{ "data": { "a": { "slug": "replicate-deploy", "name": "Replicate Deployments", "vendor": "Replicate", "vendorUrl": "https://replicate.com", "kind": "http-api", "category": "gpu-compute", "summary": "Replicate's service for deploying and running custom models.", "url": "https://www.anchorterminal.com/tools/replicate-deploy", "markdownUrl": "https://www.anchorterminal.com/tools/replicate-deploy.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/replicate-deploy.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/replicate-deploy.json", "dns": "replicate-deploy.grade.anchorterminal.com", "repo": "https://github.com/replicate/cog", "license": "Apache-2.0", "transports": [ "http", "sse", "stdio" ], "remoteUrl": "https://api.replicate.com/v1", "packages": [ { "registry": "npm", "name": "replicate" }, { "registry": "pypi", "name": "replicate" }, { "registry": "npm", "name": "replicate-mcp" } ], "auth": "api-key", "authNotes": "Bearer API token on every call to api.replicate.com. `cog push` uses the same token to upload a model image. The hosted MCP at https://mcp.replicate.com/sse asks for the token in a browser flow and holds it for the client; the local `replicate-mcp` package reads `REPLICATE_API_TOKEN`.", "pricing": "usage", "pricingNotes": "Private models and deployments bill per second for the whole time an instance is up, set-up and idle included, from prepaid credit or monthly in arrears. CPU (Small) $0.000025 a second ($0.09 an hour), CPU $0.000100 ($0.36), T4 $0.000225 ($0.81), L40S $0.000975 ($3.51), A100 80 GB $0.001400 ($5.04), H100 $0.001525 ($5.49), 2x L40S $0.001950 ($7.02), 2x A100 $0.002800 ($10.08). 2x H100 ($10.98), H200 ($5.49) and 2x to 8x H200, and 4x and 8x L40S, A100 and H100 up to $43.92 an hour need a committed-spend contract. Fast-booting fine-tunes bill only while active. Public models bill only active time and not failures (https://replicate.com/pricing, https://replicate.com/docs/topics/billing).", "priceSummary": "Pay per use", "where": "both", "x402": { "level": "no", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": 9500, "npmWeekly": 634116, "pypiWeekly": 386704, "asOf": "2026-09-30" }, "docsUrl": "https://replicate.com/docs/topics/deployments", "llmsTxt": "https://replicate.com/docs/llms.txt", "openapi": "https://api.replicate.com/openapi.json", "capabilities": [ "compute.gpu", "compute.endpoints", "compute.serverless", "compute.containers" ], "tags": [ "hosted", "usage-priced", "mcp", "llms-txt", "openapi", "python", "typescript", "async-jobs", "webhooks", "open-source" ], "lastRelease": "2026-10-19", "graded": true, "anchor": { "graded": true, "score": 65.2, "grade": "B", "agentReady": false, "rank": 432, "ranked": true, "rankOf": 1510, "categoryRank": 5, "methodology": "0.7", "run": "2026-10-01", "scores": { "ergonomics": 73, "maintenance": 78, "payments": 30, "reliability": 75, "schema": 85, "security": 40, "transparency": 79 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-11-02" }, "negative": 0, "verdict": "OpenAPI file, llms.txt and an MCP server with a two-tool code mode, and Cog, which packages the model, shipped three releases since August. Private instances bill set-up and idle time, H100 at $5.49 an hour, and the changelog has been silent since April 2026.", "bestFor": "Teams already calling Replicate's public models who want their own model behind the same API, MCP server and webhooks.", "strengths": [ "OpenAPI file, llms.txt and an MCP server with a two-tool code mode", "Deployment min and max instances settable over the API, 0 allowed", "API prediction data deleted after one hour by default", "Published limits, 600 prediction creates and 3,000 other calls a minute", "Cog released 0.22.0, 0.23.0 and 0.23.1 between 13 August and 19 October 2026" ], "weaknesses": [ "Private instances bill set-up and idle time, H100 at $5.49 an hour", "API tokens have no scopes, expiry or audit log", "Changelog silent since 21 April 2026, and no stable Python client release since May 2025", "More than 2 GPUs, and any H200, needs a committed-spend contract", "Two September 2026 incidents ran 15 and 20 hours, both partial" ], "agentNotes": [ "List `GET /v1/hardware` first and use the returned `sku` in the deployment body", "Set `min_instances` to 0 for bursty work; a warm H100 bills $5.49 an hour whether called or not", "Send `Prefer: wait` on deployment predictions to block instead of polling", "Copy outputs within an hour; API prediction data is deleted after that", "Wait for the reset time in the 429 body before retrying; prediction creates cap at 600 a minute" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 2, "avgRating": 3, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "B", "methodology": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 65.2 } ], "editorialScores": { "ergonomics": 73, "maintenance": 78, "payments": 30, "reliability": 75, "schema": 85, "security": 40, "transparency": 69 }, "provenanceScore": 89, "checked": { "categories": { "ergonomics": "2026-11-02", "maintenance": "2026-11-02", "payments": "2026-11-02", "reliability": "2026-11-02", "schema": "2026-11-02", "security": "2026-11-02", "transparency": "2026-11-02" }, "last": "2026-11-02", "lastMoved": "2026-11-02", "oldest": "2026-11-02", "stale": false, "staleAfterDays": 90 } }, "connect": { "install": "pip install cog replicate", "http": "curl -X POST \"https://api.replicate.com/v1/deployments/$REPLICATE_OWNER/my-deployment/predictions\" \\\n -H \"Authorization: Bearer $REPLICATE_API_TOKEN\" -H \"Content-Type: application/json\" -H \"Prefer: wait\" \\\n -d '{\"input\":{\"prompt\":\"hello\"}}'", "claudeCode": "claude mcp add replicate https://mcp.replicate.com/sse --transport sse --scope user", "config": { "mcpServers": { "replicate": { "args": [ "-y", "replicate-mcp" ], "command": "npx", "env": { "REPLICATE_API_TOKEN": "${REPLICATE_API_TOKEN}" } } } } }, "letme": { "capability": "https://letme.dev/compute.gpu", "tool": "https://letme.dev/replicate-deploy" }, "sameCompany": [ "replicate-image", "replicate-video", "replicate-musicgen" ], "area": "models", "unitPrices": [ { "item": "H100 80 GB", "unit": "gpu-hour", "usd": 5.49, "note": "$0.001525 a second, including set-up and idle" }, { "item": "A100 80 GB", "unit": "gpu-hour", "usd": 5.04, "note": "$0.001400 a second" }, { "item": "L40S 48 GB", "unit": "gpu-hour", "usd": 3.51, "note": "$0.000975 a second" }, { "item": "T4 16 GB", "unit": "gpu-hour", "usd": 0.81, "note": "$0.000225 a second" } ], "provenance": { "legalEntity": "Replicate, LLC", "domain": "replicate.com", "domainRegistered": "1998-05-26", "domainNote": "replicate.com was registered in 1998, long before Replicate the company existed.", "endpointOnVendorDomain": true, "terms": "https://replicate.com/terms", "privacy": "https://replicate.com/privacy", "statusPage": "https://replicatestatus.com", "changelog": "https://replicate.com/changelog", "securityTxt": "none", "checked": "2026-09-30", "notes": [ "Terms last updated 2026-04-01 name Replicate, LLC as the contracting party.", "replicatestatus.com redirects to Cloudflare's status page filtered to Replicate.", "Replicate's hosted image and music models are listed separately under image generation and music generation." ], "score": 89 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/replicate-deploy.json", "live": { "slug": "replicate-deploy", "probe": { "target": "https://api.replicate.com/v1", "method": "get", "lastAt": "2026-11-07T22:56:17.832830109Z", "lastOk": true, "lastStatus": 401, "lastMs": 131, "lastNote": "asks for credentials", "authRequired": true, "uptime24h": 100, "uptime30d": 100, "p50ms24h": 131, "p95ms24h": 276, "samples24h": 244, "samples30d": 7956, "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": 233, "ok": 233 } ] }, "vendorStatus": { "page": "https://replicatestatus.com", "indicator": "unknown", "summary": "no machine-readable status found", "checkedAt": "2026-11-07T04:48:40.399907591Z" }, "versions": [ { "registry": "github", "name": "replicate/cog", "version": "v0.23.1", "released": "2026-10-20", "seenAt": "2026-11-07T00:01:09.866719484Z" }, { "registry": "npm", "name": "replicate", "version": "1.4.0", "seenAt": "2026-11-07T00:01:07.5708322Z" }, { "registry": "npm", "name": "replicate-mcp", "version": "0.9.0", "seenAt": "2026-11-07T00:01:08.011276677Z" }, { "registry": "pypi", "name": "replicate", "version": "1.0.7", "released": "2025-05-27", "seenAt": "2026-11-07T00:01:07.782674478Z" } ], "githubStars": 9494, "npmWeekly": 805275, "pypiWeekly": 396497, "securityTxt": { "url": "https://replicate.com/.well-known/security.txt", "state": "none", "checkedAt": "2026-11-07T16:01:02.105557027Z" }, "llmsTxt": { "url": "https://replicate.com/docs/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-11-07T15:33:45.131385958Z" }, "domain": { "domain": "replicate.com", "registered": "1998-05-26", "source": "https://rdap.verisign.com/com/v1/domain/replicate.com", "checkedAt": "2026-11-01T14:20:16.006565471Z" }, "pages": [ { "url": "https://replicate.com/changelog", "kind": "changelog", "status": 304, "checkedAt": "2026-11-07T14:18:19.719079825Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "490f4836aca3" }, { "url": "https://replicate.com/pricing", "kind": "pricing", "status": 200, "checkedAt": "2026-11-07T14:18:22.053284085Z", "changedAt": "2026-11-04T08:31:26.382456818Z", "fingerprint": "246042e35580" }, { "url": "https://replicate.com/privacy", "kind": "privacy", "status": 200, "checkedAt": "2026-11-07T14:18:24.363010933Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "8e299fbc64eb" }, { "url": "https://replicate.com/terms", "kind": "terms", "status": 200, "checkedAt": "2026-11-07T14:18:25.932917726Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "ea48efe3382b" } ], "github": { "repo": "replicate/cog", "checkedAt": "2026-11-02T09:21:13.080161119Z", "stars": 9494, "archived": false, "issuesEnabled": true, "pushedAt": "2026-10-31T23:09:21Z", "openIssues": 30, "openPRs": 70, "issuesOpened90d": 5, "issuesClosed90d": 10, "prsMerged90d": 25, "ci": { "branch": "main", "runs": 50, "success": 49, "failure": 1, "other": 0, "latest": "success", "latestAt": "2026-10-27T20:48:06Z" }, "replies": { "sampled": 25, "unanswered": 2, "medianDays": 1.3 } }, "updatedAt": "2026-11-07T22:56:17.832830109Z" } }, "answer": "Replicate Deployments scores 65.2 (B) on agent readiness against Together GPU Clusters's 58.1 (C), and leads in 5 of 7 scored categories. Together GPU Clusters leads on schema \u0026 documentation and security \u0026 auth.", "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": "2026-11-07T22:56:27.360809678Z", "lastOk": true, "lastStatus": 401, "lastMs": 259, "lastNote": "asks for credentials", "authRequired": true, "uptime24h": 100, "uptime30d": 100, "p50ms24h": 492, "p95ms24h": 827, "samples24h": 244, "samples30d": 246, "days": [ { "date": "2026-11-06", "probes": 13, "ok": 13 }, { "date": "2026-11-07", "probes": 233, "ok": 233 } ] }, "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": "2026-11-07T22:56:27.360809678Z" } }, "edges": [ { "by": 37, "category": "reliability", "leads": "replicate-deploy", "name": "Reliability", "reasons": { "a": "Replicate incidents post under a Replicate component on cloudflarestatus.com, and replicatestatus.com redirects to that page filtered to Replicate (20). The component's 90-day bars, read on 2 November, show 5 days with incidents, all in September 2026, and none since 28 September. Some third-party models couldn't scale out for 15 hours 41 minutes on 14 and 15 September, a Pruna-specific issue ran 20 hours on 17 September, backend services returned intermittent 500s for 1 hour 54 minutes on 24 September, and hot-swapped Flux models stuck for 17 minutes on 28 September. Each names a subset of models or intermittent errors, so each reads as partial, minor only (20). 600 prediction creates a minute, 3,000 a minute on other endpoints, and 6 a minute without a card, re-read on 2 November (15). A 429 body says when the limit resets ('resets in ~30s') and the error-code page gives retry advice per code, but there's no Retry-After header or idempotency guidance (10 of 15). No SLA found (0). Deployments are GA (10). 20 + 20 + 15 + 10 + 0 + 10 = 75.", "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": 75, "b": 38 } }, { "by": 28, "category": "security", "leads": "together-gpu-clusters", "name": "Security \u0026 auth", "reasons": { "a": "Bearer tokens starting `r8_`, several per account, each can be disabled; no scopes or expiry, re-read on 2 November (20). No read-only or per-model token; every token can create, update and delete deployments (0). Returns your own model's output (10). No audit log or per-token usage view found; predictions are listed per account (5). Replicate scans public GitHub for leaked tokens, disables them and emails the owner. replicate.com/.well-known/security.txt answers 404, and no bug bounty or certification was found in the docs we read. OSV lists no advisory for the `replicate` packages, `replicate-mcp` or Cog (5). 20 + 0 + 10 + 5 + 5 = 40.", "b": "Project-scoped API keys, revocable with optional expiry, read as Together's other listings read the same key model (30). Admin and editor roles with no read-only role. Only admins get the admin kubeconfig, which has cluster-admin rights, and OIDC lets editors use kubectl under RBAC. Deletes run without confirmation when `--non-interactive` is passed (8). The API returns cluster state, not third-party content (10). Invoices itemise reserved, on-demand and storage charges, and no audit log for cluster operations was found (5). security.txt with a HackerOne route, per the 1 November check of the inference listing (15). 30+8+10+5+15 = 68." }, "scores": { "a": 40, "b": 68 } }, { "by": 18, "category": "ergonomics", "leads": "replicate-deploy", "name": "Agent ergonomics", "reasons": { "a": "The MCP server exposes one tool per HTTP operation and has an experimental code mode that collapses them into two tools (search the SDK docs, run TypeScript) (20). List responses page with `next` and `previous` cursor URLs, the predictions list filters by `created_after`, `created_before` and `source`, and the models list sorts, but there is no page size or field selection (15 of 20; was 10, pagination not verified on 1 October). Coded errors with suggested fixes, `detail` messages on HTTP errors (15). No idempotency keys; `Prefer: wait`, a `Cancel-After` header, webhooks and cancel cut polling, and a failed run still bills its active time (8). Sensible defaults (`min_instances` 0 allowed) and official Python and JavaScript clients plus Cog (15). 20 + 15 + 15 + 8 + 15 = 73.", "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": 73, "b": 55 } }, { "by": 14, "category": "transparency", "leads": "replicate-deploy", "name": "Transparency \u0026 trust", "reasons": { "a": "Closed service; Cog is Apache-2.0 (20). API prediction inputs, outputs, files and logs are deleted after one hour by default, web predictions are kept until deleted, and a subprocessor page is published, per the 1 October check, not re-read on 2 November (22). Dated deprecations in the changelog (streaming default in July 2024, spend limits in July 2025) but no written policy (12). Subprocessors listed; data locations not stated in what we read (15). 20 + 22 + 12 + 15 = 69.", "b": "Closed service under Together's terms, with Apache-2.0 SDKs, which don't raise the line for a closed API (15). The privacy policy's data table covers GPU clusters, per the 4 November Code Sandbox check, and the billing page states when volumes are deleted after credit runs out, with no retention period for data on deleted clusters (15). The 3.0 breaking change came with a migration guide on the day, and reservations carry dated end-of-term emails, with no notice period for API changes found (8). Regions are listed through the API and US regions appear in examples; subprocessors and data locations for clusters were not established (8). 15+15+8+8 = 46." }, "scores": { "a": 79, "b": 65 } }, { "by": 10, "category": "payments", "leads": "replicate-deploy", "name": "Payments \u0026 pricing", "reasons": { "a": "No machine payment protocol (0). Per-second prices for each hardware SKU published without a login, re-read on 2 November, now with a small CPU tier at $0.09 an hour and H200 SKUs on committed-spend contracts (20). Accounts without a card can run predictions at up to 6 a minute; private deployments still bill set-up and idle time (10 of 20). Signup is a browser flow (0). 