Skip to content

Amazon Web Services

Pricing page

800 listings across 212 models

Page 3 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

60 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
DeepSeek V3.1
$0.58batch $0.29$1.68batch $0.84128KNot measured
Devstral 2 123b Instruct 2512mistral.devstral-2-123b
$0.40batch $0.20$2.00batch $1.00256KNot measuredNot measured
Claude 3.5 Sonnetregional.anthropic.claude-3-5-sonnet-20240620-v1:0 Β· 20240620 Β· regional
$3.00cache read $0.30$15.00cache write $3.75Not published by the providerNot measured
Qwen3 Coderbedrock_mantle/qwen.qwen3-coder-480b-a35b-instruct
$0.45batch $0.225$1.80batch $0.90262KNot measured
MiniMax M2minimax.minimax-m2
$0.30batch $0.15$1.20batch $0.601MNot measuredNot measured
Mistral Large 3 675b Instructmistral.mistral-large-3-675b-instruct
Not enough data yet$0.50batch $0.25$1.50batch $0.75256KNot measuredNot measured
GPT OSS 120Bopenai.gpt-oss-120b-1:0
$0.15batch $0.09$0.60batch $0.36128K
Qwen3 Coder Nextqwen.qwen3-coder-next
$0.50batch $0.25$1.20batch $0.60256KNot measured
Qwen3 Next 80B A3B Instructbedrock_mantle/qwen.qwen3-next-80b-a3b-instruct
$0.14batch $0.07$1.20batch $0.60256KNot measuredNot measured
Qwen3 Coder 30B A3B Instructqwen.qwen3-coder-30b-a3b-v1:0
Not enough data yet$0.15batch $0.075$0.60batch $0.30262KNot measuredNot measured
GLM 4.7 Flashzai.glm-4.7-flash
$0.07batch $0.035$0.40batch $0.20203KNot measuredNot measured
Qwen3 32Bqwen.qwen3-32b-v1:0
$0.15batch $0.075$0.60batch $0.3033KNot measured
Nova Premier 1.0amazon.nova-premier-v1:0
Not enough data yet$2.50cache read $0.625batch $1.25$12.50batch $6.251MNot measuredNot measured
DeepSeek V3bedrock/ap-northeast-1/deepseek.v3-v1:0
$0.7017$2.0324128K
Pixtral Largemistral.pixtral-large-2502-v1:0 Β· 2502
Not enough data yet$2.00$6.00128KNot measuredNot measured
Nova 2 Liteamazon.nova-2-lite-v1:0
$0.30cache read $0.075batch $0.15$2.50batch $1.251MNot measuredNot measured
Llama 3.1 405B Instructus.meta.llama3-1-405b-instruct-v1:0 Β· πŸ‡ΊπŸ‡Έ us
$2.40$2.40128KNot measuredNot measured
Llama 4 Maverickus.meta.llama4-maverick-17b-instruct-v1:0 Β· πŸ‡ΊπŸ‡Έ us
$0.24batch $0.12$0.97batch $0.4851M
GPT OSS 20bopenai.gpt-oss-20b-1:0
$0.07batch $0.042$0.30batch $0.18128K
Claude 3 Opusregional.anthropic.claude-3-opus-20240229-v1:0 Β· 20240229 Β· regional
$15.00$75.00Not published by the providerNot measured
Embed Multilingual V3.0cohere.embed-multilingual-v3
Not enough data yet$0.10β€”512Not enough data yetNot measuredNot measured
Ministral 3 8b Instructmistral.ministral-3-8b-instruct
Not enough data yet$0.15batch $0.07$0.15batch $0.07128KNot enough data yetNot measuredNot measured
Ministral 3 14B Instructmistral.ministral-3-14b-instruct
Not enough data yet$0.20batch $0.10$0.20batch $0.10128KNot enough data yetNot measuredNot measured
Nemotron Nano 9b V2nvidia.nemotron-nano-9b-v2
Not enough data yet$0.06batch $0.03$0.23batch $0.12128KNot measuredNot measured
Show all 60 listings

Showing 24 of 60: 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
Devstral 2 123b Instruct 2512devstral-2512
Β Cortecs AIβ€”β€”256KNot measuredNot measured
MiniMax M2
Β Cortecs AIβ€”β€”400KNot measuredNot measured
GPT OSS 120B
Β Cortecs AIβ€”β€”131K
Qwen3 Coder Nextamazon/qwen.qwen3-coder-next
Β Eden AI$0.78$1.86262KNot measured
Β Cortecs AINot enough data yetβ€”β€”262KNot measuredNot measured
GLM 4.7 Flash
Β Cortecs AIβ€”β€”203KNot measuredNot measured
Ministral 14Bministral-14b-2512 Β· 2512
Β Cortecs AINot enough data yetβ€”β€”256KNot enough data yetNot measuredNot measured
Qwen3 32B
Β Cortecs AIβ€”β€”16KNot measured
Pixtral Largepixtral-large-2502 Β· 2502
Β Cortecs AINot enough data yetβ€”β€”128KNot measuredNot measured
Nova 2 Lite
Β Cortecs AIβ€”β€”1MNot measuredNot measured
Llama 4 Maverickmeta.llama4-maverick-17b-instruct-v1:0
Β Llmgateway$0.24$0.97Not published by the provider
GPT OSS 20b
Β Cortecs AIβ€”β€”131K
Show all 28 listings

Showing 12 of 28: one listing for each model.

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

How this data works