Gemini 3 Flash

import { createClient } from '@runware/sdk'

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

const [result] = await client.run({
  model: 'google:gemini@3-flash',
  inputs: {
    audios: [
      'https://assets.runware.ai/assets/inputs/bd44527b-b887-4333-81ae-2193e7fe5c97.mp3'
    ]
  },
  messages: [
    {
      role: 'user',
      content: 'Review the attached field-service recording and produce a maintenance-ready text deliverable with these sections: 1) Verbatim Transcript, preserving measurements, equipment identifiers, fault codes, times, and work-order numbers exactly as spoken; 2) Concise Summary in no more than four bullets; 3) Structured Service Report with site, asset, initial condition, diagnostic findings, safety controls, work performed, current operating status, recommended follow-up, and incident status; 4) Extracted Data table with every identifier, timestamp, measurement, and threshold mentioned; 5) Uncertainties or unclear audio. Ground every statement only in the recording. Do not invent missing values, diagnoses, or completed repairs. Clearly distinguish observations from recommendations.'
    }
  ]
})

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": "google:gemini@3-flash",
            "inputs": {
                "audios": [
                    "https://assets.runware.ai/assets/inputs/bd44527b-b887-4333-81ae-2193e7fe5c97.mp3"
                ]
            },
            "messages": [
                {
                    "role": "user",
                    "content": "Review the attached field-service recording and produce a maintenance-ready text deliverable with these sections: 1) Verbatim Transcript, preserving measurements, equipment identifiers, fault codes, times, and work-order numbers exactly as spoken; 2) Concise Summary in no more than four bullets; 3) Structured Service Report with site, asset, initial condition, diagnostic findings, safety controls, work performed, current operating status, recommended follow-up, and incident status; 4) Extracted Data table with every identifier, timestamp, measurement, and threshold mentioned; 5) Uncertainties or unclear audio. Ground every statement only in the recording. Do not invent missing values, diagnoses, or completed repairs. Clearly distinguish observations from recommendations."
                }
            ]
        })


asyncio.run(main())

curl https://api.runware.ai/v1 \
  -H "Authorization: Bearer $RUNWARE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '[
    {
      "taskType": "textInference",
      "taskUUID": "c2d56386-d107-46e2-9729-5b112ca9f196",
      "model": "google:gemini@3-flash",
      "inputs": {
        "audios": [
          "https://assets.runware.ai/assets/inputs/bd44527b-b887-4333-81ae-2193e7fe5c97.mp3"
        ]
      },
      "messages": [
        {
          "role": "user",
          "content": "Review the attached field-service recording and produce a maintenance-ready text deliverable with these sections: 1) Verbatim Transcript, preserving measurements, equipment identifiers, fault codes, times, and work-order numbers exactly as spoken; 2) Concise Summary in no more than four bullets; 3) Structured Service Report with site, asset, initial condition, diagnostic findings, safety controls, work performed, current operating status, recommended follow-up, and incident status; 4) Extracted Data table with every identifier, timestamp, measurement, and threshold mentioned; 5) Uncertainties or unclear audio. Ground every statement only in the recording. Do not invent missing values, diagnoses, or completed repairs. Clearly distinguish observations from recommendations."
        }
      ]
    }
  ]'

runware run google:gemini@3-flash \
  inputs.audios.0=https://assets.runware.ai/assets/inputs/bd44527b-b887-4333-81ae-2193e7fe5c97.mp3 \
  messages.0.role=user \
  messages.0.content="Review the attached field-service recording and produce a maintenance-ready text deliverable with these sections: 1) Verbatim Transcript, preserving measurements, equipment identifiers, fault codes, times, and work-order numbers exactly as spoken; 2) Concise Summary in no more than four bullets; 3) Structured Service Report with site, asset, initial condition, diagnostic findings, safety controls, work performed, current operating status, recommended follow-up, and incident status; 4) Extracted Data table with every identifier, timestamp, measurement, and threshold mentioned; 5) Uncertainties or unclear audio. Ground every statement only in the recording. Do not invent missing values, diagnoses, or completed repairs. Clearly distinguish observations from recommendations."

{
  "taskType": "textInference",
  "taskUUID": "c2d56386-d107-46e2-9729-5b112ca9f196",
  "model": "google:gemini@3-flash",
  "inputs": {
    "audios": [
      "https://assets.runware.ai/assets/inputs/bd44527b-b887-4333-81ae-2193e7fe5c97.mp3"
    ]
  },
  "messages": [
    {
      "role": "user",
      "content": "Review the attached field-service recording and produce a maintenance-ready text deliverable with these sections: 1) Verbatim Transcript, preserving measurements, equipment identifiers, fault codes, times, and work-order numbers exactly as spoken; 2) Concise Summary in no more than four bullets; 3) Structured Service Report with site, asset, initial condition, diagnostic findings, safety controls, work performed, current operating status, recommended follow-up, and incident status; 4) Extracted Data table with every identifier, timestamp, measurement, and threshold mentioned; 5) Uncertainties or unclear audio. Ground every statement only in the recording. Do not invent missing values, diagnoses, or completed repairs. Clearly distinguish observations from recommendations."
    }
  ]
}

import { createClient } from '@runware/sdk'

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

const [result] = await client.run({
  model: 'google:gemini@3-flash',
  inputs: {
    images: [
      'https://assets.runware.ai/assets/inputs/1654e049-378e-4b15-8c75-997b66177864.jpg'
    ],
    videos: [
      'https://assets.runware.ai/assets/inputs/f450ea2a-c4c3-4589-b5ca-c8b04d6ceb11.mp4'
    ]
  },
  messages: [
    {
      role: 'user',
      content: 'Act as a professional soccer set-piece analyst. Review the supplied match still and video together, then produce a concise opposition corner-kick scouting brief for the pale-blue team\'s coaching staff.\n\nUse only visible evidence. First analyze the still image for starting positions, marking scheme, goalkeeper access, overloads, short-corner threats, and likely running lanes. Then analyze every corner sequence visible in the video, citing timestamps for setup, delivery zone, runner movements, blocking actions, first contact, second-ball behavior, and transition risk. Compare the still with the moving footage to determine which features are recurring patterns rather than one-off details.\n\nStructure the deliverable as:\n1. Executive summary — 3 to 5 sentences.\n2. Evidence table — timestamp or image region, observed action, tactical interpretation, and confidence level.\n3. Recurring attacking patterns — ranked by threat.\n4. Defensive vulnerabilities visible in pale blue\'s response.\n5. Five actionable recommendations for the next match, including assignments and cues players can recognize before delivery.\n6. Uncertainties and additional footage needed.\n\nClearly distinguish direct observation from inference. Do not invent player identities, statistics, events outside the supplied assets, or precise measurements that cannot be supported visually.'
    }
  ]
})