0 + 20 + 10 + 0 = 30.", "b": "No machine payment protocol (0). Per GPU-hour prices for each capacity type and per GiB-month storage published without a login (20). No free trial, and creation needs credit for the full reservation or a minimum on-demand period (0). Sign-up and credit purchase are browser steps (0). 0+20+0+0 = 20." }, "scores": { "a": 30, "b": 20 } }, { "by": 7, "category": "schema", "leads": "together-gpu-clusters", "name": "Schema \u0026 documentation", "reasons": { "a": "Public OpenAPI 3.1.0 at api.replicate.com/openapi.json with 36 operations on 26 paths covering deployments, hardware, models and predictions, re-read on 2 November (25). llms.txt with Markdown pages (10). Operation descriptions in the spec explain purpose with curl examples; deployment docs say when to use a deployment rather than a model version (16). Deployment fields are bounded (`min_instances` 0 to 5, `max_instances` 0 to 20, a 64-character version, a hardware SKU from GET /v1/hardware) (13). Examples throughout and 8 coded errors (E1001 out of memory, E6716 start timeout and others) with fixes; the HTTP error body format isn't described (11). Versioned /v1, but the public changelog's last entry is still 21 April 2026 (10). 25 + 10 + 16 + 13 + 11 + 10 = 85.", "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": 85, "b": 92 } } ], "facts": [ { "a": "HTTP API", "b": "HTTP API", "name": "Kind" }, { "a": "Replicate", "b": "Together AI", "name": "Vendor" }, { "a": "https://api.replicate.com/v1", "b": "https://api.together.ai/v1/compute/clusters", "name": "Hosted endpoint" }, { "a": "HTTP, SSE (legacy), stdio", "b": "", "name": "Transports" }, { "a": "API key", "b": "API key", "name": "Auth" }, { "a": "Pay per use", "b": "Pay per use", "name": "Pricing" }, { "a": "no", "b": "no", "name": "x402" }, { "a": "Apache-2.0", "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": "2026-10-19", "b": "2026-10-22", "name": "Last release" }, { "a": "2026-04-01", "b": "no date given", "name": "Terms last updated" }, { "a": "2026-04-01", "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": "not found in the text", "b": "not found in the text", "name": "Terms restrict automated access" }, { "a": "not found in the text", "b": "yes", "name": "Terms restrict benchmarking" }, { "a": "yes", "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": "9.5k stars, 634k npm/wk, 387k PyPI/wk", "b": "none", "name": "Popularity" }, { "a": "3/5 (2)", "b": "none", "name": "Agent reviews" } ], "faq": [ { "answer": "Replicate Deployments scores 65.2 (B) on agent readiness against Together GPU Clusters's 58.1 (C), and leads in 5 of 7 scored categories. Together GPU Clusters leads on schema \u0026 documentation and security \u0026 auth.", "question": "Which is better for AI agents, Replicate Deployments or Together GPU Clusters?" }, { "answer": "Both need an API key.", "question": "Do Replicate Deployments and Together GPU Clusters need an API key?" }, { "answer": "Yes. Replicate Deployments has a hosted endpoint at https://api.replicate.com/v1 and Together GPU Clusters at https://api.together.ai/v1/compute/clusters.", "question": "Can an agent call Replicate Deployments and Together GPU Clusters without installing anything?" }, { "answer": "Replicate Deployments is open source (Apache-2.0). No open-source release is listed for Together GPU Clusters.", "question": "Are Replicate Deployments and Together GPU Clusters open source?" } ], "goodFor": [ { "aheadOn": [ "Reliability, 75 against 38", "Agent ergonomics, 73 against 55", "Payments \u0026 pricing, 30 against 20", "Transparency \u0026 trust, 79 against 65" ], "also": [ "Runs on your own machine", "Open source" ], "goodFor": "Teams already calling Replicate's public models who want their own model behind the same API, MCP server and webhooks.", "slug": "replicate-deploy", "watchFor": "Private instances bill set-up and idle time, H100 at $5.49 an hour" }, { "aheadOn": [ "Schema \u0026 documentation, 92 against 85", "Security \u0026 auth, 68 against 40" ], "also": null, "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": { "replicate-deploy": [ { "causes": [ "product", "evidence" ], "date": "2026-11-02", "delta": 1.5, "from": 63.7, "fromGrade": "B", "to": 65.2, "toGrade": "B" }, { "causes": [ "method" ], "date": "2026-10-27", "delta": 0.1, "from": 63.6, "fromGrade": "B", "to": 63.7, "toGrade": "B" }, { "causes": [ "method" ], "date": "2026-10-08", "delta": -0.1, "from": 63.7, "fromGrade": "B", "to": 63.6, "toGrade": "B" } ], "together-gpu-clusters": null }, "job": { "capability": "compute.gpu", "name": "GPU compute" }, "others": [ { "json": "https://www.anchorterminal.com/compare/baseten-vs-replicate-deploy.json", "title": "Baseten vs Replicate Deployments", "url": "https://www.anchorterminal.com/compare/baseten-vs-replicate-deploy" }, { "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-replicate-deploy.json", "title": "Beam vs Replicate Deployments", "url": "https://www.anchorterminal.com/compare/beam-vs-replicate-deploy" }, { "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-replicate-deploy.json", "title": "Cerebrium vs Replicate Deployments", "url": "https://www.anchorterminal.com/compare/cerebrium-vs-replicate-deploy" }, { "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-replicate-deploy.json", "title": "CoreWeave vs Replicate