{ "data": { "a": { "slug": "runpod", "name": "Runpod", "vendor": "Runpod", "vendorUrl": "https://www.runpod.io", "kind": "http-api", "category": "gpu-compute", "summary": "Serverless GPU endpoints, queue-based or load-balanced, and rented GPU Pods, billed per second from prepaid credit.", "url": "https://www.anchorterminal.com/tools/runpod", "markdownUrl": "https://www.anchorterminal.com/tools/runpod.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/runpod.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/runpod.json", "dns": "runpod.grade.anchorterminal.com", "repo": "https://github.com/runpod/runpod-python", "license": "MIT", "transports": [ "http", "streamable-http", "stdio" ], "remoteUrl": "https://api.runpod.ai/v2", "packages": [ { "registry": "pypi", "name": "runpod" }, { "registry": "npm", "name": "runpod-sdk" }, { "registry": "npm", "name": "@runpod/mcp-server" }, { "registry": "pypi", "name": "runpod-flash" } ], "auth": "mixed", "authNotes": "API key from the console sent as `Authorization: Bearer` to serverless endpoints at api.runpod.ai/v2/\u003cendpoint-id\u003e and to the management REST API v2 at api.runpod.io/v2. Keys can be All, Read Only or Restricted per serverless endpoint. The deprecated GraphQL API takes the key as `?api_key=` in the URL. The hosted MCP server at mcp.getrunpod.io signs in with OAuth (Sign in with Runpod) or takes an API key as a Bearer header; the local `@runpod/mcp-server` reads `RUNPOD_API_KEY`.", "pricing": "usage", "pricingNotes": "Prepaid credit, billed per second and rounded up to the nearest second, with no data transfer fees and no free tier. Serverless flex workers an hour are 16 GB A4000 class $0.58, L4, A5000 or RTX 3090 $0.69, RTX 4090 $1.10, RTX Pro 4500 $1.15, A6000 or A40 $1.22, RTX 5090 $1.58, L40, L40S or RTX 6000 Ada $1.75, A100 80 GB $2.72, RTX Pro 6000 $3.49, H100 $4.79, H200 $5.93, B200 $8.64, B300 $9.98. Active (always-on) workers are discounted through sales. Pods run from $0.27 an hour (RTX A5000) to $7.89 (B300) on Community or Secure Cloud. Container disk $0.10 a GB-month, volume disk $0.10 running and $0.20 idle, network volumes $0.07 a GB-month under 1 TB and $0.05 above, high-performance $0.14. Default spend cap $80 an hour. Cards, crypto after KYC, prepaid cards at $100 or more a transaction, invoicing above $5,000 (https://www.runpod.io/pricing, https://docs.runpod.io/serverless/pricing, https://docs.runpod.io/accounts-billing/billing).", "priceSummary": "Pay per use", "where": "both", "x402": { "level": "no", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": 314, "npmWeekly": 21838, "pypiWeekly": null, "asOf": "2026-09-30" }, "docsUrl": "https://docs.runpod.io", "llmsTxt": "https://docs.runpod.io/llms.txt", "openapi": "https://api.runpod.io/v2/openapi.json", "capabilities": [ "compute.gpu", "compute.serverless", "compute.endpoints", "compute.batch", "compute.containers" ], "tags": [ "hosted", "usage-priced", "prepaid", "mcp", "oauth", "llms-txt", "python", "typescript", "async-jobs", "batch", "webhooks", "enterprise" ], "lastRelease": "2026-11-03", "graded": true, "anchor": { "graded": true, "score": 55.6, "grade": "C", "agentReady": false, "rank": 864, "ranked": true, "rankOf": 1510, "categoryRank": 13, "methodology": "0.7", "run": "2026-10-01", "scores": { "ergonomics": 62, "maintenance": 82, "payments": 20, "reliability": 57, "schema": 81, "security": 67, "transparency": 64 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-11-04" }, "negative": -6, "negativeNotes": [ "-3, breaking changes in minor releases with no advance notice. `runpod` 2.1.0 (3 November 2026) changes `rp login` to read a pasted key and fail without an interactive terminal, marked [BREAKING] in the changelog that shipped with it, under its Unreleased heading, while the 2.1.0 section lists it as a feature. Folded in, `@runpod/mcp-server` 4.7.0 (26 October) stopped returning live utilisation and the SSH mapping from `list-pods`. https://github.com/runpod/runpod-python/blob/main/CHANGELOG.md, https://github.com/runpod/runpod-mcp/blob/main/CHANGELOG.md", "-3, a released fix of the MCP server's own described flaw with no advisory. `@runpod/mcp-server` 4.0.0 (16 September 2026) fixed two secret-redaction leaks in hosted feedback scrubbing, where values such as `password=abc\u0026def` were stored in plaintext after the `\u0026`. osv.dev lists no advisory. https://github.com/runpod/runpod-mcp/blob/main/CHANGELOG.md" ], "verdict": "Per-second billing across more than a dozen serverless GPU classes, with a REST v2 contract that documents rate limits, 429 handling and cursor pagination. Data-centre outages ran 6 to 24 hours in July, August and September 2026, and two minor releases in late October and early November changed CLI and MCP behaviour without notice.", "bestFor": "Cost-sensitive inference and batch work that wants the widest GPU choice, from consumer cards to B300, with an MCP control plane.", "strengths": [ "Per-second billing across more than a dozen serverless GPU classes, H100 at $4.79 and A100 80 GB at $2.72 an hour", "API keys can be Read Only or restricted per serverless endpoint", "REST v2 OpenAPI file documents per-user rate limits, 429 with `Retry-After`, cursor pagination and an audit-log endpoint", "Official MCP server, hosted with OAuth or local over stdio", "Valid security.txt and SOC 2 Type 2 and ISO 27001 in the trust centre" ], "weaknesses": [ "Data-centre outages of 6 to 24 hours in each of July, August and September 2026, per the 1 October check", "No SLA and no idempotency keys, and serverless job errors are not documented", "The GraphQL API, live until early 2027, takes the API key in the URL", "No free tier, prepaid credit only", "Minor releases changed `rp login` (3 November) and `list-pods` output (26 October) with no advance notice" ], "agentNotes": [ "Create a Restricted or Read Only key per endpoint for the agent, not an All key", "Use REST v2 at api.runpod.io/v2 with a Bearer header; avoid GraphQL, which puts the key in the URL, and read quotas from the `RateLimit-Policy` header", "Fetch `/run` results within 30 minutes and `/runsync` results within 1 minute, or they're gone", "Call `/retry` on a failed job ID rather than submitting a duplicate job", "Check `/health` before relying on an endpoint idle for a week, since max workers drop to 0", "Set `RUNPOD_API_KEY` or pass `--api-key` when running `rp login` without a terminal; since `runpod` 2.1.0 it fails fast otherwise" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 2, "avgRating": 3, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "C", "methodology": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 55.6 } ], "editorialScores": { "ergonomics": 62, "maintenance": 82, "payments": 20, "reliability": 57, "schema": 81, "security": 67, "transparency": 60 }, "provenanceScore": 68, "checked": { "categories": { "ergonomics": "2026-11-04", "maintenance": "2026-11-04", "payments": "2026-11-04", "reliability": "2026-11-04", "schema": "2026-11-04", "security": "2026-11-04", "transparency": "2026-11-04" }, "last": "2026-11-04", "lastMoved": "2026-11-04", "oldest": "2026-11-04", "stale": false, "staleAfterDays": 90 } }, "connect": { "install": "pip install runpod # or npm i runpod-sdk", "http": "curl -X POST \"https://api.runpod.ai/v2/$RUNPOD_ENDPOINT_ID/runsync\" \\\n -H \"Authorization: Bearer $RUNPOD_API_KEY\" -H \"Content-Type: application/json\" \\\n -d '{\"input\":{\"prompt\":\"Hello, world!