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": "google:gemini@3-flash",
            "inputs": {
                "images": [
                    "https://assets.runware.ai/assets/inputs/1654e049-378e-4b15-8c75-997b66177864.jpg"
                ],
                "videos": [
                    "https://assets.runware.ai/assets/inputs/f450ea2a-c4c3-4589-b5ca-c8b04d6ceb11.mp4"
                ]
            },
            "messages": [
                {
                    "role": "user",
                    "content": "Act as a professional soccer set-piece analyst. Review the supplied match still and video together, then produce a concise opposition corner-kick scouting brief for the pale-blue team's coaching staff.\n\nUse only visible evidence. First analyze the still image for starting positions, marking scheme, goalkeeper access, overloads, short-corner threats, and likely running lanes. Then analyze every corner sequence visible in the video, citing timestamps for setup, delivery zone, runner movements, blocking actions, first contact, second-ball behavior, and transition risk. Compare the still with the moving footage to determine which features are recurring patterns rather than one-off details.\n\nStructure the deliverable as:\n1. Executive summary — 3 to 5 sentences.\n2. Evidence table — timestamp or image region, observed action, tactical interpretation, and confidence level.\n3. Recurring attacking patterns — ranked by threat.\n4. Defensive vulnerabilities visible in pale blue's response.\n5. Five actionable recommendations for the next match, including assignments and cues players can recognize before delivery.\n6. Uncertainties and additional footage needed.\n\nClearly distinguish direct observation from inference. Do not invent player identities, statistics, events outside the supplied assets, or precise measurements that cannot be supported visually."
                }
            ]
        })


asyncio.run(main())

curl https://api.runware.ai/v1 \
  -H "Authorization: Bearer $RUNWARE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '[
    {
      "taskType": "textInference",
      "taskUUID": "5455fbf0-c153-469d-9b8b-d240e733bc17",
      "model": "google:gemini@3-flash",
      "inputs": {
        "images": [
          "https://assets.runware.ai/assets/inputs/1654e049-378e-4b15-8c75-997b66177864.jpg"
        ],
        "videos": [
          "https://assets.runware.ai/assets/inputs/f450ea2a-c4c3-4589-b5ca-c8b04d6ceb11.mp4"
        ]
      },
      "messages": [
        {
          "role": "user",
          "content": "Act as a professional soccer set-piece analyst. Review the supplied match still and video together, then produce a concise opposition corner-kick scouting brief for the pale-blue team's coaching staff.\n\nUse only visible evidence. First analyze the still image for starting positions, marking scheme, goalkeeper access, overloads, short-corner threats, and likely running lanes. Then analyze every corner sequence visible in the video, citing timestamps for setup, delivery zone, runner movements, blocking actions, first contact, second-ball behavior, and transition risk. Compare the still with the moving footage to determine which features are recurring patterns rather than one-off details.\n\nStructure the deliverable as:\n1. Executive summary — 3 to 5 sentences.\n2. Evidence table — timestamp or image region, observed action, tactical interpretation, and confidence level.\n3. Recurring attacking patterns — ranked by threat.\n4. Defensive vulnerabilities visible in pale blue's response.\n5. Five actionable recommendations for the next match, including assignments and cues players can recognize before delivery.\n6. Uncertainties and additional footage needed.\n\nClearly distinguish direct observation from inference. Do not invent player identities, statistics, events outside the supplied assets, or precise measurements that cannot be supported visually."
        }
      ]
    }
  ]'

runware run google:gemini@3-flash \
  inputs.images.0=https://assets.runware.ai/assets/inputs/1654e049-378e-4b15-8c75-997b66177864.jpg \
  inputs.videos.0=https://assets.runware.ai/assets/inputs/f450ea2a-c4c3-4589-b5ca-c8b04d6ceb11.mp4 \
  messages.0.role=user \
  messages.0.content="Act as a professional soccer set-piece analyst. Review the supplied match still and video together, then produce a concise opposition corner-kick scouting brief for the pale-blue team's coaching staff.

Use only visible evidence. First analyze the still image for starting positions, marking scheme, goalkeeper access, overloads, short-corner threats, and likely running lanes. Then analyze every corner sequence visible in the video, citing timestamps for setup, delivery zone, runner movements, blocking actions, first contact, second-ball behavior, and transition risk. Compare the still with the moving footage to determine which features are recurring patterns rather than one-off details.

Structure the deliverable as:
1. Executive summary — 3 to 5 sentences.
2. Evidence table — timestamp or image region, observed action, tactical interpretation, and confidence level.
3. Recurring attacking patterns — ranked by threat.
4. Defensive vulnerabilities visible in pale blue's response.
5. Five actionable recommendations for the next match, including assignments and cues players can recognize before delivery.
6. Uncertainties and additional footage needed.

Clearly distinguish direct observation from inference. Do not invent player identities, statistics, events outside the supplied assets, or precise measurements that cannot be supported visually."

{
  "taskType": "textInference",
  "taskUUID": "5455fbf0-c153-469d-9b8b-d240e733bc17",
  "model": "google:gemini@3-flash",
  "inputs": {
    "images": [
      "https://assets.runware.ai/assets/inputs/1654e049-378e-4b15-8c75-997b66177864.jpg"
    ],
    "videos": [
      "https://assets.runware.ai/assets/inputs/f450ea2a-c4c3-4589-b5ca-c8b04d6ceb11.mp4"
    ]
  },
  "messages": [
    {
      "role": "user",
      "content": "Act as a professional soccer set-piece analyst. Review the supplied match still and video together, then produce a concise opposition corner-kick scouting brief for the pale-blue team's coaching staff.\n\nUse only visible evidence. First analyze the still image for starting positions, marking scheme, goalkeeper access, overloads, short-corner threats, and likely running lanes. Then analyze every corner sequence visible in the video, citing timestamps for setup, delivery zone, runner movements, blocking actions, first contact, second-ball behavior, and transition risk. Compare the still with the moving footage to determine which features are recurring patterns rather than one-off details.\n\nStructure the deliverable as:\n1. Executive summary — 3 to 5 sentences.\n2. Evidence table — timestamp or image region, observed action, tactical interpretation, and confidence level.\n3. Recurring attacking patterns — ranked by threat.\n4. Defensive vulnerabilities visible in pale blue's response.\n5. Five actionable recommendations for the next match, including assignments and cues players can recognize before delivery.\n6. Uncertainties and additional footage needed.\n\nClearly distinguish direct observation from inference. Do not invent player identities, statistics, events outside the supplied assets, or precise measurements that cannot be supported visually."
    }
  ]
}

import { createClient } from '@runware/sdk'

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

const [result] = await client.run({
  model: 'google:gemini@3-flash',
  seed: 49334,
  settings: {
    temperature: 0.67,
    topP: 0.9,
    maxTokens: 1200,
    thinkingLevel: 'medium',
    systemPrompt: 'You are a precise multimodal analyst. Describe only what is visible or clearly inferable from the image, and separate observation from interpretation.'
  },
  messages: [
    {
      role: 'user',
      content: 'Analyze the provided image in a structured way. Return: 1) a one-sentence scene summary, 2) the 8 most important visible elements, 3) any readable or partially readable text, 4) inferred location/style clues, 5) what is happening in the scene, 6) mood and lighting analysis, and 7) two plausible stories that could explain this moment. Be specific and ground every claim in visible evidence.'
    }
  ],
  inputs: {
    images: [
      'https://assets.runware.ai/assets/inputs/947004f0-67f0-4b93-82ff-20610bab46e1.jpg'
    ]
  }
})

