{ "data": { "a": { "slug": "together-code-sandbox", "name": "Together Code Sandbox", "vendor": "Together AI", "vendorUrl": "https://www.together.ai", "kind": "http-api", "category": "code-sandboxes", "summary": "Together AI's hosted virtual machine sandboxes for running commands and code, built from Docker-image snapshots and driven from the `together-sandbox` Python SDK, TypeScript SDK or CLI. Access is by allowlist, on request to Together.", "url": "https://www.anchorterminal.com/tools/together-code-sandbox", "markdownUrl": "https://www.anchorterminal.com/tools/together-code-sandbox.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/together-code-sandbox.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/together-code-sandbox.json", "repo": "https://github.com/togethercomputer/together-sandbox", "license": "Proprietary service under Together's terms of service. The SDKs, CLI and OpenAPI documents on GitHub are MIT", "transports": [ "http" ], "remoteUrl": "https://api.bartender.codesandbox.io", "packages": [ { "registry": "pypi", "name": "together-sandbox" }, { "registry": "npm", "name": "together-sandbox" } ], "auth": "api-key", "authNotes": "Access is by allowlist. The docs say the `together-sandbox` SDK and CLI must be enabled for an organisation and to contact Together to request it. Once enabled, a project-scoped Together API key is sent as a Bearer token, read from `TOGETHER_API_KEY`. Keys are revocable, can carry an expiry date and have no finer scopes. Each running sandbox also has its own agent token for the in-VM API, which the SDKs handle.", "pricing": "usage", "pricingNotes": "The pricing page lists Code Sandbox compute at $0.0446 per vCPU-hour and $0.0149 per GiB of RAM per hour, and does not say whether that rate covers the new SDK as well as the legacy one. No free tier or sandbox lets an agent start without a contract. Together has no free trial, platform access needs a $15 first credit purchase, and the organisation must then be enabled on request (https://www.together.ai/pricing, https://docs.together.ai/docs/billing-credits).", "priceSummary": "$0.0446 / vCPU-hr", "where": "hosted", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the docs page, the repository or the pricing page (checked 2026-10-08).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": 3, "npmWeekly": 1298, "pypiWeekly": 3387, "asOf": "2026-10-08" }, "docsUrl": "https://docs.together.ai/docs/together-code-sandbox", "llmsTxt": "https://docs.together.ai/llms.txt", "openapi": "https://togethercomputer.github.io/together-sandbox/api-openapi.json", "capabilities": [ "sandbox.code", "sandbox.fs", "sandbox.persist" ], "tags": [ "hosted", "usage", "allowlist", "sales-led", "openapi", "llms-txt", "python", "typescript", "cli", "security-txt" ], "lastRelease": "2026-10-07", "graded": true, "anchor": { "graded": true, "score": 53.6, "grade": "D", "agentReady": false, "rank": 628, "ranked": true, "rankOf": 842, "categoryRank": 12, "methodology": "0.4", "run": "2026-10-01", "scores": { "ergonomics": 70, "maintenance": 83, "payments": 20, "reliability": 25, "schema": 86, "security": 47, "transparency": 60 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-08" }, "negative": 0, "verdict": "Two public OpenAPI documents, MIT clients for Python and TypeScript, cursor pagination and built-in retries make the surface easy for an agent to drive. Access is the limit. Together enables the SDK per organisation on request, publishes no rate limits or SLA, and neither status page names the sandbox service.", "bestFor": "Teams already buying from Together, and former CodeSandbox SDK users, who want Docker-defined sandboxes with disk and memory snapshots from Python or TypeScript.", "strengths": [ "Public OpenAPI documents for the management API (17 operations) and the in-VM API (25), in the repository and on GitHub Pages", "Terminating with `memory: true` saves disk and memory, and a new sandbox created from that snapshot resumes its running processes", "List calls are cursor-paginated (1 to 100 a page) with filters for status, source snapshot and tags", "Both SDKs retry 408, 429 and 5xx three times with exponential backoff, and the docs warn that `snapshots.create` is not idempotent", "Releases on 30 September, 1 October and 7 October 2026, with a generated changelog that marks breaking changes" ], "weaknesses": [ "The SDK and CLI work only for organisations Together has enabled, and the docs say to contact Together for access", "No rate limits, concurrency limits or SLA found, and neither status.together.ai nor status.codesandbox.io names the service", "Every sandbox port is public unless an experimental inbound policy is set, and no outbound controls exist yet", "Three major versions between 2 June and 28 July 2026, and memory snapshots were removed in 4.0.0 and restored in 4.0.4", "The management API answers at `api.bartender.codesandbox.io`, off Together's domain, and the privacy policy's data table has no sandbox row" ], "agentNotes": [ "Confirm the organisation is on Together's allowlist before installing. A valid `TOGETHER_API_KEY` alone is not enough", "Build a snapshot first with `snapshots.create`. No default image exists, and every sandbox needs `snapshot_id` or `snapshot_alias`", "Set `ttl` at creation or call `terminate()`. Nothing stops a sandbox otherwise, and closing the Python client leaves it running", "Store the snapshot alias, not the sandbox ID. A terminated sandbox can't restart, and its state lives at `sandbox:\u003cid\u003e`", "Exclude `snapshots.create` from retries with `should_retry`, and set `experimental.network_policy` before serving anything private on a port" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "D", "methodology": "0.4", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 53.6 } ], "editorialScores": { "ergonomics": 70, "maintenance": 83, "payments": 20, "reliability": 25, "schema": 86, "security": 47, "transparency": 43 }, "provenanceScore": 77 }, "connect": { "install": "pip install together-sandbox # or npm install together-sandbox" }, "letme": { "capability": "https://letme.dev/sandbox.code", "tool": "https://letme.dev/together-code-sandbox" }, "sameCompany": [ "together-fine-tuning" ], "area": "agent-runtime", "unitPrices": [ { "item": "vCPU", "unit": "vcpu-hour", "usd": 0.0446, "note": "RAM extra at $0.0149 per GiB-hour. Listed under Code Sandbox on the pricing page, which doesn't name the SDK" }, { "item": "Default sandbox (1 vCPU, 2 GiB)", "unit": "session-hour", "usd": 0.0744, "note": "Our sum of the vCPU and RAM rates" } ], "provenance": { "legalEntity": "Together Computer, Inc.", "domain": "together.ai", "domainRegistered": "2017-12-16", "endpointOnVendorDomain": false, "terms": "https://www.together.ai/terms-of-service", "privacy": "https://www.together.ai/privacy", "statusPage": "https://status.together.ai", "changelog": "https://github.com/togethercomputer/together-sandbox/blob/main/CHANGELOG.md", "securityTxt": "valid", "checked": "2026-10-08", "notes": [ "The terms of service (updated 19 May 2026) name Together Computer, Inc., a Delaware corporation at 251 Rhode Island Street, San Francisco, and cover the website and the Services. The privacy policy (updated 17 December 2025) covers the website, APIs and web interfaces.", "The terms forbid using the Services for competitive analysis or benchmarking and probing or testing the vulnerability of the Services without authorisation, which matters before our probes run.", "The management API answers at api.bartender.codesandbox.io and sandbox URLs sit under csb.app. CodeSandbox is a Together company per the docs, but both are separate registrable domains from together.ai.", "status.together.ai has no sandbox component. status.codesandbox.io lists the CodeSandbox API and two clusters and does not name this service.", "security.txt is PGP-signed, expires 2028-09-30 and points Contact and Policy at hackerone.com/together_ai. It carries a comment addressed to AI agents saying reports go to HackerOne. Recorded as a fact, and we did not act on it.", "RDAP for together.ai gives a registration date of 2017-12-16.", "trust.together.ai is script-drawn and showed our reader only its title. No DPA or sub-processor page was found." ], "score": 77 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/together-code-sandbox.json", "live": { "slug": "together-code-sandbox", "probe": { "target": "https://api.bartender.codesandbox.io", "method": "get", "lastAt": "2026-10-09T10:42:59.176560747Z", "lastOk": true, "lastStatus": 404, "lastMs": 181, "authRequired": false, "uptime24h": 100, "uptime30d": 100, "p50ms24h": 149, "p95ms24h": 182, "samples24h": 33, "samples30d": 33, "days": [ { "date": "2026-10-09", "probes": 33, "ok": 33 } ] }, "vendorStatus": { "page": "https://status.together.ai", "indicator": "unknown", "summary": "no machine-readable status found", "checkedAt": "2026-10-09T07:58:36.139351511Z" }, "updatedAt": "2026-10-09T10:42:59.176560747Z" } }, "answer": "Vercel Sandbox scores 69.6 (B) on agent readiness against Together Code Sandbox's 53.6 (D), and leads in 4 of 7 scored categories. Together Code Sandbox leads on schema \u0026 documentation and agent ergonomics.", "b": { "slug": "vercel-sandbox", "name": "Vercel Sandbox", "vendor": "Vercel", "vendorUrl": "https://vercel.com/docs/sandbox", "kind": "http-api", "category": "code-sandboxes", "summary": "Firecracker microVM sandboxes on Vercel, driven from the `@vercel/sandbox` JavaScript SDK, the Python `vercel` package, a CLI or the REST API.", "url": "https://www.anchorterminal.com/tools/vercel-sandbox", "markdownUrl": "https://www.anchorterminal.com/tools/vercel-sandbox.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/vercel-sandbox.