Baseten GPU instances (dedicated, inference-shaped)

per GPU-hour, converted from the page's per-minute column: H100 80GB $0.10833/min = $6.50/hr; H100 MIG 40GB $0.0625 = $3.75/hr; B200 180GB $0.16633 = $9.98/hr; A100 80GB $0.06667 = $4.00/hr; L4 $0.01414 = $0.85/hr; A10G $0.02012 = $1.21/hr; T4 $0.01052 = $0.63/hr. Fetched 2026-10-03. PRICE CLASS: this is a PUBLISHED LIST PRICE - an asking rate a new customer is quoted, not a realised, discounted or negotiated transaction rate. A real bill is at or below this and typically well below it once commitments, credits and committed-use discounts are applied PERISHABLE-FIGURE STAMP (added 2026-10-04, uniform across data/supply/ so it is greppable). PRICE CLASS: PUBLISHED LIST PRICE - an asking rate a new customer is quoted, NOT a realised, discounted or negotiated transaction rate. A real bill is at or below this and typically well below it once commitments, credits and committed-use discounts apply. OBSERVED: 2026-10-03 RE-VERIFY BY: 2027-01-04 - the repo's quarterly re-verification bar. After that date this figure is presumed drifted and must be re-checked against its source before it is quoted again. A price without its observation date is noise; this stamp exists so a reader can tell a fresh figure from a stale one without reading prose. UNIT: per GPU-hour, converted from the page's per-minute column: H100 80GB $0.10833/min = $6.50/hr; H100 MIG 40GB $0.0625 = $3.75/hr; B200 180GB $0.16633 = $9.98/hr; A100 80GB $0.06667 = $4.00/hr; L4 $0.014 READING RULE: No further perishable flag is published for this figure.

lead_time_weeks is null because the quantity is structurally not applicable: on-demand cloud capacity starts on request, so there is no order-to-delivery lead time. The constraint is the price per GPU-hour and the availability snapshot, not an interval. The one caveat worth keeping: scarce tiers gate capacity behind a reservation or Capacity Block commitment (AWS caps the booking horizon at 8 weeks, source spl-aws-capacity-block-booking-horizon), and that is a commitment window, not a lead time.

EAR 742.6(a)(6)(iii)(A) + EAR 744.23/744.6 (Entity, Unverified, MEU list screening of the end user) + the advanced-computing IaaS obligations of 91 FR 1684 (consignee KYC, and management/limitation of IaaS access to the hardware)

LAYER 1, EXPORT LICENCE: under the Jan 2026 BIS rule 91 FR 1684 (effective 2026-01-15) the license review policy for advanced-computing commodities with TPP < 21,000 AND total DRAM bandwidth < 6,500 GB/s - the NVIDIA H200 and AMD MI325X are the rule's named examples - moved from PRESUMPTION OF DENIAL to CASE-BY-CASE REVIEW, but only for exports FROM THE UNITED STATES to end users located in China or Macau, and only against six exporter certifications filed via SNAP-R before shipment: (1) items below the thresholds with the count of units shipped in the US; (2) sufficient US supply, judged 'taking into account normal lead times'; (3) no diversion of global foundry capacity away from US end users; (4) aggregate China+Macau shipments <= 50% of total US end-use shipments of that product; (5) no end-user or use prohibition; (6) the consignee runs rigorous KYC. Every shipment must then pass a qualified third-party testing lab - US-headquartered, not controlled by a D:5/Macau entity, no ownership stake in any party, qualification revocable by BIS at any time - verifying TPP, total DRAM bandwidth, interconnect bandwidth and copackaged DRAM capacity. Reexports and in-country transfers of the same chips to China/Macau REMAIN PRESUMPTION OF DENIAL. LAYER 2, END-USER AND PARENT SCREENING: per BIS guidance of 2026-05-31 a licence is required where the consignee is HEADQUARTERED in Country Group D:5 (15 CFR part 740 supplement no. 1) or Macau OR whose ULTIMATE PARENT COMPANY is so headquartered - even when the consignee itself sits outside D:5/Macau. The requirement sits at EAR 742.6(a)(6)(iii)(A) for destinations outside the US, with an exception available only under the license exception at 740.2(a)(9)(ii). The destination country alone therefore never answers the question; screen the parent. LAYER 3, REMAINING LIMITS: exports to D:5/Macau-headquartered OR -parented entities stay PRESUMPTION OF DENIAL wherever the buyer sits, and the AI Diffusion Rule that would have set a country-tier structure on who could lawfully buy what was RESCINDED on 2025-05-13 and is not being enforced, so any recorded status rests on the instruments named here rather than on tiering.

The H100 rate of $6.50/GPU-hour is unremarkable - it sits above Runpod ($3.49) and Lambda ($3.99) and just under AWS p5 ($6.88) - so the honest read is that Baseten is NOT the cheapest bare H100 in this slice, and I am recording it because it is better sourced on some axes rather than cheaper. Two things it does better. First, H100 MIG 40GB at $3.75/hr: a 40GB slice of an H100 at under 60% of the full-part price is the cheapest credible way to get Hopper-class compute for a model that fits in 40GB, and no other provider in this slice publishes an MIG price at all. Second, and more architecturally interesting, 'You can deploy Baseten on your own infrastructure' - so Baseten's runtime on your own cloud commitments is an alternative to renting their fleet at their rate, which inverts the usual neocloud trade. Baseten does not charge for idle time and bills only while your model is deploying, scaling or predicting. Volume discounts exist but are Pro/Enterprise and negotiated, not published. Other regions are contact-sales. SOC 2 Type II and HIPAA certified. EXPORT CONTROL (2026-10-04, mechanism-level; sources spl-bis-2026-05-d5-guidance, spl-bis-2026-01-advanced-computing-case-by-case): renting capacity does NOT remove the export-control question, it relocates it. Providing remote access to controlled computing capability can constitute a transfer under the EAR, so the provider must screen the end user; and separately, under the 91 FR 1684 licence regime the consignee must run KYC procedures to prevent unauthorized remote access and must manage and limit IaaS access to the hardware - obligations pushed onto the customer, who must be told to implement them. For a customer headquartered or parented in Country Group D:5 or Macau the 742.6(a)(6)(iii)(A) end-user/parent test can bite even when the capacity is consumed in a permitted region. Recorded true because the underlying hardware is controlled and the provider carries the screening duty, not because access to a US region is itself restricted. LEAD TIME: null, and correct as null. For a listed on-demand instance type the provisioning delay is effectively zero - capacity is allocated per request - so a week count would be meaningless; the real gate for scarce shapes is either a quota increase or a capacity reservation, not a lead time. Where a published commitment horizon exists it IS recorded: AWS documents that a Capacity Block may be reserved with a start time up to EIGHT WEEKS in the future (source spl-aws-capacity-block-booking-horizon), which is a floor on how far ahead scarce capacity must be committed, not a wait. On-demand and Spot tiers publish no lead time at all; their constraint is availability, and the repo records that as availability=in-stock or a spot/reality note rather than as a fabricated week figure. Probe log in source spl-negative-no-oem-publishes-lead-time.