{"jtbd":{"id":"agent-backend","slug":"agent-backend","name":"Long-running agent worker backend","shortName":"Long-running agent worker backend"},"recommended":{"role":"depot_pick","id":"modal","slug":"modal","name":"Modal","website":"https://modal.com","editorialOverall":8.44,"scoreKind":"curated_estimate","scoreAsOf":"2026-10-19","price":{"available":true,"unavailableReason":null,"skus":[{"id":"modal-cpu-physical-core-usd-per-core-second","providerId":"modal","sku":"CPU physical core","unit":"usd_per_core_second","amountUsd":0.0000131,"currency":"USD","sourceUrl":"https://modal.com/pricing","asOf":"2026-10-27","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"unit_mismatch_per_core_second","priceSortEligible":false,"qualifier":"Physical core (2 vCPU). Minimum 0.125 cores.","verifiedAsOf":"2026-10-27","sourceCheck":"reconfirmed_manual","ageDays":1,"stale":false,"firstSeen":"2026-10-03","lastChanged":null,"frequentlyChanging":false},{"id":"modal-memory-usd-per-gib-second","providerId":"modal","sku":"Memory","unit":"usd_per_gib_second","amountUsd":0.00000222,"currency":"USD","sourceUrl":"https://modal.com/pricing","asOf":"2026-10-27","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"unit_mismatch_per_gib_second","priceSortEligible":false,"qualifier":"Container memory.","verifiedAsOf":"2026-10-27","sourceCheck":"reconfirmed","ageDays":1,"stale":false,"firstSeen":"2026-10-03","lastChanged":null,"frequentlyChanging":false},{"id":"modal-network-egress-usd-per-gib","providerId":"modal","sku":"Network egress","unit":"usd_per_gib","amountUsd":0.04,"currency":"USD","sourceUrl":"https://modal.com/pricing","asOf":"2026-10-27","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"unit_mismatch_per_gib","priceSortEligible":false,"qualifier":"See plan for included usage.","verifiedAsOf":"2026-10-27","sourceCheck":"reconfirmed","ageDays":1,"stale":false,"firstSeen":"2026-10-03","lastChanged":null,"frequentlyChanging":false},{"id":"modal-nvidia-a10-usd-per-gpu-second","providerId":"modal","sku":"Nvidia A10","unit":"usd_per_gpu_second","amountUsd":0.000306,"currency":"USD","sourceUrl":"https://modal.com/pricing","asOf":"2026-10-27","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"unit_mismatch_per_gpu_second","priceSortEligible":false,"qualifier":"Per-second rate shown with the per-second toggle. Not multiplied into an hour. Reconfirmed 2026-10-27 (v0.12.140): page also says 'Region selection 1.15 - 1.75x base prices' and 'Non-preemptible execution 3x base prices' (not stored as separate rows).","verifiedAsOf":"2026-10-27","sourceCheck":"reconfirmed","ageDays":1,"stale":false,"firstSeen":"2026-10-03","lastChanged":null,"frequentlyChanging":false},{"id":"modal-nvidia-a100-40gb-usd-per-gpu-second","providerId":"modal","sku":"Nvidia A100 40GB","unit":"usd_per_gpu_second","amountUsd":0.000583,"currency":"USD","sourceUrl":"https://modal.com/pricing","asOf":"2026-10-27","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"unit_mismatch_per_gpu_second","priceSortEligible":false,"qualifier":"Per-second rate shown with the per-second toggle. Not multiplied into an hour. Reconfirmed 2026-10-27 (v0.12.140): page also says 'Region selection 1.15 - 1.75x base prices' and 'Non-preemptible execution 3x base prices' (not stored as separate rows).","verifiedAsOf":"2026-10-27","sourceCheck":"reconfirmed_manual","ageDays":1,"stale":false,"firstSeen":"2026-10-03","lastChanged":null,"frequentlyChanging":false},{"id":"modal-nvidia-a100-80gb-usd-per-gpu-second","providerId":"modal","sku":"Nvidia A100 80GB","unit":"usd_per_gpu_second","amountUsd":0.000694,"currency":"USD","sourceUrl":"https://modal.com/pricing","asOf":"2026-10-27","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"unit_mismatch_per_gpu_second","priceSortEligible":false,"qualifier":"Per-second rate shown with the per-second toggle. Not multiplied into an hour. Reconfirmed 2026-10-27 (v0.12.140): page also says 'Region selection 1.15 - 1.75x base prices' and 'Non-preemptible execution 