Provider · Founded 2023 · San Francisco, USA

OpenRouter: models, pricing and benchmarks

Unified API for routing across model providers.

Models

in this index

Avg input

$7.07

per 1M tokens

Avg output

$32.01

per 1M tokens

Open weights

models

Best model

fusion-max

by average score

Website

Visit

https://openrouter.ai

All OpenRouter 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	Fusion Max	OpenRouter	65536	$9.14	72.5
2	Fusion Pro	OpenRouter	65536	$8.69	72.2
3	Fusion Reasoning	OpenRouter	65536	$8.59	72.2
4	Fusion Turbo	OpenRouter	8192	$8.55	71.7
5	Auto Reasoning	OpenRouter	65536	$8.39	71.5
6	Auto Max	OpenRouter	8192	$8.41	71.2
7	Auto Pro	OpenRouter	8192	$8.41	71.2
8	Fusion	OpenRouter	16384	$8.41	71.1
9	Auto Turbo	OpenRouter	65536	$7.96	70.9
10	Auto	OpenRouter	32768	$7.53	70.2
11	Fusion Mini	OpenRouter	4096	$4.89	63.3
12	Auto Mini	OpenRouter	4096	$4.24	61.6
13	Auto Nano	OpenRouter	4096	$2.83	57.1
14	Fusion Nano	OpenRouter	8192	$2.96	56.8

Best OpenRouter models

mid-range

Fusion Max

Fusion Max is a mid-range model from OpenRouter. It offers a 65,536-token context window, costs $9.14 per million input tokens and $43.52 per million output tokens, and averages 72.5 across the index's benchmark suite.

$9.14 in · 65,536 context · 72.5 avg mid-range

Fusion Pro

Fusion Pro is a mid-range model from OpenRouter. It offers a 65,536-token context window, costs $8.69 per million input tokens and $46.67 per million output tokens, and averages 72.2 across the index's benchmark suite.

$8.69 in · 65,536 context · 72.2 avg mid-range

Fusion Reasoning

Fusion Reasoning is a mid-range model from OpenRouter. It offers a 65,536-token context window, costs $8.59 per million input tokens and $32.34 per million output tokens, and averages 72.2 across the index's benchmark suite.

$8.59 in · 65,536 context · 72.2 avg mid-range

Fusion Turbo

Fusion Turbo is a mid-range model from OpenRouter. It offers a 8,192-token context window, costs $8.55 per million input tokens and $40.27 per million output tokens, and averages 71.7 across the index's benchmark suite.

$8.55 in · 8,192 context · 71.7 avg mid-range

Auto Reasoning

Auto Reasoning is a mid-range model from OpenRouter. It offers a 65,536-token context window, costs $8.39 per million input tokens and $36.43 per million output tokens, and averages 71.5 across the index's benchmark suite.

$8.39 in · 65,536 context · 71.5 avg

How OpenRouter fits

OpenRouter has 14 models in the index, of which 0 are open weights. The average input price across the lineup is $7.07 per million tokens, and the average output price is $32.01 per million tokens. The strongest model by average benchmark score is fusion-max.

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 OpenRouter models are in the index?

OpenRouter has 14 models in this index, of which 0 are open weights.

What is the cheapest OpenRouter model?

Auto Nano is the cheapest OpenRouter model by input price at $2.83 per million tokens.

What is the best OpenRouter model?

Fusion Max has the highest average benchmark score in the OpenRouter lineup at 72.5.

Are OpenRouter models open weights?

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

Where is OpenRouter based?

OpenRouter was founded in 2023 and is headquartered in San Francisco, USA.