmet, white, size S\n- Resale value of the incorrect item: $64.00\n- SummitSafe size M/L is currently in stock\n\nCUSTOMER MESSAGE\n\"I ordered this helmet for a climbing certification course on September 14, but you sent the wrong model and size. I had to borrow one at the last minute. I don't want a replacement now—please refund the order, including shipping. I also think some compensation is fair because this could have kept me out of the course. Do I need to send the wrong helmet back?\"\n\nReturn exactly these sections:\n1. Decision — approved or denied, refund amount, payment destination, store credit, and return requirement.\n2. Policy Rationale — no more than four bullets, citing the relevant facts.\n3. Customer Reply — a polished email under 140 words with an empathetic but non-defensive tone.\n4. Internal Tags — 3 to 5 short comma-separated tags."
    }
  ]
}