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	$17	$35	$70	$139	$279	$557	$836	$1.1k	$1.7k		$3.3k
m7g Graviton3	$16	$32	$63	$127	$253	$507	$760	$1.0k				$1.0k
m7gd Graviton3	$20	$39	$79	$157	$315	$629	$944	$1.3k				$1.3k
m7i Xeon Sapphire Rapids		$39	$78	$156	$313	$626	$939	$1.3k	$1.9k		$3.8k
m7i-flex Xeon Sapphire Rapids		$37	$74	$149	$297	$595	$892	$1.2k
m6g Graviton2	$14	$28	$57	$114	$227	$454	$681	$908				$908
m6gd Graviton2	$17	$33	$67	$133	$266	$533	$799	$1.1k				$1.1k
m6i Xeon Ice Lake		$37	$75	$149	$298	$596	$894	$1.2k	$1.8k	$2.4k		$2.4k
m6a EPYC Milan		$34	$67	$134	$268	$536	$805	$1.1k	$1.6k	$2.1k	$3.2k	$3.2k
m5 Xeon Skylake Newest		$35	$71	$142	$283	$565	$848	$1.1k	$1.7k			$1.7k
m5d Xeon Skylake		$42	$83	$166	$333	$666	$999	$1.3k	$2.0k			$2.0k
m5a EPYC Naples		$32	$64	$128	$255	$510	$764	$1.0k	$1.5k
m5ad EPYC Naples		$38	$77	$153	$305	$610	$916	$1.2k	$1.8k
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	$16	$31	$63	$125	$251	$501	$752	$1.0k	$1.5k		$3.0k
c7g Graviton3	$14	$28	$57	$114	$228	$456	$684	$911				$911
c7gd Graviton3	$17	$34	$69	$137	$274	$548	$823	$1.1k				$1.1k
c7i Xeon Sapphire Rapids		$35	$70	$141	$281	$563	$844	$1.1k	$1.7k		$3.4k
c7i-flex Xeon Sapphire Rapids		$33	$67	$134	$267	$535	$802	$1.1k
hpc7a EPYC Genoa							$3.4k		$3.4k		$3.4k
c6g Graviton2	$13	$25	$50	$101	$202	$404	$605	$807				$807
c6gd Graviton2	$15	$29	$58	$116	$232	$464	$696	$928				$928
c6gn Graviton2	$19	$37	$75	$150	$300	$599	$899	$1.2k				$1.2k
c6i Xeon Ice Lake		$34	$67	$134	$268	$536	$804	$1.1k	$1.6k	$2.1k		$2.1k
c6id Xeon Ice Lake		$38	$76	$152	$305	$609	$914	$1.2k	$1.8k	$2.4k		$2.4k
c6in Xeon Ice Lake		$41	$82	$164	$328	$657	$985	$1.3k	$2.0k	$2.6k		$2.6k
hpc6id Xeon Ice Lake										$2.4k
c5 Xeon Skylake Newest		$32	$64	$128	$255		$764		$1.5k			$1.5k
c5d Xeon Skylake		$36	$72	$145	$290
c5n Xeon Skylake		$39	$78	$156	$312							$1.4k
c5a EPYC Rome		$28	$58	$115	$229	$459	$688	$918	$1.4k
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	$23	$46	$91	$183	$365	$731	$1.1k	$1.5k	$2.2k		$4.4k
r7g Graviton3	$21	$42	$83	$166	$332	$664	$996	$1.3k				$1.3k
r7gd Graviton3	$25	$50	$101	$202	$403	$806	$1.2k	$1.6k				$1.6k
r7i Xeon Sapphire Rapids		$51	$103	$205	$410	$821	$1.2k	$1.6k	$2.5k		$4.9k
r6g Graviton2	$19	$37	$74	$148	$296	$593	$889	$1.2k				$1.2k
r6gd Graviton2	$21	$43	$85	$171	$341	$682	$1.0k	$1.4k				$1.4k
r6i Xeon Ice Lake		$49	$98	$195	$391	$781	$1.2k	$1.6k	$2.3k	$3.1k		$3.1k
r6idn Xeon Ice Lake		$70	$140	$280	$560	$1.1k	$1.7k	$2.2k	$3.4k	$4.5k		$4.5k
r6in Xeon Ice Lake		$63	$126	$253	$505	$1.0k	$1.5k	$2.0k	$3.0k	$4.0k		$4.0k
r5 Xeon Skylake Newest		$47	$93	$187	$373	$747	$1.1k	$1.5k	$2.2k			$2.2k
r5d Xeon Skylake		$53	$107	$213	$426	$853	$1.3k	$1.7k	$2.6k			$2.6k
r5dn Xeon Cascade Lake		$60	$120	$239	$478	$957	$1.4k	$1.9k	$2.9k			$2.9k
r5n Xeon Cascade Lake		$54	$108	$216	$432	$864	$1.3k	$1.7k	$2.6k			$2.6k
r5a EPYC Naples		$42	$84	$168	$336	$671	$1.0k	$1.3k	$2.0k
r5ad EPYC Naples		$48	$96	$193	$386	$772	$1.2k	$1.5k	$2.3k
r4 Xeon Broadwell		$49	$99	$198	$396	$791		$1.6k
x2idn Xeon Ice Lake								$2.0k	$3.0k	$3.9k		$3.9k
x2iedn Xeon Ice Lake			$246	$492	$984	$2.0k		$3.9k	$5.9k	$7.9k		$7.9k
x1 Xeon Haswell								$2.0k		$3.9k
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		$70	$140	$281	$562	$1.1k		$2.2k
is4gen Graviton2	$53	$106	$212	$424	$848	$1.7k
i4i Xeon Ice Lake		$67	$134	$268	$537	$1.1k	$1.6k	$2.1k	$3.2k	$4.3k		$4.3k
d3 Xeon Cascade Lake Newest			$201	$404	$807	$1.6k
i3 Xeon Broadwell Newest		$64	$128	$255	$511	$1.0k		$2.0k
i3en Xeon Skylake		$83	$166	$333			$2.0k		$4.0k			$4.0k
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			$342	$416	$563	$857	$2.0k ×4	$1.4k	$2.8k ×4		$5.7k ×8
gr6 EPYC Milan · 24 GB per GPU					$655	$1.0k
g4dn Xeon Family · 16 GB per GPU			$218	$312	$499	$902	$1.6k ×4	$1.8k				$3.2k ×8
inf2 EPYC Milan · 32 GB per GPU Newest			$359			$931			$3.1k ×6		$6.1k ×12
inf1 Xeon Cascade Lake			$93	$148					$1.9k ×16
Burstable Cheap baseline CPU that bursts on credits
	nano	micro	small	medium	large	xlarge	2xlarge
t4g Graviton2	$1.46	$2.99	$5.91	$12	$24	$47	$95
t3 Xeon Skylake Newest	$1.82	$3.72	$7.45	$15	$30	$60	$119
t3a EPYC Naples	$1.68	$3.36	$6.72	$13	$27	$54	$107
t2 Xeon Family	$2.48	$4.89	$9.78	$20	$39	$78	$157