Provider · Founded 2019 · San Francisco, USA

Replicate: models, pricing and benchmarks

Platform for running open models via API.

Models

in this index

Avg input

$2.40

per 1M tokens

Avg output

$11.15

per 1M tokens

Open weights

models

Best model

llama-3-replicate

by average score

Website

Visit

https://replicate.com

All Replicate 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 Replicate	Replicate	200000	$3.75	75.7
2	Llama 3 Replicate Instruct	Replicate	128000	$3.71	75.1
3	Llama 3 Replicate Chat	Replicate	200000	$3.74	74.7
4	Llama 3 Replicate Base	Replicate	65536	$3.15	72.1
5	Llama 3 Replicate 8B	Replicate	32768	$1.00	57.0
6	Llama 3 Replicate 7B	Replicate	32768	$0.91	56.0
7	Llama 3 Replicate 1.5B	Replicate	4096	$0.51	49.3

Best Replicate models

multimodal

Llama 3 Replicate

Llama 3 Replicate is a multimodal model from Replicate. It offers a 200,000-token context window, costs $3.75 per million input tokens and $13.86 per million output tokens, and averages 75.7 across the index's benchmark suite.

$3.75 in · 200,000 context · 75.7 avg multimodal

Llama 3 Replicate Instruct

Llama 3 Replicate Instruct is a multimodal model from Replicate. It offers a 128,000-token context window, costs $3.71 per million input tokens and $19.99 per million output tokens, and averages 75.1 across the index's benchmark suite.

$3.71 in · 128,000 context · 75.1 avg multimodal

Llama 3 Replicate Chat

Llama 3 Replicate Chat is a multimodal model from Replicate. It offers a 200,000-token context window, costs $3.74 per million input tokens and $17.46 per million output tokens, and averages 74.7 across the index's benchmark suite.

$3.74 in · 200,000 context · 74.7 avg open-weight

Llama 3 Replicate Base

Llama 3 Replicate Base is a open-weight model from Replicate. It offers a 65,536-token context window, costs $3.15 per million input tokens and $16.13 per million output tokens, and averages 72.1 across the index's benchmark suite.

$3.15 in · 65,536 context · 72.1 avg small open-weight

Llama 3 Replicate 8B

Llama 3 Replicate 8B is a small open-weight model from Replicate. It offers a 32,768-token context window, costs $1.00 per million input tokens and $4.35 per million output tokens, and averages 57.0 across the index's benchmark suite.

$1.00 in · 32,768 context · 57.0 avg

How Replicate fits

Replicate has 7 models in the index, of which 7 are open weights. The average input price across the lineup is $2.40 per million tokens, and the average output price is $11.15 per million tokens. The strongest model by average benchmark score is llama-3-replicate.

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 Replicate models are in the index?

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

What is the cheapest Replicate model?

Llama 3 Replicate 1.5B is the cheapest Replicate model by input price at $0.51 per million tokens.

What is the best Replicate model?

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

Are Replicate models open weights?

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

Where is Replicate based?

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