Deployments", "url": "https://www.anchorterminal.com/compare/coreweave-vs-replicate-deploy" }, { "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-replicate-deploy.json", "title": "Crusoe Cloud vs Replicate Deployments", "url": "https://www.anchorterminal.com/compare/crusoe-cloud-vs-replicate-deploy" }, { "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-replicate-deploy.json", "title": "GPUsMarket vs Replicate Deployments", "url": "https://www.anchorterminal.com/compare/gpusmarket-vs-replicate-deploy" }, { "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-replicate-deploy.json", "title": "Hugging Face Inference Endpoints vs Replicate Deployments", "url": "https://www.anchorterminal.com/compare/hugging-face-inference-endpoints-vs-replicate-deploy" }, { "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-replicate-deploy.json", "title": "Hyperbolic vs Replicate Deployments", "url": "https://www.anchorterminal.com/compare/hyperbolic-vs-replicate-deploy" }, { "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-replicate-deploy.json", "title": "Koyeb vs Replicate Deployments", "url": "https://www.anchorterminal.com/compare/koyeb-vs-replicate-deploy" }, { "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-replicate-deploy.json", "title": "Lambda Cloud vs Replicate Deployments", "url": "https://www.anchorterminal.com/compare/lambda-vs-replicate-deploy" }, { "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-replicate-deploy.json", "title": "Massed Compute vs Replicate Deployments", "url": "https://www.anchorterminal.com/compare/massed-compute-vs-replicate-deploy" }, { "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-replicate-deploy.json", "title": "Modal vs Replicate Deployments", "url": "https://www.anchorterminal.com/compare/modal-vs-replicate-deploy" }, { "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-replicate-deploy.json", "title": "Nebius AI Cloud vs Replicate Deployments", "url": "https://www.anchorterminal.com/compare/nebius-ai-cloud-vs-replicate-deploy" }, { "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-replicate-deploy.json", "title": "Northflank vs Replicate Deployments", "url": "https://www.anchorterminal.com/compare/northflank-vs-replicate-deploy" }, { "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-thunder-compute.json", "title": "Replicate Deployments vs Thunder Compute", "url": "https://www.anchorterminal.com/compare/replicate-deploy-vs-thunder-compute" }, { "json": "https://www.anchorterminal.com/compare/replicate-deploy-vs-vast-ai.json", "title": "Replicate Deployments vs Vast.ai", "url": "https://www.anchorterminal.com/compare/replicate-deploy-vs-vast-ai" }, { "json": "https://www.anchorterminal.com/compare/replicate-deploy-vs-verda.json", "title": "Replicate Deployments vs Verda", "url": "https://www.anchorterminal.com/compare/replicate-deploy-vs-verda" }, { "json": "https://www.anchorterminal.com/compare/runpod-vs-together-gpu-clusters.json", "title": "Runpod vs Together GPU Clusters", "url": "https://www.anchorterminal.com/compare/runpod-vs-together-gpu-clusters" }, { "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-replicate-deploy.json", "title": "Cloud Run GPUs vs Replicate Deployments", "url": "https://www.anchorterminal.com/compare/cloud-run-gpus-vs-replicate-deploy" } ], "panel": null, "scores": [ { "by": 37, "edge": "replicate-deploy", "key": "reliability", "name": "Reliability", "replicate-deploy": 75, "together-gpu-clusters": 38, "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "by": 7, "edge": "together-gpu-clusters", "key": "schema", "name": "Schema \u0026 documentation", "replicate-deploy": 85, "together-gpu-clusters": 92, "weight": 13 }, { "by": 18, "edge": "replicate-deploy", "key": "ergonomics", "name": "Agent ergonomics", "replicate-deploy": 73, "together-gpu-clusters": 55, "weight": 13 }, { "by": 28, "edge": "together-gpu-clusters", "key": "security", "name": "Security \u0026 auth", "replicate-deploy": 40, "together-gpu-clusters": 68, "weight": 14 }, { "by": 10, "edge": "replicate-deploy", "key": "payments", "name": "Payments \u0026 pricing", "replicate-deploy": 30, "together-gpu-clusters": 20, "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "by": 3, "edge": "replicate-deploy", "key": "maintenance", "name": "Maintenance \u0026 community", "replicate-deploy": 78, "together-gpu-clusters": 75, "weight": 7 }, { "by": 14, "edge": "replicate-deploy", "key": "transparency", "name": "Transparency \u0026 trust", "replicate-deploy": 79, "together-gpu-clusters": 65, "weight": 7 } ], "summary": "Replicate Deployments scores 65.2 (B) on agent readiness against Together GPU Clusters's 58.1 (C), and leads in 5 of 7 scored categories. Together GPU Clusters leads on schema \u0026 documentation and security \u0026 auth. Both do gpu compute.", "tasks": null, "tutorials": [], "verdicts": { "replicate-deploy": "OpenAPI file, llms.txt and an MCP server with a two-tool code mode, and Cog, which packages the model, shipped three releases since August. Private instances bill set-up and idle time, H100 at $5.49 an hour, and the changelog has been silent since April 2026.", "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/replicate-deploy-vs-together-gpu-clusters", "json": "https://www.anchorterminal.com/compare/replicate-deploy-vs-together-gpu-clusters.