Provider · Founded 2019 · San Francisco, USA

Anyscale: models, pricing and benchmarks

Ray-based platform for AI compute.

Models

in this index

Avg input

$2.45

per 1M tokens

Avg output

$10.46

per 1M tokens

Open weights

models

Best model

llama-3-anyscale-instruct

by average score

Website

Visit

https://anyscale.com

All Anyscale 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 Anyscale Instruct	Anyscale	200000	$3.91	75.7
2	Llama 3 Anyscale	Anyscale	65536	$3.94	74.7
3	Llama 3 Anyscale Chat	Anyscale	65536	$3.67	74.6
4	Llama 3 Anyscale Base	Anyscale	65536	$3.23	72.9
5	Llama 3 Anyscale 8B	Anyscale	32768	$0.97	57.3
6	Llama 3 Anyscale 7B	Anyscale	4096	$0.98	56.2
7	Llama 3 Anyscale 1.5B	Anyscale	16384	$0.43	48.9

Best Anyscale models

multimodal

Llama 3 Anyscale Instruct

Llama 3 Anyscale Instruct is a multimodal model from Anyscale. It offers a 200,000-token context window, costs $3.91 per million input tokens and $14.49 per million output tokens, and averages 75.7 across the index's benchmark suite.

$3.91 in · 200,000 context · 75.7 avg multimodal

Llama 3 Anyscale

Llama 3 Anyscale is a multimodal model from Anyscale. It offers a 65,536-token context window, costs $3.94 per million input tokens and $19.76 per million output tokens, and averages 74.7 across the index's benchmark suite.

$3.94 in · 65,536 context · 74.7 avg multimodal

Llama 3 Anyscale Chat

Llama 3 Anyscale Chat is a multimodal model from Anyscale. It offers a 65,536-token context window, costs $3.67 per million input tokens and $14.56 per million output tokens, and averages 74.6 across the index's benchmark suite.

$3.67 in · 65,536 context · 74.6 avg open-weight

Llama 3 Anyscale Base

Llama 3 Anyscale Base is a open-weight model from Anyscale. It offers a 65,536-token context window, costs $3.23 per million input tokens and $14.41 per million output tokens, and averages 72.9 across the index's benchmark suite.

$3.23 in · 65,536 context · 72.9 avg small open-weight

Llama 3 Anyscale 8B

Llama 3 Anyscale 8B is a small open-weight model from Anyscale. It offers a 32,768-token context window, costs $0.97 per million input tokens and $4.27 per million output tokens, and averages 57.3 across the index's benchmark suite.

$0.97 in · 32,768 context · 57.3 avg

How Anyscale fits

Anyscale has 7 models in the index, of which 7 are open weights. The average input price across the lineup is $2.45 per million tokens, and the average output price is $10.46 per million tokens. The strongest model by average benchmark score is llama-3-anyscale-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 Anyscale models are in the index?

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

What is the cheapest Anyscale model?

Llama 3 Anyscale 1.5B is the cheapest Anyscale model by input price at $0.43 per million tokens.

What is the best Anyscale model?

Llama 3 Anyscale Instruct has the highest average benchmark score in the Anyscale lineup at 75.7.

Are Anyscale models open weights?

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

Where is Anyscale based?

Anyscale was founded in 2019 and is headquartered in San Francisco, USA.