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": "google:gemini@3-flash",
            "seed": 49334,
            "settings": {
                "temperature": 0.67,
                "topP": 0.9,
                "maxTokens": 1200,
                "thinkingLevel": "medium",
                "systemPrompt": "You are a precise multimodal analyst. Describe only what is visible or clearly inferable from the image, and separate observation from interpretation."
            },
            "messages": [
                {
                    "role": "user",
                    "content": "Analyze the provided image in a structured way. Return: 1) a one-sentence scene summary, 2) the 8 most important visible elements, 3) any readable or partially readable text, 4) inferred location/style clues, 5) what is happening in the scene, 6) mood and lighting analysis, and 7) two plausible stories that could explain this moment. Be specific and ground every claim in visible evidence."
                }
            ],
            "inputs": {
                "images": [
                    "https://assets.runware.ai/assets/inputs/947004f0-67f0-4b93-82ff-20610bab46e1.jpg"
                ]
            }
        })


asyncio.run(main())

curl https://api.runware.ai/v1 \
  -H "Authorization: Bearer $RUNWARE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '[
    {
      "taskType": "textInference",
      "taskUUID": "474e2fda-f280-4785-a9af-021b3b984c65",
      "model": "google:gemini@3-flash",
      "seed": 49334,
      "settings": {
        "temperature": 0.67,
        "topP": 0.9,
        "maxTokens": 1200,
        "thinkingLevel": "medium",
        "systemPrompt": "You are a precise multimodal analyst. Describe only what is visible or clearly inferable from the image, and separate observation from interpretation."
      },
      "messages": [
        {
          "role": "user",
          "content": "Analyze the provided image in a structured way. Return: 1) a one-sentence scene summary, 2) the 8 most important visible elements, 3) any readable or partially readable text, 4) inferred location/style clues, 5) what is happening in the scene, 6) mood and lighting analysis, and 7) two plausible stories that could explain this moment. Be specific and ground every claim in visible evidence."
        }
      ],
      "inputs": {
        "images": [
          "https://assets.runware.ai/assets/inputs/947004f0-67f0-4b93-82ff-20610bab46e1.jpg"
        ]
      }
    }
  ]'

runware run google:gemini@3-flash \
  seed=49334 \
  settings.temperature=0.67 \
  settings.topP=0.9 \
  settings.maxTokens=1200 \
  settings.thinkingLevel=medium \
  settings.systemPrompt="You are a precise multimodal analyst. Describe only what is visible or clearly inferable from the image, and separate observation from interpretation." \
  messages.0.role=user \
  messages.0.content="Analyze the provided image in a structured way. Return: 1) a one-sentence scene summary, 2) the 8 most important visible elements, 3) any readable or partially readable text, 4) inferred location/style clues, 5) what is happening in the scene, 6) mood and lighting analysis, and 7) two plausible stories that could explain this moment. Be specific and ground every claim in visible evidence." \
  inputs.images.0=https://assets.runware.ai/assets/inputs/947004f0-67f0-4b93-82ff-20610bab46e1.jpg

{
  "taskType": "textInference",
  "taskUUID": "474e2fda-f280-4785-a9af-021b3b984c65",
  "model": "google:gemini@3-flash",
  "seed": 49334,
  "settings": {
    "temperature": 0.67,
    "topP": 0.9,
    "maxTokens": 1200,
    "thinkingLevel": "medium",
    "systemPrompt": "You are a precise multimodal analyst. Describe only what is visible or clearly inferable from the image, and separate observation from interpretation."
  },
  "messages": [
    {
      "role": "user",
      "content": "Analyze the provided image in a structured way. Return: 1) a one-sentence scene summary, 2) the 8 most important visible elements, 3) any readable or partially readable text, 4) inferred location/style clues, 5) what is happening in the scene, 6) mood and lighting analysis, and 7) two plausible stories that could explain this moment. Be specific and ground every claim in visible evidence."
    }
  ],
  "inputs": {
    "images": [
      "https://assets.runware.ai/assets/inputs/947004f0-67f0-4b93-82ff-20610bab46e1.jpg"
    ]
  }
}

import { createClient } from '@runware/sdk'

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

const [result] = await client.run({
  model: 'google:gemini@3-flash',
  messages: [
    {
      role: 'user',
      content: 'Act as a healthcare capital-procurement analyst. Prepare a decision memo for the CFO and Infection Prevention Committee of a 340-bed hospital selecting a vendor for two pass-through steam sterilizers. Use only the information below; do not assume missing facts or conduct external research.\n\nMANDATORY REQUIREMENTS\n- Total installed purchase price, including required validation, must not exceed $650,000.\n- Combined rated throughput must be at least 24 DIN trays per hour.\n- Each unit must be no wider than 1,300 mm because walls cannot be moved.\n- Service response must be four hours or less.\n- Purchase order date: May 1. Operational deadline: October 1.\n\nBIDS\n\nVendor A — SteriCore SC-12\n- Installed price for two units: $612,000\n- Validation and operator training: included\n- Combined throughput: 28 trays/hour\n- Width per unit: 1,260 mm\n- Delivery, installation, and validation: 20 weeks after purchase order\n- Documented fleet uptime: 98.7%\n- Service response: 4 hours\n- Warranty: 2 years\n- Full-service contract after warranty: $31,000 per year\n- Estimated utilities and consumables: $22,000 per year\n- References: three comparable hospitals; all renewed service contracts\n\nVendor B — MedAxis MA-9\n- Installed price for two units: $578,000\n- Validation: additional $16,000; operator training included\n- Combined throughput: 24 trays/hour\n- Width per unit: 1,180 mm\n- Delivery, installation, and validation: 14 weeks after purchase order\n- Documented fleet uptime: 97.9%\n- Standard service response: 6 hours\n- Required premium plan provides a 3-hour response during the first-year warranty and costs $52,000 per year in years 2–5\n- Estimated utilities and consumables: $19,000 per year\n- References: two comparable hospitals; one reported recurring door-seal failures during its first six months\n\nVendor C — Aegis AS-15\n- Installed price for two units: $646,000\n- Validation and operator training: included\n- Combined throughput: 32 trays/hour\n- Width per unit: 1,325 mm\n- Delivery, installation, and validation: 16 weeks after purchase order\n- Documented fleet uptime: 99.1%\n- Service response: 2 hours\n- Warranty: 3 years\n- Full-service contract after warranty: $28,000 per year\n- Estimated utilities and consumables: $26,000 per year\n- References: four comparable hospitals with no material complaints\n\nEVALUATION METHOD\nFirst apply all mandatory requirements as pass/fail gates. Score only compliant bids using these weights:\n- Throughput and workflow: 30%\n- Five-year total cost of ownership: 25%\n- Reliability: 20%\n- Implementation schedule: 15%\n- Service, training, and references: 10%\n\nThe evaluation panel assigned the following 0–100 qualitative scores for every criterion except cost:\n- Vendor A: throughput 88, reliability 94, implementation 78, service/training/references 92\n- Vendor B: throughput 75, reliability 82, implementation 95, service/training/references 80\n- Vendor C: throughput 100, reliability 98, implementation 90, service/training/references 96\n\nCalculate five-year TCO as installed price plus separately priced validation, five years of utilities and consumables, and service-contract charges incurred within the five-year period. Exclude financing, taxes, and internal labor. For the cost criterion, give the lowest-TCO compliant bid a score of 100 and calculate every other compliant bid as: lowest compliant TCO divided by that bid\'s TCO, multiplied by 100.\n\nDELIVERABLE\nWrite a self-contained memo of no more than 900 words with:\n1. An executive recommendation and one-sentence rationale.\n2. A mandatory-requirements table showing pass or fail for each vendor and the specific reason for any failure.\n3. Transparent five-year TCO calculations.\n4. A weighted-score table for compliant vendors, including the cost-score calculation and total scores rounded to one decimal place.\n5. The three most important operational or contracting risks.\n6. Four concrete conditions to include in the notice of intent to award.\n7. A concise 90-day implementation plan with owners.\n\nExplicitly distinguish supplied facts from your inferences. Do not let a strong score override a failed mandatory requirement.'
    }
  ]
})