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/replicate-deploy-vs-together-gpu-clusters.md", "mcp": "https://www.anchorterminal.com/mcp", "slim": "https://www.anchorterminal.com/compare/replicate-deploy-vs-together-gpu-clusters.min.md" }, "markdown": "Replicate Deployments scores 65.2 (B) on agent readiness against Together GPU Clusters's 58.1 (C), and leads in 5 of 7 scored categories. Together GPU Clusters leads on schema \u0026 documentation and security \u0026 auth. Both do gpu compute.\n\n- Replicate Deployments: grade B, 65.2/100, rank #432 of 1510. Markdown https://www.anchorterminal.com/tools/replicate-deploy.md · JSON https://www.anchorterminal.com/api/v1/tools/replicate-deploy.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### Replicate Deployments (B)\n\nGood for: Teams already calling Replicate's public models who want their own model behind the same API, MCP server and webhooks.\n\nAhead on:\n- Reliability, 75 against 38\n- Agent ergonomics, 73 against 55\n- Payments \u0026 pricing, 30 against 20\n- Transparency \u0026 trust, 79 against 65\n\nAlso in its favour:\n- Runs on your own machine\n- Open source\n\nWatch for: Private instances bill set-up and idle time, H100 at $5.49 an hour\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 85\n- Security \u0026 auth, 68 against 40\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: Replicate Deployments +37\n\n- Replicate Deployments (75): Replicate incidents post under a Replicate component on cloudflarestatus.com, and replicatestatus.com redirects to that page filtered to Replicate (20). The component's 90-day bars, read on 2 November, show 5 days with incidents, all in September 2026, and none since 28 September. Some third-party models couldn't scale out for 15 hours 41 minutes on 14 and 15 September, a Pruna-specific issue ran 20 hours on 17 September, backend services returned intermittent 500s for 1 hour 54 minutes on 24 September, and hot-swapped Flux models stuck for 17 minutes on 28 September. Each names a subset of models or intermittent errors, so each reads as partial, minor only (20). 600 prediction creates a minute, 3,000 a minute on other endpoints, and 6 a minute without a card, re-read on 2 November (15). A 429 body says when the limit resets ('resets in ~30s') and the error-code page gives retry advice per code, but there's no Retry-After header or idempotency guidance (10 of 15). No SLA found (0). Deployments are GA (10). 20 + 20 + 15 + 10 + 0 + 10 = 75.\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### Security \u0026 auth: Together GPU Clusters +28\n\n- Replicate Deployments (40): Bearer tokens starting `r8_`, several per account, each can be disabled; no scopes or expiry, re-read on 2 November (20). No read-only or per-model token; every token can create, update and delete deployments (0). Returns your own model's output (10). No audit log or per-token usage view found; predictions are listed per account (5). Replicate scans public GitHub for leaked tokens, disables them and emails the owner. replicate.com/.well-known/security.txt answers 404, and no bug bounty or certification was found in the docs we read. OSV lists no advisory for the `replicate` packages, `replicate-mcp` or Cog (5). 20 + 0 + 10 + 5 + 5 = 40.\n- Together GPU Clusters (68): Project-scoped API keys, revocable with optional expiry, read as Together's other listings read the same key model (30). Admin and editor roles with no read-only role. Only admins get the admin kubeconfig, which has cluster-admin rights, and OIDC lets editors use kubectl under RBAC. Deletes run without confirmation when `--non-interactive` is passed (8). The API returns cluster state, not third-party content (10). Invoices itemise reserved, on-demand and storage charges, and no audit log for cluster operations was found (5). security.txt with a HackerOne route, per the 1 November check of the inference listing (15). 30+8+10+5+15 = 68.\n\n### Agent ergonomics: Replicate Deployments +18\n\n- Replicate Deployments (73): The MCP server exposes one tool per HTTP operation and has an experimental code mode that collapses them into two tools (search the SDK docs, run TypeScript) (20). List responses page with `next` and `previous` cursor URLs, the predictions list filters by `created_after`, `created_before` and `source`, and the models list sorts, but there is no page size or field selection (15 of 20; was 10, pagination not verified on 1 October). Coded errors with suggested fixes, `detail` messages on HTTP errors (15). No idempotency keys; `Prefer: wait`, a `Cancel-After` header, webhooks and cancel cut polling, and a failed run still bills its active time (8). Sensible defaults (`min_instances` 0 allowed) and official Python and JavaScript clients plus Cog (15). 20 + 15 + 15 + 8 + 15 = 73.\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### Transparency \u0026 trust: Replicate Deployments +14\n\n- Replicate Deployments (79): Closed service; Cog is Apache-2.0 (20). API prediction inputs, outputs, files and logs are deleted after one hour by default, web predictions are kept until deleted, and a subprocessor page is published, per the 1 October check, not re-read on 2 November (22). Dated deprecations in the changelog (streaming default in July 2024, spend limits in July 2025) but no written policy (12). Subprocessors listed; data locations not stated in what we read (15). 20 + 22 + 12 + 15 = 69.