atlas
On-demand1-yr3-yr
HourlyMonthly
Color by
Needs at least
Cheapest fit for any size t4g.nano at $1.460/mo

Each row is an instance family, each column a size. One step right doubles the vCPUs, the memory and the price, so the cheapest family for your workload is the lightest row.

Cheapest for its sizePriciest
General purpose 4 GiB memory per vCPU
medium 1 vCPUlarge 2 vCPUxlarge 4 vCPU2xlarge 8 vCPU4xlarge 16 vCPU8xlarge 32 vCPU12xlarge 48 vCPU16xlarge 64 vCPU24xlarge 96 vCPU32xlarge 128 vCPU48xlarge 192 vCPUmetal whole host
m8g Graviton4
$17 $33 $67 $133 $266 $533 $799 $1.1k $1.6k $3.2k
m7g Graviton3
$15 $30 $61 $121 $242 $484 $726 $968 $968
m7i Xeon Sapphire Rapids
$37 $75 $150 $299 $598 $897 $1.2k $1.8k $3.6k
m7i-flex Xeon Sapphire Rapids
$36 $71 $142 $284 $568 $852 $1.1k
m6g Graviton2
$14 $27 $54 $108 $216 $432 $648 $864 $864
m6gd Graviton2
$16 $32 $64 $127 $254 $509 $763 $1.0k $1.0k
m6i Xeon Ice Lake
$36 $71 $142 $285 $570 $854 $1.1k $1.7k $2.3k $2.3k
m6id Xeon Ice Lake
$42 $83 $167 $334 $668 $1.0k $1.3k $2.0k $2.7k $2.7k
m6idn Xeon Ice Lake
$49 $98 $196 $392 $784 $1.2k $1.6k $2.4k $3.1k $3.1k
m6in Xeon Ice Lake
$44 $87 $175 $349 $699 $1.0k $1.4k $2.1k $2.8k $2.8k
m6a EPYC Milan
$32 $64 $128 $256 $513 $769 $1.0k $1.5k $2.1k $3.1k $3.1k
m5 Xeon Skylake
Newest
$34 $67 $135 $270 $540 $810 $1.1k $1.6k $1.6k
m5d Xeon Skylake
$39 $80 $159 $318 $636 $953 $1.3k $1.9k $1.9k
m5a EPYC Naples
$30 $61 $121 $242 $485 $726 $969 $1.5k
m5ad EPYC Naples
$36 $72 $145 $290 $580 $870 $1.2k $1.7k
m4 Xeon Haswell
$35 $69 $139 $278 $1.1k
Compute optimized 2 GiB memory per vCPU
medium 1 vCPUlarge 2 vCPUxlarge 4 vCPU2xlarge 8 vCPU4xlarge 16 vCPU8xlarge 32 vCPU12xlarge 48 vCPU16xlarge 64 vCPU24xlarge 96 vCPU32xlarge 128 vCPU48xlarge 192 vCPUmetal whole host
c8g Graviton4
$14 $28 $56 $111 $223 $446 $669 $892 $1.3k $2.7k
c7g Graviton3
$13 $25 $51 $101 $203 $405 $608 $811 $811
c7gd Graviton3
$15 $31 $61 $122 $245 $489 $734 $978 $978
c7i Xeon Sapphire Rapids
$31 $63 $125 $250 $501 $751 $1.0k $1.5k $3.0k
c7i-flex Xeon Sapphire Rapids
$30 $59 $119 $238 $476 $713 $951
c6g Graviton2
$12 $23 $47 $94 $188 $375 $563 $751 $751
c6gd Graviton2
$13 $26 $52 $104 $207 $414 $621 $828 $828
c6gn Graviton2
$15 $30 $60 $120 $240 $480 $720 $960 $960
c6i Xeon Ice Lake
$30 $60 $119 $238 $477 $715 $954 $1.4k $1.9k $1.9k
c6id Xeon Ice Lake
$34 $68 $136 $272 $544 $815 $1.1k $1.6k $2.2k $2.2k
c6in Xeon Ice Lake
$33 $65 $131 $262 $523 $785 $1.0k $1.6k $2.1k $2.1k
c6a EPYC Milan
$27 $54 $107 $215 $429 $644 $858 $1.3k $1.7k $2.6k $2.6k
c5 Xeon Skylake
Newest
$28 $57 $113 $227 $680 $1.4k $1.4k
c5d Xeon Skylake
$32 $65 $129 $259 $777 $1.6k $1.6k
c5n Xeon Skylake
$31 $62 $125 $249 $1.1k
c5a EPYC Rome
$26 $53 $106 $212 $424 $636 $848 $1.3k
c4 Xeon Haswell
$36 $72 $145 $290 $580
Memory optimized 8 GiB or more memory per vCPU
medium 1 vCPUlarge 2 vCPUxlarge 4 vCPU2xlarge 8 vCPU4xlarge 16 vCPU8xlarge 32 vCPU12xlarge 48 vCPU16xlarge 64 vCPU24xlarge 96 vCPU32xlarge 128 vCPU48xlarge 192 vCPUmetal whole host
