Provider · Founded 2022 · San Francisco, USA

Together AI: models, pricing and benchmarks

Inference and training cloud for open models.

Models

in this index

Avg input

$2.28

per 1M tokens

Avg output

$10.11

per 1M tokens

Open weights

models

Best model

llama-3-1-turbo

by average score

Website

Visit

https://together.ai

All Together AI 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 Turbo	Together AI	200000	$4.17	76.8
2	Llama 3.1 Turbo Instruct	Together AI	32768	$4.21	76.7
3	Llama 3.1 Turbo Chat	Together AI	200000	$3.95	76.1
4	Llama 3.1 Turbo Base	Together AI	16384	$3.30	73.0
5	Mixtral Turbo	Together AI	65536	$3.20	72.4
6	Mixtral Turbo Instruct	Together AI	32768	$3.16	71.9
7	Mixtral Turbo Chat	Together AI	32768	$3.02	71.7
8	Mixtral Turbo Base	Together AI	32768	$2.53	69.7
9	Llama 3.1 Turbo 8B	Together AI	32768	$1.16	58.8
10	Llama 3.1 Turbo 7B	Together AI	8192	$0.98	56.4
11	Mixtral Turbo 8B	Together AI	4096	$0.75	54.1
12	Mixtral Turbo 7B	Together AI	8192	$0.68	53.2
13	Llama 3.1 Turbo 1.5B	Together AI	16384	$0.46	49.8
14	Mixtral Turbo 1.5B	Together AI	4096	$0.31	47.6

Best Together AI models

multimodal

Llama 3.1 Turbo

Llama 3.1 Turbo is a multimodal model from Together AI. It offers a 200,000-token context window, costs $4.17 per million input tokens and $21.10 per million output tokens, and averages 76.8 across the index's benchmark suite.

$4.17 in · 200,000 context · 76.8 avg multimodal

Llama 3.1 Turbo Instruct

Llama 3.1 Turbo Instruct is a multimodal model from Together AI. It offers a 32,768-token context window, costs $4.21 per million input tokens and $17.73 per million output tokens, and averages 76.7 across the index's benchmark suite.

$4.21 in · 32,768 context · 76.7 avg multimodal

Llama 3.1 Turbo Chat

Llama 3.1 Turbo Chat is a multimodal model from Together AI. It offers a 200,000-token context window, costs $3.95 per million input tokens and $20.39 per million output tokens, and averages 76.1 across the index's benchmark suite.

$3.95 in · 200,000 context · 76.1 avg open-weight

Llama 3.1 Turbo Base

Llama 3.1 Turbo Base is a open-weight model from Together AI. It offers a 16,384-token context window, costs $3.30 per million input tokens and $13.59 per million output tokens, and averages 73.0 across the index's benchmark suite.

$3.30 in · 16,384 context · 73.0 avg open-weight

Mixtral Turbo

Mixtral Turbo is a open-weight model from Together AI. It offers a 65,536-token context window, costs $3.20 per million input tokens and $13.66 per million output tokens, and averages 72.4 across the index's benchmark suite.

$3.20 in · 65,536 context · 72.4 avg

How Together AI fits

Together AI has 14 models in the index, of which 14 are open weights. The average input price across the lineup is $2.28 per million tokens, and the average output price is $10.11 per million tokens. The strongest model by average benchmark score is llama-3-1-turbo.

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 Together AI models are in the index?

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

What is the cheapest Together AI model?

Mixtral Turbo 1.5B is the cheapest Together AI model by input price at $0.31 per million tokens.

What is the best Together AI model?

Llama 3.1 Turbo has the highest average benchmark score in the Together AI lineup at 76.8.

Are Together AI models open weights?

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

Where is Together AI based?

Together AI was founded in 2022 and is headquartered in San Francisco, USA.