Runars vs Fireworks AI

Fast is table stakes. Canadian is the difference.

Fireworks AI serves open models fast, from US regions. Runars serves them from Canada, billed in CAD, with the same OpenAI and Anthropic APIs.

Get an API keySkip to the table

Credit where due

Fireworks is one of the fastest inference platforms around, and it processes an enormous volume of tokens every day. We won't pretend otherwise.

Data residency

Zero border crossings.

Fireworks' serverless platform runs in US regions, and its data-residency option pins traffic to the US. If your requirement is Canada, only a dedicated custom deployment gets close. On Runars, Canada is the default.

request trace
  1. 1your app🇨🇦 Canada
  2. 2runars.ca/v1🇨🇦 Canada
  3. 3inference🇨🇦 Montreal · Calgary
  4. 4logs + prompt cache🇨🇦 Canada

border crossings: 0

Billing

Priced in dollars. Canadian ones.

Your invoice is in CAD with the right GST/HST/PST for your province, so finance doesn't reconcile a USD card charge against a moving exchange rate every month.

invoice.pdf
Usage (tokens)CAD
GST/HSTby province
CurrencyCAD
FX surprise$0.00

Compatibility

Keep your code. Change one URL.

Runars speaks both the OpenAI and Anthropic APIs natively. Swap the base URL and key; your SDK, your agents and Claude Code keep working.

app.py
client = Anthropic(
  base_url="https://runars.ca",
  api_key=os.environ["RUNARS_API_KEY"],
)

# OpenAI SDK works too — same key.

Head to head.

The short version, row by row. Every Fireworks AI claim links to a source at the bottom of the page.

Canadian data residency
Runars
Inference, logs and prompt cache stay in Canada (Montreal & Calgary).
Fireworks AI
Serverless runs in US regions.
Billing currency
Runars
Billed in CAD with GST/HST/PST by province. No FX line on your invoice.
Fireworks AI
USD.
Anthropic Messages API
Runars
Native /v1/messages — point the Anthropic SDK or Claude Code at runars.ca.
Fireworks AI
Yes.
Pay per token, no minimum
Runars
Pay per token. No base fee, no minimum, no idle GPUs.
Fireworks AI
Yes, postpaid serverless.
GLM 5.3 · GLM 5.3 Flash · Kimi K3
Runars
GLM 5.3, GLM 5.3 Flash and Kimi K3, served from Canada.
Fireworks AI
All three.
Raw throughput
Runars
Solid for production agents; not our headline.
Fireworks AI
Among the fastest providers measured.

Switch in one line.

Point your existing OpenAI or Anthropic SDK at Runars and keep your code. If we're not the right fit next to Fireworks AI, we'll tell you.

base_url = "https://…"
base_url = "https://runars.ca/v1"
Get an API keyRead the quickstart

Two minutes. No sales call.

Sources · checked 2026-09-25

Fireworks AI is a trademark of its owner and is referenced here for comparison only. Competitor details change; check Fireworks AI's site for current terms. Spotted something out of date? Tell us and we'll fix it.