Fireworks: Models and Prices

Inference cloud for open-weight and fine-tuned models.

Finance your GPUs All inference providers

Fireworks served 2.20T tokens of other labs' open-weight models over Oct 3 to Oct 9, 2026 through a large public LLM router, #9 among providers.

Open-weight models

Model	Family	Share of model	Tokens, 7d	Input $/M	Output $/M	Tokens/s	Uptime 3d	Context
DeepSeek V4.1 Flash	DeepSeek	4.0%	1.49T	$0.30	$1.20	33	82.8%	1.05M
GLM 5.3 Flash	GLM	4.2%	472B	$0.15	$0.50	75	98.2%	1.05M
Kimi K3	Kimi	7.5%	143B	$3.00	$15.00	38	100.0%	1.05M
GLM 5.3	GLM	3.0%	100B	$1.40	$4.40	57	99.7%	1.05M

List prices per million tokens as of October 9, 2026. Share: of all tokens served on that model; a dash where the volume is not reported.

Company

Website: fireworks.ai
Headquarters: Redwood City, CA
Latest financing: $1.5B Series D at a $17.5B valuation led by Atreides, Index Ventures and TCV (July 2026).
Status page: status.fireworks.ai

Sources: OTPP.

Finance your GPUs

Serving tokens on your own GPUs? Tell us the cluster, the models you serve and the contracts behind them, and we will share it with partner funders that fit.

Prefer email? hello@amcompute.com