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": "google:gemini@3-flash",
            "messages": [
                {
                    "role": "user",
                    "content": "Act as a healthcare capital-procurement analyst. Prepare a decision memo for the CFO and Infection Prevention Committee of a 340-bed hospital selecting a vendor for two pass-through steam sterilizers. Use only the information below; do not assume missing facts or conduct external research.\n\nMANDATORY REQUIREMENTS\n- Total installed purchase price, including required validation, must not exceed $650,000.\n- Combined rated throughput must be at least 24 DIN trays per hour.\n- Each unit must be no wider than 1,300 mm because walls cannot be moved.\n- Service response must be four hours or less.\n- Purchase order date: May 1. Operational deadline: October 1.\n\nBIDS\n\nVendor A — SteriCore SC-12\n- Installed price for two units: $612,000\n- Validation and operator training: included\n- Combined throughput: 28 trays/hour\n- Width per unit: 1,260 mm\n- Delivery, installation, and validation: 20 weeks after purchase order\n- Documented fleet uptime: 98.7%\n- Service response: 4 hours\n- Warranty: 2 years\n- Full-service contract after warranty: $31,000 per year\n- Estimated utilities and consumables: $22,000 per year\n- References: three comparable hospitals; all renewed service contracts\n\nVendor B — MedAxis MA-9\n- Installed price for two units: $578,000\n- Validation: additional $16,000; operator training included\n- Combined throughput: 24 trays/hour\n- Width per unit: 1,180 mm\n- Delivery, installation, and validation: 14 weeks after purchase order\n- Documented fleet uptime: 97.9%\n- Standard service response: 6 hours\n- Required premium plan provides a 3-hour response during the first-year warranty and costs $52,000 per year in years 2–5\n- Estimated utilities and consumables: $19,000 per year\n- References: two comparable hospitals; one reported recurring door-seal failures during its first six months\n\nVendor C — Aegis AS-15\n- Installed price for two units: $646,000\n- Validation and operator training: included\n- Combined throughput: 32 trays/hour\n- Width per unit: 1,325 mm\n- Delivery, installation, and validation: 16 weeks after purchase order\n- Documented fleet uptime: 99.1%\n- Service response: 2 hours\n- Warranty: 3 years\n- Full-service contract after warranty: $28,000 per year\n- Estimated utilities and consumables: $26,000 per year\n- References: four comparable hospitals with no material complaints\n\nEVALUATION METHOD\nFirst apply all mandatory requirements as pass/fail gates. Score only compliant bids using these weights:\n- Throughput and workflow: 30%\n- Five-year total cost of ownership: 25%\n- Reliability: 20%\n- Implementation schedule: 15%\n- Service, training, and references: 10%\n\nThe evaluation panel assigned the following 0–100 qualitative scores for every criterion except cost:\n- Vendor A: throughput 88, reliability 94, implementation 78, service/training/references 92\n- Vendor B: throughput 75, reliability 82, implementation 95, service/training/references 80\n- Vendor C: throughput 100, reliability 98, implementation 90, service/training/references 96\n\nCalculate five-year TCO as installed price plus separately priced validation, five years of utilities and consumables, and service-contract charges incurred within the five-year period. Exclude financing, taxes, and internal labor. For the cost criterion, give the lowest-TCO compliant bid a score of 100 and calculate every other compliant bid as: lowest compliant TCO divided by that bid's TCO, multiplied by 100.\n\nDELIVERABLE\nWrite a self-contained memo of no more than 900 words with:\n1. An executive recommendation and one-sentence rationale.\n2. A mandatory-requirements table showing pass or fail for each vendor and the specific reason for any failure.\n3. Transparent five-year TCO calculations.\n4. A weighted-score table for compliant vendors, including the cost-score calculation and total scores rounded to one decimal place.\n5. The three most important operational or contracting risks.\n6. Four concrete conditions to include in the notice of intent to award.\n7. A concise 90-day implementation plan with owners.\n\nExplicitly distinguish supplied facts from your inferences. Do not let a strong score override a failed mandatory requirement."
                }
            ]
        })


asyncio.run(main())

