Provider · Founded 2021 · New York, USA

Modal: models, pricing and benchmarks

Serverless compute platform for AI workloads.

Models

in this index

Avg input

$2.39

per 1M tokens

Avg output

$10.89

per 1M tokens

Open weights

models

Best model

llama-3-modal-instruct

by average score

Website

Visit

https://modal.com

All Modal models

Sorted by average benchmark score. Prices are per million tokens and context is measured in tokens.

#	Model	Provider	Context	Input / 1M	Avg score
1	Llama 3 Modal Instruct	Modal	128000	$3.84	75.2
2	Llama 3 Modal	Modal	32768	$3.82	74.9
3	Llama 3 Modal Chat	Modal	65536	$3.55	73.3
4	Llama 3 Modal Base	Modal	16384	$3.21	72.2
5	Llama 3 Modal 8B	Modal	32768	$0.98	56.6
6	Llama 3 Modal 7B	Modal	4096	$0.88	55.2
7	Llama 3 Modal 1.5B	Modal	4096	$0.42	49.7

Best Modal models

multimodal

Llama 3 Modal Instruct

Llama 3 Modal Instruct is a multimodal model from Modal. It offers a 128,000-token context window, costs $3.84 per million input tokens and $18.84 per million output tokens, and averages 75.2 across the index's benchmark suite.

$3.84 in · 128,000 context · 75.2 avg multimodal

Llama 3 Modal

Llama 3 Modal is a multimodal model from Modal. It offers a 32,768-token context window, costs $3.82 per million input tokens and $17.80 per million output tokens, and averages 74.9 across the index's benchmark suite.

$3.82 in · 32,768 context · 74.9 avg multimodal

Llama 3 Modal Chat

Llama 3 Modal Chat is a multimodal model from Modal. It offers a 65,536-token context window, costs $3.55 per million input tokens and $12.52 per million output tokens, and averages 73.3 across the index's benchmark suite.

$3.55 in · 65,536 context · 73.3 avg open-weight

Llama 3 Modal Base

Llama 3 Modal Base is a open-weight model from Modal. It offers a 16,384-token context window, costs $3.21 per million input tokens and $17.08 per million output tokens, and averages 72.2 across the index's benchmark suite.

$3.21 in · 16,384 context · 72.2 avg small open-weight

Llama 3 Modal 8B

Llama 3 Modal 8B is a small open-weight model from Modal. It offers a 32,768-token context window, costs $0.98 per million input tokens and $4.54 per million output tokens, and averages 56.6 across the index's benchmark suite.

$0.98 in · 32,768 context · 56.6 avg

How Modal fits

Modal has 7 models in the index, of which 7 are open weights. The average input price across the lineup is $2.39 per million tokens, and the average output price is $10.89 per million tokens. The strongest model by average benchmark score is llama-3-modal-instruct.

Use the table above to compare individual models, or open a model page for its full benchmark breakdown. If you are choosing between providers, start with the comparison pages and then check context limits and licence terms.

FAQ

How many Modal models are in the index?

Modal has 7 models in this index, of which 7 are open weights.

What is the cheapest Modal model?

Llama 3 Modal 1.5B is the cheapest Modal model by input price at $0.42 per million tokens.

What is the best Modal model?

Llama 3 Modal Instruct has the highest average benchmark score in the Modal lineup at 75.2.

Are Modal models open weights?

7 of the 7 Modal models in this index are open weights. The rest are proprietary.

Where is Modal based?

Modal was founded in 2021 and is headquartered in New York, USA.