live
MODEL IDxai-grok-4-3

Grok 4.3

xAI
by 1M context

Grok 4.3 is xAI's flagship language model for agentic reasoning, strong instruction following, and minimal hallucinations. It supports text and image input, a 1 million token context window, configurable reasoning effort including non-reasoning mode, function calling, and structured outputs for production assistants, coding workflows, and long-context analysis.

Grok 4.3

text-generation

SaaS Pricing Migration Decision Memo$0.00265~15s
Reasoning
The task is to write a board-ready decision memo for Northstar Workflow on switching to per-seat pricing. I must use only the given facts, no external benchmarks.
Executive Recommendation
I recommend policy C: move customers at renewal but cap the first-year increase at 20%; apply full list pricing at the following renewal. This balances the 12% ARR growth target with churn protection and operational limits while preserving the 61% survey acceptance of per-seat pricing.
**Executive Recommendation**  
Policy C is the only option that stays inside the churn limit and the operational constraints while still producing a plausible path to the 12% ARR target. It requires cohort-specific rules: Starter and Team move at renewal to list pricing (Core at $10/seat with 3-seat minimum, Pro at $12/seat with 10-seat minimum); Business receives a one-year 20% ARR cap at renewal, then moves to Advanced list pricing ($14/seat, 25-seat minimum) on the subsequent renewal. The 120 largest Business accounts receive the first 180 high-touch calls each month; the remaining Business accounts and all Team accounts over 20 seats receive email-plus-self-serve migration. Enterprise contracts stay untouched. Annual prepayment keeps the two-month discount.

**Cohort Economics**  
Average monthly price before discounts and annual adjustment:  
- Starter (3 seats): $39 → $30 (Core), –23%.  
- Team (11 seats): $99 → $132 (Pro), +33%.  
- Business (31 seats): $249 → $434 (Advanced), +74%.  

These are simple arithmetic conversions of the stated average seat counts to the new per-seat rates; they do not incorporate existing discounts, within-cohort seat variance, or renewal timing. Consequently, they cannot be read as expected revenue outcomes or churn predictors. They only illustrate directional pressure on the two cohorts that will see increases.

**Policy Comparison**  
Policy A applies list pricing at the next renewal for all non-Enterprise customers. Business customers face a 74% jump; given the survey result that only 28% view increases above 25% as fair, logo churn is likely to exceed the 0.4-point cap for that cohort. Policy B defers every migration by 12 months, so no new revenue materializes inside the first 12 months and the 12% ARR goal is missed by construction. Policy C limits the first-year Business increase to 20% and therefore keeps the immediate price signal inside the fairness threshold reported in the survey, while still allowing full list pricing one renewal later.

**Migration Design**  
One migration rule per legacy cohort satisfies the engineering constraint. At renewal: Starter customers map to Core list; Team customers map to Pro list; Business customers map to a 20%-capped contract that converts to Advanced list on the next renewal. Annual prepayment continues to receive two months free on the new list price. The 180 Customer Success calls per month are allocated first to the 120 largest Business accounts (52% of Business ARR), then to the remaining Business accounts ordered by ARR, then to Team accounts with above-average seat counts. All other customers receive standardized email and in-product prompts.

**Risk Controls**  
Exception policy: any customer whose capped Business renewal still exceeds 25% receives a one-time additional 5% ARR credit for the first year only; this credit is approved by the Head of CS in batches of no more than 30 per month. Stop/go thresholds: if any cohort’s monthly logo churn rises more than 0.3 points above its trailing three-month average for two consecutive months, pause further migrations and escalate to the pricing committee within five business days. Missing data to collect before final approval: actual discount percentages by cohort, renewal-month distribution over the next 18 months, and seat-count histograms for the top 200 Business accounts.