curl https://api.runware.ai/v1 \
  -H "Authorization: Bearer $RUNWARE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '[
    {
      "taskType": "textInference",
      "taskUUID": "b2832611-43a4-4559-b134-4bbdbe045fea",
      "model": "google:gemini@3-flash",
      "messages": [
        {
          "role": "user",
          "content": "Act as a healthcare capital-procurement analyst. Prepare a decision memo for the CFO and Infection Prevention Committee of a 340-bed hospital selecting a vendor for two pass-through steam sterilizers. Use only the information below; do not assume missing facts or conduct external research.\n\nMANDATORY REQUIREMENTS\n- Total installed purchase price, including required validation, must not exceed $650,000.\n- Combined rated throughput must be at least 24 DIN trays per hour.\n- Each unit must be no wider than 1,300 mm because walls cannot be moved.\n- Service response must be four hours or less.\n- Purchase order date: May 1. Operational deadline: October 1.\n\nBIDS\n\nVendor A — SteriCore SC-12\n- Installed price for two units: $612,000\n- Validation and operator training: included\n- Combined throughput: 28 trays/hour\n- Width per unit: 1,260 mm\n- Delivery, installation, and validation: 20 weeks after purchase order\n- Documented fleet uptime: 98.7%\n- Service response: 4 hours\n- Warranty: 2 years\n- Full-service contract after warranty: $31,000 per year\n- Estimated utilities and consumables: $22,000 per year\n- References: three comparable hospitals; all renewed service contracts\n\nVendor B — MedAxis MA-9\n- Installed price for two units: $578,000\n- Validation: additional $16,000; operator training included\n- Combined throughput: 24 trays/hour\n- Width per unit: 1,180 mm\n- Delivery, installation, and validation: 14 weeks after purchase order\n- Documented fleet uptime: 97.9%\n- Standard service response: 6 hours\n- Required premium plan provides a 3-hour response during the first-year warranty and costs $52,000 per year in years 2–5\n- Estimated utilities and consumables: $19,000 per year\n- References: two comparable hospitals; one reported recurring door-seal failures during its first six months\n\nVendor C — Aegis AS-15\n- Installed price for two units: $646,000\n- Validation and operator training: included\n- Combined throughput: 32 trays/hour\n- Width per unit: 1,325 mm\n- Delivery, installation, and validation: 16 weeks after purchase order\n- Documented fleet uptime: 99.1%\n- Service response: 2 hours\n- Warranty: 3 years\n- Full-service contract after warranty: $28,000 per year\n- Estimated utilities and consumables: $26,000 per year\n- References: four comparable hospitals with no material complaints\n\nEVALUATION METHOD\nFirst apply all mandatory requirements as pass/fail gates. Score only compliant bids using these weights:\n- Throughput and workflow: 30%\n- Five-year total cost of ownership: 25%\n- Reliability: 20%\n- Implementation schedule: 15%\n- Service, training, and references: 10%\n\nThe evaluation panel assigned the following 0–100 qualitative scores for every criterion except cost:\n- Vendor A: throughput 88, reliability 94, implementation 78, service/training/references 92\n- Vendor B: throughput 75, reliability 82, implementation 95, service/training/references 80\n- Vendor C: throughput 100, reliability 98, implementation 90, service/training/references 96\n\nCalculate five-year TCO as installed price plus separately priced validation, five years of utilities and consumables, and service-contract charges incurred within the five-year period. Exclude financing, taxes, and internal labor. For the cost criterion, give the lowest-TCO compliant bid a score of 100 and calculate every other compliant bid as: lowest compliant TCO divided by that bid's TCO, multiplied by 100.\n\nDELIVERABLE\nWrite a self-contained memo of no more than 900 words with:\n1. An executive recommendation and one-sentence rationale.\n2. A mandatory-requirements table showing pass or fail for each vendor and the specific reason for any failure.\n3. Transparent five-year TCO calculations.\n4. A weighted-score table for compliant vendors, including the cost-score calculation and total scores rounded to one decimal place.\n5. The three most important operational or contracting risks.\n6. Four concrete conditions to include in the notice of intent to award.\n7. A concise 90-day implementation plan with owners.\n\nExplicitly distinguish supplied facts from your inferences. Do not let a strong score override a failed mandatory requirement."
        }
      ]
    }
  ]'

runware run google:gemini@3-flash \
  messages.0.role=user \
  messages.0.content="Act as a healthcare capital-procurement analyst. Prepare a decision memo for the CFO and Infection Prevention Committee of a 340-bed hospital selecting a vendor for two pass-through steam sterilizers. Use only the information below; do not assume missing facts or conduct external research.

MANDATORY REQUIREMENTS
- Total installed purchase price, including required validation, must not exceed \$650,000.
- Combined rated throughput must be at least 24 DIN trays per hour.
- Each unit must be no wider than 1,300 mm because walls cannot be moved.
- Service response must be four hours or less.
- Purchase order date: May 1. Operational deadline: October 1.

BIDS

Vendor A — SteriCore SC-12
- Installed price for two units: \$612,000
- Validation and operator training: included
- Combined throughput: 28 trays/hour
- Width per unit: 1,260 mm
- Delivery, installation, and validation: 20 weeks after purchase order
- Documented fleet uptime: 98.7%
- Service response: 4 hours
- Warranty: 2 years
- Full-service contract after warranty: \$31,000 per year
- Estimated utilities and consumables: \$22,000 per year
- References: three comparable hospitals; all renewed service contracts

Vendor B — MedAxis MA-9
- Installed price for two units: \$578,000
- Validation: additional \$16,000; operator training included
- Combined throughput: 24 trays/hour
- Width per unit: 1,180 mm
- Delivery, installation, and validation: 14 weeks after purchase order
- Documented fleet uptime: 97.9%
- Standard service response: 6 hours
- Required premium plan provides a 3-hour response during the first-year warranty and costs \$52,000 per year in years 2–5
- Estimated utilities and consumables: \$19,000 per year
- References: two comparable hospitals; one reported recurring door-seal failures during its first six months

Vendor C — Aegis AS-15
- Installed price for two units: \$646,000
- Validation and operator training: included
- Combined throughput: 32 trays/hour
- Width per unit: 1,325 mm
- Delivery, installation, and validation: 16 weeks after purchase order
- Documented fleet uptime: 99.1%
- Service response: 2 hours
- Warranty: 3 years
- Full-service contract after warranty: \$28,000 per year
- Estimated utilities and consumables: \$26,000 per year
- References: four comparable hospitals with no material complaints

EVALUATION METHOD
First apply all mandatory requirements as pass/fail gates. Score only compliant bids using these weights:
- Throughput and workflow: 30%
- Five-year total cost of ownership: 25%
- Reliability: 20%
- Implementation schedule: 15%
- Service, training, and references: 10%

The evaluation panel assigned the following 0–100 qualitative scores for every criterion except cost:
- Vendor A: throughput 88, reliability 94, implementation 78, service/training/references 92
- Vendor B: throughput 75, reliability 82, implementation 95, service/training/references 80
- Vendor C: throughput 100, reliability 98, implementation 90, service/training/references 96

Calculate five-year TCO as installed price plus separately priced validation, five years of utilities and consumables, and service-contract charges incurred within the five-year period. Exclude financing, taxes, and internal labor. For the cost criterion, give the lowest-TCO compliant bid a score of 100 and calculate every other compliant bid as: lowest compliant TCO divided by that bid's TCO, multiplied by 100.

DELIVERABLE
Write a self-contained memo of no more than 900 words with:
1. An executive recommendation and one-sentence rationale.
2. A mandatory-requirements table showing pass or fail for each vendor and the specific reason for any failure.
3. Transparent five-year TCO calculations.
4. A weighted-score table for compliant vendors, including the cost-score calculation and total scores rounded to one decimal place.
5. The three most important operational or contracting risks.
6. Four concrete conditions to include in the notice of intent to award.
7. A concise 90-day implementation plan with owners.

Explicitly distinguish supplied facts from your inferences. Do not let a strong score override a failed mandatory requirement."

