Provider · Founded 2022 · Redwood City, USA

Fireworks AI: models, pricing and benchmarks

Inference platform for open and custom models.

Models

in this index

Avg input

$6.84

per 1M tokens

Avg output

$31.35

per 1M tokens

Open weights

models

Best model

firefunction-max

by average score

Website

Visit

https://fireworks.ai

All Fireworks 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	Firefunction Max	Fireworks AI	32768	$9.12	73.2
2	Firefunction Pro	Fireworks AI	16384	$9.05	72.9
3	Firefunction Reasoning	Fireworks AI	8192	$9.08	72.5
4	Firefunction	Fireworks AI	16384	$8.16	72.3
5	Firefunction Turbo	Fireworks AI	32768	$8.44	70.7
6	Firesearch Pro	Fireworks AI	32768	$7.67	70.4
7	Firesearch Max	Fireworks AI	8192	$7.80	69.9
8	Firesearch Turbo	Fireworks AI	16384	$7.58	69.3
9	Firesearch Reasoning	Fireworks AI	32768	$7.74	69.0
10	Firesearch	Fireworks AI	32768	$7.03	68.5
11	Firefunction Mini	Fireworks AI	32768	$4.63	63.2
12	Firesearch Mini	Fireworks AI	32768	$3.94	61.5
13	Firefunction Nano	Fireworks AI	16384	$3.07	58.1
14	Firesearch Nano	Fireworks AI	8192	$2.49	55.6

Best Fireworks AI models

mid-range

Firefunction Max

Firefunction Max is a mid-range model from Fireworks AI. It offers a 32,768-token context window, costs $9.12 per million input tokens and $43.08 per million output tokens, and averages 73.2 across the index's benchmark suite.

$9.12 in · 32,768 context · 73.2 avg mid-range

Firefunction Pro

Firefunction Pro is a mid-range model from Fireworks AI. It offers a 16,384-token context window, costs $9.05 per million input tokens and $49.41 per million output tokens, and averages 72.9 across the index's benchmark suite.

$9.05 in · 16,384 context · 72.9 avg mid-range

Firefunction Reasoning

Firefunction Reasoning is a mid-range model from Fireworks AI. It offers a 8,192-token context window, costs $9.08 per million input tokens and $42.16 per million output tokens, and averages 72.5 across the index's benchmark suite.

$9.08 in · 8,192 context · 72.5 avg mid-range

Firefunction

Firefunction is a mid-range model from Fireworks AI. It offers a 16,384-token context window, costs $8.16 per million input tokens and $41.40 per million output tokens, and averages 72.3 across the index's benchmark suite.

$8.16 in · 16,384 context · 72.3 avg mid-range

Firefunction Turbo

Firefunction Turbo is a mid-range model from Fireworks AI. It offers a 32,768-token context window, costs $8.44 per million input tokens and $36.83 per million output tokens, and averages 70.7 across the index's benchmark suite.

$8.44 in · 32,768 context · 70.7 avg

How Fireworks AI fits

Fireworks AI has 14 models in the index, of which 0 are open weights. The average input price across the lineup is $6.84 per million tokens, and the average output price is $31.35 per million tokens. The strongest model by average benchmark score is firefunction-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 Fireworks AI models are in the index?

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

What is the cheapest Fireworks AI model?

Firesearch Nano is the cheapest Fireworks AI model by input price at $2.49 per million tokens.

What is the best Fireworks AI model?

Firefunction Max has the highest average benchmark score in the Fireworks AI lineup at 73.2.

Are Fireworks AI models open weights?

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

Where is Fireworks AI based?

Fireworks AI was founded in 2022 and is headquartered in Redwood City, USA.