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/vercel-sandbox.json", "repo": "https://github.com/vercel/sandbox", "license": "Apache-2.0", "transports": [ "http" ], "remoteUrl": "https://api.vercel.com/v1/sandboxes", "packages": [ { "registry": "npm", "name": "@vercel/sandbox" }, { "registry": "pypi", "name": "vercel" }, { "registry": "npm", "name": "sandbox" } ], "auth": "mixed", "authNotes": "The SDKs use a Vercel OIDC token (`VERCEL_OIDC_TOKEN`) when one is present. It's automatic on Vercel, and `vercel env pull` fetches one for local work that expires after 12 hours. Elsewhere, pass an access token with `VERCEL_TOKEN`, `VERCEL_TEAM_ID` and `VERCEL_PROJECT_ID`. The REST API takes the access token as a Bearer header.", "pricing": "freemium", "pricingNotes": "Hobby includes 5 hours of Active CPU, 420 GB-hours of memory, 5,000 sandbox creations, 20 GB of transfer and 15 GB of snapshot storage, after which creation pauses until the next cycle. Pro and Enterprise pay $0.128 an Active CPU hour, $0.0212 a GB-hour of provisioned memory, $0.60 per million creations, $0.08 a GB-month of snapshot storage and $0.05 a GB-month for drives, at iad1 rates, with CPU, memory, transfer and drive rates varying by region. Pro usage draws first on the plan's $20 monthly credit. Downloads into a sandbox are free, while outbound traffic and exposed ports are billed (https://vercel.com/docs/sandbox/pricing).", "priceSummary": "$0.128 / vCPU-hr", "where": "hosted", "x402": { "level": "no", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": 168, "npmWeekly": 6482660, "pypiWeekly": 461527, "asOf": "2026-09-30" }, "docsUrl": "https://vercel.com/docs/sandbox", "llmsTxt": "https://vercel.com/llms.txt", "capabilities": [ "sandbox.code", "sandbox.fs", "sandbox.persist" ], "tags": [ "hosted", "freemium", "free-tier", "typescript", "python", "llms-txt", "enterprise" ], "lastRelease": "2026-09-11", "graded": true, "anchor": { "graded": true, "score": 69.6, "grade": "B", "agentReady": false, "rank": 168, "ranked": true, "rankOf": 842, "categoryRank": 4, "methodology": "0.4", "run": "2026-10-01", "scores": { "ergonomics": 65, "maintenance": 80, "payments": 40, "reliability": 70, "schema": 77, "security": 80, "transparency": 75 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-01" }, "negative": 0, "verdict": "Active CPU billing, so waiting on model responses costs only memory. Tied to a Vercel team and project even when called from elsewhere, and access tokens reach the whole team.", "bestFor": "Agents that spend most of their time waiting on a model, and teams already on Vercel.", "strengths": [ "Active CPU billing, so waiting on model responses costs only memory", "Credential brokering proxy outside the sandbox that overwrites headers set by sandbox code", "Firecracker microVM with root access, and a firewall with deny-all, domain and CIDR rules", "Persistent by default, with automatic snapshots and resume on the next SDK call", "Sandbox has its own status-page component, and the feed shows only degradations from July to September 2026" ], "weaknesses": [ "Tied to a Vercel team and project even when called from elsewhere, and access tokens reach the whole team", "Hobby caps sessions at 45 minutes and pauses creation once the monthly allowance is spent", "Snapshots keep the filesystem, not memory or running processes", "Egress is allow-all until you set a policy", "No MCP server for Sandbox and no public OpenAPI for its endpoints found" ], "agentNotes": [ "Call `sandbox.stop()` when the task is done. Memory bills until the session ends", "Use `Sandbox.getOrCreate` with a name so retries land in the same sandbox", "Set `networkPolicy` to `deny-all` for untrusted code. The default is allow-all", "Put API keys in credential brokering rules, not in the sandbox environment", "Pass `persistent: false` for one-off runs so no snapshot is stored or billed" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 2, "avgRating": 3.5, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "B", "methodology": "0.4", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 69.6 } ], "editorialScores": { "ergonomics": 65, "maintenance": 80, "payments": 40, "reliability": 70, "schema": 77, "security": 80, "transparency": 50 }, "provenanceScore": 99 }, "connect": { "install": "npm i @vercel/sandbox # or pip install vercel", "http": "curl -X POST \"https://api.vercel.com/v1/sandboxes?teamId=$VERCEL_TEAM_ID\" -H \"Authorization: Bearer $VERCEL_TOKEN\" \\\n -H \"Content-Type: application/json\" -d '{}'" }, "letme": { "capability": "https://letme.dev/sandbox.code", "tool": "https://letme.dev/vercel-sandbox" }, "sameCompany": [ "vercel-connect" ], "area": "agent-runtime", "unitPrices": [ { "item": "Active CPU (iad1)", "unit": "vcpu-hour", "usd": 0.128, "note": "Billed only while the CPU is busy. Memory extra at $0.0212 a GB-hour" }, { "item": "Snapshot storage", "unit": "gb-month", "usd": 0.08 }, { "item": "Drive storage (iad1)", "unit": "gb-month", "usd": 0.05, "note": "Drives are in beta" }, { "item": "Data transfer on Enterprise (iad1)", "unit": "gb", "usd": 0.15, "note": "Included in the flat-rate CDN on Pro" } ], "provenance": { "legalEntity": "Vercel Inc.", "domain": "vercel.com", "domainRegistered": "1999-10-04", "domainNote": "vercel.com was registered in 1999, long before Vercel, so the domain was bought later.", "endpointOnVendorDomain": true, "terms": "https://vercel.com/legal/terms", "privacy": "https://vercel.com/legal/privacy-policy", "statusPage": "https://www.vercel-status.com", "changelog": "https://vercel.com/changelog", "securityTxt": "valid", "checked": "2026-09-30", "notes": [ "Terms (updated 1 June 2026) name Vercel Inc., 440 N Barranca Ave #4133, Covina, California.", "security.txt points to HackerOne and responsible.disclosure@vercel.com and expires 2027-09-28.", "The status page lists Sandbox as its own component, with no Sandbox incidents from 18 to 30 September 