3x base prices' (not stored as separate rows).","verifiedAsOf":"2026-10-27","sourceCheck":"reconfirmed_manual","ageDays":1,"stale":false,"firstSeen":"2026-10-03","lastChanged":null,"frequentlyChanging":false},{"id":"modal-nvidia-b200-usd-per-gpu-second","providerId":"modal","sku":"Nvidia B200","unit":"usd_per_gpu_second","amountUsd":0.001736,"currency":"USD","sourceUrl":"https://modal.com/pricing","asOf":"2026-10-27","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"unit_mismatch_per_gpu_second","priceSortEligible":false,"qualifier":"Per-second rate shown with the per-second toggle. Not multiplied into an hour. Reconfirmed 2026-10-27 (v0.12.140): page also says 'Region selection 1.15 - 1.75x base prices' and 'Non-preemptible execution 3x base prices' (not stored as separate rows).","verifiedAsOf":"2026-10-27","sourceCheck":"reconfirmed","ageDays":1,"stale":false,"firstSeen":"2026-10-03","lastChanged":null,"frequentlyChanging":false},{"id":"modal-nvidia-b300-usd-per-gpu-second","providerId":"modal","sku":"Nvidia B300","unit":"usd_per_gpu_second","amountUsd":0.001972,"currency":"USD","sourceUrl":"https://modal.com/pricing","asOf":"2026-10-27","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"unit_mismatch_per_gpu_second","priceSortEligible":false,"qualifier":"Per-second rate shown with the per-second toggle. Not multiplied into an hour. Reconfirmed 2026-10-27 (v0.12.140): page also says 'Region selection 1.15 - 1.75x base prices' and 'Non-preemptible execution 3x base prices' (not stored as separate rows).","verifiedAsOf":"2026-10-27","sourceCheck":"reconfirmed","ageDays":1,"stale":false,"firstSeen":"2026-10-03","lastChanged":null,"frequentlyChanging":false},{"id":"modal-nvidia-h100-sxm5-usd-per-gpu-second","providerId":"modal","sku":"Nvidia H100 SXM5","unit":"usd_per_gpu_second","amountUsd":0.001097,"currency":"USD","sourceUrl":"https://modal.com/pricing","asOf":"2026-10-27","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"unit_mismatch_per_gpu_second","priceSortEligible":false,"qualifier":"Per-second rate shown with the per-second toggle. Not multiplied into an hour. Reconfirmed 2026-10-27 (v0.12.140): page also says 'Region selection 1.15 - 1.75x base prices' and 'Non-preemptible execution 3x base prices' (not stored as separate rows).","verifiedAsOf":"2026-10-27","sourceCheck":"reconfirmed","ageDays":1,"stale":false,"firstSeen":"2026-10-03","lastChanged":null,"frequentlyChanging":false},{"id":"modal-nvidia-h200-sxm-usd-per-gpu-second","providerId":"modal","sku":"Nvidia H200 SXM","unit":"usd_per_gpu_second","amountUsd":0.001261,"currency":"USD","sourceUrl":"https://modal.com/pricing","asOf":"2026-10-27","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"unit_mismatch_per_gpu_second","priceSortEligible":false,"qualifier":"Per-second rate shown with the per-second toggle. Not multiplied into an hour. Reconfirmed 2026-10-27 (v0.12.140): page also says 'Region selection 1.15 - 1.75x base prices' and 'Non-preemptible execution 3x base prices' (not stored as separate rows).","verifiedAsOf":"2026-10-27","sourceCheck":"reconfirmed","ageDays":1,"stale":false,"firstSeen":"2026-10-03","lastChanged":null,"frequentlyChanging":false},{"id":"modal-nvidia-l4-usd-per-gpu-second","providerId":"modal","sku":"Nvidia L4","unit":"usd_per_gpu_second","amountUsd":0.000222,"currency":"USD","sourceUrl":"https://modal.com/pricing","asOf":"2026-10-27","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"unit_mismatch_per_gpu_second","priceSortEligible":false,"qualifier":"Per-second rate shown with the per-second toggle. Not multiplied into an hour. Reconfirmed 2026-10-27 (v0.12.140): page also says 'Region selection 1.15 - 1.75x base prices' and 'Non-preemptible execution 3x base prices' (not stored as separate rows).","verifiedAsOf":"2026-10-27","sourceCheck":"reconfirmed","ageDays":1,"stale":false,"firstSeen":"2026-10-03","lastChanged":null,"frequentlyChanging":false},{"id":"modal-nvidia-l40s-usd-per-gpu-second","providerId":"modal","sku":"Nvidia