**90-Day Plan**  
Days 1
Finish reason: length
Try in Playground
import { createClient } from '@runware/sdk'

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

const [result] = await client.run({
  model: 'xai:grok@4.3',
  settings: {
    thinkingLevel: 'high',
    maxTokens: 700
  },
  messages: [
    {
      role: 'user',
      content: 'Act as a senior B2B SaaS pricing strategist. Write a board-ready decision memo for Northstar Workflow, which plans to replace bundled plans with per-seat pricing on January 1. Use only the facts below; do not introduce external benchmarks.\n\nCurrent annualized revenue is $8.0M. Customer mix and performance:\n- Starter: 44% of customers, $1.35M ARR, $39/month for up to 5 seats, average 3 active seats, 2.4% monthly logo churn.\n- Team: 38% of customers, $2.85M ARR, $99/month for up to 20 seats, average 11 active seats, 1.5% monthly logo churn.\n- Business: 14% of customers, $2.40M ARR, $249/month for up to 50 seats, average 31 active seats, 0.9% monthly logo churn.\n- Enterprise: 4% of customers, $1.40M ARR, negotiated contracts. Enterprise pricing will not change.\n\nProposed plans:\n- Core: $10 per active seat per month, 3-seat minimum.\n- Pro: $12 per active seat per month, 10-seat minimum.\n- Advanced: $14 per active seat per month, 25-seat minimum.\n- Annual prepayment receives two months free.\n- Intended mapping is Starter to Core, Team to Pro, and Business to Advanced.\n\nManagement objectives and constraints:\n- Increase total ARR by at least 12% within 12 months.\n- Keep any increase in monthly logo churn below 0.4 percentage points for each cohort.\n- Do not change signed Enterprise contracts.\n- Billing engineering can support only one migration rule per legacy cohort.\n- Customer Success can conduct at most 180 high-touch migration calls per month.\n- The 120 largest Business accounts represent 52% of Business ARR.\n- A recent survey found that 61% of Team and Business respondents accept per-seat pricing in principle, but only 28% consider a first-year increase above 25% fair.\n- No reliable price-elasticity study exists.\n\nEvaluate these three policies:\nA. Move every non-Enterprise customer to list pricing at the next renewal.\nB. Grandfather all existing customers for 12 months, then move them to list pricing.\nC. Move customers at renewal but cap the first-year increase at 20%; apply full list pricing at the following renewal.\n\nShow the implied monthly price change for the average customer in each legacy cohort before discounts. Explain what can and cannot be concluded from those averages. Recommend one policy, including any cohort-specific migration rules that remain operationally feasible. Provide a practical exception policy, a prioritized allocation of the 180 monthly Customer Success calls, customer-communication principles, measurable stop/go thresholds, and a 90-day implementation plan.\n\nWrite in direct natural language with these sections: Executive Recommendation, Cohort Economics, Policy Comparison, Migration Design, Risk Controls, and 90-Day Plan. Distinguish calculations from assumptions, avoid false precision, surface tensions with the 12% ARR objective, and identify any missing data that should be collected before final approval.'
    }
  ],
  toolChoice: {
    type: 'none'
  }
})
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": "xai:grok@4.3",
            "settings": {
                "thinkingLevel": "high",
                "maxTokens": 700
            },
            "messages": [
                {
                    "role": "user",
                    "content": "Act as a senior B2B SaaS pricing strategist. Write a board-ready decision memo for Northstar Workflow, which plans to replace bundled plans with per-seat pricing on January 1. Use only the facts below; do not introduce external benchmarks.\n\nCurrent annualized revenue is $8.0M. Customer mix and performance:\n- Starter: 44% of customers, $1.35M ARR, $39/month for up to 5 seats, average 3 active seats, 2.4% monthly logo churn.\n- Team: 38% of customers, $2.85M ARR, $99/month for up to 20 seats, average 11 active seats, 1.5% monthly logo churn.\n- Business: 14% of customers, $2.40M ARR, $249/month for up to 50 seats, average 31 active seats, 0.9% monthly logo churn.\n- Enterprise: 4% of customers, $1.40M ARR, negotiated contracts. Enterprise pricing will not change.\n\nProposed plans:\n- Core: $10 per active seat per month, 3-seat minimum.\n- Pro: $12 per active seat per month, 10-seat minimum.\n- Advanced: $14 per active seat per month, 25-seat minimum.\n- Annual prepayment receives two months free.\n- Intended mapping is Starter to Core, Team to Pro, and Business to Advanced.\n\nManagement objectives and constraints:\n- Increase total ARR by at least 12% within 12 months.\n- Keep any increase in monthly logo churn below 0.4 percentage points for each cohort.\n- Do not change signed Enterprise contracts.\n- Billing engineering can support only one migration rule per legacy cohort.\n- Customer Success can conduct at most 180 high-touch migration calls per month.\n- The 120 largest Business accounts represent 52% of Business ARR.\n- A recent survey found that 61% of Team and Business respondents accept per-seat pricing in principle, but only 28% consider a first-year increase above 25% fair.\n- No reliable price-elasticity study exists.\n\nEvaluate these three policies:\nA. Move every non-Enterprise customer to list pricing at the next renewal.\nB. Grandfather all existing customers for 12 months, then move them to list pricing.\nC. Move customers at renewal but cap the first-year increase at 20%; apply full list pricing at the following renewal.\n\nShow the implied monthly price change for the average customer in each legacy cohort before discounts. Explain what can and cannot be concluded from those averages. Recommend one policy, including any cohort-specific migration rules that remain operationally feasible. Provide a practical exception policy, a prioritized allocation of the 180 monthly Customer Success calls, customer-communication principles, measurable stop/go thresholds, and a 90-day implementation plan.\n\nWrite in direct natural language with these sections: Executive Recommendation, Cohort Economics, Policy Comparison, Migration Design, Risk Controls, and 90-Day Plan. Distinguish calculations from assumptions, avoid false precision, surface tensions with the 12% ARR objective, and identify any missing data that should be collected before final approval."
                }
            ],
            "toolChoice": {
                "type": "none"
            }
        })