\"}}'", "claudeCode": "claude mcp add --transport http runpod https://mcp.getrunpod.io/ --header \"Authorization: Bearer $RUNPOD_API_KEY\"", "config": { "mcpServers": { "runpod": { "args": [ "-y", "@runpod/mcp-server@latest" ], "command": "npx", "env": { "RUNPOD_API_KEY": "${RUNPOD_API_KEY}" } } } } }, "letme": { "capability": "https://letme.dev/compute.gpu", "tool": "https://letme.dev/runpod" }, "area": "models", "unitPrices": [ { "item": "H100 80 GB serverless flex", "unit": "gpu-hour", "usd": 4.79, "note": "Billed per second" }, { "item": "H200 141 GB serverless flex", "unit": "gpu-hour", "usd": 5.93 }, { "item": "B200 180 GB serverless flex", "unit": "gpu-hour", "usd": 8.64 }, { "item": "A100 80 GB serverless flex", "unit": "gpu-hour", "usd": 2.72 }, { "item": "L40S 48 GB serverless flex", "unit": "gpu-hour", "usd": 1.75 }, { "item": "RTX 4090 24 GB serverless flex", "unit": "gpu-hour", "usd": 1.1 }, { "item": "L4 24 GB serverless flex", "unit": "gpu-hour", "usd": 0.69 }, { "item": "Container disk", "unit": "gb-month", "usd": 0.1 }, { "item": "Network volume under 1 TB", "unit": "gb-month", "usd": 0.07, "note": "$0.05 above 1 TB, $0.14 high-performance" } ], "provenance": { "legalEntity": "Runpod, Inc.", "domain": "runpod.io", "domainRegistered": "", "endpointOnVendorDomain": false, "terms": "https://www.runpod.io/legal/terms-of-service", "privacy": "https://www.runpod.io/legal/privacy-policy", "statusPage": "https://uptime.runpod.io", "changelog": "https://docs.runpod.io/release-notes", "securityTxt": "valid", "checked": "2026-11-04", "notes": [ "Terms effective 24 March 2026 name Runpod, Inc. under Delaware law. The privacy policy gives 329 Bryant St #4D, San Francisco.", "Serverless endpoints are served from api.runpod.ai and the management API from api.runpod.io, while the hosted MCP server sits on getrunpod.io.", "security.txt points to trust.runpod.io and expires 2027-01-31.", "The .io registry's RDAP server rate-limited our lookup, so the registration date is unrecorded.", "The terms (last updated 24 March 2026) cover the Runpod.io website and its subdomains and bar access to the Site or the Service \"through automated or non-human means, whether through a bot, script or otherwise\", so runpod.io hosts weren't read on 4 November beyond robots.txt and the terms. www.runpod.io robots.txt carries `Content-Signal: search=yes, ai-input=yes, ai-train=no`." ], "score": 68 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/runpod.json", "live": { "slug": "runpod", "probe": { "target": "https://api.runpod.ai/v2", "method": "get", "lastAt": "2026-11-07T19:22:30.546761224Z", "lastOk": true, "lastStatus": 404, "lastMs": 124, "authRequired": false, "uptime24h": 100, "uptime30d": 100, "p50ms24h": 50, "p95ms24h": 122, "samples24h": 238, "samples30d": 7920, "days": [ { "date": "2026-10-07", "probes": 272, "ok": 272 }, { "date": "2026-10-08", "probes": 268, "ok": 268 }, { "date": "2026-10-09", "probes": 250, "ok": 250 }, { "date": "2026-10-10", "probes": 247, "ok": 247 }, { "date": "2026-10-11", "probes": 247, "ok": 247 }, { "date": "2026-10-12", "probes": 247, "ok": 247 }, { "date": "2026-10-13", "probes": 248, "ok": 248 }, { "date": "2026-10-14", "probes": 249, "ok": 249 }, { "date": "2026-10-15", "probes": 253, "ok": 253 }, { "date": "2026-10-16", "probes": 252, "ok": 252 }, { "date": "2026-10-17", "probes": 253, "ok": 253 }, { "date": "2026-10-18", "probes": 256, "ok": 256 }, { "date": "2026-10-19", "probes": 255, "ok": 255 }, { "date": "2026-10-20", "probes": 252, "ok": 252 }, { "date": "2026-10-21", "probes": 253, "ok": 253 }, { "date": "2026-10-22", "probes": 253, "ok": 253 }, { "date": "2026-10-23", "probes": 248, "ok": 248 }, { "date": "2026-10-24", "probes": 251, "ok": 251 }, { "date": "2026-10-25", "probes": 250, "ok": 250 }, { "date": "2026-10-26", "probes": 252, "ok": 252 }, { "date": "2026-10-27", "probes": 249, "ok": 249 }, { "date": "2026-10-28", "probes": 250, "ok": 250 }, { "date": "2026-10-29", "probes": 249, "ok": 249 }, { "date": "2026-10-30", "probes": 249, "ok": 249 }, { "date": "2026-10-31", "probes": 251, "ok": 251 }, { "date": "2026-11-01", "probes": 249, "ok": 249 }, { "date": "2026-11-02", "probes": 250, "ok": 250 }, { "date": "2026-11-03", "probes": 248, "ok": 248 }, { "date": "2026-11-04", "probes": 246, "ok": 246 }, { "date": "2026-11-05", "probes": 185, "ok": 185 }, { "date": "2026-11-06", "probes": 241, "ok": 241 }, { "date": "2026-11-07", "probes": 197, "ok": 197 } ] }, "vendorStatus": { "page": "https://uptime.runpod.io", "indicator": "unknown", "summary": "no machine-readable status found", "checkedAt": "2026-11-07T04:48:42.840910979Z" }, "versions": [ { "registry": "github", "name": "runpod/runpod-python", "version": "v2.1.0", "released": "2026-11-03", "seenAt": "2026-11-07T00:02:36.912646594Z" }, { "registry": "npm", "name": "@runpod/mcp-server", "version": "4.10.1", "seenAt": "2026-11-07T00:02:35.345662617Z" }, { "registry": "npm", "name": "runpod-sdk", "version": "1.1.2", "seenAt": "2026-11-07T00:02:34.505000188Z" }, { "registry": "pypi", "name": "runpod", "version": "2.1.0", "released": "2026-11-03", "seenAt": "2026-11-07T00:02:34.324818257Z" }, { "registry": "pypi", "name": "runpod-flash", "version": "1.21.1", "released": "2026-10-30", "seenAt": "2026-11-07T00:02:36.830640041Z" } ], "githubStars": 317, "npmWeekly": 43036, "pypiWeekly": 142496, "securityTxt": { "url": "https://runpod.io/.well-known/security.txt", "state": "valid", "expires": "2027-01-31T23:59:59Z", "checkedAt": "2026-11-07T16:01:21.877389665Z" }, "llmsTxt": { "url": "https://docs.runpod.io/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-11-07T15:33:51.538935947Z" }, "domain": { "domain": "runpod.io", "checkedAt": "2026-11-01T14:25:04.106344556Z" }, "pages": [ { "url": "https://docs.runpod.io/release-notes", "kind": "deprecations", "status": 200, "checkedAt": "2026-11-07T14:07:46.580181776Z", "changedAt": "2026-10-30T05:38:29.54889903Z", "fingerprint": "9261270f388a" }, { "url": "https://raw.githubusercontent.com/runpod/runpod-mcp/main/CHANGELOG.md", "kind": "deprecations", "status": 200, "checkedAt": "2026-11-07T14:23:23.075251745Z", "changedAt": "2026-11-07T14:23:23.075251745Z", "fingerprint": "1c4b9ad8bf22" }, { "url": "https://raw.githubusercontent.com/runpod/runpod-python/main/CHANGELOG.md", "kind": "deprecations", "status": 304, "checkedAt": "2026-11-07T14:23:25.16737017Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "fb230f277f30" }, { "url": "https://docs.runpod.io/serverless/pricing", "kind": "pricing", "status": 200, "checkedAt": "2026-11-07T14:07:48.912650228Z", "changedAt": "2026-10-31T06:11:01.576033108Z", "fingerprint": "007010d3924d" }, { "url": "https://www.runpod.io/pricing", "kind": "pricing", "status": 304, "checkedAt": "2026-11-07T14:33:58.84079219Z", "changedAt": "2026-11-05T13:17:25.96037232Z", "fingerprint": "17bdd00f4752" }, { "url": "https://www.runpod.io/legal/privacy-policy", "kind": "privacy", "status": 304, "checkedAt": "2026-11-07T14:33:54.797238441Z", "changedAt": "2026-10-29T05:27:09.002064424Z", "fingerprint": "85273c62698f" }, { "url": "https://www.runpod.io/legal/terms-of-service", "kind": "terms", "status": 304, "checkedAt": "2026-11-07T14:33:56.923267536Z", "changedAt": "2026-10-29T05:27:11.771911831Z", "fingerprint": "ee53e652368c" } ], "mcpTools": { "url": "https://mcp.getrunpod.io/", "checkedAt": "2026-11-07T01:47:30.018217094Z", "status": "auth", "note": "asks for credentials before listing its tools", "changedAt": "2026-11-07T01:47:30.018217094Z" }, "github": { "repo": "runpod/runpod-python", "checkedAt": "2026-11-02T09:23:01.82138493Z", "stars": 318, "archived": false, "issuesEnabled": true, "pushedAt": "2026-11-01T15:00:09Z", "openIssues": 63, "openPRs": 33, "issuesOpened90d": 8, "issuesClosed90d": 1, "prsMerged90d": 61, "ci": { "branch": "main", "runs": 50, "success": 39, "failure": 11, "other": 0, "latest": "success", "latestAt": "2026-10-30T21:00:14Z" }, "replies": { "sampled": 25, "unanswered": 14, "medianDays": 4.2 } }, "updatedAt": "2026-11-07T19:22:30.546761224Z" } }, "answer": "Together GPU Clusters scores 58.1 (C) on agent readiness against Runpod's 55.6 (C), and leads in 3 of 7 scored categories. Runpod leads on reliability, agent ergonomics and maintenance \u0026 community.", "b": { "slug": "together-gpu-clusters", "name": "Together GPU Clusters", "vendor": "Together AI", "vendorUrl": "https://www.together.ai", "kind": "http-api", "category": "gpu-compute", "summary": "Together GPU Clusters rents multi-node NVIDIA H100, H200, B200 and B300 clusters with InfiniBand and shared storage, run as Kubernetes or Slurm, by the GPU-hour. Clusters are created and scaled from the console, the tg CLI, SDKs or REST API.", "url": "https://www.anchorterminal.com/tools/together-gpu-clusters", "markdownUrl": "https://www.anchorterminal.com/tools/together-gpu-clusters.