Skip to content

Listings

All listings: Amazon Web Services

Every listing for the models on page 5 of 9 of Amazon Web Services, including each model's other versions and routes. Back to Amazon Web Services

Sold by Amazon Web Services

30 listings on this page sold by Amazon Web Services.

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
Modelllminfo IQCoding IQInput $/1MOutput $/1MMax Input TokensValueEpoch Capabilities Index
Gemma 3 4B IT
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
google.gemma-3-4b-it
95.2
From 249 benchmarks. Plenty of data behind it.
67 ±19
Coding IQ 66.8, 95% interval 48–86. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.04batch $0.02$0.08batch $0.04128K
38.3
Poor value (38.3). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measured
Titan Text Embeddings V2
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
amazon.titan-embed-text-v2:0
Not enough data yetNot enough data yet$0.02—8KNot enough data yetNot measured
Titan Text Embeddings V2
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
amazon.titan-embed-text-v2:0:8k · 8k
Not enough data yetNot enough data yet——Not published by the providerNot enough data yetNot measured
Voxtral Mini 3B 2507
🇫🇷
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
mistral.voxtral-mini-3b-2507
Not enough data yetNot enough data yet$0.04batch $0.02$0.04batch $0.0233KNot enough data yetNot measured
nova-sonic-v1
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
amazon.nova-sonic-v1:0
Not enough data yetNot enough data yet$0.06$0.24Not published by the providerNot enough data yetNot measured
Embed English V3.0
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
cohere.embed-english-v3
Not enough data yetNot enough data yet$0.10—512Not enough data yetNot measured
Embed English V3.0
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
cohere.embed-english-v3:0:512 · 512
Not enough data yetNot enough data yet——Not published by the providerNot enough data yetNot measured
Titan Embed G1 Text 02
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
amazon.titan-embed-g1-text-02
Not enough data yetNot enough data yet$0.10—8KNot enough data yetNot measured
Titan Embeddings G1 - Text
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionTitan Text Embeddings V2We compared the version names in our catalogue.
amazon.titan-embed-text-v1
Not enough data yetNot enough data yet$0.10—8KNot enough data yetNot measured
Titan Embeddings G1 - Text
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionTitan Text Embeddings V2We compared the version names in our catalogue.
amazon.titan-embed-text-v1:2:8k · 8k
Not enough data yetNot enough data yet——Not published by the providerNot enough data yetNot measured
Voxtral Small 24B
🇫🇷
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
mistral.voxtral-small-24b-2507 · 2507
Not enough data yetNot enough data yet$0.10batch $0.05$0.30batch $0.1533K
51.5
Fair value (51.5). Costs per task about what its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measured
Embed v4
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
cohere.embed-v4:0
Not enough data yetNot enough data yet$0.12—128KNot enough data yetNot measured
Embed v4
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
eu.cohere.embed-v4:0 · 🇪🇺 eu
Not enough data yetNot enough data yet$0.12—128KNot enough data yetNot measured
Embed v4
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
global.cohere.embed-v4:0 · global
Not enough data yetNot enough data yet$0.12—128KNot enough data yetNot measured
Embed v4
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
us.cohere.embed-v4:0 · 🇺🇸 us
Not enough data yetNot enough data yet$0.12—128KNot enough data yetNot measured
titan-text-lite-v1
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
amazon.titan-text-lite-v1
Not enough data yetNot enough data yet$0.15$0.2042KNot enough data yetNot measured
Nova 2 Multimodal Embeddings v1
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
amazon.nova-2-multimodal-embeddings-v1:0
Not enough data yetNot enough data yet$0.162batch $0.081—8KNot enough data yetNot measured
titan-text-express-v1
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
amazon.titan-text-express-v1
Not enough data yetNot enough data yet$0.20$0.6042KNot enough data yetNot measured
command-light-text-v14
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
cohere.command-light-text-v14
Not enough data yetNot enough data yet$0.30$0.604KNot enough data yetNot measured
Nova 2.5 Sonic
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
amazon.nova-2-5-sonic
Not enough data yetNot enough data yet$0.33$2.75256KNot enough data yetNot measured
Nova 2 Sonic v1
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
amazon.nova-2-sonic-v1:0
Not enough data yetNot enough data yet$0.33$2.751MNot enough data yetNot measured
Jamba Instruct
🇮🇱
Maker headquartered in IL, according to the company's own website. The citation is on the model page.
ai21.jamba-instruct-v1:0
Not enough data yetNot enough data yet$0.50$0.7070KNot enough data yetNot measured
titan-text-premier-v1
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
amazon.titan-text-premier-v1:0
Not enough data yetNot enough data yet$0.50$1.5042KNot enough data yetNot measured
claude-instant
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
anthropic.claude-instant-v1
Not enough data yetNot enough data yet$0.80$2.40100KNot enough data yet
114
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
claude-instant
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Not enough data yetNot enough data yet$0.80$2.40Not published by the providerNot enough data yet
114
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Titan Multimodal Embeddings G1
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
amazon.titan-embed-image-v1
Not enough data yetNot enough data yet$0.80$25.00128Not enough data yetNot measured
Titan Multimodal Embeddings G1
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
amazon.titan-embed-image-v1:0
Not enough data yetNot enough data yet——Not published by the providerNot enough data yetNot measured
command-text-v14
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
cohere.command-text-v14
Not enough data yetNot enough data yet$1.00$2.004KNot enough data yetNot measured
Mistral Small 2402 v1
🇫🇷
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
mistral.mistral-small-2402-v1:0
Not enough data yetNot enough data yet$1.00batch $0.50$3.00batch $1.5032KNot enough data yetNot measured
Claude Haiku 4.5 (India)
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
in.anthropic.claude-haiku-4-5-20251001-v1:0 · 20251001
Not enough data yetNot enough data yet$1.10cache read $0.11$5.50cache write $1.375200KNot enough data yetNot measured