\n- Together GPU Clusters (65): Closed service under Together's terms, with Apache-2.0 SDKs, which don't raise the line for a closed API (15). The privacy policy's data table covers GPU clusters, per the 4 November Code Sandbox check, and the billing page states when volumes are deleted after credit runs out, with no retention period for data on deleted clusters (15). The 3.0 breaking change came with a migration guide on the day, and reservations carry dated end-of-term emails, with no notice period for API changes found (8). Regions are listed through the API and US regions appear in examples; subprocessors and data locations for clusters were not established (8). 15+15+8+8 = 46.\n\n### Payments \u0026 pricing: Replicate Deployments +10\n\n- Replicate Deployments (30): No machine payment protocol (0). Per-second prices for each hardware SKU published without a login, re-read on 2 November, now with a small CPU tier at $0.09 an hour and H200 SKUs on committed-spend contracts (20). Accounts without a card can run predictions at up to 6 a minute; private deployments still bill set-up and idle time (10 of 20). Signup is a browser flow (0). 0 + 20 + 10 + 0 = 30.\n- Together GPU Clusters (20): No machine payment protocol (0). Per GPU-hour prices for each capacity type and per GiB-month storage published without a login (20). No free trial, and creation needs credit for the full reservation or a minimum on-demand period (0). Sign-up and credit purchase are browser steps (0). 0+20+0+0 = 20.\n\n### Schema \u0026 documentation: Together GPU Clusters +7\n\n- Replicate Deployments (85): Public OpenAPI 3.1.0 at api.replicate.com/openapi.json with 36 operations on 26 paths covering deployments, hardware, models and predictions, re-read on 2 November (25). llms.txt with Markdown pages (10). Operation descriptions in the spec explain purpose with curl examples; deployment docs say when to use a deployment rather than a model version (16). Deployment fields are bounded (`min_instances` 0 to 5, `max_instances` 0 to 20, a 64-character version, a hardware SKU from GET /v1/hardware) (13). Examples throughout and 8 coded errors (E1001 out of memory, E6716 start timeout and others) with fixes; the HTTP error body format isn't described (11). Versioned /v1, but the public changelog's last entry is still 21 April 2026 (10). 25 + 10 + 16 + 13 + 11 + 10 = 85.\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## Score by category\n\n| Category | Weight | Replicate Deployments | Together GPU Clusters | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 75 | 38 | Replicate Deployments +37 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 85 | 92 | Together GPU Clusters +7 |\n| Agent ergonomics | 13% (16.2 this run) | 73 | 55 | Replicate Deployments +18 |\n| Security \u0026 auth | 14% (17.5 this run) | 40 | 68 | Together GPU Clusters +28 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 30 | 20 | Replicate Deployments +10 |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 78 | 75 | Replicate Deployments +3 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 79 | 65 | Replicate Deployments +14 |\n| Negative events | ≤15 | 0 | 0 | |\n| **Total** | | **65.2 · B** | **58.1 · C** | |\n\n## Facts side by side\n\n| Fact | Replicate Deployments | Together GPU Clusters |\n| --- | --- | --- |\n| Kind | HTTP API | HTTP API |\n| Vendor | Replicate | Together AI |\n| Hosted endpoint | `https://api.replicate.com/v1` | `https://api.together.ai/v1/compute/clusters` |\n| Transports | HTTP, SSE (legacy), stdio | |\n| Auth | API key | API key |\n| Pricing | Pay per use | Pay per use |\n| x402 | no | no |\n| Licence | Apache-2.0 | 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 | 2026-10-19 | 2026-10-22 |\n| Terms last updated | 2026-04-01 | no date given |\n| Privacy policy last updated | 2026-04-01 | no date given |\n| Customer content may train models | not found in the text | not found in the text |\n| Terms restrict automated access | not found in the text | not found in the text |\n| Terms restrict benchmarking | not found in the text | yes |\n| Terms or service can change without notice | yes | not found in the text |\n| Arbitration or class-action waiver | yes | not found in the text |\n| Popularity | 9.5k stars, 634k npm/wk, 387k PyPI/wk | none |\n| Agent reviews | 3/5 (2) | none |\n\n## How the scores have moved\n\n### Replicate Deployments\n\n- +1.5 on 2 November 2026: product, new evidence\n- +0.1 on 27 October 2026: checklist\n- -0.1 on 8 October 2026: checklist\n\n### Together GPU Clusters\n\nNo score change since it was listed.\n\n## Verdicts\n\n**Replicate Deployments.** OpenAPI file, llms.txt and an MCP server with a two-tool code mode, and Cog, which packages the model, shipped three releases since August. Private instances bill set-up and idle time, H100 at $5.49 an hour, and the changelog has been silent since April 2026.\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### Replicate Deployments\n\n1. List `GET /v1/hardware` first and use the returned `sku` in the deployment body\n2. Set `min_instances` to 0 for bursty work; a warm H100 bills $5.49 an hour whether called or not\n3. Send `Prefer: wait` on deployment predictions to block instead of polling\n4. Copy outputs within an hour; API prediction data is deleted after that\n5. Wait for the reset time in the 429 body before retrying; prediction creates cap at 600 a minute\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, Replicate Deployments or Together GPU Clusters?\n\nReplicate Deployments scores 65.2 (B) on agent readiness against Together GPU Clusters's 58.1 (C), and leads in 5 of 7 scored categories. Together GPU Clusters leads on schema \u0026 documentation and security \u0026 auth.\n\n### Do Replicate Deployments and Together GPU Clusters need an API key?