Provider · Founded 2015 · Sunnyvale, USA

Cerebras: models, pricing and benchmarks

Wafer-scale AI chip and inference company.

Models

in this index

Avg input

$2.57

per 1M tokens

Avg output

$11.47

per 1M tokens

Open weights

models

Best model

llama-3-1-cerebras-instruct

by average score

Website

Visit

https://cerebras.ai

All Cerebras 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 3.1 Cerebras Instruct	Cerebras	65536	$4.11	76.1
2	Llama 3.1 Cerebras	Cerebras	128000	$4.01	76.0
3	Llama 3.1 Cerebras Chat	Cerebras	32768	$4.07	76.0
4	Llama 3.1 Cerebras Base	Cerebras	65536	$3.36	72.7
5	Llama 3.1 Cerebras 8B	Cerebras	32768	$1.02	58.2
6	Llama 3.1 Cerebras 7B	Cerebras	32768	$0.95	56.5
7	Llama 3.1 Cerebras 1.5B	Cerebras	4096	$0.48	50.2

Best Cerebras models

multimodal

Llama 3.1 Cerebras Instruct

Llama 3.1 Cerebras Instruct is a multimodal model from Cerebras. It offers a 65,536-token context window, costs $4.11 per million input tokens and $20.72 per million output tokens, and averages 76.1 across the index's benchmark suite.

$4.11 in · 65,536 context · 76.1 avg multimodal

Llama 3.1 Cerebras

Llama 3.1 Cerebras is a multimodal model from Cerebras. It offers a 128,000-token context window, costs $4.01 per million input tokens and $15.13 per million output tokens, and averages 76.0 across the index's benchmark suite.

$4.01 in · 128,000 context · 76.0 avg multimodal

Llama 3.1 Cerebras Chat

Llama 3.1 Cerebras Chat is a multimodal model from Cerebras. It offers a 32,768-token context window, costs $4.07 per million input tokens and $16.82 per million output tokens, and averages 76.0 across the index's benchmark suite.

$4.07 in · 32,768 context · 76.0 avg open-weight

Llama 3.1 Cerebras Base

Llama 3.1 Cerebras Base is a open-weight model from Cerebras. It offers a 65,536-token context window, costs $3.36 per million input tokens and $15.59 per million output tokens, and averages 72.7 across the index's benchmark suite.

$3.36 in · 65,536 context · 72.7 avg small open-weight

Llama 3.1 Cerebras 8B

Llama 3.1 Cerebras 8B is a small open-weight model from Cerebras. It offers a 32,768-token context window, costs $1.02 per million input tokens and $5.02 per million output tokens, and averages 58.2 across the index's benchmark suite.

$1.02 in · 32,768 context · 58.2 avg

How Cerebras fits

Cerebras has 7 models in the index, of which 7 are open weights. The average input price across the lineup is $2.57 per million tokens, and the average output price is $11.47 per million tokens. The strongest model by average benchmark score is llama-3-1-cerebras-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 Cerebras models are in the index?

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

What is the cheapest Cerebras model?

Llama 3.1 Cerebras 1.5B is the cheapest Cerebras model by input price at $0.48 per million tokens.

What is the best Cerebras model?

Llama 3.1 Cerebras Instruct has the highest average benchmark score in the Cerebras lineup at 76.1.

Are Cerebras models open weights?

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

Where is Cerebras based?

Cerebras was founded in 2015 and is headquartered in Sunnyvale, USA.