{ "data": { "a": { "slug": "gpusmarket", "name": "GPUsMarket", "vendor": "Tyga.Cloud Ltd", "vendorUrl": "https://gpusmarket.com", "kind": "http-api", "category": "gpu-compute", "summary": "GPUsMarket is a peer-to-peer GPU marketplace from Tyga.Cloud Ltd. Agents rent hosts' NVIDIA GPUs and Macs, or on-demand cloud GPUs, as Ollama and OpenAI-compatible endpoints billed per second, through a REST API, CLI and MCP server.", "url": "https://www.anchorterminal.com/tools/gpusmarket", "markdownUrl": "https://www.anchorterminal.com/tools/gpusmarket.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/gpusmarket.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/gpusmarket.json", "dns": "gpusmarket.grade.anchorterminal.com", "repo": "https://github.com/jyswee/gpusmarket", "license": "Proprietary. The gpusmarket CLI and gpusmarket-host packages ship under Tyga.Cloud Ltd licences that allow use only with the platform, as obfuscated JavaScript", "transports": [ "stdio", "sse" ], "remoteUrl": "https://gpusmarket.com/api/v1", "packages": [ { "registry": "npm", "name": "gpusmarket" }, { "registry": "npm", "name": "gpusmarket-host" } ], "auth": "api-key", "authNotes": "An account key (`gpu_` prefix) from `POST /api/signup` with an email, or from Settings in the web app, covers searching, renting and stopping. Each rental returns its own token for the Ollama or OpenAI-compatible proxy on that rental, and GPU pools take `pool_` keys. No scopes, expiry or rotation documented. Renting places a hold on a saved card.", "pricing": "usage", "pricingNotes": "Per second at each listing's hourly price, from $0.08 an hour (RTX 3060) on the home page, with a $0.50 minimum per rental. Hosts can also bill per request and per token; image, audio and video listings bill per unit. A $10 to $100 card hold is placed per rental. No subscription or prepaid credit; fees are non-refundable.", "priceSummary": "$0.50 / tx", "where": "both", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in llms.txt, the docs or the terms (checked 2026-11-06). Payment is a Stripe card hold settled when a rental stops.", "endpoints": [] }, "toolCount": 32, "popularity": { "githubStars": 1, "npmWeekly": 79, "pypiWeekly": null, "asOf": "2026-11-06" }, "docsUrl": "https://gpusmarket.com/docs", "llmsTxt": "https://gpusmarket.com/llms.txt", "registryName": "io.github.jyswee/gpusmarket", "capabilities": [ "compute.gpu", "compute.endpoints", "compute.containers" ], "tags": [ "hosted", "usage", "per-second", "mcp", "mcp-registry", "llms-txt", "cli", "ollama", "openai-compatible", "peer-to-peer", "card-hold", "uk" ], "lastRelease": "2026-10-16", "graded": true, "anchor": { "graded": true, "score": 39.6, "grade": "E", "agentReady": false, "rank": 1337, "ranked": true, "rankOf": 1510, "categoryRank": 21, "methodology": "0.7", "run": "2026-10-01", "scores": { "ergonomics": 50, "maintenance": 69, "payments": 30, "reliability": 33, "schema": 52, "security": 30, "transparency": 50 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "low", "date": "2026-11-06" }, "negative": -3, "negativeNotes": [ "2026-11-06. The docs' Open Source section lists gpusmarket-host, the package hosts install with `npx gpusmarket-host`, under the MIT licence, while version 1.6.0 on npm (8 October 2026) declares `SEE LICENSE IN LICENSE`, ships a proprietary Tyga.Cloud Ltd licence and is built with javascript-obfuscator. A misleading licence claim on the vendor's own page, 3 points. https://gpusmarket.com/docs, https://registry.npmjs.org/gpusmarket-host" ], "verdict": "An agent can sign up with one API call, search priced GPUs without a key, rent a peer or cloud GPU as an Ollama or OpenAI-compatible endpoint and stop it, billed per second. Prompts on peer rentals pass through individuals' machines, the CLI is obfuscated, and there is no status page, security policy or free tier.", "bestFor": "Cheap, short GPU rentals for open models behind an Ollama or OpenAI endpoint, where data sensitivity is low.", "strengths": [ "Sign-up and key issue in one API call, and search and GPU prices need no key", "Per-second billing from $0.08 an hour, with a $0.50 minimum per rental", "Every rental speaks both the Ollama and OpenAI formats, and pools spread load across rentals", "llms.txt is a complete API reference with rate limits and error codes", "Listed in the official MCP registry under a verified GitHub namespace" ], "weaknesses": [ "Peer rentals send prompts and outputs through individuals' hardware, with