Instance grid · atlas

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 vCPU	large 2 vCPU	xlarge 4 vCPU	2xlarge 8 vCPU	4xlarge 16 vCPU	8xlarge 32 vCPU	12xlarge 48 vCPU	16xlarge 64 vCPU	24xlarge 96 vCPU	32xlarge 128 vCPU	48xlarge 192 vCPU	metal whole host
m8g Graviton4	$15	$31	$62	$124	$247	$495	$742	$990	$1.5k		$3.0k
m7g Graviton3	$14	$28	$56	$112	$225	$450	$675	$900				$900
m7gd Graviton3	$16	$33	$65	$131	$261	$522	$784	$1.0k				$1.0k
m7i Xeon Sapphire Rapids		$51	$102	$205	$409	$818	$1.2k	$1.6k	$2.5k		$4.9k
m7i-flex Xeon Sapphire Rapids		$49	$97	$194	$389	$777	$1.2k	$1.6k
m6g Graviton2	$12	$23	$47	$93	$186	$372	$559	$745				$745
m6gd Graviton2	$14	$28	$56	$111	$222	$444	$667	$889				$889
m6i Xeon Ice Lake		$49	$97	$195	$390	$779	$1.2k	$1.6k	$2.3k	$3.1k		$3.1k
m6id Xeon Ice Lake		$59	$118	$236	$471	$943	$1.4k	$1.9k	$2.8k	$3.8k		$3.8k
m6idn Xeon Ice Lake		$78	$156	$312	$624	$1.2k	$1.9k	$2.5k	$3.7k	$5.0k		$5.0k
m6in Xeon Ice Lake		$67	$133	$267	$534	$1.1k	$1.6k	$2.1k	$3.2k	$4.3k		$4.3k
m6a EPYC Milan		$27	$54	$107	$214	$428	$643	$857	$1.3k	$1.7k	$2.6k	$2.6k
m5 Xeon Skylake Newest		$47	$93	$186	$372	$743	$1.1k	$1.5k	$2.2k			$2.2k
m5d Xeon Skylake		$56	$112	$224	$449	$898	$1.3k	$1.8k	$2.7k			$2.7k
m5a EPYC Naples		$26	$51	$102	$204	$409	$613	$818	$1.2k
m5ad EPYC Naples		$31	$62	$123	$247	$493	$741	$988	$1.5k
m4 Xeon Haswell		$48	$96	$191	$382			$1.5k
Compute optimized 2 GiB memory per vCPU
	medium 1 vCPU	large 2 vCPU	xlarge 4 vCPU	2xlarge 8 vCPU	4xlarge 16 vCPU	8xlarge 32 vCPU	12xlarge 48 vCPU	16xlarge 64 vCPU	24xlarge 96 vCPU	32xlarge 128 vCPU	48xlarge 192 vCPU	metal whole host
c8g Graviton4	$13	$26	$52	$104	$209	$417	$626	$835	$1.3k		$2.5k
c7g Graviton3	$12	$24	$47	$95	$190	$380	$569	$759				$759
c7gd Graviton3	$13	$26	$53	$106	$212	$424	$636	$848				$848
c7i Xeon Sapphire Rapids		$43	$86	$173	$345	$690	$1.0k	$1.4k	$2.1k		$4.1k
c7i-flex Xeon Sapphire Rapids		$41	$82	$164	$328	$656	$983	$1.3k
c6g Graviton2	$9.78	$20	$39	$78	$157	$313	$470	$627				$627
c6gd Graviton2	$11	$23	$45	$90	$180	$361	$541	$721				$721
c6gn Graviton2	$20	$40	$80	$159	$319	$638	$957	$1.3k
c6i Xeon Ice Lake		$41	$82	$164	$329	$657	$986	$1.3k	$2.0k	$2.6k		$2.6k
c6in Xeon Ice Lake		$52	$104	$209	$417	$834	$1.3k	$1.7k	$2.5k	$3.3k		$3.3k
c6a EPYC Milan		$23	$45	$90	$181	$362	$542	$723	$1.1k	$1.4k	$2.2k	$2.2k
c5 Xeon Skylake Newest		$39	$78	$156	$312		$938		$1.9k			$1.9k
c5d Xeon Skylake		$45	$91	$182	$364		$1.1k		$2.2k			$2.2k
c5n Xeon Skylake		$50	$99	$199	$397							$1.8k
c5a EPYC Rome		$22	$43	$86	$173	$346	$519	$692	$1.0k
c4 Xeon Haswell		$50	$99	$198	$396	$791
Memory optimized 8 GiB or more memory per vCPU
	medium 1 vCPU	large 2 vCPU	xlarge 4 vCPU	2xlarge 8 vCPU	4xlarge 16 vCPU	8xlarge 32 vCPU	12xlarge 48 vCPU	16xlarge 64 vCPU	24xlarge 96 vCPU	32xlarge 128 vCPU	48xlarge 192 vCPU	metal whole host
r8g Graviton4	$20	$40	$79	$158	$317	$634	$951	$1.3k	$1.9k		$3.8k