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/together-gpu-clusters.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/together-gpu-clusters.json", "dns": "together-gpu-clusters.grade.anchorterminal.com", "repo": "https://github.com/togethercomputer/together-py", "license": "Proprietary service under Together's terms of service. The Python SDK and CLI are Apache-2.0 and the OpenAPI document is MIT", "transports": [], "remoteUrl": "https://api.together.ai/v1/compute/clusters", "packages": [ { "registry": "pypi", "name": "together" }, { "registry": "npm", "name": "together-ai" } ], "auth": "api-key", "authNotes": "Bearer `TOGETHER_API_KEY`, scoped to a project, revocable and optionally expiring, the same keys as Together's other APIs. Only a project admin's key returns the cluster's admin kubeconfig. Team members can reach the Kubernetes API through OIDC with their own identity provider, and SSH uses OIDC or uploaded keys.", "pricing": "usage", "pricingNotes": "On-demand from $3.99 per GPU-hour (H100) to $9.99 (B300); reserved 3 to 180 days from $3.19 to $7.99; preemptible (preview) from $1.99. Storage per GiB-month. No ingress or egress fees. Reservations are prepaid and non-refundable, and creation needs enough credit to cover them.", "priceSummary": "Pay per use", "where": "hosted", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the GPU clusters docs, billing pages or OpenAPI document (checked 2026-11-06). An exhausted balance returns 402 to scale requests with no payment requirements.", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": null, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-11-06" }, "docsUrl": "https://docs.together.ai/docs/gpu-clusters-overview", "llmsTxt": "https://docs.together.ai/llms.txt", "openapi": "https://github.com/togethercomputer/openapi", "capabilities": [ "compute.gpu", "compute.containers", "compute.batch" ], "tags": [ "hosted", "official", "usage", "prepaid", "openapi", "llms-txt", "kubernetes", "slurm", "python", "typescript", "cli", "h100", "b200" ], "lastRelease": "2026-10-22", "graded": true, "anchor": { "graded": true, "score": 58.1, "grade": "C", "agentReady": false, "rank": 768, "ranked": true, "rankOf": 1510, "categoryRank": 10, "methodology": "0.7", "run": "2026-10-01", "scores": { "ergonomics": 55, "maintenance": 75, "payments": 20, "reliability": 38, "schema": 92, "security": 68, "transparency": 65 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-11-06" }, "negative": 0, "verdict": "Multi-node H100 to B300 clusters on Kubernetes or Slurm, created and deleted headlessly through an OpenAPI-described API, a CLI with JSON output and two SDKs, at published GPU-hour prices. Clusters take 10 minutes to an hour to provision, can't be paused, and have no status component, SLA or idempotent create.", "bestFor": "Training, fine-tuning and batch jobs that need several 8-GPU nodes with InfiniBand, run by a pipeline that creates and deletes clusters.", "strengths": [ "Public OpenAPI 3.1, llms.txt and Markdown docs, with an automation guide for CI pipelines", "Published per GPU-hour prices for on-demand, reserved and preemptible capacity, with no egress fees", "Kubernetes or Slurm on the same hardware, with InfiniBand and a persistent shared volume", "Automatic health checks and node repair, approved by hand or run automatically", "Project-scoped keys, admin-only kubeconfig and OIDC access for team members" ], "weaknesses": [ "Provisioning takes 10 minutes to an hour, and a cluster can't be paused or scaled to zero", "No status page component, SLA or published rate limits for GPU clusters", "No idempotency key on creation, so a retried create can bill a second cluster", "No free trial; reservations are prepaid and non-refundable", "Volumes bill until deleted and outlive the clusters they were attached to" ], "agentNotes": [ "Use `tg clusters`, not `tg beta clusters`, which stopped working with CLI 3.0 on 22 October 2026", "Pass `--json` and `--non-interactive`, poll `tg clusters retrieve` until status is Ready, and delete the cluster in a cleanup step", "Check for an existing cluster by name before retrying a create, since creation has no idempotency key", "Read live availability from the regions API and prices from the pricing page; the regions response has no prices", "Use a project admin's key when the task needs the kubeconfig, since other roles get none" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "C", "methodology": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 58.1 } ], "editorialScores": { "ergonomics": 55, "maintenance": 75, "payments": 20, "reliability": 38, "schema": 92, "security": 68, "transparency": 46 }, "provenanceScore": 83, "checked": { "categories": { "ergonomics": "2026-11-06", "maintenance": "2026-11-06", "payments": "2026-11-06", "reliability": "2026-11-06", "schema": "2026-11-06", "security": "2026-11-06", "transparency": "2026-11-06" }, "last": "2026-11-06", "oldest": "2026-11-06", "stale": false, "staleAfterDays": 90 } }, "connect": { "install": "uv tool install \"together[cli]\"", "http": "curl -H \"Authorization: Bearer $TOGETHER_API_KEY\" https://api.together.ai/v1/compute/clusters" }, "letme": { "capability": "https://letme.dev/compute.gpu", "tool": "https://letme.dev/together-gpu-clusters" }, "sameCompany": [ "together-inference", "together-fine-tuning", "together-code-sandbox" ], "area": "models", "unitPrices": [ { "item": "H100 on-demand", "unit": "gpu-hour", "usd": 3.99, "note": "reserved $3.69 to $3.19, preemptible $1.99" }, { "item": "H200 on-demand", "unit": "gpu-hour", "usd": 5.99, "note": "reserved $4.99 to $3.99, preemptible $2.99" }, { "item": "B200 on-demand", "unit": "gpu-hour", "usd": 8.19, "note": "reserved $7.99 to $6.79, preemptible $4.09" }, { "item": "B300 on-demand", "unit": "gpu-hour", "usd": 9.99, "note": "preemptible $4.99, reserved by sales" } ], "provenance": { "legalEntity": "Together Computer, Inc.", "domain": "together.ai", "domainRegistered": "", "endpointOnVendorDomain": true, "terms": "https://www.together.ai/terms-of-service", "privacy": "https://www.together.ai/privacy", "statusPage": "https://status.together.ai", "changelog": "https://docs.together.ai/docs/changelog", "securityTxt": "valid", "checked": "2026-11-06", "notes": [ "Legal entity, terms, privacy and security.txt as on the Together AI Inference listing, checked 1 November 2026, and not re-read for this listing.", "docs.together.ai/robots.txt disallows only /cdn-cgi/ and /_next/, with Content-Signal ai-train=yes, search=yes, ai-input=yes. www.together.ai/robots.txt allows all.", "status.together.ai has no component for GPU clusters on 6 November 2026." ], "score": 83 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/together-gpu-clusters.json", "live": { "slug": "together-gpu-clusters", "probe": { "target": "https://api.together.ai/v1/compute/clusters", "method": "get", "lastAt": "2026-11-07T19:22:40.660879578Z", "lastOk": true, "lastStatus": 401, "lastMs": 263, "lastNote": "asks for credentials", "authRequired": true, "uptime24h": 100, "uptime30d": 100, "p50ms24h": 493, "p95ms24h": 857, "samples24h": 210, "samples30d": 210, "days": [ { "date": "2026-11-06", "probes": 13, "ok": 13 }, { "date": "2026-11-07", "probes": 197, "ok": 197 } ] }, "versions": [ { "registry": "github", "name": "togethercomputer/together-py", "version": "v3.1.1", "released": "2026-11-04", "seenAt": "2026-11-07T00:12:15.100983119Z" }, { "registry": "npm", "name": "together-ai", "version": "1.0.0", "seenAt": "2026-11-07T00:12:15.067840103Z" }, { "registry": "pypi", "name": "together", "version": "3.1.1", "released": "2026-11-04", "seenAt": "2026-11-07T00:12:14.921893617Z" } ], "githubStars": 