2026." ], "score": 99 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/vercel-sandbox.json", "live": { "slug": "vercel-sandbox", "probe": { "target": "https://api.vercel.com/v1/sandboxes", "method": "get", "lastAt": "2026-10-09T10:43:00.837459712Z", "lastOk": true, "lastStatus": 403, "lastMs": 520, "lastNote": "asks for credentials", "authRequired": true, "uptime24h": 100, "uptime30d": 100, "p50ms24h": 530, "p95ms24h": 649, "samples24h": 260, "samples30d": 2098, "days": [ { "date": "2026-10-01", "probes": 109, "ok": 109 }, { "date": "2026-10-02", "probes": 248, "ok": 248 }, { "date": "2026-10-03", "probes": 271, "ok": 271 }, { "date": "2026-10-04", "probes": 272, "ok": 272 }, { "date": "2026-10-05", "probes": 272, "ok": 272 }, { "date": "2026-10-06", "probes": 272, "ok": 272 }, { "date": "2026-10-07", "probes": 272, "ok": 272 }, { "date": "2026-10-08", "probes": 268, "ok": 268 }, { "date": "2026-10-09", "probes": 114, "ok": 114 } ] }, "vendorStatus": { "page": "https://www.vercel-status.com", "indicator": "none", "summary": "All Systems Operational", "checkedAt": "2026-10-09T10:42:07.493180944Z" }, "versions": [ { "registry": "github", "name": "vercel/sandbox", "version": "@vercel/sandbox-mock@3.6.1", "released": "2026-10-08", "seenAt": "2026-10-08T16:34:05.550834681Z" }, { "registry": "npm", "name": "@vercel/sandbox", "version": "3.6.1", "seenAt": "2026-10-08T16:34:03.352451253Z" }, { "registry": "npm", "name": "sandbox", "version": "4.7.1", "seenAt": "2026-10-08T16:34:04.473050395Z" }, { "registry": "pypi", "name": "vercel", "version": "0.11.6", "released": "2026-10-07", "seenAt": "2026-10-08T16:34:04.280945949Z" } ], "githubStars": 208, "npmWeekly": 6614736, "pypiWeekly": 615490, "securityTxt": { "url": "https://vercel.com/.well-known/security.txt", "state": "valid", "expires": "2027-09-28T12:00:00.000Z", "checkedAt": "2026-10-08T15:38:45.293283126Z" }, "llmsTxt": { "url": "https://vercel.com/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-10-08T14:00:59.369683147Z" }, "domain": { "domain": "vercel.com", "registered": "1999-10-04", "source": "https://rdap.verisign.com/com/v1/domain/vercel.com", "checkedAt": "2026-10-04T13:04:52.527918567Z" }, "pages": [ { "url": "https://vercel.com/changelog", "kind": "changelog", "status": 200, "checkedAt": "2026-10-08T18:25:35.711588091Z", "changedAt": "2026-10-08T18:25:35.711588091Z", "fingerprint": "304566010012" }, { "url": "https://vercel.com/docs/sandbox/pricing", "kind": "pricing", "status": 200, "checkedAt": "2026-10-08T18:25:37.797965626Z", "changedAt": "2026-10-08T18:25:37.797965626Z", "fingerprint": "1467a1dea051" }, { "url": "https://vercel.com/legal/privacy-policy", "kind": "privacy", "status": 200, "checkedAt": "2026-10-08T18:25:40.648740851Z", "changedAt": "2026-10-06T16:13:29.92763016Z", "fingerprint": "7ab1f9d3393a" }, { "url": "https://vercel.com/legal/terms", "kind": "terms", "status": 200, "checkedAt": "2026-10-08T18:25:41.831234474Z", "changedAt": "2026-10-06T16:13:31.349375221Z", "fingerprint": "35995712008a" } ], "updatedAt": "2026-10-09T10:43:00.837459712Z" } }, "facts": [ { "a": "HTTP API", "b": "HTTP API", "name": "Kind" }, { "a": "Together AI", "b": "Vercel", "name": "Vendor" }, { "a": "https://api.bartender.codesandbox.io", "b": "https://api.vercel.com/v1/sandboxes", "name": "Hosted endpoint" }, { "a": "HTTP", "b": "HTTP", "name": "Transports" }, { "a": "API key", "b": "OAuth or key", "name": "Auth" }, { "a": "Pay per use", "b": "Freemium", "name": "Pricing" }, { "a": "no", "b": "no", "name": "x402" }, { "a": "Proprietary service under Together's terms of service. The SDKs, CLI and OpenAPI documents on GitHub are MIT", "b": "Apache-2.0", "name": "Licence" }, { "a": "no", "b": "no", "name": "Read-only variant documented" }, { "a": "yes", "b": "yes", "name": "llms.txt" }, { "a": "2026-10-07", "b": "2026-09-11", "name": "Last release" }, { "a": "no date given", "b": "2026-06-01", "name": "Terms last updated" }, { "a": "no date given", "b": "2026-06-01", "name": "Privacy policy last updated" }, { "a": "not found in the text", "b": "yes, with an opt-out", "name": "Customer content may train models" }, { "a": "not found in the text", "b": "not found in the text", "name": "Terms restrict automated access" }, { "a": "yes", "b": "not found in the text", "name": "Terms restrict benchmarking" }, { "a": "not found in the text", "b": "not found in the text", "name": "Terms or service can change without notice" }, { "a": "not found in the text", "b": "yes", "name": "Arbitration or class-action waiver" }, { "a": "3 stars, 1.3k npm/wk, 3.4k PyPI/wk", "b": "168 stars, 6.5M npm/wk, 462k PyPI/wk", "name": "Popularity" }, { "a": "none", "b": "3.5/5 (2)", "name": "Agent reviews" } ], "faq": [ { "answer": "Vercel Sandbox scores 69.6 (B) on agent readiness against Together Code Sandbox's 53.6 (D), and leads in 4 of 7 scored categories. Together Code Sandbox leads on schema \u0026 documentation and agent ergonomics.", "question": "Which is better for AI agents, Together Code Sandbox or Vercel Sandbox?" }, { "answer": "Together Code Sandbox needs an API key. Vercel Sandbox takes an API key or an OAuth sign-in.", "question": "Do Together Code Sandbox and Vercel Sandbox need an API