L40S","unit":"usd_per_gpu_second","amountUsd":0.000542,"currency":"USD","sourceUrl":"https://modal.com/pricing","asOf":"2026-10-27","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"unit_mismatch_per_gpu_second","priceSortEligible":false,"qualifier":"Per-second rate shown with the per-second toggle. Not multiplied into an hour. Reconfirmed 2026-10-27 (v0.12.140): page also says 'Region selection 1.15 - 1.75x base prices' and 'Non-preemptible execution 3x base prices' (not stored as separate rows).","verifiedAsOf":"2026-10-27","sourceCheck":"reconfirmed","ageDays":1,"stale":false,"firstSeen":"2026-10-03","lastChanged":null,"frequentlyChanging":false},{"id":"modal-nvidia-rtx-pro-6000-usd-per-gpu-second","providerId":"modal","sku":"Nvidia RTX PRO 6000","unit":"usd_per_gpu_second","amountUsd":0.000842,"currency":"USD","sourceUrl":"https://modal.com/pricing","asOf":"2026-10-27","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"unit_mismatch_per_gpu_second","priceSortEligible":false,"qualifier":"Per-second rate shown with the per-second toggle. Not multiplied into an hour. Reconfirmed 2026-10-27 (v0.12.140): page also says 'Region selection 1.15 - 1.75x base prices' and 'Non-preemptible execution 3x base prices' (not stored as separate rows).","verifiedAsOf":"2026-10-27","sourceCheck":"reconfirmed","ageDays":1,"stale":false,"firstSeen":"2026-10-03","lastChanged":null,"frequentlyChanging":false},{"id":"modal-nvidia-t4-usd-per-gpu-second","providerId":"modal","sku":"Nvidia T4","unit":"usd_per_gpu_second","amountUsd":0.000164,"currency":"USD","sourceUrl":"https://modal.com/pricing","asOf":"2026-10-27","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"unit_mismatch_per_gpu_second","priceSortEligible":false,"qualifier":"Per-second rate shown with the per-second toggle. Not multiplied into an hour. Reconfirmed 2026-10-27 (v0.12.140): page also says 'Region selection 1.15 - 1.75x base prices' and 'Non-preemptible execution 3x base prices' (not stored as separate rows).","verifiedAsOf":"2026-10-27","sourceCheck":"reconfirmed","ageDays":1,"stale":false,"firstSeen":"2026-10-03","lastChanged":null,"frequentlyChanging":false},{"id":"modal-sandbox-cpu-usd-per-core-second","providerId":"modal","sku":"Sandbox CPU","unit":"usd_per_core_second","amountUsd":0.00003942,"currency":"USD","sourceUrl":"https://modal.com/pricing","asOf":"2026-10-27","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"unit_mismatch_per_core_second","priceSortEligible":false,"qualifier":"Modal Sandbox rate (page: 'Modal Sandbox pricing', 'CPU (non-preemptible)'; 'Sandboxes are billed at non-preemptible rates of 3x list price'), separate from the default CPU rate.","verifiedAsOf":"2026-10-27","sourceCheck":"reconfirmed_manual","ageDays":1,"stale":false,"firstSeen":"2026-10-03","lastChanged":null,"frequentlyChanging":false},{"id":"modal-sandbox-memory-usd-per-gib-second","providerId":"modal","sku":"Sandbox memory","unit":"usd_per_gib_second","amountUsd":0.00000667,"currency":"USD","sourceUrl":"https://modal.com/pricing","asOf":"2026-10-27","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"unit_mismatch_per_gib_second","priceSortEligible":false,"qualifier":"Sandbox memory (page: 'Memory (non-preemptible)' under 'Modal Sandbox pricing').","verifiedAsOf":"2026-10-27","sourceCheck":"reconfirmed_manual","ageDays":1,"stale":false,"firstSeen":"2026-10-03","lastChanged":null,"frequentlyChanging":false},{"id":"modal-team-plan-usd-per-month","providerId":"modal","sku":"Team plan","unit":"usd_per_month","amountUsd":250,"currency":"USD","sourceUrl":"https://modal.com/pricing","asOf":"2026-10-27","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"unit_mismatch_per_month","priceSortEligible":false,"qualifier":"Plus compute. $100/mo credits not