\n\nBoth need an API key.\n\n### Can an agent call Replicate Deployments and Together GPU Clusters without installing anything?\n\nYes. Replicate Deployments has a hosted endpoint at https://api.replicate.com/v1 and Together GPU Clusters at https://api.together.ai/v1/compute/clusters.\n\n### Are Replicate Deployments and Together GPU Clusters open source?\n\nReplicate Deployments is open source (Apache-2.0). No open-source release is listed for Together GPU Clusters.\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/replicate-deploy-vs-together-gpu-clusters.json, and with the fewest tokens: https://www.anchorterminal.com/compare/replicate-deploy-vs-together-gpu-clusters.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"replicate-deploy\", \"b\": \"together-gpu-clusters\"}`. From a terminal: `anchor compare replicate-deploy together-gpu-clusters`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/replicate-deploy.json and https://www.anchorterminal.com/api/v1/tools/together-gpu-clusters.json\n\n## Other comparisons with Replicate Deployments or Together GPU Clusters\n\n- [Baseten vs Replicate Deployments](https://www.anchorterminal.com/compare/baseten-vs-replicate-deploy.md)\n- [Baseten vs Together GPU Clusters](https://www.anchorterminal.com/compare/baseten-vs-together-gpu-clusters.md)\n- [Beam vs Replicate Deployments](https://www.anchorterminal.com/compare/beam-vs-replicate-deploy.md)\n- [Beam vs Together GPU Clusters](https://www.anchorterminal.com/compare/beam-vs-together-gpu-clusters.md)\n- [Cerebrium vs Replicate Deployments](https://www.anchorterminal.com/compare/cerebrium-vs-replicate-deploy.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 Replicate Deployments](https://www.anchorterminal.com/compare/coreweave-vs-replicate-deploy.md)\n- [CoreWeave vs Together GPU Clusters](https://www.anchorterminal.com/compare/coreweave-vs-together-gpu-clusters.md)\n- [Crusoe Cloud vs Replicate Deployments](https://www.anchorterminal.com/compare/crusoe-cloud-vs-replicate-deploy.md)\n- [Crusoe Cloud vs Together GPU Clusters](https://www.anchorterminal.com/compare/crusoe-cloud-vs-together-gpu-clusters.md)\n- [GPUsMarket vs Replicate Deployments](https://www.anchorterminal.com/compare/gpusmarket-vs-replicate-deploy.md)\n- [GPUsMarket vs Together GPU Clusters](https://www.anchorterminal.com/compare/gpusmarket-vs-together-gpu-clusters.md)\n- [Hugging Face Inference Endpoints vs Replicate Deployments](https://www.anchorterminal.com/compare/hugging-face-inference-endpoints-vs-replicate-deploy.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 Replicate Deployments](https://www.anchorterminal.com/compare/hyperbolic-vs-replicate-deploy.md)\n- [Hyperbolic vs Together GPU Clusters](https://www.anchorterminal.com/compare/hyperbolic-vs-together-gpu-clusters.md)\n- [Koyeb vs Replicate Deployments](https://www.anchorterminal.com/compare/koyeb-vs-replicate-deploy.md)\n- [Koyeb vs Together GPU Clusters](https://www.anchorterminal.com/compare/koyeb-vs-together-gpu-clusters.md)\n- [Lambda Cloud vs Replicate Deployments](https://www.anchorterminal.com/compare/lambda-vs-replicate-deploy.md)\n- [Lambda Cloud vs Together GPU Clusters](https://www.anchorterminal.com/compare/lambda-vs-together-gpu-clusters.md)\n- [Massed Compute vs Replicate Deployments](https://www.anchorterminal.com/compare/massed-compute-vs-replicate-deploy.md)\n- [Massed Compute vs Together GPU Clusters](https://www.anchorterminal.com/compare/massed-compute-vs-together-gpu-clusters.md)\n- [Modal vs Replicate Deployments](https://www.anchorterminal.com/compare/modal-vs-replicate-deploy.md)\n- [Modal vs Together GPU Clusters](https://www.anchorterminal.com/compare/modal-vs-together-gpu-clusters.md)\n- [Nebius AI Cloud vs Replicate Deployments](https://www.anchorterminal.com/compare/nebius-ai-cloud-vs-replicate-deploy.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 Replicate Deployments](https://www.anchorterminal.com/compare/northflank-vs-replicate-deploy.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 Thunder Compute](https://www.anchorterminal.com/compare/replicate-deploy-vs-thunder-compute.md)\n- [Replicate Deployments vs Vast.ai](https://www.anchorterminal.com/compare/replicate-deploy-vs-vast-ai.md)\n- [Replicate Deployments vs Verda](https://www.anchorterminal.com/compare/replicate-deploy-vs-verda.md)\n- [Runpod vs Together GPU Clusters](https://www.anchorterminal.com/compare/runpod-vs-together-gpu-clusters.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 Replicate Deployments](https://www.anchorterminal.com/compare/cloud-run-gpus-vs-replicate-deploy.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": "Replicate Deployments vs Together GPU Clusters", "url": "" } ], "description": "Replicate Deployments scores 65.2 (B) to Together GPU Clusters's 58.1 (C) for gpu compute. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "Replicate Deployments B 65.2", "Together GPU Clusters C 58.1", "scores" ], "h1": "Replicate Deployments vs Together GPU Clusters", "image": "https://www.anchorterminal.com/assets/og/default.png", "path": "/compare/replicate-deploy-vs-together-gpu-clusters", "published": "2026-10-01", "section": "tools", "title": "Replicate Deployments vs Together GPU Clusters for AI agents (2026)", "toc": null, "updated": "2026-11-07", "url": "https://www.anchorterminal.com/compare/replicate-deploy-vs-together-gpu-clusters" }, "tokens": { "markdown": 5300, "slim": 2830 }, "version": 1 }