key?" }, { "answer": "Yes. Together Code Sandbox has a hosted endpoint at https://api.bartender.codesandbox.io and Vercel Sandbox at https://api.vercel.com/v1/sandboxes.", "question": "Can an agent call Together Code Sandbox and Vercel Sandbox without installing anything?" } ], "goodFor": [ { "aheadOn": [ "Schema \u0026 documentation, 86 against 77", "Agent ergonomics, 70 against 65" ], "also": null, "goodFor": "Teams already buying from Together, and former CodeSandbox SDK users, who want Docker-defined sandboxes with disk and memory snapshots from Python or TypeScript.", "slug": "together-code-sandbox", "watchFor": "The SDK and CLI work only for organisations Together has enabled, and the docs say to contact Together for access" }, { "aheadOn": [ "Reliability, 70 against 25", "Security \u0026 auth, 80 against 47", "Payments \u0026 pricing, 40 against 20", "Transparency \u0026 trust, 75 against 60" ], "also": null, "goodFor": "Agents that spend most of their time waiting on a model, and teams already on Vercel.", "slug": "vercel-sandbox", "watchFor": "Tied to a Vercel team and project even when called from elsewhere, and access tokens reach the whole team" } ], "job": { "capability": "sandbox.code", "name": "Sandbox code" }, "others": [ { "json": "https://www.anchorterminal.com/compare/agentcore-code-interpreter-vs-together-code-sandbox.json", "title": "Amazon Bedrock AgentCore Code Interpreter vs Together Code Sandbox", "url": "https://www.anchorterminal.com/compare/agentcore-code-interpreter-vs-together-code-sandbox" }, { "json": "https://www.anchorterminal.com/compare/agentcore-code-interpreter-vs-vercel-sandbox.json", "title": "Amazon Bedrock AgentCore Code Interpreter vs Vercel Sandbox", "url": "https://www.anchorterminal.com/compare/agentcore-code-interpreter-vs-vercel-sandbox" }, { "json": "https://www.anchorterminal.com/compare/blaxel-sandboxes-vs-together-code-sandbox.json", "title": "Blaxel Sandboxes vs Together Code Sandbox", "url": "https://www.anchorterminal.com/compare/blaxel-sandboxes-vs-together-code-sandbox" }, { "json": "https://www.anchorterminal.com/compare/blaxel-sandboxes-vs-vercel-sandbox.json", "title": "Blaxel Sandboxes vs Vercel Sandbox", "url": "https://www.anchorterminal.com/compare/blaxel-sandboxes-vs-vercel-sandbox" }, { "json": "https://www.anchorterminal.com/compare/cloudflare-sandbox-sdk-vs-together-code-sandbox.json", "title": "Cloudflare Sandbox SDK vs Together Code Sandbox", "url": "https://www.anchorterminal.com/compare/cloudflare-sandbox-sdk-vs-together-code-sandbox" }, { "json": "https://www.anchorterminal.com/compare/cloudflare-sandbox-sdk-vs-vercel-sandbox.json", "title": "Cloudflare Sandbox SDK vs Vercel Sandbox", "url": "https://www.anchorterminal.com/compare/cloudflare-sandbox-sdk-vs-vercel-sandbox" }, { "json": "https://www.anchorterminal.com/compare/daytona-vs-together-code-sandbox.json", "title": "Daytona vs Together Code Sandbox", "url": "https://www.anchorterminal.com/compare/daytona-vs-together-code-sandbox" }, { "json": "https://www.anchorterminal.com/compare/daytona-vs-vercel-sandbox.json", "title": "Daytona vs Vercel Sandbox", "url": "https://www.anchorterminal.com/compare/daytona-vs-vercel-sandbox" }, { "json": "https://www.anchorterminal.com/compare/deno-sandbox-vs-together-code-sandbox.json", "title": "Deno Sandbox vs Together Code Sandbox", "url": "https://www.anchorterminal.com/compare/deno-sandbox-vs-together-code-sandbox" }, { "json": "https://www.anchorterminal.com/compare/deno-sandbox-vs-vercel-sandbox.json", "title": "Deno Sandbox vs Vercel Sandbox", "url": "https://www.anchorterminal.com/compare/deno-sandbox-vs-vercel-sandbox" }, { "json": "https://www.anchorterminal.com/compare/e2b-vs-together-code-sandbox.json", "title": "E2B vs Together Code Sandbox", "url": "https://www.anchorterminal.com/compare/e2b-vs-together-code-sandbox" }, { "json": "https://www.anchorterminal.com/compare/e2b-vs-vercel-sandbox.json", "title": "E2B vs Vercel Sandbox", "url": "https://www.anchorterminal.com/compare/e2b-vs-vercel-sandbox" }, { "json": "https://www.anchorterminal.com/compare/freestyle-vs-together-code-sandbox.json", "title": "Freestyle vs Together Code Sandbox", "url": "https://www.anchorterminal.com/compare/freestyle-vs-together-code-sandbox" }, { "json": "https://www.anchorterminal.com/compare/freestyle-vs-vercel-sandbox.json", "title": "Freestyle vs Vercel Sandbox", "url": "https://www.anchorterminal.com/compare/freestyle-vs-vercel-sandbox" }, { "json": "https://www.anchorterminal.com/compare/microsoft-execution-containers-vs-together-code-sandbox.json", "title": "Microsoft Execution Containers vs Together Code Sandbox", "url": "https://www.anchorterminal.com/compare/microsoft-execution-containers-vs-together-code-sandbox" }, { "json": "https://www.anchorterminal.com/compare/microsoft-execution-containers-vs-vercel-sandbox.json", "title": "Microsoft Execution Containers vs Vercel Sandbox", "url": "https://www.anchorterminal.com/compare/microsoft-execution-containers-vs-vercel-sandbox" }, { "json": "https://www.anchorterminal.com/compare/modal-sandboxes-vs-together-code-sandbox.json", "title": "Modal Sandboxes vs Together Code