subtracted.","verifiedAsOf":"2026-10-27","sourceCheck":"reconfirmed","ageDays":1,"stale":false,"firstSeen":"2026-10-03","lastChanged":null,"frequentlyChanging":false},{"id":"modal-volumes-usd-per-gib-month","providerId":"modal","sku":"Volumes","unit":"usd_per_gib_month","amountUsd":0.09,"currency":"USD","sourceUrl":"https://modal.com/pricing","asOf":"2026-10-27","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"unit_mismatch_per_gib_month","priceSortEligible":false,"qualifier":"Includes 1 TiB/mo free, not folded into this rate.","verifiedAsOf":"2026-10-27","sourceCheck":"reconfirmed","ageDays":1,"stale":false,"firstSeen":"2026-10-03","lastChanged":null,"frequentlyChanging":false}],"normalizedUsdPerMillionTokens":null,"normalizationStatus":"unit_mismatch","normalizationReason":"unit_mismatch"}},"priceComparison":{"skuKind":"none","unit":null,"comparison":"no comparable sourced unit for this job; chat input $/1M and other units were not borrowed","amountLabel":"Matching price","reportsUsdPerMillion":false,"matchedCandidates":0},"cheapestInput":null,"cheapest":null,"recommendedWorkloadQuote":{"providerId":"modal","providerName":"Modal","skuId":"modal-nvidia-t4-usd-per-gpu-second","item":"Nvidia T4","plan":"Nvidia T4 — Per-second rate shown with the per-second toggle","unit":"usd_per_gpu_second","amountUsd":0.000164,"outputSkuId":null,"outputItem":null,"outputAmountUsd":null,"outputUnit":null,"sourceUrl":"https://modal.com/pricing","asOf":"2026-10-27","pricingLastVerifiedAt":"2026-10-27","isFlagshipForJob":false,"differsFromFloorCheapest":false,"representativeQuote":{"skuId":"modal-nvidia-t4-usd-per-gpu-second","item":"Nvidia T4","plan":"Nvidia T4 — Per-second rate shown with the per-second toggle","amountUsd":0.000164,"inputOrUnitUsd":0.000164,"unit":"usd_per_gpu_second","outputUsd":null,"outputUnit":null,"sourceUrl":"https://modal.com/pricing","asOf":"2026-10-27"},"estimatedTaskCost":{"tasks":1000,"retryAndToolOverheadMultiplier":1.15,"retryToolOverheadMultiplier":1.15,"unitsPerTask":1,"baseCostPer1kTasksUsd":0.0002,"totalUsd":0.0002,"estimatedTotalUsd":0.0002,"perTaskUsd":0,"estimatedCostPerTaskUsd":0,"formula":"$0.000164 (usd_per_gpu_second) * 1.15 overhead","assumptions":"1,000 tasks in job native unit with 1.15x retry overhead."}},"representativeQuote":{"skuId":"modal-nvidia-t4-usd-per-gpu-second","item":"Nvidia T4","plan":"Nvidia T4 — Per-second rate shown with the per-second toggle","amountUsd":0.000164,"inputOrUnitUsd":0.000164,"unit":"usd_per_gpu_second","outputUsd":null,"outputUnit":null,"sourceUrl":"https://modal.com/pricing","asOf":"2026-10-27"},"estimatedTaskCost":{"tasks":1000,"retryAndToolOverheadMultiplier":1.15,"retryToolOverheadMultiplier":1.15,"unitsPerTask":1,"baseCostPer1kTasksUsd":0.0002,"totalUsd":0.0002,"estimatedTotalUsd":0.0002,"perTaskUsd":0,"estimatedCostPerTaskUsd":0,"formula":"$0.000164 (usd_per_gpu_second) * 1.15 overhead","assumptions":"1,000 tasks in job native unit with 1.15x retry overhead."},"cheapestGoodEnough":{"band":{"rule":"editorial overall >= Depot Pick overall - 0.5","minOverall":7.94,"pickOverall":8.44,"points":0.5},"pick":null,"reason":"no_matching_sourced_price","cheaperButBelowBand":[]},"dates":{"scoreAsOf":"2026-10-19","scoreKind":"curated_estimate","priceVerifiedAsOf":"2026-10-27","note":"scoreAsOf is when the editorial score was last set; priceVerifiedAsOf is the newest fact-check of the pick's price rows. They are separate: a fresh price check does not re-score."},"sourcedInputs":[],"pickIsPriceWinner":null,"priceWinnerReason":"no_comparison_no_candidate_has_matching_sourced_price","priceWinnerNote":"Nothing was compared. no comparable sourced unit for this job; chat input $/1M and other units were not borrowed pickIsPriceWinner is null.","excluded":11,"coverage":{"candidates":16,"withAnySourcedRow":5,"withSourcedInputUsdPerMillion":0,"withMatchingPrice":0,"excludedNoSourcedPrice":11,"excludedFromCheapestInput":16},"normalizedUsdPerMillionTokens":null,"normalizationReason":"input_and_output_are_not_blended","seo":{"published":false,"reason":"Only 0 candidate(s) have a matching Matching price (none). Need 3 before a crawlable price section. Quote JSON is still returned."