12, "npmWeekly": 99619, "pypiWeekly": 424792, "securityTxt": { "url": "https://together.ai/.well-known/security.txt", "state": "valid", "expires": "2028-09-30T00:00:00.000Z", "checkedAt": "2026-11-07T16:00:47.073630606Z" }, "llmsTxt": { "url": "https://docs.together.ai/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-11-07T15:34:12.138384896Z" }, "updatedAt": "2026-11-07T19:22:40.660879578Z" } }, "edges": [ { "by": 19, "category": "reliability", "leads": "runpod", "name": "Reliability", "reasons": { "a": "Better Stack page at uptime.runpod.io with per-service and per-region history, per the 1 October check, not re-read on 4 November (Runpod's terms bar automated access to runpod.io and its subdomains) (20). Incident line kept at 0. The 1 October reading counted several majors, among them US-IL-1 without power for 6 hours 10 minutes on 14 and 15 August and serverless API errors for 1 hour 25 minutes on 6 September. The window since 1 October is unread, so the recorded award stands (0). The REST v2 OpenAPI file, in the copy Runpod keeps in its MCP repository (synced with production on 27 October), says limits are per user across every `/v2` route, with minute, hour and day windows, and gives `\"minute\";q=180;w=60, \"hour\";q=3600;w=3600, \"day\";q=43200;w=86400` as the policy header (15). The same file documents 429 with `Retry-After` and `RateLimit` headers, and the Python SDK's error guide (2.1.0, 3 November) honours `Retry-After`, backs off with jitter and does not retry other errors because a failed response can follow a successful mutation. Safe-retry guidance with no idempotency keys (12). No SLA found (0). Serverless and REST v2 are GA; batch jobs are beta (10). 20 + 0 + 15 + 12 + 0 + 10 = 57.", "b": "Read with the hosted lines. status.together.ai lists the website, the playground and serverless models with no component for GPU clusters, and a vendor page with no component for the product takes 15 in this run, as for Together's Code Sandbox and fine-tuning listings (15). No incident history for clusters can be read (5). No rate limits for the clusters API found (0). Together's docs give 429 and 503 backoff guidance for its APIs, per the inference listing's 1 November check, and the CLI has `--non-interactive` and `--json` for scripted retries, but creation has no idempotency key (8). No SLA for clusters found; the published 99% commitment covers provisioned inference throughput only (0). Generally available since 9 September 2025 and out of the CLI's beta paths since 22 October 2026, with preemptible nodes in preview (10). 15+5+0+8+0+10 = 38." }, "scores": { "a": 57, "b": 38 } }, { "by": 11, "category": "schema", "leads": "together-gpu-clusters", "name": "Schema \u0026 documentation", "reasons": { "a": "OpenAPI for REST v2 at api.runpod.io/v2/openapi.json, with v1 and GraphQL schemas also published (25). llms.txt with .md pages (10). Guides explain queue-based against load-balanced endpoints and sync against async calls, with result retention for each (14). Job statuses are a fixed set (`IN_QUEUE`, `IN_PROGRESS`, `COMPLETED`, `FAILED`) and payload limits are stated (20 MB sync, 10 MB async, 1 MB per stream chunk) (10). Examples throughout; no error responses documented for the serverless operations (7). Dated release notes and a versioned API (15).", "b": "Public OpenAPI 3.1 for /v1/compute/clusters and shared volumes, MIT, embedded in every reference page (25). llms.txt and a Markdown twin of every page (10). The docs say when to choose Kubernetes or Slurm and each capacity type, and the management page carries instructions for agents on reporting live availability and prices (18). Enums for cluster type, billing type, GPU type and status, required fields marked (13). CLI, Python, TypeScript and console steps on each task, with 402 and 403 cases documented, though no error catalogue for the clusters API (11). Versioned SDKs and a dated changelog with cluster entries (15). 25+10+18+13+11+15 = 92." }, "scores": { "a": 81, "b": 92 } }, { "by": 7, "category": "ergonomics", "leads": "runpod", "name": "Agent ergonomics", "reasons": { "a": "Results can be streamed in chunks of up to 1 MB and polled by job ID, and `include` sizes some REST v2 responses (12). REST v2 list calls take an opaque `cursor` with `limit` (1 to 1,000, 100 for builds, 200 for audit logs) and filters such as actor, action and time on audit logs, per the OpenAPI file in Runpod's MCP repository (20). No error codes or messages documented for serverless operations, per 1 October (5). `/retry`, `/cancel` and `/purge-queue` give safe recovery for jobs, and the MCP server marks destructive tools. No idempotency keys (10). FlashBoot on by default, Python and JavaScript SDKs, the Flash SDK and an official MCP server (15). 12 + 20 + 5 + 10 + 15 = 62.", "b": "Cluster objects are compact, and `--json` gives machine-readable output, but list calls take no field selection (15). No pagination or filters on the clusters list (8). 402 and 403 with readable messages such as \"Insufficient credits for cluster creation\", and troubleshooting for common failures (12). Status polling until Ready is documented and deletes run non-interactively, but there is no idempotency key on creation and a duplicate create bills a second cluster (8). Official Python and TypeScript SDKs and a CLI, though a create takes GPU type, region, driver and CUDA versions, cluster type and billing type (12). 15+8+12+8+12 = 55." }, "scores": { "a": 62, "b": 55 } }, { "by": 7, "category": "maintenance", "leads": "runpod", "name": "Maintenance \u0026 community", "reasons": { "a": "Latest release `runpod` 2.1.0 on 3 November 2026, and `@runpod/mcp-server` 4.9.1 on 2 November (30). In the window from 6 August, runpod-python tagged v1.12.0, v2.0.0 and v2.1.0, runpod-mcp thirteen releases from v3.3.0 (17 August) to 4.9.1, and flash v1.20.0 to v1.21.1, besides release candidates (20). Closed service with dated release notes and support; GitHub issue response times weren't readable (github.com refuses us) (12 of 25). Python and JavaScript SDKs, the Flash SDK and the MCP server are official; the standalone `runpod-flash` package was deprecated in October in favour of `runpod` (15). Package health not checked (5). 30 + 20 + 12 + 15 + 5 = 82.", "b": "Closed service. The newest cluster change is CLI and SDK 3.0 on 22 October 2026, 15 days before this check (30). Dated cluster entries in the 90 days from 8 August include 12, 18, 19, 24, 27 and 28 August, 10 September and 22 October (20). Dated changelog, a support portal and Discord, with responsiveness not tested (8). Python SDK 3.1 and TypeScript SDK 1.0 are current and cover clusters (15). SDK CI and dependencies weren't audited (2). 