serverless inference · api · Layer 2.5
Fireworks AI
Latency-sensitive open-weight inference where throughput per dollar matters more than owning the stack.
low portability Sticky. Leaving means rewriting against a different interface, not changing a hostname.
What you are buying
- Business model
- You never see a GPU. You send a request and pay per token or per second of execution.
- How you reach it
- You call an endpoint. There is no infrastructure to see, and no infrastructure to move.
- Accelerators
- Not disclosed per endpoint; NVIDIA datacentre class
- Regions
- US
- Pricing model
- Per token, with dedicated deployments available.
- Getting started
- API key.
- Capacity
- Good on popular open-weight models.
- Ownership
- Private.
Verified 2026-09-09. Fields reading “not published” are exactly that — we do not estimate a figure a vendor withholds.
The counterparty
Low for serverless use. The lock-in is the tuned-model artefact, not the compute.
A multi-year GPU commitment is a credit decision wearing a cloud contract. This is the section no benchmark covers and the one that decides what happens to your workload in 2028.
The catch
Serving optimisations are the product and they are proprietary. Benchmarks against a self-hosted baseline are not portable to your own hardware.
The economics
Compete on tokens per second per dollar rather than on raw GPU price. Measure with your prompt shape, not theirs.
No rate is quoted on this page on purpose. Published list prices at this layer move weekly and essentially nobody signing a real contract pays them. Dated, sourced figures live in the GPU rental price index, where the spread between the cheapest and dearest seller of the identical chip runs to roughly 9x.
The layers underneath this one
Whatever you rent here is a chip in a building that needs power. In 2026 megawatts, not silicon, are the binding constraint on the whole industry — a frontier rack draws 120–200 kW against a 2026 average near 27 kW, and the US interconnection queue exceeds 2,600 GW.
Layer 2 — Silicon · Layer 1 — Energy · The interconnection queue · Tokens per watt
Compared against
- Together AI vs Fireworks AI — Per-token serving where the benchmark that matters is your prompt shape, not theirs.Compare with Together AI
Related providers
- Baseten — serverless inference, low portability
- Replicate — serverless inference, low portability
- Together AI — serverless inference, low portability
- Modal — serverless inference, low portability
- Akash Network — marketplace, medium portability
- AWS (P5, P6, G6) — hyperscaler, medium portability