Provider · Founded 2019 · San Francisco, USA

DeepInfra: models, pricing and benchmarks

Low-cost inference API for open models.

Models

in this index

Avg input

$2.38

per 1M tokens

Avg output

$10.83

per 1M tokens

Open weights

models

Best model

llama-3-deepinfra-instruct

by average score

Website

Visit

https://deepinfra.com

All DeepInfra 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 DeepInfra Instruct	DeepInfra	65536	$3.84	75.5
2	Llama 3 DeepInfra Chat	DeepInfra	200000	$3.74	75.0
3	Llama 3 DeepInfra	DeepInfra	128000	$3.67	74.0
4	Llama 3 DeepInfra Base	DeepInfra	16384	$2.95	71.8
5	Llama 3 DeepInfra 8B	DeepInfra	8192	$1.05	57.4
6	Llama 3 DeepInfra 7B	DeepInfra	16384	$0.95	55.6
7	Llama 3 DeepInfra 1.5B	DeepInfra	32768	$0.48	48.8

Best DeepInfra models

multimodal

Llama 3 DeepInfra Instruct

Llama 3 DeepInfra Instruct is a multimodal model from DeepInfra. It offers a 65,536-token context window, costs $3.84 per million input tokens and $20.22 per million output tokens, and averages 75.5 across the index's benchmark suite.

$3.84 in · 65,536 context · 75.5 avg multimodal

Llama 3 DeepInfra Chat

Llama 3 DeepInfra Chat is a multimodal model from DeepInfra. It offers a 200,000-token context window, costs $3.74 per million input tokens and $15.32 per million output tokens, and averages 75.0 across the index's benchmark suite.

$3.74 in · 200,000 context · 75.0 avg multimodal

Llama 3 DeepInfra

Llama 3 DeepInfra is a multimodal model from DeepInfra. It offers a 128,000-token context window, costs $3.67 per million input tokens and $14.87 per million output tokens, and averages 74.0 across the index's benchmark suite.

$3.67 in · 128,000 context · 74.0 avg open-weight

Llama 3 DeepInfra Base

Llama 3 DeepInfra Base is a open-weight model from DeepInfra. It offers a 16,384-token context window, costs $2.95 per million input tokens and $15.78 per million output tokens, and averages 71.8 across the index's benchmark suite.

$2.95 in · 16,384 context · 71.8 avg small open-weight

Llama 3 DeepInfra 8B

Llama 3 DeepInfra 8B is a small open-weight model from DeepInfra. It offers a 8,192-token context window, costs $1.05 per million input tokens and $3.99 per million output tokens, and averages 57.4 across the index's benchmark suite.

$1.05 in · 8,192 context · 57.4 avg

How DeepInfra fits

DeepInfra has 7 models in the index, of which 7 are open weights. The average input price across the lineup is $2.38 per million tokens, and the average output price is $10.83 per million tokens. The strongest model by average benchmark score is llama-3-deepinfra-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 DeepInfra models are in the index?

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

What is the cheapest DeepInfra model?

Llama 3 DeepInfra 1.5B is the cheapest DeepInfra model by input price at $0.48 per million tokens.

What is the best DeepInfra model?

Llama 3 DeepInfra Instruct has the highest average benchmark score in the DeepInfra lineup at 75.5.

Are DeepInfra models open weights?

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

Where is DeepInfra based?

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