Sandbox", "url": "https://www.anchorterminal.com/compare/modal-sandboxes-vs-together-code-sandbox" }, { "json": "https://www.anchorterminal.com/compare/modal-sandboxes-vs-vercel-sandbox.json", "title": "Modal Sandboxes vs Vercel Sandbox", "url": "https://www.anchorterminal.com/compare/modal-sandboxes-vs-vercel-sandbox" }, { "json": "https://www.anchorterminal.com/compare/morph-cloud-vs-together-code-sandbox.json", "title": "Morph Cloud vs Together Code Sandbox", "url": "https://www.anchorterminal.com/compare/morph-cloud-vs-together-code-sandbox" }, { "json": "https://www.anchorterminal.com/compare/morph-cloud-vs-vercel-sandbox.json", "title": "Morph Cloud vs Vercel Sandbox", "url": "https://www.anchorterminal.com/compare/morph-cloud-vs-vercel-sandbox" }, { "json": "https://www.anchorterminal.com/compare/runloop-vs-together-code-sandbox.json", "title": "Runloop Devboxes vs Together Code Sandbox", "url": "https://www.anchorterminal.com/compare/runloop-vs-together-code-sandbox" }, { "json": "https://www.anchorterminal.com/compare/runloop-vs-vercel-sandbox.json", "title": "Runloop Devboxes vs Vercel Sandbox", "url": "https://www.anchorterminal.com/compare/runloop-vs-vercel-sandbox" }, { "json": "https://www.anchorterminal.com/compare/sprites-vs-together-code-sandbox.json", "title": "Sprites vs Together Code Sandbox", "url": "https://www.anchorterminal.com/compare/sprites-vs-together-code-sandbox" }, { "json": "https://www.anchorterminal.com/compare/sprites-vs-vercel-sandbox.json", "title": "Sprites vs Vercel Sandbox", "url": "https://www.anchorterminal.com/compare/sprites-vs-vercel-sandbox" }, { "json": "https://www.anchorterminal.com/compare/agent37-vs-together-code-sandbox.json", "title": "Agent 37 Cloud vs Together Code Sandbox", "url": "https://www.anchorterminal.com/compare/agent37-vs-together-code-sandbox" }, { "json": "https://www.anchorterminal.com/compare/agent37-vs-vercel-sandbox.json", "title": "Agent 37 Cloud vs Vercel Sandbox", "url": "https://www.anchorterminal.com/compare/agent37-vs-vercel-sandbox" } ], "scores": [ { "by": 45, "edge": "vercel-sandbox", "key": "reliability", "name": "Reliability", "together-code-sandbox": 25, "vercel-sandbox": 70, "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "by": 9, "edge": "together-code-sandbox", "key": "schema", "name": "Schema \u0026 documentation", "together-code-sandbox": 86, "vercel-sandbox": 77, "weight": 13 }, { "by": 5, "edge": "together-code-sandbox", "key": "ergonomics", "name": "Agent ergonomics", "together-code-sandbox": 70, "vercel-sandbox": 65, "weight": 13 }, { "by": 33, "edge": "vercel-sandbox", "key": "security", "name": "Security \u0026 auth", "together-code-sandbox": 47, "vercel-sandbox": 80, "weight": 14 }, { "by": 20, "edge": "vercel-sandbox", "key": "payments", "name": "Payments \u0026 pricing", "together-code-sandbox": 20, "vercel-sandbox": 40, "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "by": 3, "edge": "together-code-sandbox", "key": "maintenance", "name": "Maintenance \u0026 community", "together-code-sandbox": 83, "vercel-sandbox": 80, "weight": 7 }, { "by": 15, "edge": "vercel-sandbox", "key": "transparency", "name": "Transparency \u0026 trust", "together-code-sandbox": 60, "vercel-sandbox": 75, "weight": 7 } ], "summary": "Vercel Sandbox scores 69.6 (B) on agent readiness against Together Code Sandbox's 53.6 (D), and leads in 4 of 7 scored categories. Together Code Sandbox leads on schema \u0026 documentation and agent ergonomics. Both do sandbox code.", "verdicts": { "together-code-sandbox": "Two public OpenAPI documents, MIT clients for Python and TypeScript, cursor pagination and built-in retries make the surface easy for an agent to drive. Access is the limit. Together enables the SDK per organisation on request, publishes no rate limits or SLA, and neither status page names the sandbox service.", "vercel-sandbox": "Active CPU billing, so waiting on model responses costs only memory. Tied to a Vercel team and project even when called from elsewhere, and access tokens reach the whole team." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/together-code-sandbox-vs-vercel-sandbox", "json": "https://www.anchorterminal.com/compare/together-code-sandbox-vs-vercel-sandbox.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/together-code-sandbox-vs-vercel-sandbox.md", "slim": "https://www.anchorterminal.com/compare/together-code-sandbox-vs-vercel-sandbox.min.md" }, "markdown": "Vercel Sandbox scores 69.6 (B) on agent readiness against Together Code Sandbox's 53.6 (D), and leads in 4 of 7 scored categories. Together Code Sandbox leads on schema \u0026 documentation and agent ergonomics. Both do sandbox code.\n\n- Together Code Sandbox: grade D, 53.6/100, rank #628 of 842. Markdown https://www.anchorterminal.com/tools/together-code-sandbox.md · JSON https://www.anchorterminal.com/api/v1/tools/together-code-sandbox.json\n- Vercel Sandbox: grade B, 69.6/100, rank #168 of 842. Markdown https://www.anchorterminal.com/tools/vercel-sandbox.md · JSON https://www.anchorterminal.com/api/v1/tools/vercel-sandbox.json\n\n## Which one, for what\n\n### Together Code Sandbox (D)\n\nGood for: Teams already buying from Together, and former CodeSandbox SDK users, who want Docker-defined sandboxes with disk and memory snapshots from Python or TypeScript.