Run by Amazon Web Services

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

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
ModelProviderllminfo IQCoding IQInput $/1MOutput $/1MMax Input TokensValueEpoch Capabilities Index
Llama 3.1 8B Instruct
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
Newer version
Newer versionLlama-3.3-8B-InstructWe compared the version names in our catalogue.
 Hugging Face
95.6
From 343 benchmarks. Plenty of data behind it.
70 ±9
Coding IQ 69.9, 95% interval 61–79. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.22$0.22131K
39.5
Poor value (39.5). Costs more per task than its benchmark results predict. A fair amount of data behind it.
Not measured
Llama 3.1 8B Instruct
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
Newer version
Newer versionLlama-3.3-8B-InstructWe compared the version names in our catalogue.
us-east-1
 OpenRouter
95.6
From 343 benchmarks. Plenty of data behind it.
70 ±9
Coding IQ 69.9, 95% interval 61–79. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.22$0.22131K
39.5
Poor value (39.5). Costs more per task than its benchmark results predict. A fair amount of data behind it.
Not measured
Gemma 3 4B IT
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
amazon/google.gemma-3-4b-it
 Eden AI
95.2
From 249 benchmarks. Plenty of data behind it.
67 ±19
Coding IQ 66.8, 95% interval 48–86. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.04$0.08128K
38.3
Poor value (38.3). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measured
Gemma 3 4B IT
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
amazon/google.gemma-3-4b-it@us · 🇺🇸 us
 Eden AI
95.2
From 249 benchmarks. Plenty of data behind it.
67 ±19
Coding IQ 66.8, 95% interval 48–86. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.04$0.08128K
38.3
Poor value (38.3). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measured
Mixtral 8x7B Instruct v0.1
🇫🇷
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
 Cortecs AI
92.0
From 202 benchmarks. Plenty of data behind it.
≈ 76 ±12
Coding IQ 75.7, 95% interval 64–88. Little data behind it, so treat it as a rough estimate. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
——32KNot enough data yetNot measured
Mistral 7B Instruct v0.2
🇫🇷
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
 Cortecs AI
88.3
From 144 benchmarks. Plenty of data behind it.
≈ 76 ±12
Coding IQ 75.7, 95% interval 64–88. Little data behind it, so treat it as a rough estimate. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
——32K
46.7
Poor value (46.7). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measured
Voxtral Mini 3B 2507
🇫🇷
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
amazon/mistral.voxtral-mini-3b-2507
 Eden AINot enough data yetNot enough data yet$0.04$0.0433KNot enough data yetNot measured
Voxtral Mini 3B 2507
🇫🇷
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
amazon/mistral.voxtral-mini-3b-2507@us · 🇺🇸 us
 Eden AINot enough data yetNot enough data yet$0.04$0.0433KNot enough data yetNot measured
Voxtral Small 24B
🇫🇷
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
amazon/mistral.voxtral-small-24b-2507 · 2507
 Eden AINot enough data yetNot enough data yet$0.10$0.3033K
51.5
Fair value (51.5). Costs per task about what its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measured
Voxtral Small 24B
🇫🇷
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
amazon/mistral.voxtral-small-24b-2507@us · 2507 · 🇺🇸 us
 Eden AINot enough data yetNot enough data yet$0.10$0.3033K
51.5
Fair value (51.5). Costs per task about what its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measured

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

How this data works