Provider · Founded 2020 · Remote

EleutherAI: models, pricing and benchmarks

Open research collective behind Pythia and GPT-NeoX.

Models

in this index

Avg input

$0.83

per 1M tokens

Avg output

$3.56

per 1M tokens

Open weights

models

Best model

gpt-neox-instruct

by average score

Website

Visit

https://eleuther.ai

All EleutherAI 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	GPT-NeoX Instruct	EleutherAI	16384	$1.52	62.6
2	GPT-NeoX	EleutherAI	16384	$1.57	61.7
3	Pythia Instruct	EleutherAI	8192	$1.41	60.8
4	GPT-NeoX Chat	EleutherAI	16384	$1.49	60.1
5	Pythia	EleutherAI	32768	$1.29	59.8
6	GPT-NeoX Base	EleutherAI	16384	$1.22	59.7
7	Pythia Chat	EleutherAI	4096	$1.31	59.1
8	Pythia Base	EleutherAI	16384	$0.99	55.9
9	GPT-NeoX 8B	EleutherAI	16384	$0.25	43.7
10	GPT-NeoX 7B	EleutherAI	8192	$0.20	42.4
11	Pythia 8B	EleutherAI	32768	$0.16	41.4
12	Pythia 7B	EleutherAI	8192	$0.10	40.7
13	GPT-NeoX 1.5B	EleutherAI	32768	$0.06	36.4
14	Pythia 1.5B	EleutherAI	4096	$0.10	35.8

Best EleutherAI models

open-weight

GPT-NeoX Instruct

GPT-NeoX Instruct is a open-weight model from EleutherAI. It offers a 16,384-token context window, costs $1.52 per million input tokens and $5.60 per million output tokens, and averages 62.6 across the index's benchmark suite.

$1.52 in · 16,384 context · 62.6 avg open-weight

GPT-NeoX

GPT-NeoX is a open-weight model from EleutherAI. It offers a 16,384-token context window, costs $1.57 per million input tokens and $7.57 per million output tokens, and averages 61.7 across the index's benchmark suite.

$1.57 in · 16,384 context · 61.7 avg open-weight

Pythia Instruct

Pythia Instruct is a open-weight model from EleutherAI. It offers a 8,192-token context window, costs $1.41 per million input tokens and $5.70 per million output tokens, and averages 60.8 across the index's benchmark suite.

$1.41 in · 8,192 context · 60.8 avg open-weight

GPT-NeoX Chat

GPT-NeoX Chat is a open-weight model from EleutherAI. It offers a 16,384-token context window, costs $1.49 per million input tokens and $7.20 per million output tokens, and averages 60.1 across the index's benchmark suite.

$1.49 in · 16,384 context · 60.1 avg open-weight

Pythia

Pythia is a open-weight model from EleutherAI. It offers a 32,768-token context window, costs $1.29 per million input tokens and $5.47 per million output tokens, and averages 59.8 across the index's benchmark suite.

$1.29 in · 32,768 context · 59.8 avg

How EleutherAI fits

EleutherAI has 14 models in the index, of which 14 are open weights. The average input price across the lineup is $0.83 per million tokens, and the average output price is $3.56 per million tokens. The strongest model by average benchmark score is gpt-neox-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 EleutherAI models are in the index?

EleutherAI has 14 models in this index, of which 14 are open weights.

What is the cheapest EleutherAI model?

GPT-NeoX 1.5B is the cheapest EleutherAI model by input price at $0.060 per million tokens.

What is the best EleutherAI model?

GPT-NeoX Instruct has the highest average benchmark score in the EleutherAI lineup at 62.6.

Are EleutherAI models open weights?

14 of the 14 EleutherAI models in this index are open weights. The rest are proprietary.

Where is EleutherAI based?

EleutherAI was founded in 2020 and is headquartered in Remote.