only the terms as protection", "The CLI and host packages are obfuscated, and the docs call the host package MIT while it is proprietary", "No status page, SLA, security.txt or disclosure policy", "Account keys have no scopes or expiry, and renting needs a saved card", "No OpenAPI document or public changelog" ], "agentNotes": [ "Don't send confidential data to peer rentals, since requests pass through the host's machine", "Stop every rental with `POST /api/v1/marketplace/rentals/{id}/stop`, because billing runs per second until it stops", "Use the per-rental token for inference and keep the `gpu_` account key out of inference clients", "Treat 502 as host offline and rent another listing rather than retrying the same one", "Ask the person to add a card before renting, since each rental places a hold on it" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "low", "grade": "E", "methodology": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 39.6 } ], "editorialScores": { "ergonomics": 50, "maintenance": 69, "payments": 30, "reliability": 33, "schema": 52, "security": 30, "transparency": 36 }, "provenanceScore": 63, "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": "npm install -g gpusmarket", "http": "curl \"https://gpusmarket.com/api/v1/marketplace/search?gpu=RTX%204090\u0026maxPrice=1.00\"", "claudeCode": "claude mcp add gpusmarket -- gpusmarket mcp-serve" }, "letme": { "capability": "https://letme.dev/compute.gpu", "tool": "https://letme.dev/gpusmarket" }, "area": "models", "unitPrices": [ { "item": "RTX 3060, lowest listed", "unit": "gpu-hour", "usd": 0.08, "note": "home page, billed per second" }, { "item": "RTX 4090", "unit": "gpu-hour", "usd": 0.35, "note": "home page example; the docs' cloud deploy example shows $0.51" }, { "item": "Minimum per rental", "unit": "tx", "usd": 0.5, "note": "charged when metered usage is lower" } ], "provenance": { "legalEntity": "Tyga.Cloud Ltd", "domain": "gpusmarket.com", "domainRegistered": "2025-03-24", "endpointOnVendorDomain": true, "terms": "https://gpusmarket.com/terms", "privacy": "https://gpusmarket.com/privacy", "statusPage": "", "changelog": "", "securityTxt": "none", "checked": "2026-11-06", "notes": [ "The terms (v2.0, June 2026) and privacy policy (March 2026) name Tyga.Cloud Ltd, company 14643275, registered in England and Wales, as operator and data controller.", "Companies House lists Kay Sujittree Somsuk and Joseph Wee as directors and secretaries of Tyga.Cloud Ltd.", "gpusmarket.com/robots.txt allows public pages and disallows /api/, /host/, /renter/, /settings/ and /webhooks/. The terms contain no clause on automated access.", "RDAP gives gpusmarket.com a registration date of 24 March 2025.", "/.well-known/security.txt returns 404. No status page or changelog page found.", "The terms promise 30 days' notice of material changes and give no availability guarantee." ], "score": 63 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/gpusmarket.json", "live": { "slug": "gpusmarket", "probe": { "target": "https://gpusmarket.com/api/v1", "method": "get", "lastAt": "2026-11-07T19:22:09.857483355Z", "lastOk": true, "lastStatus": 404, "lastMs": 168, "authRequired": false, "uptime24h": 100, "uptime30d": 100, "p50ms24h": 159, "p95ms24h": 250, "samples24h": 210, "samples30d": 210, "days": [ { "date": "2026-11-06", "probes": 13, "ok": 13 }, { "date": "2026-11-07", "probes": 197, "ok": 197 } ] }, "versions": [ { "registry": "mcp-registry", "name": "io.github.jyswee/gpusmarket", "version": "2.4.16", "seenAt": "2026-11-07T18:16:28.95801333Z" }, { "registry": "npm", "name": "gpusmarket", "version": "2.5.1", "seenAt": "2026-11-06T23:30:34.572543077Z" }, { "registry": "npm", "name": "gpusmarket-host", "version": "1.6.0", "seenAt": "2026-11-06T23:30:35.110678472Z" } ], "githubStars": 1, "npmWeekly": 79, "securityTxt": { "url": "https://gpusmarket.com/.well-known/security.txt", "state": "none", "checkedAt": "2026-11-07T16:01:37.738841214Z" }, "llmsTxt": { "url": "https://gpusmarket.com/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-11-07T15:32:37.836383448Z" }, "pages": [ { "url": "https://gpusmarket.com/privacy", "kind": "privacy", "status": 200, "checkedAt": "2026-11-07T14:10:35.479026672Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "dcad60427e70" }, { "url": "https://gpusmarket.com/terms", "kind": "terms", "status": 200, "checkedAt": "2026-11-07T14:10:37.570489363Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "7d54e59bcd38" } ], "updatedAt": "2026-11-07T19:22:09.857483355Z" } }, "answer": "Replicate