asyncio.run(main())
curl https://api.runware.ai/v1 \
  -H "Authorization: Bearer $RUNWARE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '[
    {
      "taskType": "textInference",
      "taskUUID": "92746ab4-ff1f-471f-9067-eeae8c92d14a",
      "model": "xai:grok@4.3",
      "settings": {
        "thinkingLevel": "high",
        "maxTokens": 700
      },
      "messages": [
        {
          "role": "user",
          "content": "Act as a senior B2B SaaS pricing strategist. Write a board-ready decision memo for Northstar Workflow, which plans to replace bundled plans with per-seat pricing on January 1. Use only the facts below; do not introduce external benchmarks.\n\nCurrent annualized revenue is $8.0M. Customer mix and performance:\n- Starter: 44% of customers, $1.35M ARR, $39/month for up to 5 seats, average 3 active seats, 2.4% monthly logo churn.\n- Team: 38% of customers, $2.85M ARR, $99/month for up to 20 seats, average 11 active seats, 1.5% monthly logo churn.\n- Business: 14% of customers, $2.40M ARR, $249/month for up to 50 seats, average 31 active seats, 0.9% monthly logo churn.\n- Enterprise: 4% of customers, $1.40M ARR, negotiated contracts. Enterprise pricing will not change.\n\nProposed plans:\n- Core: $10 per active seat per month, 3-seat minimum.\n- Pro: $12 per active seat per month, 10-seat minimum.\n- Advanced: $14 per active seat per month, 25-seat minimum.\n- Annual prepayment receives two months free.\n- Intended mapping is Starter to Core, Team to Pro, and Business to Advanced.\n\nManagement objectives and constraints:\n- Increase total ARR by at least 12% within 12 months.\n- Keep any increase in monthly logo churn below 0.4 percentage points for each cohort.\n- Do not change signed Enterprise contracts.\n- Billing engineering can support only one migration rule per legacy cohort.\n- Customer Success can conduct at most 180 high-touch migration calls per month.\n- The 120 largest Business accounts represent 52% of Business ARR.\n- A recent survey found that 61% of Team and Business respondents accept per-seat pricing in principle, but only 28% consider a first-year increase above 25% fair.\n- No reliable price-elasticity study exists.\n\nEvaluate these three policies:\nA. Move every non-Enterprise customer to list pricing at the next renewal.\nB. Grandfather all existing customers for 12 months, then move them to list pricing.\nC. Move customers at renewal but cap the first-year increase at 20%; apply full list pricing at the following renewal.\n\nShow the implied monthly price change for the average customer in each legacy cohort before discounts. Explain what can and cannot be concluded from those averages. Recommend one policy, including any cohort-specific migration rules that remain operationally feasible. Provide a practical exception policy, a prioritized allocation of the 180 monthly Customer Success calls, customer-communication principles, measurable stop/go thresholds, and a 90-day implementation plan.\n\nWrite in direct natural language with these sections: Executive Recommendation, Cohort Economics, Policy Comparison, Migration Design, Risk Controls, and 90-Day Plan. Distinguish calculations from assumptions, avoid false precision, surface tensions with the 12% ARR objective, and identify any missing data that should be collected before final approval."
        }
      ],
      "toolChoice": {
        "type": "none"
      }
    }
  ]'
runware run xai:grok@4.3 \
  settings.thinkingLevel=high \
  settings.maxTokens=700 \
  messages.0.role=user \
  messages.0.content="Act as a senior B2B SaaS pricing strategist. Write a board-ready decision memo for Northstar Workflow, which plans to replace bundled plans with per-seat pricing on January 1. Use only the facts below; do not introduce external benchmarks.