{
  "taskType": "textInference",
  "taskUUID": "b2832611-43a4-4559-b134-4bbdbe045fea",
  "model": "google:gemini@3-flash",
  "messages": [
    {
      "role": "user",
      "content": "Act as a healthcare capital-procurement analyst. Prepare a decision memo for the CFO and Infection Prevention Committee of a 340-bed hospital selecting a vendor for two pass-through steam sterilizers. Use only the information below; do not assume missing facts or conduct external research.\n\nMANDATORY REQUIREMENTS\n- Total installed purchase price, including required validation, must not exceed $650,000.\n- Combined rated throughput must be at least 24 DIN trays per hour.\n- Each unit must be no wider than 1,300 mm because walls cannot be moved.\n- Service response must be four hours or less.\n- Purchase order date: May 1. Operational deadline: October 1.\n\nBIDS\n\nVendor A — SteriCore SC-12\n- Installed price for two units: $612,000\n- Validation and operator training: included\n- Combined throughput: 28 trays/hour\n- Width per unit: 1,260 mm\n- Delivery, installation, and validation: 20 weeks after purchase order\n- Documented fleet uptime: 98.7%\n- Service response: 4 hours\n- Warranty: 2 years\n- Full-service contract after warranty: $31,000 per year\n- Estimated utilities and consumables: $22,000 per year\n- References: three comparable hospitals; all renewed service contracts\n\nVendor B — MedAxis MA-9\n- Installed price for two units: $578,000\n- Validation: additional $16,000; operator training included\n- Combined throughput: 24 trays/hour\n- Width per unit: 1,180 mm\n- Delivery, installation, and validation: 14 weeks after purchase order\n- Documented fleet uptime: 97.9%\n- Standard service response: 6 hours\n- Required premium plan provides a 3-hour response during the first-year warranty and costs $52,000 per year in years 2–5\n- Estimated utilities and consumables: $19,000 per year\n- References: two comparable hospitals; one reported recurring door-seal failures during its first six months\n\nVendor C — Aegis AS-15\n- Installed price for two units: $646,000\n- Validation and operator training: included\n- Combined throughput: 32 trays/hour\n- Width per unit: 1,325 mm\n- Delivery, installation, and validation: 16 weeks after purchase order\n- Documented fleet uptime: 99.1%\n- Service response: 2 hours\n- Warranty: 3 years\n- Full-service contract after warranty: $28,000 per year\n- Estimated utilities and consumables: $26,000 per year\n- References: four comparable hospitals with no material complaints\n\nEVALUATION METHOD\nFirst apply all mandatory requirements as pass/fail gates. Score only compliant bids using these weights:\n- Throughput and workflow: 30%\n- Five-year total cost of ownership: 25%\n- Reliability: 20%\n- Implementation schedule: 15%\n- Service, training, and references: 10%\n\nThe evaluation panel assigned the following 0–100 qualitative scores for every criterion except cost:\n- Vendor A: throughput 88, reliability 94, implementation 78, service/training/references 92\n- Vendor B: throughput 75, reliability 82, implementation 95, service/training/references 80\n- Vendor C: throughput 100, reliability 98, implementation 90, service/training/references 96\n\nCalculate five-year TCO as installed price plus separately priced validation, five years of utilities and consumables, and service-contract charges incurred within the five-year period. Exclude financing, taxes, and internal labor. For the cost criterion, give the lowest-TCO compliant bid a score of 100 and calculate every other compliant bid as: lowest compliant TCO divided by that bid's TCO, multiplied by 100.\n\nDELIVERABLE\nWrite a self-contained memo of no more than 900 words with:\n1. An executive recommendation and one-sentence rationale.\n2. A mandatory-requirements table showing pass or fail for each vendor and the specific reason for any failure.\n3. Transparent five-year TCO calculations.\n4. A weighted-score table for compliant vendors, including the cost-score calculation and total scores rounded to one decimal place.\n5. The three most important operational or contracting risks.\n6. Four concrete conditions to include in the notice of intent to award.\n7. A concise 90-day implementation plan with owners.\n\nExplicitly distinguish supplied facts from your inferences. Do not let a strong score override a failed mandatory requirement."
    }
  ]
}

import { createClient } from '@runware/sdk'

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

const [result] = await client.run({
  model: 'google:gemini@3-flash',
  seed: 37,
  settings: {
    temperature: 0.42,
    topP: 0.9,
    maxTokens: 300,
    thinkingLevel: 'medium',
    systemPrompt: 'You are a precise visual reasoning assistant. Ground every conclusion in details visible in the image and avoid inventing facts.'
  },
  inputs: {
    images: [
      'https://assets.runware.ai/assets/inputs/86f8954c-d52b-483e-8db5-2b5cea99e255.jpg'
    ]
  },
  messages: [
    {
      role: 'user',
      content: 'Analyze the image carefully. First list the key visible clues exactly as seen, including text, numbers, object positions, and the clock time. Then answer this question: which crate is safest to load onto the last ferry, and why? Keep the final answer under 120 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": "google:gemini@3-flash",
            "seed": 37,
            "settings": {
                "temperature": 0.42,
                "topP": 0.9,
                "maxTokens": 300,
                "thinkingLevel": "medium",
                "systemPrompt": "You are a precise visual reasoning assistant. Ground every conclusion in details visible in the image and avoid inventing facts."
            },
            "inputs": {
                "images": [
                    "https://assets.runware.ai/assets/inputs/86f8954c-d52b-483e-8db5-2b5cea99e255.jpg"
                ]
            },
            "messages": [
                {
                    "role": "user",
                    "content": "Analyze the image carefully. First list the key visible clues exactly as seen, including text, numbers, object positions, and the clock time. Then answer this question: which crate is safest to load onto the last ferry, and why? Keep the final answer under 120 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": "dc5de2d2-c9ed-4153-840f-b47ef0ed368b",
      "model": "google:gemini@3-flash",
      "seed": 37,
      "settings": {
        "temperature": 0.42,
        "topP": 0.9,
        "maxTokens": 300,
        "thinkingLevel": "medium",
        "systemPrompt": "You are a precise visual reasoning assistant. Ground every conclusion in details visible in the image and avoid inventing facts."
      },
      "inputs": {
        "images": [
          "https://assets.runware.ai/assets/inputs/86f8954c-d52b-483e-8db5-2b5cea99e255.jpg"
        ]
      },
      "messages": [
        {
          "role": "user",
          "content": "Analyze the image carefully. First list the key visible clues exactly as seen, including text, numbers, object positions, and the clock time. Then answer this question: which crate is safest to load onto the last ferry, and why? Keep the final answer under 120 words."
        }
      ]
    }
  ]'

runware run google:gemini@3-flash \
  seed=37 \
  settings.temperature=0.42 \
  settings.topP=0.9 \
  settings.maxTokens=300 \
  settings.thinkingLevel=medium \
  settings.systemPrompt="You are a precise visual reasoning assistant. Ground every conclusion in details visible in the image and avoid inventing facts." \
  inputs.images.0=https://assets.runware.ai/assets/inputs/86f8954c-d52b-483e-8db5-2b5cea99e255.jpg \
  messages.0.role=user \
  messages.0.content="Analyze the image carefully. First list the key visible clues exactly as seen, including text, numbers, object positions, and the clock time. Then answer this question: which crate is safest to load onto the last ferry, and why? Keep the final answer under 120 words."