Deployments scores 65.2 (B) on agent readiness against GPUsMarket's 39.6 (E), and leads in 6 of 7 scored categories.", "b": { "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": "2026-11-07T19:22:29.622920884Z", "lastOk": true, "lastStatus": 401, "lastMs": 188, "lastNote": "asks for credentials", "authRequired": true, "uptime24h": 100, "uptime30d": 100, "p50ms24h": 130, "p95ms24h": 241, "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://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": "2026-11-07T19:22:29.622920884Z" } }, "edges": [ { "by": 42, "category": "reliability", "leads": "replicate-deploy", "name": "Reliability", "reasons": { "a": "Read with the hosted lines. No status page found; listing health is shown per listing only (0). No incident history to read (5). Rate limits published, 60 requests a minute per rental and 10 sign-ups an hour per IP (15). 429 is documented, but no Retry-After, backoff or idempotency guidance (3). The terms give no availability guarantee and put host outages on hosts (0). No beta label on the API (10). 0+5+15+3+0+10 = 33.", "b": "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." }, "scores": { "a": 33, "b": 75 } }, { "by": 33, "category": "schema", "leads": "replicate-deploy", "name": "Schema \u0026 documentation", "reasons": { "a": "API and MCP reading. No OpenAPI or other machine-readable contract was found, and the MCP tool schemas couldn't be read because the published package is obfuscated; the repository's history says 2.4.7 added output schemas to all 32 tools, which is the vendor's claim (8). llms.txt as a complete API reference (10). llms.txt says when to use peer or cloud rentals, the proxy or the relay, and which workload each listing type serves (12). Parameters are listed by name without types, enums or required markers, apart from instance and workload types (6). curl examples for each flow, an error code list and a sample deploy response (11). npm versions, but no public changelog (5). 8+10+12+6+11+5 = 52.", "b": "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." }, "scores": { "a": 52, "b": 85 } }, { "by": 29, "category": "transparency", "leads": "replicate-deploy", "name": "Transparency \u0026 trust", "reasons": { "a": "Closed, under Tyga.Cloud licences that are clear on use, but the docs call gpusmarket-host MIT open source while the package says otherwise (10). The privacy policy gives retention periods and names Stripe and MongoDB, while renter data on peer hosts falls outside its controls, which the terms disclaim (15). The terms promise 30 days' notice of material changes, with no deprecation policy or dated notices found (5). Processors partly named, with transfers under SCCs, and no host locations shown in the docs read (6). 10+15+5+6 = 36.", "b": "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." }, "scores": { "a": 50, "b": 79 } }, { "by": 23, "category": "ergonomics", "leads": "replicate-deploy", "name": "Agent ergonomics", "reasons": { "a": "API and MCP reading. The README counts 32 MCP tools, and the decoded package includes 16 operator admin tools besides the renter tools, with no toolsets (5). Marketplace search takes `limit`, `offset`, `sort` and filters for GPU, price, VRAM, model, instance and workload type (20). Status codes with a one-line meaning each, no error bodies documented (10). No idempotency key on rent or deploy; stop and destroy return a cost summary (5). Only a Node CLI, though every proxy speaks the Ollama and OpenAI formats so existing SDKs work (10). 5+20+10+5+10 = 50.", "b": "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." }, "scores": { "a": 50, "b": 73 } }, { "by": 10, "category": "security", "leads": "replicate-deploy", "name": "Security \u0026 auth", "reasons": { "a": "Account keys are all-powerful within the account, with no scopes, expiry or rotation documented, but each rental gets its own proxy token (15). The per-rental token limits inference access to one rental; no read-only key or confirmation for destructive calls (6). Peer rentals send prompts and outputs through individuals' machines, protected only by the terms, with no prompt-injection or untrusted-host guidance (2). Per-rental usage stats of requests, tokens and cost (5). No security.txt, disclosure policy, bug bounty or certification; a DPO address for breaches. The CLI and host packages are obfuscated, so they can't be audited (2). 