Current annualized revenue is \$8.0M. Customer mix and performance:
- Starter: 44% of customers, \$1.35M ARR, \$39/month for up to 5 seats, average 3 active seats, 2.4% monthly logo churn.
- Team: 38% of customers, \$2.85M ARR, \$99/month for up to 20 seats, average 11 active seats, 1.5% monthly logo churn.
- Business: 14% of customers, \$2.40M ARR, \$249/month for up to 50 seats, average 31 active seats, 0.9% monthly logo churn.
- Enterprise: 4% of customers, \$1.40M ARR, negotiated contracts. Enterprise pricing will not change.

Proposed plans:
- Core: \$10 per active seat per month, 3-seat minimum.
- Pro: \$12 per active seat per month, 10-seat minimum.
- Advanced: \$14 per active seat per month, 25-seat minimum.
- Annual prepayment receives two months free.
- Intended mapping is Starter to Core, Team to Pro, and Business to Advanced.

Management objectives and constraints:
- Increase total ARR by at least 12% within 12 months.
- Keep any increase in monthly logo churn below 0.4 percentage points for each cohort.
- Do not change signed Enterprise contracts.
- Billing engineering can support only one migration rule per legacy cohort.
- Customer Success can conduct at most 180 high-touch migration calls per month.
- The 120 largest Business accounts represent 52% of Business ARR.
- A recent survey found that 61% of Team and Business respondents accept per-seat pricing in principle, but only 28% consider a first-year increase above 25% fair.
- No reliable price-elasticity study exists.

Evaluate these three policies:
A. Move every non-Enterprise customer to list pricing at the next renewal.
B. Grandfather all existing customers for 12 months, then move them to list pricing.
C. Move customers at renewal but cap the first-year increase at 20%; apply full list pricing at the following renewal.

Show the implied monthly price change for the average customer in each legacy cohort before discounts. Explain what can and cannot be concluded from those averages. Recommend one policy, including any cohort-specific migration rules that remain operationally feasible. Provide a practical exception policy, a prioritized allocation of the 180 monthly Customer Success calls, customer-communication principles, measurable stop/go thresholds, and a 90-day implementation plan.