{
  "taskType": "textInference",
  "taskUUID": "dc5de2d2-c9ed-4153-840f-b47ef0ed368b",
  "model": "google:gemini@3-flash",
  "seed": 37,
  "settings": {
    "temperature": 0.42,
    "topP": 0.9,
    "maxTokens": 300,
    "thinkingLevel": "medium",
    "systemPrompt": "You are a precise visual reasoning assistant. Ground every conclusion in details visible in the image and avoid inventing facts."
  },
  "inputs": {
    "images": [
      "https://assets.runware.ai/assets/inputs/86f8954c-d52b-483e-8db5-2b5cea99e255.jpg"
    ]
  },
  "messages": [
    {
      "role": "user",
      "content": "Analyze the image carefully. First list the key visible clues exactly as seen, including text, numbers, object positions, and the clock time. Then answer this question: which crate is safest to load onto the last ferry, and why? Keep the final answer under 120 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: 'google:gemini@3-flash',
  seed: 74218,
  settings: {
    systemPrompt: 'You are a meticulous infrastructure inspection assistant. Describe only observable evidence, avoid speculation, and organize findings clearly for operations staff.',
    temperature: 0.34,
    topP: 0.9,
    maxTokens: 900,
    thinkingLevel: 'medium'
  },
  inputs: {
    videos: [
      'https://assets.runware.ai/assets/inputs/7f2503ba-1274-47da-af00-86c07567d2f1.mp4'
    ]
  },
  messages: [
    {
      role: 'user',
      content: 'Analyze this harbor inspection video for emergency response planning. Provide: 1) a concise scene summary, 2) a bullet list of visible damage, 3) immediate safety hazards, 4) the top 3 repair priorities in order, and 5) a final severity rating from Low, Moderate, High, or Critical. Base your answer only on what is visible in the video and note any uncertainty clearly.'
    }
  ]
})

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": "google:gemini@3-flash",
            "seed": 74218,
            "settings": {
                "systemPrompt": "You are a meticulous infrastructure inspection assistant. Describe only observable evidence, avoid speculation, and organize findings clearly for operations staff.",
                "temperature": 0.34,
                "topP": 0.9,
                "maxTokens": 900,
                "thinkingLevel": "medium"
            },
            "inputs": {
                "videos": [
                    "https://assets.runware.ai/assets/inputs/7f2503ba-1274-47da-af00-86c07567d2f1.mp4"
                ]
            },
            "messages": [
                {
                    "role": "user",
                    "content": "Analyze this harbor inspection video for emergency response planning. Provide: 1) a concise scene summary, 2) a bullet list of visible damage, 3) immediate safety hazards, 4) the top 3 repair priorities in order, and 5) a final severity rating from Low, Moderate, High, or Critical. Base your answer only on what is visible in the video and note any uncertainty clearly."
                }
            ]
        })


asyncio.run(main())

curl https://api.runware.ai/v1 \
  -H "Authorization: Bearer $RUNWARE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '[
    {
      "taskType": "textInference",
      "taskUUID": "7b395ae6-9486-4ead-9314-33c45001da27",
      "model": "google:gemini@3-flash",
      "seed": 74218,
      "settings": {
        "systemPrompt": "You are a meticulous infrastructure inspection assistant. Describe only observable evidence, avoid speculation, and organize findings clearly for operations staff.",
        "temperature": 0.34,
        "topP": 0.9,
        "maxTokens": 900,
        "thinkingLevel": "medium"
      },
      "inputs": {
        "videos": [
          "https://assets.runware.ai/assets/inputs/7f2503ba-1274-47da-af00-86c07567d2f1.mp4"
        ]
      },
      "messages": [
        {
          "role": "user",
          "content": "Analyze this harbor inspection video for emergency response planning. Provide: 1) a concise scene summary, 2) a bullet list of visible damage, 3) immediate safety hazards, 4) the top 3 repair priorities in order, and 5) a final severity rating from Low, Moderate, High, or Critical. Base your answer only on what is visible in the video and note any uncertainty clearly."
        }
      ]
    }
  ]'

runware run google:gemini@3-flash \
  seed=74218 \
  settings.systemPrompt="You are a meticulous infrastructure inspection assistant. Describe only observable evidence, avoid speculation, and organize findings clearly for operations staff." \
  settings.temperature=0.34 \
  settings.topP=0.9 \
  settings.maxTokens=900 \
  settings.thinkingLevel=medium \
  inputs.videos.0=https://assets.runware.ai/assets/inputs/7f2503ba-1274-47da-af00-86c07567d2f1.mp4 \
  messages.0.role=user \
  messages.0.content="Analyze this harbor inspection video for emergency response planning. Provide: 1) a concise scene summary, 2) a bullet list of visible damage, 3) immediate safety hazards, 4) the top 3 repair priorities in order, and 5) a final severity rating from Low, Moderate, High, or Critical. Base your answer only on what is visible in the video and note any uncertainty clearly."

{
  "taskType": "textInference",
  "taskUUID": "7b395ae6-9486-4ead-9314-33c45001da27",
  "model": "google:gemini@3-flash",
  "seed": 74218,
  "settings": {
    "systemPrompt": "You are a meticulous infrastructure inspection assistant. Describe only observable evidence, avoid speculation, and organize findings clearly for operations staff.",
    "temperature": 0.34,
    "topP": 0.9,
    "maxTokens": 900,
    "thinkingLevel": "medium"
  },
  "inputs": {
    "videos": [
      "https://assets.runware.ai/assets/inputs/7f2503ba-1274-47da-af00-86c07567d2f1.mp4"
    ]
  },
  "messages": [
    {
      "role": "user",
      "content": "Analyze this harbor inspection video for emergency response planning. Provide: 1) a concise scene summary, 2) a bullet list of visible damage, 3) immediate safety hazards, 4) the top 3 repair priorities in order, and 5) a final severity rating from Low, Moderate, High, or Critical. Base your answer only on what is visible in the video and note any uncertainty clearly."
    }
  ]
}

import { createClient } from '@runware/sdk'

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

const [result] = await client.run({
  model: 'google:gemini@3-flash',
  seed: 80140,
  settings: {
    systemPrompt: 'You are a precise multimodal captioning assistant. Base the caption only on visible evidence, making careful and plausible inferences without overstating certainty.',
    temperature: 0.72,
    topP: 0.9,
    maxTokens: 220,
    thinkingLevel: 'medium'
  },
  inputs: {
    images: [
      'https://assets.runware.ai/assets/inputs/05589366-3499-45ae-881f-27ce2ca7c8b0.jpg'
    ]
  },
  messages: [
    {
      role: 'user',
      content: 'Write a vivid 2-3 sentence caption for this image as if it were displayed in a maritime museum. Identify the main objects, infer what may have happened recently, and mention at least two visible clues that support the inference.'
    }
  ]
})