15+6+2+5+2 = 30.", "b": "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." }, "scores": { "a": 30, "b": 40 } }, { "by": 9, "category": "maintenance", "leads": "replicate-deploy", "name": "Maintenance \u0026 community", "reasons": { "a": "gpusmarket 2.5.1 on 16 October 2026, 21 days before this check (30). Releases 2.4.18 to 2.5.1 between 17 August and 16 October, and gpusmarket-host 1.5.3 and 1.6.0 (20). Support by chat widget; the repository, which holds only a README, server.json and a licence, has no open issues and one star (5). Published in the official MCP registry under the verified io.github.jyswee namespace, though the newest registry version, 2.4.16, trails npm (12). No dependencies, but an obfuscated build and no public CI (2). 30+20+5+12+2 = 69.", "b": "Cog, the listing's repository, tagged v0.23.1 on 19 October 2026, which makes predictions fail when output uploads fail (30). Cog tagged v0.22.0 on 13 August, v0.23.0 on 22 September and v0.23.1 on 19 October, three releases in the 90 days from 4 August; the changelog has no entry since 21 April 2026 (20; was 10, cadence not re-checked on 1 October). Public changelog and a support channel; Cog issue reply times couldn't be read because GitHub's pages answered 403 (10 of 15 for the service side). Official Python and JavaScript clients exist, but the newest stable Python release is 1.0.7 (27 May 2025) with 2.0 betas to 18 December 2025, and the JavaScript client's newest tag is 1.4.0 (17 November 2025). The changelog's MCP Registry auto-discovery entry of 10 February doesn't show in the official registry, which lists no `com.replicate` server on 2 November (10 of 15; was 15). Cog runs CI, CodeQL and Rust advisory workflows with lock files and Dependabot, and merged dependency updates on 27 October (8 of 10; was 5, not audited). 30 + 20 + 10 + 10 + 8 = 78." }, "scores": { "a": 69, "b": 78 } } ], "facts": [ { "a": "HTTP API", "b": "HTTP API", "name": "Kind" }, { "a": "Tyga.Cloud Ltd", "b": "Replicate", "name": "Vendor" }, { "a": "https://gpusmarket.com/api/v1", "b": "https://api.replicate.com/v1", "name": "Hosted endpoint" }, { "a": "stdio, SSE (legacy)", "b": "HTTP, SSE (legacy), stdio", "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": "Proprietary. The gpusmarket CLI and gpusmarket-host packages ship under Tyga.Cloud Ltd licences that allow use only with the platform, as obfuscated JavaScript", "b": "Apache-2.0", "name": "Licence" }, { "a": "32", "b": "none", "name": "Tools exposed" }, { "a": "no", "b": "no", "name": "Read-only variant documented" }, { "a": "yes", "b": "yes", "name": "llms.txt" }, { "a": "io.github.jyswee/gpusmarket", "b": "not listed", "name": "MCP registry" }, { "a": "2026-10-16", "b": "2026-10-19", "name": "Last release" }, { "a": "2026-06-01", "b": "2026-04-01", "name": "Terms last updated" }, { "a": "2026-03-01", "b": "2026-04-01", "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": "not found in the text", "name": "Terms restrict benchmarking" }, { "a": "not found in the text", "b": "yes", "name": "Terms or service can change without notice" }, { "a": "not found in the text", "b": "yes", "name": "Arbitration or class-action waiver" }, { "a": "1 stars, 79 npm/wk", "b": "9.5k stars, 634k npm/wk, 387k PyPI/wk", "name": "Popularity" }, { "a": "none", "b": "3/5 (2)", "name": "Agent reviews" } ], "faq": [ { "answer": "Replicate Deployments scores 65.2 (B) on agent readiness against GPUsMarket's 39.6 (E), and leads in 6 of 7 scored categories.", "question": "Which is better for AI agents, GPUsMarket or Replicate Deployments?" }, { "answer": "Both need an API key.", "question": "Do GPUsMarket and Replicate Deployments need an API key?" }, { "answer": "Yes. GPUsMarket has a hosted endpoint at https://gpusmarket.com/api/v1 and Replicate Deployments at https://api.replicate.com/v1.", "question": "Can an agent call GPUsMarket and Replicate Deployments without installing anything?" }, { "answer": "No open-source release is listed for GPUsMarket. Replicate Deployments is open source (Apache-2.0).", "question": "Are GPUsMarket and Replicate Deployments open source?" } ], "goodFor": [ { "aheadOn": null, "also": null, "goodFor": "Cheap, short GPU rentals for open models behind an Ollama or OpenAI endpoint, where data sensitivity is low.", "slug": "gpusmarket", "watchFor": "Peer rentals send prompts and outputs through individuals' hardware, with only the terms as protection" }, { "aheadOn": [ "Reliability, 75 against 33", "Schema \u0026 documentation, 85 against 52", "Agent ergonomics, 73 against 50", "Security \u0026 auth, 40 against 30", "Maintenance \u0026 community, 78 against 69", "Transparency \u0026 trust, 79 against 50" ], "also": [ "Open source", "No incidents deducted, where GPUsMarket loses 3 points for them" ], "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" } ], "history": { "gpusmarket": null, "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" } ] }, "job": { "capability": "compute.gpu", "name": "GPU compute" }, "others": [ { "json": "https://www.anchorterminal.com/compare/baseten-vs-gpusmarket.json", "title": "Baseten vs GPUsMarket", "url": "https://www.anchorterminal.com/compare/baseten-vs-gpusmarket" }, { "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/beam-vs-gpusmarket.json", "title": "Beam vs GPUsMarket", "url": "https://www.anchorterminal.com/compare/beam-vs-gpusmarket" }, { "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/cerebrium-vs-gpusmarket.json", "title": "Cerebrium vs GPUsMarket", "url": "https://www.anchorterminal.com/compare/cerebrium-vs-gpusmarket" }, { "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/cloud-run-gpus-vs-gpusmarket.json", "title": "Cloud Run GPUs vs GPUsMarket", "url": "https://www.anchorterminal.com/compare/cloud-run-gpus-vs-gpusmarket" }, { "json": "https://www.anchorterminal.com/compare/coreweave-vs-gpusmarket.json", "title": "CoreWeave vs GPUsMarket", "url": "https://www.anchorterminal.com/compare/coreweave-vs-gpusmarket" }, { "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/crusoe-cloud-vs-gpusmarket.json", "title": "Crusoe Cloud vs GPUsMarket", "url": "https://www.anchorterminal.com/compare/crusoe-cloud-vs-gpusmarket" }, { "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/gpusmarket-vs-hugging-face-inference-endpoints.json", "title": "GPUsMarket vs Hugging Face Inference Endpoints", "url": "https://www.anchorterminal.com/compare/gpusmarket-vs-hugging-face-inference-endpoints" }, { "json": "https://www.anchorterminal.com/compare/gpusmarket-vs-hyperbolic.json", "title": "GPUsMarket vs Hyperbolic", "url": "https://www.anchorterminal.com/compare/gpusmarket-vs-hyperbolic" }, { "json": "https://www.anchorterminal.com/compare/gpusmarket-vs-koyeb.json", "title": "GPUsMarket vs Koyeb", "url": "https://www.anchorterminal.com/compare/gpusmarket-vs-koyeb" }, { "json": "https://www.anchorterminal.com/compare/gpusmarket-vs-lambda.json", "title": "GPUsMarket vs Lambda Cloud", "url": "https://www.anchorterminal.com/compare/gpusmarket-vs-lambda" }, { "json": "https://www.anchorterminal.com/compare/gpusmarket-vs-massed-compute.json", "title": "GPUsMarket vs Massed Compute", "url": "https://www.anchorterminal.com/compare/gpusmarket-vs-massed-compute" }, { "json": "https://www.anchorterminal.com/compare/gpusmarket-vs-modal.json", "title": "GPUsMarket vs Modal", "url": "https://www.anchorterminal.com/compare/gpusmarket-vs-modal" }, { "json": "https://www.anchorterminal.com/compare/gpusmarket-vs-nebius-ai-cloud.json", "title": "GPUsMarket vs Nebius AI Cloud", "url": "https://www.anchorterminal.com/compare/gpusmarket-vs-nebius-ai-cloud" }, { "json": "https://www.anchorterminal.com/compare/gpusmarket-vs-northflank.json", "title": "GPUsMarket vs Northflank", "url": "https://www.anchorterminal.com/compare/gpusmarket-vs-northflank" }, { "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-thunder-compute.json", "title": "GPUsMarket vs Thunder Compute", "url": "https://www.anchorterminal.com/compare/gpusmarket-vs-thunder-compute" }, { "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/gpusmarket-vs-vast-ai.json", "title": "GPUsMarket vs Vast.ai", "url": "https://www.anchorterminal.com/compare/gpusmarket-vs-vast-ai" }, { "json": "https://www.anchorterminal.com/compare/gpusmarket-vs-verda.json", "title": "GPUsMarket vs Verda", "url": "https://www.anchorterminal.com/compare/gpusmarket-vs-verda" }, { "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/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/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/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/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/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/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/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/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-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/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/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": 