Which is better, Fly Sprites or Northflank?
It depends on whether your agent waits or computes. For an agent that spends most of a run waiting on a model, Runtime costs the least: $0.64 for 1,000 one-minute runs, against $1.11 on Northflank and $2.40 on Sprites, because it meters CPU and charges little for memory. Pick Northflank for CPU-bound jobs, where its allocated rate costs less; for GPUs; or for your own cloud account. Pick Fly Sprites for a 100 GB disk that costs little while asleep, and filesystem checkpoints that take about a second.
At a glance
Northflank's isolation and regions are from its sandbox page, read 26 October 2026.
| Fly Sprites | Northflank | Runtime | |
|---|---|---|---|
| Isolation | Firecracker microVM | microVMs for CPU workloads, gVisor for GPU workloads | Firecracker microVM, own kernel |
| CPU | $0.0385 per CPU-hour of measured CPU | $0.01667 per allocated vCPU-hour | $0.025 per vCPU-hour of measured CPU, with a small floor |
| Memory | $0.021875 per GB-hour of memory in use | $0.00833 per GB-hour | $0.0075 per reserved GiB-hour |
| Idle | Pauses itself about 30 seconds after the last activity | Ephemeral by default; volumes and databases for state | Pause keeps files, memory and processes while you have credit |
| Lifetime | Persistent; the disk survives every pause | No time limit, in Northflank's words | No time limit: runs while it works, or persistent: true |
| Plan fee | None required; optional monthly plans | None published for compute | None; prepaid credit from $10 |
| Free start | $30 of trial credit | 2 services, 2 jobs and 1 database free | 100 free hours of a 1 GB machine in the first 30 days, no card |
| Sandbox model | A Sprite, created by name | A service with a deployment plan | A sandbox, created in one call |
Is paying only for the CPU you use always cheaper?
No. What matters is the price of each meter, and memory is where the two differ. A Sprite's memory costs $0.021875 per GB-hour; Northflank's costs $0.00833, under half. In the example below, a Sprite's 4 GB of memory alone costs $2.19 per 1,000 runs, where Northflank's whole bill, CPU and memory, is $1.11.
Metering CPU helps Sprites only on the CPU line: $0.21 for 20 CPU-seconds per run, against Northflank's $0.56 for two allocated vCPUs. With both CPUs busy the whole minute, Sprites' CPU line rises to $1.28 and Northflank's stays where it was.
Runtime pairs metered CPU at $0.025 per vCPU-hour with the lowest memory rate of the three, $0.0075 per GiB-hour. That makes it the cheapest option while an agent waits. Northflank's allocated vCPU rate is lower still, so for work that keeps every CPU busy the whole time, Northflank costs less.
Cost for the same job
Priced for 1,000 runs of 60 seconds on 2 vCPU and 4 GiB (4 GB on each other provider), with 20 CPU-seconds of work per run. The Sprite is billed as though all 4 GB are in use for the full minute.
- CPU
- 1,000 × 20 s / 3,600 × $0.0385
- $0.21
- Memory
- 1,000 × 90 s / 3,600 × 4 × $0.021875
- $2.19
- CPU
- 1,000 × 60 s / 3,600 × 2 × $0.01667
- $0.556
- Memory
- 1,000 × 60 s / 3,600 × 4 × $0.00833
- $0.555
- CPU
- 1,000 × 20 s / 3,600 × $0.025
- $0.14
- Memory
- 1,000 × 60 s / 3,600 × 4 × $0.0075
- $0.50
At 100,000 runs per month, the totals are $240.14 on Sprites, $111.10 on Northflank and $63.89 on Runtime. With both CPUs busy for the whole minute, it is $1.11 on Northflank, $1.33 on Runtime and $3.47 on Sprites, so for code that never pauses, Northflank's allocated rate is the cheapest. A Sprite using only 1 GB would pay $0.76 for the waiting job. Plan fees, storage, network and free allowances are left out.
Which one to pick
- Fly Sprites, for a 100 GB disk that costs little to keep while the Sprite sleeps, and checkpoints of the filesystem that take about a second.
- Northflank, for CPU-bound jobs, GPUs as large as B200, or sandboxes placed in your own AWS, GCP, Azure or Oracle account.
- Runtime, for agents that wait on a model: the lowest price of the three for that pattern, a pause that keeps memory and processes, and forks of a running sandbox.
Runtime Cloud
Metering CPU is not enough on its own. Runtime meters CPU and charges little for memory, so it costs 73% less than Sprites and 42% less than Northflank for a waiting agent. 1,000 one-minute runs of a 2 vCPU, 4 GiB sandbox cost $2.40 on Fly Sprites, $1.11 on Northflank and $0.64 on Runtime. Runtime's CPU rate is 35% below Sprites', and its memory rate is below both. Rates checked 25 October 2026.
A Runtime pause keeps memory and processes, and there is no plan fee. Start free with npx withruntime login, then follow the migration guide to move existing code.
Moving to Runtime
A Sprite you reach by name maps to a named Runtime sandbox, which is woken if paused and created if it does not exist yet:
Pythonfrom withruntime import Sandboxdev = Sandbox.get_or_create("agent-42", idle_pause_seconds=300)dev.exec("git pull || true")Other Sprites calls map directly: client.createSprite(name) is
Sandbox.create(), and sprite.execFile(cmd, args) is
exec([cmd, ...args]). On Northflank, the service and deployment plan
collapse into one create call. npx withruntime compare --from fly or
--from northflank reprices past usage. Credit you add within 30 days of signing up is matched, up to $1,000 in total. A coding agent can
make the change from the one instruction in migration, on a
branch and on the free usage. See
Runtime vs Fly.io and
Runtime vs Northflank.
Sources
Fly.io prices checked 25 October 2026.
Rates checked 25 October 2026; the Sprites, Sprites lifecycle and Northflank sandbox pages read 26 October 2026.
- Fly.io pricing, Sprites, Sprites lifecycle
- Northflank pricing, Northflank sandboxes, Sandboxes on Northflank
- Runtime pricing and Python SDK
Facts on this page were checked on 26 October 2026.