Write in direct natural language with these sections: Executive Recommendation, Cohort Economics, Policy Comparison, Migration Design, Risk Controls, and 90-Day Plan. Distinguish calculations from assumptions, avoid false precision, surface tensions with the 12% ARR objective, and identify any missing data that should be collected before final approval." \
  toolChoice.type=none
{
  "taskType": "textInference",
  "taskUUID": "92746ab4-ff1f-471f-9067-eeae8c92d14a",
  "model": "xai:grok@4.3",
  "settings": {
    "thinkingLevel": "high",
    "maxTokens": 700
  },
  "messages": [
    {
      "role": "user",
      "content": "Act as a senior B2B SaaS pricing strategist. Write a board-ready decision memo for Northstar Workflow, which plans to replace bundled plans with per-seat pricing on January 1. Use only the facts below; do not introduce external benchmarks.\n\nCurrent annualized revenue is $8.0M. Customer mix and performance:\n- Starter: 44% of customers, $1.35M ARR, $39/month for up to 5 seats, average 3 active seats, 2.4% monthly logo churn.\n- Team: 38% of customers, $2.85M ARR, $99/month for up to 20 seats, average 11 active seats, 1.5% monthly logo churn.\n- Business: 14% of customers, $2.40M ARR, $249/month for up to 50 seats, average 31 active seats, 0.9% monthly logo churn.\n- Enterprise: 4% of customers, $1.40M ARR, negotiated contracts. Enterprise pricing will not change.\n\nProposed plans:\n- Core: $10 per active seat per month, 3-seat minimum.\n- Pro: $12 per active seat per month, 10-seat minimum.\n- Advanced: $14 per active seat per month, 25-seat minimum.\n- Annual prepayment receives two months free.\n- Intended mapping is Starter to Core, Team to Pro, and Business to Advanced.\n\nManagement objectives and constraints:\n- Increase total ARR by at least 12% within 12 months.\n- Keep any increase in monthly logo churn below 0.4 percentage points for each cohort.\n- Do not change signed Enterprise contracts.\n- Billing engineering can support only one migration rule per legacy cohort.\n- Customer Success can conduct at most 180 high-touch migration calls per month.\n- The 120 largest Business accounts represent 52% of Business ARR.\n- A recent survey found that 61% of Team and Business respondents accept per-seat pricing in principle, but only 28% consider a first-year increase above 25% fair.\n- No reliable price-elasticity study exists.\n\nEvaluate these three policies:\nA. Move every non-Enterprise customer to list pricing at the next renewal.\nB. Grandfather all existing customers for 12 months, then move them to list pricing.\nC. Move customers at renewal but cap the first-year increase at 20%; apply full list pricing at the following renewal.\n\nShow the implied monthly price change for the average customer in each legacy cohort before discounts. Explain what can and cannot be concluded from those averages. Recommend one policy, including any cohort-specific migration rules that remain operationally feasible. Provide a practical exception policy, a prioritized allocation of the 180 monthly Customer Success calls, customer-communication principles, measurable stop/go thresholds, and a 90-day implementation plan.\n\nWrite in direct natural language with these sections: Executive Recommendation, Cohort Economics, Policy Comparison, Migration Design, Risk Controls, and 90-Day Plan. Distinguish calculations from assumptions, avoid false precision, surface tensions with the 12% ARR objective, and identify any missing data that should be collected before final approval."
    }
  ],
  "toolChoice": {
    "type": "none"
  }
}
Response
{
  "taskType": "textInference",
  "taskUUID": "92746ab4-ff1f-471f-9067-eeae8c92d14a",
  "text": "**Executive Recommendation**  \nPolicy C is the only option that stays inside the churn limit and the operational constraints while still producing a plausible path to the 12% ARR target. It requires cohort-specific rules: Starter and Team move at renewal to list pricing (Core at $10/seat with 3-seat minimum, Pro at $12/seat with 10-seat minimum); Business receives a one-year 20% ARR cap at renewal, then moves to Advanced list pricing ($14/seat, 25-seat minimum) on the subsequent renewal. The 120 largest Business accounts receive the first 180 high-touch calls each month; the remaining Business accounts and all Team accounts over 20 seats receive email-plus-self-serve migration. Enterprise contracts stay untouched. Annual prepayment keeps the two-month discount.\n\n**Cohort Economics**  \nAverage monthly price before discounts and annual adjustment:  \n- Starter (3 seats): $39 → $30 (Core), –23%.  \n- Team (11 seats): $99 → $132 (Pro), +33%.  \n- Business (31 seats): $249 → $434 (Advanced), +74%.  \n\nThese are simple arithmetic conversions of the stated average seat counts to the new per-seat rates; they do not incorporate existing discounts, within-cohort seat variance, or renewal timing. Consequently, they cannot be read as expected revenue outcomes or churn predictors. They only illustrate directional pressure on the two cohorts that will see increases.\n\n**Policy Comparison**  \nPolicy A applies list pricing at the next renewal for all non-Enterprise customers. Business customers face a 74% jump; given the survey result that only 28% view increases above 25% as fair, logo churn is likely to exceed the 0.4-point cap for that cohort. Policy B defers every migration by 12 months, so no new revenue materializes inside the first 12 months and the 12% ARR goal is missed by construction. Policy C limits the first-year Business increase to 20% and therefore keeps the immediate price signal inside the fairness threshold reported in the survey, while still allowing full list pricing one renewal later.\n\n**Migration Design**  \nOne migration rule per legacy cohort satisfies the engineering constraint. At renewal: Starter customers map to Core list; Team customers map to Pro list; Business customers map to a 20%-capped contract that converts to Advanced list on the next renewal. Annual prepayment continues to receive two months free on the new list price. The 180 Customer Success calls per month are allocated first to the 120 largest Business accounts (52% of Business ARR), then to the remaining Business accounts ordered by ARR, then to Team accounts with above-average seat counts. All other customers receive standardized email and in-product prompts.\n\n**Risk Controls**  \nException policy: any customer whose capped Business renewal still exceeds 25% receives a one-time additional 5% ARR credit for the first year only; this credit is approved by the Head of CS in batches of no more than 30 per month. Stop/go thresholds: if any cohort’s monthly logo churn rises more than 0.3 points above its trailing three-month average for two consecutive months, pause further migrations and escalate to the pricing committee within five business days. Missing data to collect before final approval: actual discount percentages by cohort, renewal-month distribution over the next 18 months, and seat-count histograms for the top 200 Business accounts.\n\n**90-Day Plan**  \nDays 1",
  "cost": 0.00264935,
  "finishReason": "length",
  "reasoningContent": [
    "The task is to write a board-ready decision memo for Northstar Workflow on switching to per-seat pricing. I must use only the given facts, no external benchmarks.\nExecutive Recommendation\nI recommend policy C: move customers at renewal but cap the first-year increase at 20%; apply full list pricing at the following renewal. This balances the 12% ARR growth target with churn protection and operational limits while preserving the 61% survey acceptance of per-seat pricing."
  ]
}