30+20+8+15+2 = 75." }, "scores": { "a": 82, "b": 75 } } ], "facts": [ { "a": "HTTP API", "b": "HTTP API", "name": "Kind" }, { "a": "Runpod", "b": "Together AI", "name": "Vendor" }, { "a": "https://api.runpod.ai/v2", "b": "https://api.together.ai/v1/compute/clusters", "name": "Hosted endpoint" }, { "a": "HTTP, Streamable HTTP, stdio", "b": "", "name": "Transports" }, { "a": "OAuth or key", "b": "API key", "name": "Auth" }, { "a": "Pay per use", "b": "Pay per use", "name": "Pricing" }, { "a": "no", "b": "no", "name": "x402" }, { "a": "MIT", "b": "Proprietary service under Together's terms of service. The Python SDK and CLI are Apache-2.0 and the OpenAPI document is MIT", "name": "Licence" }, { "a": "no", "b": "no", "name": "Read-only variant documented" }, { "a": "yes", "b": "yes", "name": "llms.txt" }, { "a": "2026-11-03", "b": "2026-10-22", "name": "Last release" }, { "a": "2026-03-24", "b": "no date given", "name": "Terms last updated" }, { "a": "2025-08-07", "b": "no date given", "name": "Privacy policy last updated" }, { "a": "not found in the text", "b": "not found in the text", "name": "Customer content may train models" }, { "a": "yes", "b": "not found in the text", "name": "Terms restrict automated access" }, { "a": "yes", "b": "yes", "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": "yes", "b": "not found in the text", "name": "Arbitration or class-action waiver" }, { "a": "314 stars, 22k npm/wk", "b": "none", "name": "Popularity" }, { "a": "3/5 (2)", "b": "none", "name": "Agent reviews" } ], "faq": [ { "answer": "Together GPU Clusters scores 58.1 (C) on agent readiness against Runpod's 55.6 (C), and leads in 3 of 7 scored categories. Runpod leads on reliability, agent ergonomics and maintenance \u0026 community.", "question": "Which is better for AI agents, Runpod or Together GPU Clusters?" }, { "answer": "Runpod takes an API key or an OAuth sign-in. Together GPU Clusters needs an API key.", "question": "Do Runpod and Together GPU Clusters need an API key?" }, { "answer": "Yes. Runpod has a hosted endpoint at https://api.runpod.ai/v2 and Together GPU Clusters at https://api.together.ai/v1/compute/clusters.", "question": "Can an agent call Runpod and Together GPU Clusters without installing anything?" } ], "goodFor": [ { "aheadOn": [ "Reliability, 57 against 38", "Agent ergonomics, 62 against 55", "Maintenance \u0026 community, 82 against 75" ], "also": [ "Runs on your own machine" ], "goodFor": "Cost-sensitive inference and batch work that wants the widest GPU choice, from consumer cards to B300, with an MCP control plane.", "slug": "runpod", "watchFor": "Data-centre outages of 6 to 24 hours in each of July, August and September 2026, per the 1 October check" }, { "aheadOn": [ "Schema \u0026 documentation, 92 against 81" ], "also": [ "No incidents deducted, where Runpod loses 6 points for them" ], "goodFor": "Training, fine-tuning and batch jobs that need several 8-GPU nodes with InfiniBand, run by a pipeline that creates and deletes clusters.", "slug": "together-gpu-clusters", "watchFor": "Provisioning takes 10 minutes to an hour, and a cluster can't be paused or scaled to zero" } ], "history": { "runpod": [ { "causes": [ "product", "evidence", "event" ], "date": "2026-11-04", "delta": 2, "from": 53.6, "fromGrade": "D", "to": 55.6, "toGrade": "C" }, { "causes": [ "method" ], "date": "2026-10-27", "delta": 0.1, "from": 53.5, "fromGrade": "D", "to": 53.6, "toGrade": "D" }, { "causes": [ "method" ], "date": "2026-10-08", "delta": -0.2, "from": 53.7, "fromGrade": "D", "to": 53.5, "toGrade": "D" } ], "together-gpu-clusters": null }, "job": { "capability": "compute.gpu", "name": "GPU compute" }, "others": [ { "json": "https://www.anchorterminal.com/compare/baseten-vs-runpod.json", "title": "Baseten vs Runpod", "url": "https://www.anchorterminal.com/compare/baseten-vs-runpod" }, { "json": "https://www.anchorterminal.com/compare/baseten-vs-together-gpu-clusters.json", "title": "Baseten vs Together GPU Clusters", "url": "https://www.anchorterminal.com/compare/baseten-vs-together-gpu-clusters" }, { "json": "https://www.anchorterminal.com/compare/beam-vs-runpod.json", "title": "Beam vs Runpod", "url": "https://www.anchorterminal.com/compare/beam-vs-runpod" }, { "json": "https://www.anchorterminal.com/compare/beam-vs-together-gpu-clusters.json", "title": "Beam vs Together GPU Clusters", "url": "https://www.anchorterminal.com/compare/beam-vs-together-gpu-clusters" }, { "json": "https://www.anchorterminal.com/compare/cerebrium-vs-runpod.json", "title": "Cerebrium vs Runpod", "url": "https://www.anchorterminal.com/compare/cerebrium-vs-runpod" }, { "json": "https://www.anchorterminal.com/compare/cerebrium-vs-together-gpu-clusters.json", "title": "Cerebrium vs Together GPU Clusters", "url": "https://www.anchorterminal.com/compare/cerebrium-vs-together-gpu-clusters" }, { "json": "https://www.anchorterminal.com/compare/cloud-run-gpus-vs-together-gpu-clusters.json", "title": "Cloud Run GPUs vs Together GPU Clusters", "url": "https://www.anchorterminal.com/compare/cloud-run-gpus-vs-together-gpu-clusters" }, { "json": "https://www.anchorterminal.com/compare/coreweave-vs-runpod.json", "title": "CoreWeave vs Runpod", "url": "https://www.anchorterminal.com/compare/coreweave-vs-runpod" }, { "json": "https://www.anchorterminal.com/compare/coreweave-vs-together-gpu-clusters.json", "title": "CoreWeave vs Together GPU Clusters", "url": "https://www.anchorterminal.com/compare/coreweave-vs-together-gpu-clusters" }, { "json": "https://www.anchorterminal.com/compare/crusoe-cloud-vs-runpod.json", "title": "Crusoe Cloud vs Runpod", "url": "https://www.anchorterminal.com/compare/crusoe-cloud-vs-runpod" }, { "json": "https://www.anchorterminal.com/compare/crusoe-cloud-vs-together-gpu-clusters.json", "title": "Crusoe Cloud vs Together GPU Clusters", "url": "https://www.anchorterminal.com/compare/crusoe-cloud-vs-together-gpu-clusters" }, { "json": "https://www.anchorterminal.com/compare/gpusmarket-vs-runpod.json", "title": "GPUsMarket vs Runpod", "url": "https://www.anchorterminal.com/compare/gpusmarket-vs-runpod" }, { "json": "https://www.anchorterminal.com/compare/gpusmarket-vs-together-gpu-clusters.json", "title": "GPUsMarket vs Together GPU Clusters", "url": "https://www.anchorterminal.com/compare/gpusmarket-vs-together-gpu-clusters" }, { "json": "https://www.anchorterminal.com/compare/hugging-face-inference-endpoints-vs-runpod.json", "title": "Hugging Face Inference Endpoints vs Runpod", "url": "https://www.anchorterminal.com/compare/hugging-face-inference-endpoints-vs-runpod" }, { "json": "https://www.anchorterminal.com/compare/hugging-face-inference-endpoints-vs-together-gpu-clusters.json", "title": "Hugging Face Inference Endpoints vs Together GPU Clusters", "url": "https://www.anchorterminal.com/compare/hugging-face-inference-endpoints-vs-together-gpu-clusters" }, { "json": "https://www.anchorterminal.com/compare/hyperbolic-vs-runpod.json", "title": "Hyperbolic vs Runpod", "url": "https://www.anchorterminal.com/compare/hyperbolic-vs-runpod" }, { "json": "https://www.anchorterminal.com/compare/hyperbolic-vs-together-gpu-clusters.json", "title": "Hyperbolic vs Together GPU Clusters", "url": "https://www.anchorterminal.com/compare/hyperbolic-vs-together-gpu-clusters" }, { "json": "https://www.anchorterminal.com/compare/koyeb-vs-runpod.json", "title": "Koyeb vs Runpod", "url": "https://www.anchorterminal.com/compare/koyeb-vs-runpod" }, { "json": "https://www.anchorterminal.com/compare/koyeb-vs-together-gpu-clusters.json", "title": "Koyeb vs Together GPU Clusters", "url": "https://www.anchorterminal.com/compare/koyeb-vs-together-gpu-clusters" }, { "json": "https://www.anchorterminal.com/compare/lambda-vs-runpod.json", "title": "Lambda Cloud vs Runpod", "url": "https://www.anchorterminal.com/compare/lambda-vs-runpod" }, { "json": "https://www.anchorterminal.com/compare/lambda-vs-together-gpu-clusters.json", "title": "Lambda Cloud vs Together GPU Clusters", "url": "https://www.anchorterminal.com/compare/lambda-vs-together-gpu-clusters" }, { "json": "https://www.anchorterminal.com/compare/massed-compute-vs-runpod.json", "title": "Massed Compute vs Runpod", "url": "https://www.anchorterminal.com/compare/massed-compute-vs-runpod" }, { "json": "https://www.anchorterminal.com/compare/massed-compute-vs-together-gpu-clusters.json", "title": "Massed Compute vs Together GPU Clusters", "url": "https://www.anchorterminal.com/compare/massed-compute-vs-together-gpu-clusters" }, { "json": "https://www.anchorterminal.com/compare/modal-vs-runpod.json", "title": "Modal vs Runpod", "url": "https://www.anchorterminal.com/compare/modal-vs-runpod" }, { "json": "https://www.anchorterminal.com/compare/modal-vs-together-gpu-clusters.json", "title": "Modal vs Together GPU Clusters", "url": "https://www.anchorterminal.com/compare/modal-vs-together-gpu-clusters" }, { "json": "https://www.anchorterminal.com/compare/nebius-ai-cloud-vs-runpod.json", "title": "Nebius AI Cloud vs