},"cite":"Depot Pick for agent-backend: modal (asOf 2026-10-19). See GET /api/jtbds/agent-backend + GET /api/methodology.","asOf":"2026-10-27","honesty":["Recommended provider is the current Depot Pick from GET /api/decide. This quote does not change scores.","SKU rows are copied from data/pricing-rows.json via GET /api/pricing. No new pages were scraped for this response.","normalizedUsdPerMillionTokens on this quote is always null. Input and output stay on separate rows.","cheapestInput compares one native unit that matches this job. Chat and coding jobs use priceSortEligible input $/1M. Embedding jobs use embedding SKUs only. Speech-to-text uses a stored speech unit only (per minute when that unit exists; a voice-agent hosting minute and a speech-engine minute are not speech-to-text). Speech synthesis uses one stored TTS unit in preference order (per minute, then per 1k characters, then per million characters) and does not mix those units or a speech-engine minute. Hosted-browser jobs compare usd_per_browser_hour only (lowest tier per provider, not quality-adjusted); proxy per GB, CAPTCHA solves, monthly plans, and chat tokens are not included. Sandbox, code-interpreter, ephemeral CI, and persistent dev env compare usd_per_vcpu_hour only, and only when the Depot Pick has that row; GPU-hour, GiB-hour, and vCPU-second are not converted. Secret jobs compare identity-month or user-month, never both; if both are stored, cheapestInput is null (mixed_secret_units). Voice-agent platform jobs compare a voice-agent hosting minute only. Transactional email compares usd_per_1k_emails only. Marketing email compares usd_per_1k_emails when a non-transactional per-1k SKU exists; otherwise it ranks a marketing-labeled usd_per_email and does not convert that rate to per 1k or mix it with per-1k. Monthly plans are not a unit price (plan_not_a_unit_price). Outbound and inbound webhook jobs compare usd_per_message only. Queue jobs compare usd_per_100k_messages or usd_per_million_events, never both (mixed_units). Push does not rank MAU or monthly plans. Error observability ranks a unit only when every candidate shares it; per-error fractions are not ranked against monthly plans. MotherDuck CU-hours and flight hours are not vCPU-hours. Composio's unsplit sandbox token rate is not chat $/1M. CAPTCHA SKUs are not ranked. Other non-token jobs do not borrow a chat $/1M rate. If nothing matches, cheapestInput is null.","excluded counts candidates with zero sourced pricing rows. excludedFromCheapestInput also counts candidates whose rows are a different unit than this job.","A Depot Pick is not a price winner unless its matching sourced price is the lowest among candidates. The comparison is not quality-adjusted. pickIsPriceWinner is null (not false) when nothing was compared."],"links":{"decide":"/api/decide?jtbd=agent-backend","quote":"/api/quote?jtbd=agent-backend","pricing":"/api/pricing?provider=modal","leaderboardPrice":"/api/leaderboards?jtbd=agent-backend&sort=price","humanPage":"/jtbds/agent-backend#quote","methodology":"/api/methodology"},"sourceConflicts":[{"providerId":"railway","field":"Volume storage rate and billing granularity","sourceUrl":"https://railway.com/pricing","asOf":"2026-10-22","quotes":["Volumes $ 0.00000006 per GB / sec (https://railway.com/pricing; 'Pay only for what your app uses, by the second')","| [**Volume Storage**](/volumes) | $0.15 / GB / month ($0.000003472222222 / GB / minute) | (https://docs.railway.com/pricing/plans)","You're billed by the minute for compute resources, so you only pay for what you use. (https://docs.railway.com/pricing)"],"safeAssumption":"Price volumes at the docs' $0.15 per GB-month (its per-minute figure, $0.000003472222222, equals $0.15 over a 30-day month; the page's $0.00000006 per GB-second is that rate rounded up, about 4% higher over a month). CPU and RAM use the page's per-second rates, which equal the docs' per-minute and per-month rates within 0.1%. Whether compute is metered per second (page) or per minute (docs) changes nothing for monthly totals sent as seconds."