Fireworks AI API pricing
by Fireworks AIper 1M tokens
$0.20 / 1M outputNVIDIA Nemotron 3.5 Lightning 30B A3B (Fireworks) · the cheapest model
Fireworks AI API costs $0.05–$3.00 per 1M input tokens and $0.20–$15.00 per 1M output tokens. Output tokens cost several times more than input, so long answers drive the bill. Fireworks AI sells API access only; there is no chat subscription.
Cheapest output$0.20NVIDIA Nemotron 3.5 Lightning 30B A3B (Fireworks) · per 1M
Top model$15.00Kimi K3 (Fireworks) · per 1M output
Every model, per 1M tokens
USD list price, before batch or volume discounts| Model | Input | Output | Cached input | Context |
|---|---|---|---|---|
| Ember-1 (Fireworks) | $3.00 | $15.00 | $0.30 | — |
| Kimi K3 (Fireworks) | $3.00 | $15.00 | $0.30 | — |
| Qwen 3.8 Max (Fireworks) | $2.00 | $6.00 | $0.25 | — |
| GLM 5.3 (Fireworks) | $1.40 | $4.40 | $0.26 | — |
| Muse Spark Open (Fireworks) | $1.25 | $4.25 | $0.15 | — |
| NVIDIA Nemotron 3 Ultra (Preview) (Fireworks) | $0.60 | $2.40 | $0.12 | — |
| DeepSeek V4.1 Flash (Fireworks) | $0.30 | $1.20 | $0.006 | — |
| DeepSeek V4.1 Flash 1017 (Fireworks) | $0.30 | $1.20 | $0.006 | — |
| MiniMax M3 (Fireworks) | $0.30 | $1.20 | $0.06 | — |
| GLM 5.3 Flash (Fireworks) | $0.15 | $0.50 | $0.03 | — |
| OpenAI GPT OSS 120B (Fireworks) | $0.15 | $0.60 | $0.015 | — |
| NVIDIA Nemotron 3.5 Lightning 30B A3B (Fireworks) | $0.05 | $0.20 | $0.01 | — |
What will you pay?
$240.00
per month on Kimi K3 (Fireworks)
Prices from fireworks.ai/pricing How we collect prices Some links are affiliate links; they never change the prices or the order shown. Disclosure