Runpod", "url": "https://www.anchorterminal.com/compare/nebius-ai-cloud-vs-runpod" }, { "json": "https://www.anchorterminal.com/compare/nebius-ai-cloud-vs-together-gpu-clusters.json", "title": "Nebius AI Cloud vs Together GPU Clusters", "url": "https://www.anchorterminal.com/compare/nebius-ai-cloud-vs-together-gpu-clusters" }, { "json": "https://www.anchorterminal.com/compare/northflank-vs-runpod.json", "title": "Northflank vs Runpod", "url": "https://www.anchorterminal.com/compare/northflank-vs-runpod" }, { "json": "https://www.anchorterminal.com/compare/northflank-vs-together-gpu-clusters.json", "title": "Northflank vs Together GPU Clusters", "url": "https://www.anchorterminal.com/compare/northflank-vs-together-gpu-clusters" }, { "json": "https://www.anchorterminal.com/compare/replicate-deploy-vs-runpod.json", "title": "Replicate Deployments vs Runpod", "url": "https://www.anchorterminal.com/compare/replicate-deploy-vs-runpod" }, { "json": "https://www.anchorterminal.com/compare/replicate-deploy-vs-together-gpu-clusters.json", "title": "Replicate Deployments vs Together GPU Clusters", "url": "https://www.anchorterminal.com/compare/replicate-deploy-vs-together-gpu-clusters" }, { "json": "https://www.anchorterminal.com/compare/runpod-vs-thunder-compute.json", "title": "Runpod vs Thunder Compute", "url": "https://www.anchorterminal.com/compare/runpod-vs-thunder-compute" }, { "json": "https://www.anchorterminal.com/compare/runpod-vs-vast-ai.json", "title": "Runpod vs Vast.ai", "url": "https://www.anchorterminal.com/compare/runpod-vs-vast-ai" }, { "json": "https://www.anchorterminal.com/compare/runpod-vs-verda.json", "title": "Runpod vs Verda", "url": "https://www.anchorterminal.com/compare/runpod-vs-verda" }, { "json": "https://www.anchorterminal.com/compare/thunder-compute-vs-together-gpu-clusters.json", "title": "Thunder Compute vs Together GPU Clusters", "url": "https://www.anchorterminal.com/compare/thunder-compute-vs-together-gpu-clusters" }, { "json": "https://www.anchorterminal.com/compare/together-gpu-clusters-vs-vast-ai.json", "title": "Together GPU Clusters vs Vast.ai", "url": "https://www.anchorterminal.com/compare/together-gpu-clusters-vs-vast-ai" }, { "json": "https://www.anchorterminal.com/compare/together-gpu-clusters-vs-verda.json", "title": "Together GPU Clusters vs Verda", "url": "https://www.anchorterminal.com/compare/together-gpu-clusters-vs-verda" }, { "json": "https://www.anchorterminal.com/compare/cloud-run-gpus-vs-runpod.json", "title": "Cloud Run GPUs vs Runpod", "url": "https://www.anchorterminal.com/compare/cloud-run-gpus-vs-runpod" } ], "panel": null, "scores": [ { "by": 19, "edge": "runpod", "key": "reliability", "name": "Reliability", "runpod": 57, "together-gpu-clusters": 38, "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "by": 11, "edge": "together-gpu-clusters", "key": "schema", "name": "Schema \u0026 documentation", "runpod": 81, "together-gpu-clusters": 92, "weight": 13 }, { "by": 7, "edge": "runpod", "key": "ergonomics", "name": "Agent ergonomics", "runpod": 62, "together-gpu-clusters": 55, "weight": 13 }, { "by": 1, "edge": "together-gpu-clusters", "key": "security", "name": "Security \u0026 auth", "runpod": 67, "together-gpu-clusters": 68, "weight": 14 }, { "by": 0, "edge": "", "key": "payments", "name": "Payments \u0026 pricing", "runpod": 20, "together-gpu-clusters": 20, "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "by": 7, "edge": "runpod", "key": "maintenance", "name": "Maintenance \u0026 community", "runpod": 82, "together-gpu-clusters": 75, "weight": 7 }, { "by": 1, "edge": "together-gpu-clusters", "key": "transparency", "name": "Transparency \u0026 trust", "runpod": 64, "together-gpu-clusters": 65, "weight": 7 } ], "summary": "Together GPU Clusters scores 58.1 (C) on agent readiness against Runpod's 55.6 (C), and leads in 3 of 7 scored categories. Runpod leads on reliability, agent ergonomics and maintenance \u0026 community. Both do gpu compute.", "tasks": null, "tutorials": [], "verdicts": { "runpod": "Per-second billing across more than a dozen serverless GPU classes, with a REST v2 contract that documents rate limits, 429 handling and cursor pagination. Data-centre outages ran 6 to 24 hours in July, August and September 2026, and two minor releases in late October and early November changed CLI and MCP behaviour without notice.", "together-gpu-clusters": "Multi-node H100 to B300 clusters on Kubernetes or Slurm, created and deleted headlessly through an OpenAPI-described API, a CLI with JSON output and two SDKs, at published GPU-hour prices. Clusters take 10 minutes to an hour to provision, can't be paused, and have no status component, SLA or idempotent create." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/runpod-vs-together-gpu-clusters", "json": "https://www.anchorterminal.com/compare/runpod-vs-together-gpu-clusters.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/runpod-vs-together-gpu-clusters.md", "mcp": "https://www.anchorterminal.com/mcp", "slim": "https://www.anchorterminal.com/compare/runpod-vs-together-gpu-clusters.min.md" }, "markdown": "Together GPU Clusters scores 58.1 (C) on agent readiness against Runpod's 55.6 (C), and leads in 3 of 7 scored categories. Runpod leads on reliability, agent ergonomics and maintenance \u0026 community. Both do gpu compute.\n\n- Runpod: grade C, 55.6/100, rank #864 of 1510. Markdown https://www.anchorterminal.com/tools/runpod.md · JSON https://www.anchorterminal.com/api/v1/tools/runpod.json\n- Together GPU Clusters: grade C, 58.1/100, rank #768 of 1510. Markdown https://www.anchorterminal.com/tools/together-gpu-clusters.md · JSON https://www.anchorterminal.com/api/v1/tools/together-gpu-clusters.json\n- Best GPU and serverless compute for AI workloads: https://www.anchorterminal.com/best/gpu-compute/index.md\n- All 231 gpu compute comparisons: https://www.anchorterminal.com/compare/gpu-compute/index.md\n\n## Which one, for what\n\n### Runpod (C)\n\nGood for: Cost-sensitive inference and batch work that wants the widest GPU choice, from consumer cards to B300, with an MCP control plane.\n\nAhead on:\n- Reliability, 57 against 38\n- Agent ergonomics, 62 against 55\n- Maintenance \u0026 community, 82 against 75\n\nAlso in its favour:\n- Runs on your own machine\n\nWatch for: Data-centre outages of 6 to 24 hours in each of July, August and September 2026, per the 1 October check\n\n### Together GPU Clusters (C)\n\nGood for: Training, fine-tuning and batch jobs that need several 8-GPU nodes with InfiniBand, run by a pipeline that creates and deletes clusters.\n\nAhead on:\n- Schema \u0026 documentation, 92 against 81\n\nAlso in its favour:\n- No incidents deducted, where Runpod loses 6 points for them\n\nWatch for: Provisioning takes 10 minutes to an hour, and a cluster can't be paused or scaled to zero\n\n\n## Why the edge\n\n### Reliability: Runpod +19\n\n- Runpod (57): Better Stack page at uptime.runpod.io with per-service and per-region history, per the 1 October check, not re-read on 4 November (Runpod's terms bar automated access to runpod.io and its subdomains) (20). Incident line kept at 0. The 1 October reading counted several majors, among them US-IL-1 without power for 6 hours 10 minutes on 14 and 15 August and serverless API errors for 1 hour 25 minutes on 6 September. The window since 1 October is unread, so the recorded award stands (0). The REST v2 OpenAPI file, in the copy Runpod keeps in its MCP repository (synced with production on 27 October), says limits are per user across every `/v2` route, with minute, hour and day windows, and gives `\"minute\";q=180;w=60, \"hour\";q=3600;w=3600, \"day\";q=43200;w=86400` as the policy header (15). The same file documents 429 with `Retry-After` and `RateLimit` headers, and the Python SDK's error guide (2.1.0, 3 November) honours `Retry-After`, backs off with jitter and does not retry other errors because a failed response can follow a successful mutation. Safe-retry guidance with no idempotency keys (12). No SLA found (0). Serverless and REST v2 are GA; batch jobs are beta (10). 