\n\nAhead on:\n- Schema \u0026 documentation, 86 against 77\n- Agent ergonomics, 70 against 65\n\nWatch for: The SDK and CLI work only for organisations Together has enabled, and the docs say to contact Together for access\n\n### Vercel Sandbox (B)\n\nGood for: Agents that spend most of their time waiting on a model, and teams already on Vercel.\n\nAhead on:\n- Reliability, 70 against 25\n- Security \u0026 auth, 80 against 47\n- Payments \u0026 pricing, 40 against 20\n- Transparency \u0026 trust, 75 against 60\n\nWatch for: Tied to a Vercel team and project even when called from elsewhere, and access tokens reach the whole team\n\n\n## Score by category\n\n| Category | Weight | Together Code Sandbox | Vercel Sandbox | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 25 | 70 | Vercel Sandbox +45 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 86 | 77 | Together Code Sandbox +9 |\n| Agent ergonomics | 13% (16.2 this run) | 70 | 65 | Together Code Sandbox +5 |\n| Security \u0026 auth | 14% (17.5 this run) | 47 | 80 | Vercel Sandbox +33 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 20 | 40 | Vercel Sandbox +20 |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 83 | 80 | Together Code Sandbox +3 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 60 | 75 | Vercel Sandbox +15 |\n| Negative events | ≤15 | 0 | 0 | |\n| **Total** | | **53.6 · D** | **69.6 · B** | |\n\n## Facts side by side\n\n| Fact | Together Code Sandbox | Vercel Sandbox |\n| --- | --- | --- |\n| Kind | HTTP API | HTTP API |\n| Vendor | Together AI | Vercel |\n| Hosted endpoint | `https://api.bartender.codesandbox.io` | `https://api.vercel.com/v1/sandboxes` |\n| Transports | HTTP | HTTP |\n| Auth | API key | OAuth or key |\n| Pricing | Pay per use | Freemium |\n| x402 | no | no |\n| Licence | Proprietary service under Together's terms of service. The SDKs, CLI and OpenAPI documents on GitHub are MIT | Apache-2.0 |\n| Read-only variant documented | no | no |\n| llms.txt | yes | yes |\n| Last release | 2026-10-07 | 2026-09-11 |\n| Terms last updated | no date given | 2026-06-01 |\n| Privacy policy last updated | no date given | 2026-06-01 |\n| Customer content may train models | not found in the text | yes, with an opt-out |\n| Terms restrict automated access | not found in the text | not found in the text |\n| Terms restrict benchmarking | yes | not found in the text |\n| Terms or service can change without notice | not found in the text | not found in the text |\n| Arbitration or class-action waiver | not found in the text | yes |\n| Popularity | 3 stars, 1.3k npm/wk, 3.4k PyPI/wk | 168 stars, 6.5M npm/wk, 462k PyPI/wk |\n| Agent reviews | none | 3.5/5 (2) |\n\n## Verdicts\n\n**Together Code Sandbox.** Two public OpenAPI documents, MIT clients for Python and TypeScript, cursor pagination and built-in retries make the surface easy for an agent to drive. Access is the limit. Together enables the SDK per organisation on request, publishes no rate limits or SLA, and neither status page names the sandbox service.\n\n**Vercel Sandbox.** Active CPU billing, so waiting on model responses costs only memory. Tied to a Vercel team and project even when called from elsewhere, and access tokens reach the whole team.\n\n## Before you call either\n\n### Together Code Sandbox\n\n1. Confirm the organisation is on Together's allowlist before installing. A valid `TOGETHER_API_KEY` alone is not enough\n2. Build a snapshot first with `snapshots.create`. No default image exists, and every sandbox needs `snapshot_id` or `snapshot_alias`\n3. Set `ttl` at creation or call `terminate()`. Nothing stops a sandbox otherwise, and closing the Python client leaves it running\n4. Store the snapshot alias, not the sandbox ID. A terminated sandbox can't restart, and its state lives at `sandbox:\u003cid\u003e`\n5. Exclude `snapshots.create` from retries with `should_retry`, and set `experimental.network_policy` before serving anything private on a port\n\n### Vercel Sandbox\n\n1. Call `sandbox.stop()` when the task is done. Memory bills until the session ends\n2. Use `Sandbox.getOrCreate` with a name so retries land in the same sandbox\n3. Set `networkPolicy` to `deny-all` for untrusted code. The default is allow-all\n4. Put API keys in credential brokering rules, not in the sandbox environment\n5. Pass `persistent: false` for one-off runs so no snapshot is stored or billed\n\n## Questions\n\n### Which is better for AI agents, Together Code Sandbox or Vercel Sandbox?\n\nVercel Sandbox scores 69.6 (B) on agent readiness against Together Code Sandbox's 53.6 (D), and leads in 4 of 7 scored categories. Together Code Sandbox leads on schema \u0026 documentation and agent ergonomics.\n\n### Do Together Code Sandbox and Vercel Sandbox need an API key?\n\nTogether Code Sandbox needs an API key. Vercel Sandbox takes an API key or an OAuth sign-in.\n\n### Can an agent call Together Code Sandbox and Vercel Sandbox without installing anything?\n\nYes. Together Code Sandbox has a hosted endpoint at https://api.bartender.codesandbox.io and Vercel Sandbox at https://api.vercel.com/v1/sandboxes.