tool-calling

Newsroom Embargo Timestamp Lookup$0.000206~4s
Reasoning
The task is: "Our international desk is lifting the embargo on the Helios Energy acquisition announcement immediately. Retrieve the current UTC date and time in RFC 3339 format, precise to the second,...
{
  "taskType": "textInference",
  "taskUUID": "1312b239-3d56-4998-ad89-f9d64ed5165c",
  "cost": 0.0002059,
  "finishReason": "tools",
  "reasoningContent": [
    "The task is: \"Our international desk is lifting the embargo on the Helios Energy acquisition announcement immediately. Retrieve the current UTC date and time in RFC 3339 format, precise to the second,..."
  ],
  "tools": [
    {
      "id": "call-7f1252fe-af96-48a9-a304-de6bf8c69efc-0",
      "name": "get_current_utc_time"
    }
  ]
}
Finish reason: tools
Try in Playground
import { createClient } from '@runware/sdk'

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

const [result] = await client.run({
  model: 'xai:grok@4.3',
  settings: {
    temperature: 0.2,
    thinkingLevel: 'low',
    maxTokens: 300
  },
  messages: [
    {
      role: 'user',
      content: 'Our international desk is lifting the embargo on the Helios Energy acquisition announcement immediately. Retrieve the current UTC date and time in RFC 3339 format, precise to the second, so our publishing system can record the official release timestamp.'
    }
  ],
  tools: [
    {
      type: 'function',
      name: 'get_current_utc_time',
      description: 'Returns the current date and time in UTC.',
      schema: {}
    }
  ],
  toolChoice: {
    type: 'tool',
    name: 'get_current_utc_time'
  }
})
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": "xai:grok@4.3",
            "settings": {
                "temperature": 0.2,
                "thinkingLevel": "low",
                "maxTokens": 300
            },
            "messages": [
                {
                    "role": "user",
                    "content": "Our international desk is lifting the embargo on the Helios Energy acquisition announcement immediately. Retrieve the current UTC date and time in RFC 3339 format, precise to the second, so our publishing system can record the official release timestamp."
                }
            ],
            "tools": [
                {
                    "type": "function",
                    "name": "get_current_utc_time",
                    "description": "Returns the current date and time in UTC.",
                    "schema": {}
                }
            ],
            "toolChoice": {
                "type": "tool",
                "name": "get_current_utc_time"
            }
        })