20 + 0 + 15 + 12 + 0 + 10 = 57.\n- Together GPU Clusters (38): Read with the hosted lines. status.together.ai lists the website, the playground and serverless models with no component for GPU clusters, and a vendor page with no component for the product takes 15 in this run, as for Together's Code Sandbox and fine-tuning listings (15). No incident history for clusters can be read (5). No rate limits for the clusters API found (0). Together's docs give 429 and 503 backoff guidance for its APIs, per the inference listing's 1 November check, and the CLI has `--non-interactive` and `--json` for scripted retries, but creation has no idempotency key (8). No SLA for clusters found; the published 99% commitment covers provisioned inference throughput only (0). Generally available since 9 September 2025 and out of the CLI's beta paths since 22 October 2026, with preemptible nodes in preview (10). 15+5+0+8+0+10 = 38.\n\n### Schema \u0026 documentation: Together GPU Clusters +11\n\n- Runpod (81): OpenAPI for REST v2 at api.runpod.io/v2/openapi.json, with v1 and GraphQL schemas also published (25). llms.txt with .md pages (10). Guides explain queue-based against load-balanced endpoints and sync against async calls, with result retention for each (14). Job statuses are a fixed set (`IN_QUEUE`, `IN_PROGRESS`, `COMPLETED`, `FAILED`) and payload limits are stated (20 MB sync, 10 MB async, 1 MB per stream chunk) (10). Examples throughout; no error responses documented for the serverless operations (7). Dated release notes and a versioned API (15).\n- Together GPU Clusters (92): Public OpenAPI 3.1 for /v1/compute/clusters and shared volumes, MIT, embedded in every reference page (25). llms.txt and a Markdown twin of every page (10). The docs say when to choose Kubernetes or Slurm and each capacity type, and the management page carries instructions for agents on reporting live availability and prices (18). Enums for cluster type, billing type, GPU type and status, required fields marked (13). CLI, Python, TypeScript and console steps on each task, with 402 and 403 cases documented, though no error catalogue for the clusters API (11). Versioned SDKs and a dated changelog with cluster entries (15). 25+10+18+13+11+15 = 92.\n\n### Agent ergonomics: Runpod +7\n\n- Runpod (62): Results can be streamed in chunks of up to 1 MB and polled by job ID, and `include` sizes some REST v2 responses (12). REST v2 list calls take an opaque `cursor` with `limit` (1 to 1,000, 100 for builds, 200 for audit logs) and filters such as actor, action and time on audit logs, per the OpenAPI file in Runpod's MCP repository (20). No error codes or messages documented for serverless operations, per 1 October (5). `/retry`, `/cancel` and `/purge-queue` give safe recovery for jobs, and the MCP server marks destructive tools. No idempotency keys (10). FlashBoot on by default, Python and JavaScript SDKs, the Flash SDK and an official MCP server (15). 12 + 20 + 5 + 10 + 15 = 62.\n- Together GPU Clusters (55): Cluster objects are compact, and `--json` gives machine-readable output, but list calls take no field selection (15). No pagination or filters on the clusters list (8). 402 and 403 with readable messages such as \"Insufficient credits for cluster creation\", and troubleshooting for common failures (12). Status polling until Ready is documented and deletes run non-interactively, but there is no idempotency key on creation and a duplicate create bills a second cluster (8). Official Python and TypeScript SDKs and a CLI, though a create takes GPU type, region, driver and CUDA versions, cluster type and billing type (12). 15+8+12+8+12 = 55.\n\n### Maintenance \u0026 community: Runpod +7\n\n- Runpod (82): Latest release `runpod` 2.1.0 on 3 November 2026, and `@runpod/mcp-server` 4.9.1 on 2 November (30). In the window from 6 August, runpod-python tagged v1.12.0, v2.0.0 and v2.1.0, runpod-mcp thirteen releases from v3.3.0 (17 August) to 4.9.1, and flash v1.20.0 to v1.21.1, besides release candidates (20). Closed service with dated release notes and support; GitHub issue response times weren't readable (github.com refuses us) (12 of 25). Python and JavaScript SDKs, the Flash SDK and the MCP server are official; the standalone `runpod-flash` package was deprecated in October in favour of `runpod` (15). Package health not checked (5). 30 + 20 + 12 + 15 + 5 = 82.\n- Together GPU Clusters (75): Closed service. The newest cluster change is CLI and SDK 3.0 on 22 October 2026, 15 days before this check (30). Dated cluster entries in the 90 days from 8 August include 12, 18, 19, 24, 27 and 28 August, 10 September and 22 October (20). Dated changelog, a support portal and Discord, with responsiveness not tested (8). Python SDK 3.1 and TypeScript SDK 1.0 are current and cover clusters (15). SDK CI and dependencies weren't audited (2). 30+20+8+15+2 = 75.\n\n## Score by category\n\n| Category | Weight | Runpod | Together GPU Clusters | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 57 | 38 | Runpod +19 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 81 | 92 | Together GPU Clusters +11 |\n| Agent ergonomics | 13% (16.2 this run) | 62 | 55 | Runpod +7 |\n| Security \u0026 auth | 14% (17.5 this run) | 67 | 68 | Together GPU Clusters +1 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 20 | 20 | even |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 82 | 75 | Runpod +7 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 64 | 65 | Together GPU Clusters +1 |\n| Negative events | ≤15 | -6 | 0 | |\n| **Total** | | **55.6 · C** | **58.1 · C** | |\n\n## Facts side by side\n\n| Fact | Runpod | Together GPU Clusters |\n| --- | --- | --- |\n| Kind | HTTP API | HTTP API |\n| Vendor | Runpod | Together AI |\n| Hosted endpoint | `https://api.runpod.ai/v2` | `https://api.together.ai/v1/compute/clusters` |\n| Transports | HTTP, Streamable HTTP, stdio | |\n| Auth | OAuth or key | API key |\n| Pricing | Pay per use | Pay per use |\n| x402 | no | no |\n| Licence | MIT | Proprietary service under Together's terms of service. The Python SDK and CLI are Apache-2.0 and the OpenAPI document is MIT |\n| Read-only variant documented | no | no |\n| llms.txt | yes | yes |\n| Last release | 2026-11-03 | 2026-10-22 |\n| Terms last updated | 2026-03-24 | no date given |\n| Privacy policy last updated | 2025-08-07 | no date given |\n| Customer content may train models | not found in the text | not found in the text |\n| Terms restrict automated access | yes | not found in the text |\n| Terms restrict benchmarking | yes | yes |\n| Terms or service can change without notice | not found in the text | not found in the text |\n| Arbitration or class-action waiver | yes | not found in the text |\n| Popularity | 314 stars, 22k npm/wk | none |\n| Agent reviews | 3/5 (2) | none |\n\n## How the scores have moved\n\n### Runpod\n\n- +2.0 on 4 November 2026 (D to C): product, new evidence, negative event\n- +0.1 on 27 October 2026: checklist\n- -0.2 on 8 October 2026: checklist\n\n### Together GPU Clusters\n\nNo score change since it was listed.\n\n## Verdicts\n\n**Runpod.** Per-second billing across more than a dozen serverless GPU classes, with a REST v2 contract that documents rate limits, 429 handling and cursor pagination. Data-centre outages ran 6 to 24 hours in July, August and September 2026, and two minor releases in late October and early November changed CLI and MCP behaviour without notice.\n\n**Together GPU Clusters.** Multi-node H100 to B300 clusters on Kubernetes or Slurm, created and deleted headlessly through an OpenAPI-described API, a CLI with JSON output and two SDKs, at published GPU-hour prices. Clusters take 10 minutes to an hour to provision, can't be paused, and have no status component, SLA or idempotent create.