r8g Graviton4
$21 $43 $85 $170 $341 $681 $1.0k $1.4k $2.0k $4.1k
r7g Graviton3
$19 $39 $77 $155 $310 $619 $929 $1.2k $1.2k
r7gd Graviton3
$24 $47 $94 $188 $377 $753 $1.1k $1.5k $1.5k
r7i Xeon Sapphire Rapids
$48 $96 $191 $382 $765 $1.1k $1.5k $2.3k $4.6k
r6g Graviton2
$17 $35 $70 $139 $278 $557 $836 $1.1k $1.1k
r6gd Graviton2
$20 $40 $80 $159 $319 $638 $957 $1.3k $1.3k
r6i Xeon Ice Lake
$46 $91 $182 $364 $728 $1.1k $1.5k $2.2k $2.9k $2.9k
r6idn Xeon Ice Lake
$64 $128 $256 $511 $1.0k $1.5k $2.0k $3.1k $4.1k $4.1k
r6in Xeon Ice Lake
$54 $108 $216 $432 $863 $1.3k $1.7k $2.6k $3.5k $3.5k
r6a EPYC Milan
$41 $82 $164 $328 $656 $983 $1.3k $2.0k $2.6k $3.9k $3.9k
r5 Xeon Skylake
Newest
$44 $87 $174 $348 $696 $1.0k $1.4k $2.1k $2.1k
r5b Xeon Cascade Lake
$46 $92 $184 $369 $738 $1.1k $1.5k $2.2k $2.2k
r5d Xeon Skylake
$50 $100 $199 $399 $797 $1.2k $1.6k $2.4k $2.4k
r5n Xeon Cascade Lake
$46 $92 $185 $369 $738 $1.1k $1.5k $2.2k $2.2k
r5a EPYC Naples
$39 $78 $156 $313 $626 $939 $1.3k $1.9k
r5ad EPYC Naples
$45 $91 $182 $364 $726 $1.1k $1.5k $2.2k
r4 Xeon Broadwell
$46 $91 $183 $366 $732 $1.5k
x2idn Xeon Ice Lake
$1.7k $2.6k $3.4k $3.4k
x2iedn Xeon Ice Lake
$215 $429 $859 $1.7k $3.4k $5.2k $6.9k $6.9k
x1 Xeon Haswell
$1.7k $3.4k
x1e Xeon Haswell
$215 $430 $860 $1.7k $3.4k $6.9k
Storage optimized Fast local disks attached to the host
medium 1 vCPUlarge 2 vCPUxlarge 4 vCPU2xlarge 8 vCPU4xlarge 16 vCPU8xlarge 32 vCPU12xlarge 48 vCPU16xlarge 64 vCPU24xlarge 96 vCPU32xlarge 128 vCPU48xlarge 192 vCPUmetal whole host
i4g Graviton2
$57 $115 $230 $460 $920 $1.8k
im4gn Graviton2
$67 $134 $267 $534 $1.1k $2.1k
is4gen Graviton2
$51 $101 $202 $404 $808 $1.6k
i4i Xeon Ice Lake
$64 $128 $255 $510 $1.0k $1.5k $2.0k $3.1k $4.1k $4.1k
d3 Xeon Cascade Lake
Newest
$174 $347 $694 $1.4k
i3 Xeon Broadwell
Newest
$61 $123 $246 $492 $984 $2.0k
i3en Xeon Skylake
$80 $158 $318 $1.9k $3.8k $3.8k
Accelerated computing GPUs and AWS ML chips
medium 1 vCPUlarge 2 vCPUxlarge 4 vCPU2xlarge 8 vCPU4xlarge 16 vCPU8xlarge 32 vCPU12xlarge 48 vCPU16xlarge 64 vCPU24xlarge 96 vCPU32xlarge 128 vCPU48xlarge 192 vCPUmetal whole host
g6 EPYC Milan · 24 GB per GPU
$299 $364 $492 $749 $1.7k ×4$1.3k $2.5k ×4$5.0k ×8
gr6 EPYC Milan · 24 GB per GPU
$573 $910
g5 EPYC Rome · 24 GB per GPU
$352 $424 $569 $857 $2.0k ×4$1.4k $2.9k ×4$5.7k ×8
p5 EPYC Milan · 80 GB per GPU
Newest
$20k ×8
g4dn Xeon Family · 16 GB per GPU
$184 $264 $421 $762 $1.4k ×4$1.5k $2.7k ×8
p4d Xeon Cascade Lake · 40 GB per GPU
$7.9k ×8
inf1 Xeon Cascade Lake
$89 $142 $1.8k ×16
Burstable Cheap baseline CPU that bursts on credits
nano micro small medium large xlarge 2xlarge
t4g Graviton2
$1.46 $2.92 $5.84 $12 $23 $47 $93
t3 Xeon Skylake
Newest
$1.82 $3.65 $7.30 $15 $29 $59 $117
t3a EPYC Naples
$1.68 $3.28 $6.57 $13 $26 $53 $105
t2 Xeon Family
$2.04 $4.09 $8.10 $16 $32 $65 $130