Changelog

Four RapidAPI plans and controlled public HTTPS

V4.0 makes the commercial model easier to understand and adds opt-in managed public HTTPS for paid API plans. Pro remains the recommended paid entry point, Ultra is positioned for serious workflows, and Mega adds the highest marketplace request allowance for teams and scale.

• Basic: $0/month with 500 requests per RapidAPI subscription period.
• Pro: $19/month with 10,000 requests; Ultra: $49/month with 50,000; Mega: $149/month with 200,000, each per RapidAPI subscription period.
• One call to any endpoint is one RapidAPI request. One batch call remains one request regardless of item count; each session endpoint call is separate.
• RapidAPI measures bandwidth in 1 MB units, with 10,240 MB/month currently included on every plan, then charges $0.001 per MB above that allowance.
• Network remains off by default. Basic and playground workloads are denied; Pro can opt in to managed public HTTPS, and Ultra or Mega can optionally add up to 32 exact or explicit wildcard domain rules.
• The managed proxy is HTTPS CONNECT-only on port 443, blocks raw-IP and non-public destinations, pins DNS, enforces TLS SNI, uses short-lived signed execution tokens, meters transfer, and writes structured operator logs.
• Customer-facing audit logs and a static egress IP remain planned or deployment-dependent.
• Paid per-RapidAPI-account session ceilings are Pro 2, Ultra 5, and Mega 8. RapidAPI owns the 500 / 10,000 / 50,000 / 200,000 request allowances on each subscription period; SandboxAPI enforces 15 / 30 / 60 / 60 requests-per-minute burst limits per subscriber identity and has no duplicate calendar-month allowance counter. Sync, stream, session, hosted MCP, and batch work stops at 150s under RapidAPI's 180s gateway, while production async alone exposes Ultra 300s and Mega 600s. Mega accepts up to 200 batch items, has a 30-minute idle maximum, and uses the curated popular-package cache with 300 installs per subscriber identity/hour. Package installs publish only explicitly requested artifacts: pip accepts cached wheels only with --only-binary=:all: --no-deps --no-build-isolation and rejects source distributions, while npm uses validated npm pack --ignore-scripts extraction with dependency and lifecycle-script metadata removed. Batch items run through bounded workers within the 150-second request wall.
• Session caps are per-RapidAPI-account ceilings. Shared service capacity is not reserved; during saturation, session creation may return HTTP 503 with Retry-After.
• The hosted MCP adapter now exposes four stateless tools and forwards one tool invocation to exactly one RapidAPI endpoint call. Sessions, package install, managed HTTPS, streaming, and async remain REST-only; one-click OAuth onboarding is planned.

Package installation in sessions

The piece that makes code interpreters credible. Inside supported sessions, your agent can install packages through cached package mirrors. A curated popular-package list per ecosystem is cached for fast installs. The session container itself keeps network egress disabled.

• New POST /v1/sessions/{id}/install endpoint.
• Stable public managers: pip for Python and npm for JavaScript/TypeScript.
• Curated popular packages cached locally for fast installs.
• An MCP package-install schema was introduced, but the hosted service did not wire a session manager; V4 removes that unsupported tool from discovery.

Stateful sessions

Persistent sandboxes that retain files and installed packages across calls. The single biggest unlock for AI-agent code interpreters: setup work survives the next retry. Sessions auto-renew on activity and expire at the idle TTL.

• POST /v1/sessions, POST /v1/sessions/{id}/execute, GET /v1/sessions/{id}, DELETE /v1/sessions/{id}.
• Per-API-key concurrent session limits enforced by tier (5 / 20).
• Idle TTL up to 30 minutes; auto-renew on execute and install.

Streaming output and async polling

Two long-requested integration modes shipped together. Streaming uses Server-Sent Events to deliver live stdout/stderr as code runs. Async lets you enqueue long jobs and poll for completion.

• POST /v1/execute/stream — SSE events: stdout, stderr, result.
• POST /v1/execute?async=true — returns job_id and poll_url; results are polled at /v1/executions/{job_id}.

Ultra tier, gVisor, and the playground

Phase 1's flagship release. Adds the Ultra tier (50K exec/mo), enables gVisor isolation as the default runtime, raises batch size to 100, lifts the timeout to 300s, and ships the public playground at sandboxapi.dev/playground.

Sandbox pre-warming

Pre-warmed sandbox pools take container creation off the request path for pooled languages (historical 1.2.0 measurement; Java and pool misses still create a container on demand). Adds memory_used_kb to the response.

Batch execution

New POST /v1/execute/batch endpoint runs up to 50 snippets in a single round trip — perfect for grading and bulk validation.

Stable release

API surface frozen. Pro tier launches. Standard rate-limit headers (X-RateLimit-Remaining, X-RateLimit-Reset) included on every response. GET /health endpoint and the full error-code taxonomy land.

All 8 launch languages, stdin

Adds Java, C, C++ to bring Phase 1 language coverage to 8. Adds stdin support and the /v1/languages discovery endpoint.

TypeScript, Go, Bash

First language expansion. TypeScript transpiles via tsc, Go compiles per-call, Bash runs via the system shell — all under gVisor.

Alpha — Python and JavaScript

The first cut. Synchronous execution only, two languages, no batch, no stdin. Just enough to prove the model.