asyncio.run(main())
curl https://api.runware.ai/v1 \
  -H "Authorization: Bearer $RUNWARE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '[
    {
      "taskType": "textInference",
      "taskUUID": "1312b239-3d56-4998-ad89-f9d64ed5165c",
      "model": "xai:grok@4.3",
      "settings": {
        "temperature": 0.2,
        "thinkingLevel": "low",
        "maxTokens": 300
      },
      "messages": [
        {
          "role": "user",
          "content": "Our international desk is lifting the embargo on the Helios Energy acquisition announcement immediately. Retrieve the current UTC date and time in RFC 3339 format, precise to the second, so our publishing system can record the official release timestamp."
        }
      ],
      "tools": [
        {
          "type": "function",
          "name": "get_current_utc_time",
          "description": "Returns the current date and time in UTC.",
          "schema": {}
        }
      ],
      "toolChoice": {
        "type": "tool",
        "name": "get_current_utc_time"
      }
    }
  ]'
runware run xai:grok@4.3 \
  settings.temperature=0.2 \
  settings.thinkingLevel=low \
  settings.maxTokens=300 \
  messages.0.role=user \
  messages.0.content="Our international desk is lifting the embargo on the Helios Energy acquisition announcement immediately. Retrieve the current UTC date and time in RFC 3339 format, precise to the second, so our publishing system can record the official release timestamp." \
  tools.0.type=function \
  tools.0.name=get_current_utc_time \
  tools.0.description="Returns the current date and time in UTC." \
  toolChoice.type=tool \
  toolChoice.name=get_current_utc_time
{
  "taskType": "textInference",
  "taskUUID": "1312b239-3d56-4998-ad89-f9d64ed5165c",
  "model": "xai:grok@4.3",
  "settings": {
    "temperature": 0.2,
    "thinkingLevel": "low",
    "maxTokens": 300
  },
  "messages": [
    {
      "role": "user",
      "content": "Our international desk is lifting the embargo on the Helios Energy acquisition announcement immediately. Retrieve the current UTC date and time in RFC 3339 format, precise to the second, so our publishing system can record the official release timestamp."
    }
  ],
  "tools": [
    {
      "type": "function",
      "name": "get_current_utc_time",
      "description": "Returns the current date and time in UTC.",
      "schema": {}
    }
  ],
  "toolChoice": {
    "type": "tool",
    "name": "get_current_utc_time"
  }
}
Response
{
  "taskType": "textInference",
  "taskUUID": "1312b239-3d56-4998-ad89-f9d64ed5165c",
  "cost": 0.0002059,
  "finishReason": "tools",
  "reasoningContent": [
    "The task is: \"Our international desk is lifting the embargo on the Helios Energy acquisition announcement immediately. Retrieve the current UTC date and time in RFC 3339 format, precise to the second,..."
  ],
  "tools": [
    {
      "id": "call-7f1252fe-af96-48a9-a304-de6bf8c69efc-0",
      "name": "get_current_utc_time"
    }
  ]
}

tool-calling

Pharmaceutical Recall Timestamp Record$0.000236~4s
Reasoning
The task is: "Open the official action log for recall RC-2026-017 covering Cardiomab 50 mg prefilled syringes, lots CM50-24081 and CM50-24082. Retrieve the current UTC date and time from the authorita...
{
  "taskType": "textInference",
  "taskUUID": "78aa0396-d278-44f0-b92d-f9aa681292d8",
  "cost": 0.0002359,
  "finishReason": "tools",
  "reasoningContent": [
    "The task is: \"Open the official action log for recall RC-2026-017 covering Cardiomab 50 mg prefilled syringes, lots CM50-24081 and CM50-24082. Retrieve the current UTC date and time from the authorita..."
  ],
  "tools": [
    {
      "id": "call-dfb29085-8ca9-4646-b6ff-ee982af774a6-0",
      "name": "get_current_utc_time"
    }
  ]
}
Finish reason: tools
Try in Playground
import { createClient } from '@runware/sdk'