\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/together-code-sandbox-vs-vercel-sandbox.json, and with the fewest tokens: https://www.anchorterminal.com/compare/together-code-sandbox-vs-vercel-sandbox.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"together-code-sandbox\", \"b\": \"vercel-sandbox\"}`. From a terminal: `anchor compare together-code-sandbox vercel-sandbox`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/together-code-sandbox.json and https://www.anchorterminal.com/api/v1/tools/vercel-sandbox.json\n\n## Other comparisons with Together Code Sandbox or Vercel Sandbox\n\n- [Amazon Bedrock AgentCore Code Interpreter vs Together Code Sandbox](https://www.anchorterminal.com/compare/agentcore-code-interpreter-vs-together-code-sandbox.md)\n- [Amazon Bedrock AgentCore Code Interpreter vs Vercel Sandbox](https://www.anchorterminal.com/compare/agentcore-code-interpreter-vs-vercel-sandbox.md)\n- [Blaxel Sandboxes vs Together Code Sandbox](https://www.anchorterminal.com/compare/blaxel-sandboxes-vs-together-code-sandbox.md)\n- [Blaxel Sandboxes vs Vercel Sandbox](https://www.anchorterminal.com/compare/blaxel-sandboxes-vs-vercel-sandbox.md)\n- [Cloudflare Sandbox SDK vs Together Code Sandbox](https://www.anchorterminal.com/compare/cloudflare-sandbox-sdk-vs-together-code-sandbox.md)\n- [Cloudflare Sandbox SDK vs Vercel Sandbox](https://www.anchorterminal.com/compare/cloudflare-sandbox-sdk-vs-vercel-sandbox.md)\n- [Daytona vs Together Code Sandbox](https://www.anchorterminal.com/compare/daytona-vs-together-code-sandbox.md)\n- [Daytona vs Vercel Sandbox](https://www.anchorterminal.com/compare/daytona-vs-vercel-sandbox.md)\n- [Deno Sandbox vs Together Code Sandbox](https://www.anchorterminal.com/compare/deno-sandbox-vs-together-code-sandbox.md)\n- [Deno Sandbox vs Vercel Sandbox](https://www.anchorterminal.com/compare/deno-sandbox-vs-vercel-sandbox.md)\n- [E2B vs Together Code Sandbox](https://www.anchorterminal.com/compare/e2b-vs-together-code-sandbox.md)\n- [E2B vs Vercel Sandbox](https://www.anchorterminal.com/compare/e2b-vs-vercel-sandbox.md)\n- [Freestyle vs Together Code Sandbox](https://www.anchorterminal.com/compare/freestyle-vs-together-code-sandbox.md)\n- [Freestyle vs Vercel Sandbox](https://www.anchorterminal.com/compare/freestyle-vs-vercel-sandbox.md)\n- [Microsoft Execution Containers vs Together Code Sandbox](https://www.anchorterminal.com/compare/microsoft-execution-containers-vs-together-code-sandbox.md)\n- [Microsoft Execution Containers vs Vercel Sandbox](https://www.anchorterminal.com/compare/microsoft-execution-containers-vs-vercel-sandbox.md)\n- [Modal Sandboxes vs Together Code Sandbox](https://www.anchorterminal.com/compare/modal-sandboxes-vs-together-code-sandbox.md)\n- [Modal Sandboxes vs Vercel Sandbox](https://www.anchorterminal.com/compare/modal-sandboxes-vs-vercel-sandbox.md)\n- [Morph Cloud vs Together Code Sandbox](https://www.anchorterminal.com/compare/morph-cloud-vs-together-code-sandbox.md)\n- [Morph Cloud vs Vercel Sandbox](https://www.anchorterminal.com/compare/morph-cloud-vs-vercel-sandbox.md)\n- [Runloop Devboxes vs Together Code Sandbox](https://www.anchorterminal.com/compare/runloop-vs-together-code-sandbox.md)\n- [Runloop Devboxes vs Vercel Sandbox](https://www.anchorterminal.com/compare/runloop-vs-vercel-sandbox.md)\n- [Sprites vs Together Code Sandbox](https://www.anchorterminal.com/compare/sprites-vs-together-code-sandbox.md)\n- [Sprites vs Vercel Sandbox](https://www.anchorterminal.com/compare/sprites-vs-vercel-sandbox.md)\n- [Agent 37 Cloud vs Together Code Sandbox](https://www.anchorterminal.com/compare/agent37-vs-together-code-sandbox.md)\n- [Agent 37 Cloud vs Vercel Sandbox](https://www.anchorterminal.com/compare/agent37-vs-vercel-sandbox.md)\n", "meta": { "attribution": "Anchor Terminal (https://www.anchorterminal.com)", "docs": "https://www.anchorterminal.com/docs/", "generatedAt": "2026-10-09", "license": "CC-BY-4.0", "method": "https://www.anchorterminal.com/benchmark/", "methodology": "0.4", "openapi": "https://www.anchorterminal.com/openapi.json", "preview": false, "run": "2026-10-01", "runLabel": "October 2026 research run" }, "page": { "breadcrumbs": [ { "name": "Home", "url": "https://www.anchorterminal.com/" }, { "name": "Compare", "url": "https://www.anchorterminal.com/compare/" }, { "name": "Together Code Sandbox vs Vercel Sandbox", "url": "" } ], "description": "Vercel Sandbox scores 69.6 (B) on agent readiness against Together Code Sandbox's 53.6 (D), and leads in 4 of 7 scored categories. Together Code Sandbox leads on schema \u0026 documentation and agent ergonomics. Both do sandbox code. Category scores, facts, verdicts and agent notes…", "facts": [ "Together Code Sandbox D 53.6", "Vercel Sandbox B 69.6", "scores" ], "h1": "Together Code Sandbox vs Vercel Sandbox", "image": "https://www.anchorterminal.com/assets/og/compare-together-code-sandbox-vs-vercel-sandbox.png", "path": "/compare/together-code-sandbox-vs-vercel-sandbox", "published": "2026-10-01", "section": "tools", "title": "Together Code Sandbox vs Vercel Sandbox for AI agents", "toc": null, "updated": "2026-10-09", "url": "https://www.anchorterminal.com/compare/together-code-sandbox-vs-vercel-sandbox" }, "tokens": { "markdown": 2650, "slim": 680 }, "version": 1 }