Riza

Riza — WASM-isolated code interpreter API for LLM output, with no filesystem or network. Riza compiles language runtimes to WebAssembly and runs untrusted code inside a WASM sandbox with no filesystem and no network unless you explicitly grant them. That makes it the strictest isolation model here and the most limited: no package installs, no processes, no shell. For the narrow case of evaluating a model's Python or JavaScript safely and instantly, the constraint is the feature. Founded 2024. Seed.

We track it in 1 comparison — Sandbox providers — so every claim below is a cell in a table you can open and check rather than an impression. Across those rosters it sits against 19 other tools, and what follows is where it visibly separates from them.

Where it wins.

• Cold start — 120 ms, the best figure of the 16 here.
• Idle cost — free-when-stopped, tied for best across 5 of 16 tools.

Each of those is ranked against the whole roster on its category page, not against a hand-picked subset, so a first place here means first of everything we list.

Where it gives ground.

• Snapshot & fork — No. Daytona records Yes.
• Custom images — No. E2B records Yes.
• Streaming output — No. E2B records Yes.
• Max runtime — 1 min, the weakest of the 16 here. E2B records 1440 min.

None of these disqualify it on their own. They are the fields to check against your own requirements before you commit, because they are the ones where a competitor genuinely does better.

Provenance. 22 of 26 tracked fields carry a value for Riza, and 5 of those cite a document you can open. Last verified 2026-01-15. Every figure keeps its own provenance — measured by us, claimed by the vendor, inferred, or community-reported — and we would rather print a dash than a guess.

Its nearest neighbour in our data is ascii. Riza is ahead on Meter (per-request against subscription). ascii takes Root in guest (Yes against No) and Snapshot & fork (Partial against No). That pattern repeats across the rest of the roster — see Riza alternatives for the other rivals, each compared the same way.

Founded

2024

Funding

Seed

Fields we track

22 of 26

Last verified

2026-01-15

The strictest isolation on the page and the smallest blast radius: no filesystem, no network, no processes unless you ask. That constraint is exactly right for evaluating a model's arithmetic or data transform, and completely wrong for anything that needs to install a dependency.

Cold start

120 ms1st of 16

Inferred

Snapshot & fork

○No15th of 18

Inferred

Custom images

○No18th of 20

Vendor-claimedverified 2026-01-15source

Streaming output

○No15th of 16

Inferred

Idle cost

free-when-stopped1st of 16

Inferred

Max runtime

1 min16th of 16

Inferred

Persistent FS

○No14th of 16

Vendor-claimedverified 2026-01-15source

Preview URLs

○No18th of 19

Inferred

Riza is the right call in these situations, each one drawn from a field we actually record:

• Executing model-written expressions with the tightest possible default.
• Multi-language interpreter tooling without maintaining images.
• You want deny-by-default network and filesystem out of the box.
• Cold start is your binding constraint. Riza records 120 ms, the best figure in the Sandbox providers roster. We define that field as p50 wall-clock from a single client in a fixed region calling create-sandbox on an account with nothing running, until a trivial command returns output.
• Idle cost is your binding constraint. Riza records free-when-stopped, the best figure in the Sandbox providers roster. We define that field as what you pay while a sandbox exists but is doing nothing — the common case when an agent is blocked on model inference.

Reach for something else when any of the following is a requirement rather than a nice-to-have:

• Snapshot & fork. Riza records No on the Sandbox providers table. Daytona records Yes on the same field. If that is a hard requirement rather than a preference, start elsewhere.
• Custom images. Riza records No on the Sandbox providers table. E2B records Yes on the same field. If that is a hard requirement rather than a preference, start elsewhere.
• Streaming output. Riza records No on the Sandbox providers table. E2B records Yes on the same field. If that is a hard requirement rather than a preference, start elsewhere.
• Max runtime. Riza records 1 min, the weakest of the 16 tools in the Sandbox providers roster. E2B records 1440 min on the same field. If that is a hard requirement rather than a preference, start elsewhere.
• Persistent FS. Riza records No on the Sandbox providers table. Modal records Yes on the same field. If that is a hard requirement rather than a preference, start elsewhere.

We publish this block because a comparison that only lists what a tool is good at is marketing. Every figure above sits on the same page as its source, and the field definitions are on the category tables if you want to check how we measured them.

What we don't know. 4 of the 26 fields we track for Riza are still blank: Cold start (claimed), Concurrent limit, Price / hour and GitHub stars. Those render as dashes rather than as zeroes or assumptions, because an empty cell and a bad cell are not the same thing and only one of them is honest. If you know any of these figures and can point at a document, tell us.