Categories / Fireworks AI
Fireworks AI
Visit Website ↗Fast inference platform for open models. Serverless is billed per token against prepaid credits; fine-tuning, dedicated GPUs and enterprise reserved capacity are also offered.
Prices may change. These are correct as of 10 Nov 2026. Please confirm on the vendor's own page before you pay.
Verified. Fireworks publishes per-token rates only. The headline models and their prices change often, so check the live table.
Free plan
No free plan. No free plan; usage draws down prepaid credits. Some models run free during promotions.
Plans and prices (USD)
Swipe the table sideways to see what each plan includes.
| Plan | Billed monthly | Yearly, per month | What it includes |
|---|---|---|---|
| Serverless (pay per token) per per 1M tokens, input / output |
not recorded | not recorded |
|
"Not recorded" means we did not find that price, not that it is free. Prices exclude tax and can differ by country.
Where it may fit
- D
- e
- v
- e
- l
- o
- p
- e
- r
- s
- w
- h
- o
- w
- a
- n
- t
- p
- a
- y
- -
- p
- e
- r
- -
- t
- o
- k
- e
- n
- a
- c
- c
- e
- s
- s
- t
- o
- o
- p
- e
- n
- -
- w
- e
- i
- g
- h
- t
- m
- o
- d
- e
- l
- s
Taken from what the vendor says the tool does. We have not tested it.
What to watch
- Model lineup and rates change often
- Priority and fast modes cost more than standard
- Dedicated GPU and training are priced separately
Sources
- Fireworks pricing (checked 10 Nov 2026)
- Serverless pricing docs (checked 10 Nov 2026)
Open Fireworks AI's own site · Report a mistake on this page