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
- Epoch Capabilities Index
- Epoch Capabilities Index benchmark details
| Model | llminfo IQ | Coding IQ | Input $/1M | Output $/1M | Max Input Tokens | Value | Epoch 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. | 95.2From 249 benchmarks. Plenty of data behind it. | 67 ±19Coding 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 $0.04 | 128K | 38.3Poor 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. | —Not enough data yet | —Not enough data yet | $0.02 | — | 8K | —Not enough data yet | —Not measured |
Titan Text Embeddings V2 🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. | —Not enough data yet | —Not enough data yet | — | — | —Not published by the provider | —Not enough data yet | —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. | —Not enough data yet | —Not enough data yet | $0.04batch $0.02 | $0.04batch $0.02 | 33K | —Not enough data yet | —Not measured |
nova-sonic-v1 🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. | —Not enough data yet | —Not enough data yet | $0.06 | $0.24 | —Not published by the provider | —Not enough data yet | —Not 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. | —Not enough data yet | —Not enough data yet | $0.10 | — | 512 | —Not enough data yet | —Not 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. | —Not enough data yet | —Not enough data yet | — | — | —Not published by the provider | —Not enough data yet | —Not measured |
Titan Embed G1 Text 02 🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. | —Not enough data yet | —Not enough data yet | $0.10 | — | 8K | —Not enough data yet | —Not 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 | —Not enough data yet | —Not enough data yet | $0.10 | — | 8K | —Not enough data yet | —Not 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 | —Not enough data yet | —Not enough data yet | — | — | —Not published by the provider | —Not enough data yet | —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. | —Not enough data yet | —Not enough data yet | $0.10batch $0.05 | $0.30batch $0.15 | 33K | 51.5Fair 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. | —Not enough data yet | —Not enough data yet | $0.12 | — | 128K | —Not enough data yet | —Not measured |
Embed v4 🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. | —Not enough data yet | —Not enough data yet | $0.12 | — | 128K | —Not enough data yet | —Not measured |
Embed v4 🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. | —Not enough data yet | —Not enough data yet | $0.12 | — | 128K | —Not enough data yet | —Not measured |
Embed v4 🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. | —Not enough data yet | —Not enough data yet | $0.12 | — | 128K | —Not enough data yet | —Not measured |
titan-text-lite-v1 🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. | —Not enough data yet | —Not enough data yet | $0.15 | $0.20 | 42K | —Not enough data yet | —Not measured |
Nova 2 Multimodal Embeddings v1 🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. | —Not enough data yet | —Not enough data yet | $0.162batch $0.081 | — | 8K | —Not enough data yet | —Not measured |
titan-text-express-v1 🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. | —Not enough data yet | —Not enough data yet | $0.20 | $0.60 | 42K | —Not enough data yet | —Not measured |
command-light-text-v14 🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. | —Not enough data yet | —Not enough data yet | $0.30 | $0.60 | 4K | —Not enough data yet | —Not measured |
Nova 2.5 Sonic 🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. | —Not enough data yet | —Not enough data yet | $0.33 | $2.75 | 256K | —Not enough data yet | —Not measured |
Nova 2 Sonic v1 🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. | —Not enough data yet | —Not enough data yet | $0.33 | $2.75 | 1M | —Not enough data yet | —Not measured |
Jamba Instruct 🇮🇱Maker headquartered in IL, according to the company's own website. The citation is on the model page. | —Not enough data yet | —Not enough data yet | $0.50 | $0.70 | 70K | —Not enough data yet | —Not measured |
titan-text-premier-v1 🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. | —Not enough data yet | —Not enough data yet | $0.50 | $1.50 | 42K | —Not enough data yet | —Not measured |
claude-instant 🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. | —Not enough data yet | —Not enough data yet | $0.80 | $2.40 | 100K | —Not enough data yet | 114Epoch 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 yet | —Not enough data yet | $0.80 | $2.40 | —Not published by the provider | —Not enough data yet | 114Epoch 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. | —Not enough data yet | —Not enough data yet | $0.80 | $25.00 | 128 | —Not enough data yet | —Not measured |
Titan Multimodal Embeddings G1 🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. | —Not enough data yet | —Not enough data yet | — | — | —Not published by the provider | —Not enough data yet | —Not measured |
command-text-v14 🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. | —Not enough data yet | —Not enough data yet | $1.00 | $2.00 | 4K | —Not enough data yet | —Not measured |
Mistral Small 2402 v1 🇫🇷Maker headquartered in FR, according to the company's own website. The citation is on the model page. | —Not enough data yet | —Not enough data yet | $1.00batch $0.50 | $3.00batch $1.50 | 32K | —Not enough data yet | —Not measured |
Claude Haiku 4.5 (India) 🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. | —Not enough data yet | —Not enough data yet | $1.10cache read $0.11 | $5.50cache write $1.375 | 200K | —Not enough data yet | —Not 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
- Epoch Capabilities Index
- Epoch Capabilities Index benchmark details
| Model | Provider | llminfo IQ | Coding IQ | Input $/1M | Output $/1M | Max Input Tokens | Value | Epoch 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 | 95.6From 343 benchmarks. Plenty of data behind it. | 70 ±9Coding 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 | $0.22 | 131K | 39.5Poor 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 | 95.6From 343 benchmarks. Plenty of data behind it. | 70 ±9Coding 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 | $0.22 | 131K | 39.5Poor 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. | 95.2From 249 benchmarks. Plenty of data behind it. | 67 ±19Coding 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 | $0.08 | 128K | 38.3Poor 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. | 95.2From 249 benchmarks. Plenty of data behind it. | 67 ±19Coding 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 | $0.08 | 128K | 38.3Poor 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. | 92.0From 202 benchmarks. Plenty of data behind it. | ≈ 76 ±12Coding 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 | —Not enough data yet | —Not measured | |
Mistral 7B Instruct v0.2 🇫🇷Maker headquartered in FR, according to the company's own website. The citation is on the model page. | 88.3From 144 benchmarks. Plenty of data behind it. | ≈ 76 ±12Coding 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 | 46.7Poor 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. | —Not enough data yet | —Not enough data yet | $0.04 | $0.04 | 33K | —Not enough data yet | —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. | —Not enough data yet | —Not enough data yet | $0.04 | $0.04 | 33K | —Not enough data yet | —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. | —Not enough data yet | —Not enough data yet | $0.10 | $0.30 | 33K | 51.5Fair 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. | —Not enough data yet | —Not enough data yet | $0.10 | $0.30 | 33K | 51.5Fair 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)