I launched a GA EC2 T8i instance in the Tokyo region and checked CPU information and other details
This page has been translated by machine translation. View original
Introduction
On September 17, 2026, Amazon EC2 T8i instances, the new generation of low-cost burstable instances, became generally available and can now be used in the Tokyo region as well.
Launching an Instance
For verification, I launched a t8i.small in the Tokyo region (ap-northeast-1) using the Amazon Linux 2023 AMI al2023-ami-2023.12.20260917.1-kernel-6.18-x86_64 (as of 2026-09-18).
Verification Environment
The CPU information below was obtained in the following environment. These are values confirmed from uname -r and /etc/os-release.
kernel: 6.18.48-107.148.amzn2023.x86_64
PRETTY_NAME="Amazon Linux 2023.12.20260917"
CPU Information
I connected via SSM Session Manager and ran lscpu.
Architecture: x86_64
CPU op-mode(s): 32-bit, 64-bit
Address sizes: 48 bits physical, 48 bits virtual
Byte Order: Little Endian
CPU(s): 2
On-line CPU(s) list: 0,1
Vendor ID: GenuineIntel
BIOS Vendor ID: Intel(R) Corporation
Model name: Intel(R) Xeon(R) 6975P-C
BIOS Model name: Intel(R) Xeon(R) 6975P-C
CPU family: 6
Model: 173
Thread(s) per core: 2
Core(s) per socket: 1
Socket(s): 1
Stepping: 1
BogoMIPS: 5400.00
Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ss ht syscall nx pdpe1gb rdtscp lm constant_tsc rep_good nopl xtopology nonstop_tsc cpuid tsc_known_freq pni pclmulqdq ssse3 fma cx16 pdcm pcid sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand hypervisor lahf_lm abm 3dnowprefetch cpuid_fault ssbd ibrs ibpb stibp ibrs_enhanced fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves avx_vnni avx512_bf16 wbnoinvd ida arat avx512vbmi umip pku ospke waitpkg avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg tme avx512_vpopcntdq rdpid bus_lock_detect cldemote movdiri movdir64b md_clear serialize amx_bf16 avx512_fp16 amx_tile amx_int8 flush_l1d arch_capabilities
Hypervisor vendor: KVM
Virtualization type: full
L1d cache: 48 KiB (1 instance)
L1i cache: 64 KiB (1 instance)
L2 cache: 2 MiB (1 instance)
L3 cache: 480 MiB (1 instance)
NUMA node(s): 1
NUMA node0 CPU(s): 0,1
Vulnerability Gather data sampling: Not affected
Vulnerability Ghostwrite: Not affected
Vulnerability Indirect target selection: Not affected
Vulnerability Itlb multihit: Not affected
Vulnerability L1tf: Not affected
Vulnerability Mds: Not affected
Vulnerability Meltdown: Not affected
Vulnerability Mmio stale data: Not affected
Vulnerability Old microcode: Not affected
Vulnerability Reg file data sampling: Not affected
Vulnerability Retbleed: Not affected
Vulnerability Spec rstack overflow: Not affected
Vulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl
Vulnerability Spectre v1: Mitigation; usercopy/swapgs barriers and __user pointer sanitization
Vulnerability Spectre v2: Mitigation; Enhanced / Automatic IBRS; IBPB conditional; PBRSB-eIBRS Not affected; BHI BHI_DIS_S
Vulnerability Srbds: Not affected
Vulnerability Tsa: Not affected
Vulnerability Tsx async abort: Not affected
Vulnerability Vmscape: Not affected
The Model name field alone does not reveal the generation, but the official blog describes the T8i processor as a custom 6th-generation Intel Xeon Scalable (Granite Rapids). The Xeon 6975P-C shown here corresponds to that custom part number.
Pricing
I retrieved T8i and T3 pricing for ap-northeast-1 via the Pricing API and placed the same sizes side by side. vCPU and memory are from DescribeInstanceTypes (confirmed 2026-09-18), pricing is for Linux On-Demand as of 2026-09-18. Monthly cost is calculated at 720 hours (excluding taxes, data transfer, EBS, etc.).
| Size | vCPU | Memory | T8i (USD/hr) | T3 (USD/hr) | vs T3 | T8i Monthly (720 hrs) | T3 Monthly (720 hrs) |
|---|---|---|---|---|---|---|---|
| nano | 2 | 0.5 GiB | 0.00816 | 0.0068 | +20.0% | 5.88 | 4.90 |
| micro | 2 | 1 GiB | 0.01632 | 0.0136 | +20.0% | 11.75 | 9.79 |
| small | 2 | 2 GiB | 0.03264 | 0.0272 | +20.0% | 23.50 | 19.58 |
| medium | 2 | 4 GiB | 0.06528 | 0.0544 | +20.0% | 47.00 | 39.17 |
The vCPU and memory configurations are the same as T3. Since the ratio is uniform across all four sizes from nano to medium, replacing T3 with T8i at the same size within this range will result in a 20% price increase regardless of which size you choose.
Comparing the same T8i between ap-northeast-1 and us-east-1 yields the following (Linux, On-Demand, as of 2026-09-18).
| Size | ap-northeast-1 (USD/hr) | us-east-1 (USD/hr) | vs us-east-1 |
|---|---|---|---|
| nano | 0.00816 | 0.00624 | +30.8% |
| micro | 0.01632 | 0.01248 | +30.8% |
| small | 0.03264 | 0.02496 | +30.8% |
| medium | 0.06528 | 0.04992 | +30.8% |
Summary
T8i has become generally available and can now be used in the Tokyo region, although availability is limited to certain regions.
The "8" in T8i is the 8th-generation Intel generation number shared with M8i, C8i, and R8i. The t8i.small launched this time was assigned the Intel(R) Xeon(R) 6975P-C, which has also been confirmed in M8i instances.
For workloads that use M8i or similar instances in production, T8i—which shares the same CPU and Nitro generation—can be introduced on a small scale for development and verification environments. It is also a strong option when you want to verify compatibility of applications, middleware, and extended drivers such as ENA on an execution platform close to production.
The on-demand pricing for nano through medium confirmed in the Tokyo region this time is 20% higher than T3 at the same size. AWS states that T8i offers up to 30% better price-performance and up to 70% better compute performance compared to T3. If you are experiencing issues with T3 such as slow build times, give it a try to see if the 20% cost increase is worthwhile.