},{"providerId":"railway","field":"Hobby replica limit","sourceUrl":"https://railway.com/pricing","asOf":"2026-10-22","quotes":["Hobby … Up to 5 replicas, at 8 vCPU / 8 GB RAM per replica (https://railway.com/pricing)","| **Hobby**      | **6**        | **48 GB**    | **48 vCPU**    | (Replicas column, https://docs.railway.com/pricing/plans)"],"safeAssumption":"Not used in any cost: replica counts are per-service ceilings, not billed meters. Check the dashboard before relying on a 6th Hobby replica."},{"providerId":"render","field":"Plan name for the Performance build pipeline (Pro vs Professional)","sourceUrl":"https://render.com/pricing","asOf":"2026-10-22","quotes":["Hobby Pro Scale Enterprise … $25/mo + compute (tier cards, https://render.com/pricing)","With a Professional plan or higher, you can enable the Performance pipeline to run builds on larger compute instances (FAQ 'What are build pipeline minutes, and how can I track my usage?', same page)","Performance 16 CPU 64 GB RAM Requires a Pro plan or higher. (https://render.com/docs/build-pipeline)"],"safeAssumption":"Treat 'Professional' as the Pro workspace plan ($25/mo); the docs and the comparison table say Pro. Performance pipeline minutes are not costed in any plan, so no estimate depends on this."},{"providerId":"fly-io","field":"Machine per-hour vs per-month price (month length and rounding)","sourceUrl":"https://fly.io/pricing","asOf":"2026-10-22","quotes":["shared-cpu-1x · 256MB $0.0030 $2.19 (Per hour, Per month, https://fly.io/pricing): $0.0030 × 720 h = $2.16, × 730 h = $2.19","performance-16x · 32GB $0.7334 $528.02 (same table): $0.7334 × 720 h = $528.05, × 730 h = $535.38","Monthly Machine prices assume 30 days of continuous runtime. (https://fly.io/docs/about/pricing/)","Per-month figures are the hourly rate over a 730-hour month. (Sprites storage, https://fly.io/pricing)"],"safeAssumption":"The per-hour column is rounded to 4 decimals; the per-month column matches a 30-day (720 h) month for performance presets, as the docs state. Depot prices Machine-months at the per-month figure (30 days) and never multiplies the rounded hourly figure; the 730-hour month applies to Sprites only (not encoded)."},{"providerId":"fly-io","field":"Which region an egress GB is priced in (source vs destination)","sourceUrl":"https://fly.io/pricing","asOf":"2026-10-22","quotes":["A region's price is the Ashburn price above times its multiplier, applied to vCPU and RAM. Volumes and snapshots do not take this markup, and egress is priced by destination rather than by the Machine's region. (https://fly.io/pricing, markdown rendering fetched 2026-10-22)","100GB outbound data from iad and fra at $0.02/GB (assumed) … 50GB outbound data from sin at $0.04/GB (assumed) (https://fly.io/docs/about/pricing/ example)","The request is billed at the rate for the region it leaves, and the response at the rate for the region it leaves. (https://fly.io/docs/about/pricing/, cross-region private network)"],"safeAssumption":"Depot does not pick a region group: callers put each GB in fly_egress_gb_na_eu, fly_egress_gb_apac_oc_sa or fly_egress_gb_af_in themselves. When unsure, price the GB at the higher of the source and destination groups."},{"providerId":"fly-io","field":"shared-cpu-1x 1GB monthly price (docs list vs preset + extra RAM)","sourceUrl":"https://fly.io/docs/about/pricing/","asOf":"2026-10-22","quotes":["Started Machine, shared-cpu-1x with 1GB RAM $6.70/month (https://fly.io/docs/about/pricing/)","shared-cpu-1x · 256MB $0.0030 $2.19 … every one takes more RAM at $6.00 per GB per month (https://fly.io/pricing): $2.19 + 0.75 GB × $6.00 = $6.69"],"safeAssumption":"A 1¢ rounding gap. Depot costs shared-cpu-1x · 256MB + 0.75 extra RAM GB-months = $6.69 and treats the docs' $6.70 as the same price rounded."}],"volumeEstimateHint":"Add &volume=<number> for a plan-level monthly cost (GET /api/estimate?jtbd=agent-backend&workload=...)"}