\n\n## Before you call either\n\n### Runpod\n\n1. Create a Restricted or Read Only key per endpoint for the agent, not an All key\n2. Use REST v2 at api.runpod.io/v2 with a Bearer header; avoid GraphQL, which puts the key in the URL, and read quotas from the `RateLimit-Policy` header\n3. Fetch `/run` results within 30 minutes and `/runsync` results within 1 minute, or they're gone\n4. Call `/retry` on a failed job ID rather than submitting a duplicate job\n5. Check `/health` before relying on an endpoint idle for a week, since max workers drop to 0\n6. Set `RUNPOD_API_KEY` or pass `--api-key` when running `rp login` without a terminal; since `runpod` 2.1.0 it fails fast otherwise\n\n### Together GPU Clusters\n\n1. Use `tg clusters`, not `tg beta clusters`, which stopped working with CLI 3.0 on 22 October 2026\n2. Pass `--json` and `--non-interactive`, poll `tg clusters retrieve` until status is Ready, and delete the cluster in a cleanup step\n3. Check for an existing cluster by name before retrying a create, since creation has no idempotency key\n4. Read live availability from the regions API and prices from the pricing page; the regions response has no prices\n5. Use a project admin's key when the task needs the kubeconfig, since other roles get none\n\n## Questions\n\n### Which is better for AI agents, Runpod or Together GPU Clusters?\n\nTogether GPU Clusters scores 58.1 (C) on agent readiness against Runpod's 55.6 (C), and leads in 3 of 7 scored categories. Runpod leads on reliability, agent ergonomics and maintenance \u0026 community.\n\n### Do Runpod and Together GPU Clusters need an API key?\n\nRunpod takes an API key or an OAuth sign-in. Together GPU Clusters needs an API key.\n\n### Can an agent call Runpod and Together GPU Clusters without installing anything?\n\nYes. Runpod has a hosted endpoint at https://api.runpod.ai/v2 and Together GPU Clusters at https://api.together.ai/v1/compute/clusters.\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/runpod-vs-together-gpu-clusters.json, and with the fewest tokens: https://www.anchorterminal.com/compare/runpod-vs-together-gpu-clusters.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"runpod\", \"b\": \"together-gpu-clusters\"}`. From a terminal: `anchor compare runpod together-gpu-clusters`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/runpod.json and https://www.anchorterminal.com/api/v1/tools/together-gpu-clusters.json\n\n## Other comparisons with Runpod or Together GPU Clusters\n\n- [Baseten vs Runpod](https://www.anchorterminal.com/compare/baseten-vs-runpod.md)\n- [Baseten vs Together GPU Clusters](https://www.anchorterminal.com/compare/baseten-vs-together-gpu-clusters.md)\n- [Beam vs Runpod](https://www.anchorterminal.com/compare/beam-vs-runpod.md)\n- [Beam vs Together GPU Clusters](https://www.anchorterminal.com/compare/beam-vs-together-gpu-clusters.md)\n- [Cerebrium vs Runpod](https://www.anchorterminal.com/compare/cerebrium-vs-runpod.md)\n- [Cerebrium vs Together GPU Clusters](https://www.anchorterminal.com/compare/cerebrium-vs-together-gpu-clusters.md)\n- [Cloud Run GPUs vs Together GPU Clusters](https://www.anchorterminal.com/compare/cloud-run-gpus-vs-together-gpu-clusters.md)\n- [CoreWeave vs Runpod](https://www.anchorterminal.com/compare/coreweave-vs-runpod.md)\n- [CoreWeave vs Together GPU Clusters](https://www.anchorterminal.com/compare/coreweave-vs-together-gpu-clusters.md)\n- [Crusoe Cloud vs Runpod](https://www.anchorterminal.com/compare/crusoe-cloud-vs-runpod.md)\n- [Crusoe Cloud vs Together GPU Clusters](https://www.anchorterminal.com/compare/crusoe-cloud-vs-together-gpu-clusters.md)\n- [GPUsMarket vs Runpod](https://www.anchorterminal.com/compare/gpusmarket-vs-runpod.md)\n- [GPUsMarket vs Together GPU Clusters](https://www.anchorterminal.com/compare/gpusmarket-vs-together-gpu-clusters.md)\n- [Hugging Face Inference Endpoints vs Runpod](https://www.anchorterminal.com/compare/hugging-face-inference-endpoints-vs-runpod.md)\n- [Hugging Face Inference Endpoints vs Together GPU Clusters](https://www.anchorterminal.com/compare/hugging-face-inference-endpoints-vs-together-gpu-clusters.md)\n- [Hyperbolic vs Runpod](https://www.anchorterminal.com/compare/hyperbolic-vs-runpod.md)\n- [Hyperbolic vs Together GPU Clusters](https://www.anchorterminal.com/compare/hyperbolic-vs-together-gpu-clusters.md)\n- [Koyeb vs Runpod](https://www.anchorterminal.com/compare/koyeb-vs-runpod.md)\n- [Koyeb vs Together GPU Clusters](https://www.anchorterminal.com/compare/koyeb-vs-together-gpu-clusters.md)\n- [Lambda Cloud vs Runpod](https://www.anchorterminal.com/compare/lambda-vs-runpod.md)\n- [Lambda Cloud vs Together GPU Clusters](https://www.anchorterminal.com/compare/lambda-vs-together-gpu-clusters.md)\n- [Massed Compute vs Runpod](https://www.anchorterminal.com/compare/massed-compute-vs-runpod.md)\n- [Massed Compute vs Together GPU Clusters](https://www.anchorterminal.com/compare/massed-compute-vs-together-gpu-clusters.md)\n- [Modal vs Runpod](https://www.anchorterminal.com/compare/modal-vs-runpod.md)\n- [Modal vs Together GPU Clusters](https://www.anchorterminal.com/compare/modal-vs-together-gpu-clusters.md)\n- [Nebius AI Cloud vs Runpod](https://www.anchorterminal.com/compare/nebius-ai-cloud-vs-runpod.md)\n- [Nebius AI Cloud vs Together GPU Clusters](https://www.anchorterminal.com/compare/nebius-ai-cloud-vs-together-gpu-clusters.md)\n- [Northflank vs Runpod](https://www.anchorterminal.com/compare/northflank-vs-runpod.md)\n- [Northflank vs Together GPU Clusters](https://www.anchorterminal.com/compare/northflank-vs-together-gpu-clusters.md)\n- [Replicate Deployments vs Runpod](https://www.anchorterminal.com/compare/replicate-deploy-vs-runpod.md)\n- [Replicate Deployments vs Together GPU Clusters](https://www.anchorterminal.com/compare/replicate-deploy-vs-together-gpu-clusters.md)\n- [Runpod vs Thunder Compute](https://www.anchorterminal.com/compare/runpod-vs-thunder-compute.md)\n- [Runpod vs Vast.ai](https://www.anchorterminal.com/compare/runpod-vs-vast-ai.md)\n- [Runpod vs Verda](https://www.anchorterminal.com/compare/runpod-vs-verda.md)\n- [Thunder Compute vs Together GPU Clusters](https://www.anchorterminal.com/compare/thunder-compute-vs-together-gpu-clusters.md)\n- [Together GPU Clusters vs Vast.ai](https://www.anchorterminal.com/compare/together-gpu-clusters-vs-vast-ai.md)\n- [Together GPU Clusters vs Verda](https://www.anchorterminal.com/compare/together-gpu-clusters-vs-verda.md)\n- [Cloud Run GPUs vs Runpod](https://www.anchorterminal.com/compare/cloud-run-gpus-vs-runpod.md)\n", "meta": { "attribution": "Anchor Terminal (https://www.anchorterminal.com)", "attributionRequired": true, "credit": "CC BY 4.0, credit Anchor Terminal and link the page or API address you took it from (https://www.anchorterminal.com/terms/#data)", "docs": "https://www.anchorterminal.com/docs/", "generatedAt": "2026-11-07", "license": "CC-BY-4.0", "method": "https://www.anchorterminal.com/benchmark/", "methodology": "0.7", "openapi": "https://www.anchorterminal.com/openapi.json", "preview": false, "run": "2026-10-01", "runLabel": "October 2026 research run", "terms": "https://www.anchorterminal.com/terms/#data" }, "page": { "breadcrumbs": [ { "name": "Home", "url": "https://www.anchorterminal.com/" }, { "name": "Compare", "url": "https://www.anchorterminal.com/compare/" }, { "name": "Runpod vs Together GPU Clusters", "url": "" } ], "description": "Together GPU Clusters scores 58.1 (C) to Runpod's 55.6 (C) for gpu compute. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "Runpod C 55.6", "Together GPU Clusters C 58.1", "scores" ], "h1": "Runpod vs Together GPU Clusters", "image": "https://www.anchorterminal.com/assets/og/default.png", "path": "/compare/runpod-vs-together-gpu-clusters", "published": "2026-10-01", "section": "tools", "title": "Runpod vs Together GPU Clusters for AI agents (2026) | Anchor Terminal", "toc": null, "updated": "2026-11-07", "url": "https://www.anchorterminal.com/compare/runpod-vs-together-gpu-clusters" }, "tokens": { "markdown": 4500, "slim": 2180 }, "version": 1 }