Skip to content

Amazon Web Services

Pricing page

800 listings across 212 models

Page 4 of 9. The lists below split this page's listings into those sold by Amazon Web Services, run by Amazon Web Services, or sent to Amazon Web Services by a marketplace.

Sold by Amazon Web Services

53 listings on this page sold by Amazon Web Services.

Default order. Select a score for details.

About these columns
llminfo IQ
llminfo IQ (capability index). How llminfo IQ is computed
Coding IQ
llminfo Coding IQ (coding capability, its own scale). How Coding IQ is computed
Value
Value for money. 50 means as expected for its results. Above 50, cheaper per task. How Value for money works
Yap
Tokens used per coding task vs. models with the same results. Includes agents that write code. Chattiness on maths doesn't predict it. How the Yap score works
Claude Haiku 3.5regional.anthropic.claude-3-5-haiku-20241022-v1:0 ยท 20241022 ยท regional
$0.80cache read $0.08$4.00cache write $1.00Not published by the providerNot measured
Magistral Small 2509mistral.magistral-small-2509 ยท 2509
Not enough data yet$0.50batch $0.25$1.50batch $0.75128KNot measuredNot measured
Gemma 3 27B ITgoogle.gemma-3-27b-it
$0.23batch $0.12$0.38batch $0.19128KNot measured
Llama 3.3 70B Instructus.meta.llama3-3-70b-instruct-v1:0 ยท ๐Ÿ‡บ๐Ÿ‡ธ us
$0.72batch $0.36$0.72batch $0.36128KNot measured
Mistral Largemistral.mistral-large-2402-v1:0 ยท 2402
$4.00$12.0032KNot measured
Gemma 3 12B ITgoogle.gemma-3-12b-it
$0.09batch $0.05$0.29batch $0.15128KNot measuredNot measured
Llama 3.1 70B Instructus.meta.llama3-1-70b-instruct-v1:0 ยท ๐Ÿ‡บ๐Ÿ‡ธ us
$0.72batch $0.36$0.72batch $0.36128KNot measuredNot measured
Ministral 3 3b Instructmistral.ministral-3-3b-instruct
Not enough data yet$0.10batch $0.05$0.10batch $0.05128KNot enough data yetNot measuredNot measured
Nova Proamazon.nova-pro-v1:0
Not enough data yet$0.80cache read $0.20batch $0.40$3.20batch $1.60300KNot measuredNot measured
Llama 4 Scoutus.meta.llama4-scout-17b-instruct-v1:0 ยท ๐Ÿ‡บ๐Ÿ‡ธ us
$0.17batch $0.085$0.66batch $0.3310MNot measured
Gemma 4 E2B ITbedrock_mantle/google.gemma-4-e2b
Not enough data yet$0.04batch $0.02$0.08batch $0.04128KNot enough data yetNot measuredNot measured
Nova Liteamazon.nova-lite-v1:0
$0.06cache read $0.015batch $0.03$0.24batch $0.12300KNot measured
Claude 3 Sonnetregional.anthropic.claude-3-sonnet-20240229-v1:0 ยท 20240229 ยท regional
$3.00cache read $0.30$15.00cache write $3.75Not published by the providerNot measured
Claude 2anthropic.claude-v2
Not enough data yet$8.00$24.00Not published by the providerNot enough data yetNot measured
Nova Microamazon.nova-micro-v1:0
Not enough data yet$0.035cache read $0.0088batch $0.0175$0.14batch $0.07128KNot measuredNot measured
Claude 3 Haikuregional.anthropic.claude-3-haiku-20240307-v1:0 ยท 20240307 ยท regional
$0.25$1.25Not published by the providerNot measured
Claude 2.1anthropic.claude-v2:1
Not enough data yet$8.00$24.00100KNot measuredNot measured
Llama 3.2 11B Instructmeta.llama3-2-11b-instruct-v1:0
Not enough data yet$0.16$0.16128KNot enough data yetNot measuredNot measured
Llama 2 70B Chatmeta.llama2-70b-chat-v1
Not enough data yet$1.95$2.564KNot enough data yetNot measuredNot measured
Command R+cohere.command-r-v1:0
$0.50$1.50Not published by the providerNot enough data yetNot measuredNot measured
Command R Pluscohere.command-r-plus-v1:0
Not enough data yet$3.00$15.00Not published by the providerNot measuredNot measured
Show all 53 listings

Showing 21 of 53: one listing for each model.

Run by Amazon Web Services

28 listings on this page where Amazon Web Services runs the model. Another provider sells these listings.

Default order. Select a score for details.

About these columns
llminfo IQ
llminfo IQ (capability index). How llminfo IQ is computed
Coding IQ
llminfo Coding IQ (coding capability, its own scale). How Coding IQ is computed
Value
Value for money. 50 means as expected for its results. Above 50, cheaper per task. How Value for money works
Yap
Tokens used per coding task vs. models with the same results. Includes agents that write code. Chattiness on maths doesn't predict it. How the Yap score works
Nemotron 3 Nano 30B A3Bnvidia-nemotron-3-nano-30b-a3b
ย Cortecs AIโ€”โ€”256KNot measuredNot measured
Gemma 3 27B ITamazon/google.gemma-3-27b-it
ย Eden AI$0.23$0.38128KNot measured
Llama 3.3 70B Instruct
ย Hugging Face$0.72$0.72131KNot measured
Mistral Largemistral-large-2402 ยท 2402
ย Cortecs AIโ€”โ€”32KNot measured
Gemma 3 12B ITamazon/google.gemma-3-12b-it
ย Eden AI$0.09$0.29128KNot measuredNot measured
Ministral 8Bministral-8b-2512 ยท 2512
ย Cortecs AINot enough data yetโ€”โ€”256KNot measuredNot measured
Llama 3.1 70B Instruct
ย Hugging Face$0.72$0.72131KNot measuredNot measured
Nova Pronova-pro-v1
ย Cortecs AINot enough data yetโ€”โ€”300KNot measuredNot measured
Llama 4 Scoutmeta.llama4-scout-17b-instruct-v1:0
ย Llmgateway$0.17$0.66Not published by the providerNot measured
Nova Litenova-lite-v1
ย Cortecs AIโ€”โ€”300KNot measured
Nova Micronova-micro-v1
ย Cortecs AINot enough data yetโ€”โ€”128KNot measuredNot measured
Show all 28 listings

Showing 11 of 28: one listing for each model.

Data credits: Epoch AI Benchmarking Hub, CC BY 4.0 (licence)

How this data works