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": "google:gemini@3-flash",
            "seed": 80140,
            "settings": {
                "systemPrompt": "You are a precise multimodal captioning assistant. Base the caption only on visible evidence, making careful and plausible inferences without overstating certainty.",
                "temperature": 0.72,
                "topP": 0.9,
                "maxTokens": 220,
                "thinkingLevel": "medium"
            },
            "inputs": {
                "images": [
                    "https://assets.runware.ai/assets/inputs/05589366-3499-45ae-881f-27ce2ca7c8b0.jpg"
                ]
            },
            "messages": [
                {
                    "role": "user",
                    "content": "Write a vivid 2-3 sentence caption for this image as if it were displayed in a maritime museum. Identify the main objects, infer what may have happened recently, and mention at least two visible clues that support the inference."
                }
            ]
        })


asyncio.run(main())

curl https://api.runware.ai/v1 \
  -H "Authorization: Bearer $RUNWARE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '[
    {
      "taskType": "textInference",
      "taskUUID": "9ce1e395-ed82-4bd2-b224-c1e460e800f4",
      "model": "google:gemini@3-flash",
      "seed": 80140,
      "settings": {
        "systemPrompt": "You are a precise multimodal captioning assistant. Base the caption only on visible evidence, making careful and plausible inferences without overstating certainty.",
        "temperature": 0.72,
        "topP": 0.9,
        "maxTokens": 220,
        "thinkingLevel": "medium"
      },
      "inputs": {
        "images": [
          "https://assets.runware.ai/assets/inputs/05589366-3499-45ae-881f-27ce2ca7c8b0.jpg"
        ]
      },
      "messages": [
        {
          "role": "user",
          "content": "Write a vivid 2-3 sentence caption for this image as if it were displayed in a maritime museum. Identify the main objects, infer what may have happened recently, and mention at least two visible clues that support the inference."
        }
      ]
    }
  ]'

runware run google:gemini@3-flash \
  seed=80140 \
  settings.systemPrompt="You are a precise multimodal captioning assistant. Base the caption only on visible evidence, making careful and plausible inferences without overstating certainty." \
  settings.temperature=0.72 \
  settings.topP=0.9 \
  settings.maxTokens=220 \
  settings.thinkingLevel=medium \
  inputs.images.0=https://assets.runware.ai/assets/inputs/05589366-3499-45ae-881f-27ce2ca7c8b0.jpg \
  messages.0.role=user \
  messages.0.content="Write a vivid 2-3 sentence caption for this image as if it were displayed in a maritime museum. Identify the main objects, infer what may have happened recently, and mention at least two visible clues that support the inference."

{
  "taskType": "textInference",
  "taskUUID": "9ce1e395-ed82-4bd2-b224-c1e460e800f4",
  "model": "google:gemini@3-flash",
  "seed": 80140,
  "settings": {
    "systemPrompt": "You are a precise multimodal captioning assistant. Base the caption only on visible evidence, making careful and plausible inferences without overstating certainty.",
    "temperature": 0.72,
    "topP": 0.9,
    "maxTokens": 220,
    "thinkingLevel": "medium"
  },
  "inputs": {
    "images": [
      "https://assets.runware.ai/assets/inputs/05589366-3499-45ae-881f-27ce2ca7c8b0.jpg"
    ]
  },
  "messages": [
    {
      "role": "user",
      "content": "Write a vivid 2-3 sentence caption for this image as if it were displayed in a maritime museum. Identify the main objects, infer what may have happened recently, and mention at least two visible clues that support the inference."
    }
  ]
}

import { createClient } from '@runware/sdk'

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

const [result] = await client.run({
  model: 'google:gemini@3-flash',
  messages: [
    {
      role: 'user',
      content: 'We are making a go/no-go decision for a mobile-crane glass-panel lift at Battersea Power Station, 188 Kirtling Street, London SW11 8BN, United Kingdom. Look up the current weather there in metric units, including wind speed, wind gusts, precipitation, and visibility. Use live observations rather than estimates or general advice.'
    }
  ],
  tools: [
    {
      type: 'function',
      name: 'lookup_weather',
      description: 'Looks up the current weather for a requested location.',
      schema: {}
    }
  ],
  toolChoice: {
    type: 'tool',
    name: 'lookup_weather'
  }
})

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": "google:gemini@3-flash",
            "messages": [
                {
                    "role": "user",
                    "content": "We are making a go/no-go decision for a mobile-crane glass-panel lift at Battersea Power Station, 188 Kirtling Street, London SW11 8BN, United Kingdom. Look up the current weather there in metric units, including wind speed, wind gusts, precipitation, and visibility. Use live observations rather than estimates or general advice."
                }
            ],
            "tools": [
                {
                    "type": "function",
                    "name": "lookup_weather",
                    "description": "Looks up the current weather for a requested location.",
                    "schema": {}
                }
            ],
            "toolChoice": {
                "type": "tool",
                "name": "lookup_weather"
            }
        })


asyncio.run(main())

curl https://api.runware.ai/v1 \
  -H "Authorization: Bearer $RUNWARE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '[
    {
      "taskType": "textInference",
      "taskUUID": "500b07a0-9dcc-46c5-a4de-0dd773148f5f",
      "model": "google:gemini@3-flash",
      "messages": [
        {
          "role": "user",
          "content": "We are making a go/no-go decision for a mobile-crane glass-panel lift at Battersea Power Station, 188 Kirtling Street, London SW11 8BN, United Kingdom. Look up the current weather there in metric units, including wind speed, wind gusts, precipitation, and visibility. Use live observations rather than estimates or general advice."
        }
      ],
      "tools": [
        {
          "type": "function",
          "name": "lookup_weather",
          "description": "Looks up the current weather for a requested location.",
          "schema": {}
        }
      ],
      "toolChoice": {
        "type": "tool",
        "name": "lookup_weather"
      }
    }
  ]'

runware run google:gemini@3-flash \
  messages.0.role=user \
  messages.0.content="We are making a go/no-go decision for a mobile-crane glass-panel lift at Battersea Power Station, 188 Kirtling Street, London SW11 8BN, United Kingdom. Look up the current weather there in metric units, including wind speed, wind gusts, precipitation, and visibility. Use live observations rather than estimates or general advice." \
  tools.0.type=function \
  tools.0.name=lookup_weather \
  tools.0.description="Looks up the current weather for a requested location." \
  toolChoice.type=tool \
  toolChoice.name=lookup_weather

{
  "taskType": "textInference",
  "taskUUID": "500b07a0-9dcc-46c5-a4de-0dd773148f5f",
  "model": "google:gemini@3-flash",
  "messages": [
    {
      "role": "user",
      "content": "We are making a go/no-go decision for a mobile-crane glass-panel lift at Battersea Power Station, 188 Kirtling Street, London SW11 8BN, United Kingdom. Look up the current weather there in metric units, including wind speed, wind gusts, precipitation, and visibility. Use live observations rather than estimates or general advice."
    }
  ],
  "tools": [
    {
      "type": "function",
      "name": "lookup_weather",
      "description": "Looks up the current weather for a requested location.",
      "schema": {}
    }
  ],
  "toolChoice": {
    "type": "tool",
    "name": "lookup_weather"
  }
}