Fireworks AI pricing: GPU rental rates
updated 2026-10-12
Fireworks AI's cheapest GPU today is the H100 at $8.00/hr (serverless, updated 2026-10-12). Fireworks AI is an AI inference platform. Most of its pricing is per-token serverless model pricing, which is out of scope for a GPU-hour tracker; what we track is its on-demand deployments table, where you rent dedicated GPUs for your own model deployment, billed per GPU-second with no extra charge for start-up times. Current hardware covers H100, H200, B200 and B300. There is no VM or SSH access, so we label these rates serverless in our tables.
Compare the full daily GPU market
GPU prices compared with the market
| GPU | Provider lowest firm rate | Market median | Difference |
|---|
The market median gives each provider equal weight. GPU variants, node size, included CPU and memory can differ. A lower rate does not establish equivalent performance.
Live Fireworks AI prices (2026-10-12)
More filters: provider, memory, node size, stock, sort, price unit
| GPU / provider | Billing | $/GPU-hour | Node · total per hour | Rent |
|---|---|---|---|---|
| H100 · Fireworks AI80 GB | serverless | $8.00$0.002222/sec | – | Rent → |
| H200 (SXM) · Fireworks AI141 GB | serverless | $8.00$0.002222/sec | – | Rent → |
| B200 · Fireworks AI180 GB | serverless | $13.00$0.003611/sec | – | Rent → |
| B300 · Fireworks AI288 GB | serverless | $15.00$0.004167/sec | – | Rent → |
| GB300 · Fireworks AI288 GB | serverless | $20.00$0.005556/sec | – | Rent → |
Try another provider or reduce the minimum memory.
Tables rank by price, lowest first. Commercial relationships never affect ordering. How we collect and rank prices.
Same GPU, provider, billing and price on several hosts or listings: one row, with the count. – means the provider does not state it.
Monthly view assumes 730 hours of continuous use. Daily view assumes 24 hours.
Cheapest listed per-GPU-hour rates verified at the source. Before storage, egress and networking.
Fireworks AI access and company facts
| Check | Published information | Updated |
|---|---|---|
| Minimum account funding | Not recorded | 2026-07-07 |
A company fact or certification is not a guarantee for every product or region. Unrecorded fields are left unknown. The smallest recorded node does not establish immediate stock or account approval.
Pricing model
On-demand deployments are billed per GPU-second at a published hourly rate per GPU type, and Fireworks states there are no extra charges for start-up times. This buys a dedicated GPU serving your chosen model on the Fireworks platform rather than a virtual machine. The same page prices serverless inference per token and fine-tuning per training token; those are model-level prices, not GPU rentals, so our tracker deliberately excludes them.
Hardware lineup
The on-demand deployment table currently lists H100 80GB, H200 141GB, B200 180GB and B300 288GB GPUs. Fireworks also documents reinforcement fine-tuning jobs priced per GPU-hour at the same rates as on-demand deployments.
Who should pick Fireworks AI
Pick Fireworks on-demand deployments if you want a dedicated GPU serving your model with per-second billing and platform-managed infrastructure, especially for production inference where serverless per-token pricing stops making sense at volume. It is not a fit for general-purpose GPU compute, training your own stack with custom images, or anything needing root access; for raw GPU rentals, compare the VM providers in our tables. A formal public uptime SLA for on-demand deployments was not found on the pages reviewed. Not publicly documented.
Similar providers
DataCrunch
European GPU cloud, per-minute billing, spot options.
from $0.212/hr on-demand
5 GPU families in common
Prime Intellect
Compute marketplace aggregating multiple clouds; on-demand and spot.
from $2.43/hr on-demand
4 GPU families in common
Lium
GPU marketplace. Rates, rental minimums and availability come from its public node feed. The listing link lets Lium count referrals; no commission is arranged.
from $0.12/hr marketplace host
4 GPU families in common
Ranked by overlap in the GPU models both providers list today; not an endorsement and never affected by commercial relationships.
FAQ
No. On-demand deployments provide dedicated GPUs running your model on the Fireworks platform, billed per GPU-second. There is no VM or SSH access, so we label the rates serverless.
The current table lists H100 80GB, H200 141GB, B200 180GB and B300 288GB.
Most of the page prices serverless inference per token and fine-tuning per training token. Those are model prices, not per-GPU-hour rental prices, so only the on-demand GPU deployment table qualifies for our index.
Profile updated 2026-07-18. Sources: fireworks.ai · fireworks.ai