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

const [result] = await client.run({
  model: 'xai:grok@4.3',
  settings: {
    temperature: 0.2,
    thinkingLevel: 'low',
    maxTokens: 300
  },
  messages: [
    {
      role: 'user',
      content: 'Open the official action log for recall RC-2026-017 covering Cardiomab 50 mg prefilled syringes, lots CM50-24081 and CM50-24082. Retrieve the current UTC date and time from the authoritative time service and record it as the recall activation timestamp. Do not estimate the time or derive it from the conversation.'
    }
  ],
  tools: [
    {
      type: 'function',
      name: 'get_current_utc_time',
      description: 'Returns the current date and time in UTC.',
      schema: {}
    }
  ],
  toolChoice: {
    type: 'tool',
    name: 'get_current_utc_time'
  }
})
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": "xai:grok@4.3",
            "settings": {
                "temperature": 0.2,
                "thinkingLevel": "low",
                "maxTokens": 300
            },
            "messages": [
                {
                    "role": "user",
                    "content": "Open the official action log for recall RC-2026-017 covering Cardiomab 50 mg prefilled syringes, lots CM50-24081 and CM50-24082. Retrieve the current UTC date and time from the authoritative time service and record it as the recall activation timestamp. Do not estimate the time or derive it from the conversation."
                }
            ],
            "tools": [
                {
                    "type": "function",
                    "name": "get_current_utc_time",
                    "description": "Returns the current date and time in UTC.",
                    "schema": {}
                }
            ],
            "toolChoice": {
                "type": "tool",
                "name": "get_current_utc_time"
            }
        })


asyncio.run(main())
curl https://api.runware.ai/v1 \
  -H "Authorization: Bearer $RUNWARE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '[
    {
      "taskType": "textInference",
      "taskUUID": "78aa0396-d278-44f0-b92d-f9aa681292d8",
      "model": "xai:grok@4.3",
      "settings": {
        "temperature": 0.2,
        "thinkingLevel": "low",
        "maxTokens": 300
      },
      "messages": [
        {
          "role": "user",
          "content": "Open the official action log for recall RC-2026-017 covering Cardiomab 50 mg prefilled syringes, lots CM50-24081 and CM50-24082. Retrieve the current UTC date and time from the authoritative time service and record it as the recall activation timestamp. Do not estimate the time or derive it from the conversation."
        }
      ],
      "tools": [
        {
          "type": "function",
          "name": "get_current_utc_time",
          "description": "Returns the current date and time in UTC.",
          "schema": {}
        }
      ],
      "toolChoice": {
        "type": "tool",
        "name": "get_current_utc_time"
      }
    }
  ]'
runware run xai:grok@4.3 \
  settings.temperature=0.2 \
  settings.thinkingLevel=low \
  settings.maxTokens=300 \
  messages.0.role=user \
  messages.0.content="Open the official action log for recall RC-2026-017 covering Cardiomab 50 mg prefilled syringes, lots CM50-24081 and CM50-24082. Retrieve the current UTC date and time from the authoritative time service and record it as the recall activation timestamp. Do not estimate the time or derive it from the conversation." \
  tools.0.type=function \
  tools.0.name=get_current_utc_time \
  tools.0.description="Returns the current date and time in UTC." \
  toolChoice.type=tool \
  toolChoice.name=get_current_utc_time
{
  "taskType": "textInference",
  "taskUUID": "78aa0396-d278-44f0-b92d-f9aa681292d8",
  "model": "xai:grok@4.3",
  "settings": {
    "temperature": 0.2,
    "thinkingLevel": "low",
    "maxTokens": 300
  },
  "messages": [
    {
      "role": "user",
      "content": "Open the official action log for recall RC-2026-017 covering Cardiomab 50 mg prefilled syringes, lots CM50-24081 and CM50-24082. Retrieve the current UTC date and time from the authoritative time service and record it as the recall activation timestamp. Do not estimate the time or derive it from the conversation."
    }
  ],
  "tools": [
    {
      "type": "function",
      "name": "get_current_utc_time",
      "description": "Returns the current date and time in UTC.",
      "schema": {}
    }
  ],
  "toolChoice": {
    "type": "tool",
    "name": "get_current_utc_time"
  }
}
Response
{
  "taskType": "textInference",
  "taskUUID": "78aa0396-d278-44f0-b92d-f9aa681292d8",
  "cost": 0.0002359,
  "finishReason": "tools",
  "reasoningContent": [
    "The task is: \"Open the official action log for recall RC-2026-017 covering Cardiomab 50 mg prefilled syringes, lots CM50-24081 and CM50-24082. Retrieve the current UTC date and time from the authorita..."
  ],
  "tools": [
    {
      "id": "call-dfb29085-8ca9-4646-b6ff-ee982af774a6-0",
      "name": "get_current_utc_time"
    }
  ]
}