r7g Graviton3	$18	$36	$72	$144	$288	$576	$864	$1.2k				$1.2k
r7gd Graviton3	$20	$40	$81	$162	$324	$648	$971	$1.3k				$1.3k
r7i Xeon Sapphire Rapids		$65	$131	$262	$524	$1.0k	$1.6k	$2.1k	$3.1k		$6.3k
r6g Graviton2	$15	$30	$60	$120	$239	$478	$717	$957				$957
r6gd Graviton2	$17	$34	$69	$137	$275	$550	$825	$1.1k				$1.1k
r6i Xeon Ice Lake		$62	$125	$249	$499	$998	$1.5k	$2.0k	$3.0k	$4.0k		$4.0k
r6id Xeon Ice Lake		$73	$146	$292	$584	$1.2k	$1.8k	$2.3k	$3.5k	$4.7k		$4.7k
r6a EPYC Milan		$34	$69	$137	$274	$549	$823	$1.1k	$1.6k	$2.2k	$3.3k	$3.3k
r5 Xeon Skylake Newest		$59	$119	$238	$476	$952	$1.4k	$1.9k	$2.9k			$2.9k
r5d Xeon Skylake		$69	$139	$278	$556	$1.1k	$1.7k	$2.2k	$3.3k			$3.3k
r5n Xeon Cascade Lake		$70	$141	$282	$563	$1.1k	$1.7k	$2.3k	$3.4k			$3.4k
r5a EPYC Naples		$33	$66	$131	$262	$523	$785	$1.0k	$1.6k
r5ad EPYC Naples		$38	$77	$153	$306	$611	$917	$1.2k	$1.8k
r4 Xeon Broadwell		$63	$126	$251	$503	$1.0k		$2.0k
x2idn Xeon Ice Lake								$3.1k	$4.6k	$6.2k		$6.2k
x2iedn Xeon Ice Lake			$386	$773	$1.5k	$3.1k		$6.2k	$9.3k	$12k		$12k
x1 Xeon Haswell								$3.1k		$6.1k
x1e Xeon Haswell			$384	$768	$1.5k	$3.1k		$6.1k		$12k
z1d Xeon Skylake		$90	$180	$361			$2.2k					$2.2k
Storage optimized Fast local disks attached to the host
	medium 1 vCPU	large 2 vCPU	xlarge 4 vCPU	2xlarge 8 vCPU	4xlarge 16 vCPU	8xlarge 32 vCPU	12xlarge 48 vCPU	16xlarge 64 vCPU	24xlarge 96 vCPU	32xlarge 128 vCPU	48xlarge 192 vCPU	metal whole host
im4gn Graviton2		$97	$194	$388	$776	$1.6k		$3.1k
is4gen Graviton2	$82	$163	$327	$653	$1.3k	$2.6k
i4i Xeon Ice Lake		$93	$185	$370	$740	$1.5k	$2.2k	$3.0k	$4.4k	$5.9k		$5.9k
d3 Xeon Cascade Lake Newest			$241	$482	$964	$1.9k
i3 Xeon Broadwell Newest		$89	$178	$356	$711	$1.4k		$2.8k
i3en Xeon Skylake		$128	$256	$512			$3.1k		$6.1k			$6.1k
Accelerated computing GPUs and AWS ML chips
	medium 1 vCPU	large 2 vCPU	xlarge 4 vCPU	2xlarge 8 vCPU	4xlarge 16 vCPU	8xlarge 32 vCPU	12xlarge 48 vCPU	16xlarge 64 vCPU	24xlarge 96 vCPU	32xlarge 128 vCPU	48xlarge 192 vCPU	metal whole host
g6 EPYC Milan · 24 GB per GPU			$459	$558	$755	$1.1k	$2.6k ×4	$1.9k	$3.8k ×4		$7.6k ×8
g6e EPYC Milan · 48 GB per GPU			$1.0k	$1.2k	$1.7k	$2.5k	$5.8k ×4	$4.2k	$8.3k ×4		$17k ×8
gr6 EPYC Milan · 24 GB per GPU					$878	$1.4k
g5 EPYC Rome · 24 GB per GPU			$556	$669	$897	$1.4k	$3.1k ×4	$2.3k	$4.5k ×4		$9.0k ×8
g4dn Xeon Family · 16 GB per GPU			$266	$380	$610	$1.1k	$2.0k ×4	$2.2k				$4.0k ×8
p4d Xeon Cascade Lake · 40 GB per GPU									$12k ×8
inf2 EPYC Milan · 32 GB per GPU Newest			$453			$1.2k			$3.9k ×6		$7.8k ×12
inf1 Xeon Cascade Lake			$110	$175					$2.3k ×16
Burstable Cheap baseline CPU that bursts on credits
	nano	micro	small	medium	large	xlarge	2xlarge
t4g Graviton2	$1.31	$2.56	$5.18	$10	$21	$41	$83
t3 Xeon Skylake Newest	$2.56	$5.18	$10	$21	$41	$82	$165
t3a EPYC Naples	$1.39	$2.85	$5.69	$11	$23	$45	$91
t2 Xeon Family	$2.85	$5.62	$11	$23	$45	$90	$181