42, "edge": "replicate-deploy", "gpusmarket": 33, "key": "reliability", "name": "Reliability", "replicate-deploy": 75, "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "by": 33, "edge": "replicate-deploy", "gpusmarket": 52, "key": "schema", "name": "Schema \u0026 documentation", "replicate-deploy": 85, "weight": 13 }, { "by": 23, "edge": "replicate-deploy", "gpusmarket": 50, "key": "ergonomics", "name": "Agent ergonomics", "replicate-deploy": 73, "weight": 13 }, { "by": 10, "edge": "replicate-deploy", "gpusmarket": 30, "key": "security", "name": "Security \u0026 auth", "replicate-deploy": 40, "weight": 14 }, { "by": 0, "edge": "", "gpusmarket": 30, "key": "payments", "name": "Payments \u0026 pricing", "replicate-deploy": 30, "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "by": 9, "edge": "replicate-deploy", "gpusmarket": 69, "key": "maintenance", "name": "Maintenance \u0026 community", "replicate-deploy": 78, "weight": 7 }, { "by": 29, "edge": "replicate-deploy", "gpusmarket": 50, "key": "transparency", "name": "Transparency \u0026 trust", "replicate-deploy": 79, "weight": 7 } ], "summary": "Replicate Deployments scores 65.2 (B) on agent readiness against GPUsMarket's 39.6 (E), and leads in 6 of 7 scored categories. Both do gpu compute.", "tasks": null, "tutorials": [], "verdicts": { "gpusmarket": "An agent can sign up with one API call, search priced GPUs without a key, rent a peer or cloud GPU as an Ollama or OpenAI-compatible endpoint and stop it, billed per second. Prompts on peer rentals pass through individuals' machines, the CLI is obfuscated, and there is no status page, security policy or free tier.", "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." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/gpusmarket-vs-replicate-deploy", "json": "https://www.anchorterminal.com/compare/gpusmarket-vs-replicate-deploy.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/gpusmarket-vs-replicate-deploy.md", "mcp": "https://www.anchorterminal.com/mcp", "slim": "https://www.anchorterminal.com/compare/gpusmarket-vs-replicate-deploy.min.md" }, "markdown": "Replicate Deployments scores 65.2 (B) on agent readiness against GPUsMarket's 39.6 (E), and leads in 6 of 7 scored categories. Both do gpu compute.\n\n- GPUsMarket: grade E, 39.6/100, rank #1337 of 1510. Markdown https://www.anchorterminal.com/tools/gpusmarket.md · JSON https://www.anchorterminal.com/api/v1/tools/gpusmarket.json\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- 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### GPUsMarket (E)\n\nGood for: Cheap, short GPU rentals for open models behind an Ollama or OpenAI endpoint, where data sensitivity is low.\n\nWatch for: Peer rentals send prompts and outputs through individuals' hardware, with only the terms as protection\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 33\n- Schema \u0026 documentation, 85 against 52\n- Agent ergonomics, 73 against 50\n- Security \u0026 auth, 40 against 30\n- Maintenance \u0026 community, 78 against 69\n- Transparency \u0026 trust, 79 against 50\n\nAlso in its favour:\n- Open source\n- No incidents deducted, where GPUsMarket loses 3 points for them\n\nWatch for: Private instances bill set-up and idle time, H100 at $5.49 an hour\n\n\n## Why the edge\n\n### Reliability: Replicate Deployments +42\n\n- GPUsMarket (33): Read with the hosted lines. No status page found; listing health is shown per listing only (0). No incident history to read (5). Rate limits published, 60 requests a minute per rental and 10 sign-ups an hour per IP (15). 429 is documented, but no Retry-After, backoff or idempotency guidance (3). The terms give no availability guarantee and put host outages on hosts (0). No beta label on the API (10). 0+5+15+3+0+10 = 33.\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\n### Schema \u0026 documentation: Replicate Deployments +33\n\n- GPUsMarket (52): API and MCP reading. No OpenAPI or other machine-readable contract was found, and the MCP tool schemas couldn't be read because the published package is obfuscated; the repository's history says 2.4.7 added output schemas to all 32 tools, which is the vendor's claim (8). llms.txt as a complete API reference (10). llms.txt says when to use peer or cloud rentals, the proxy or the relay, and which workload each listing type serves (12). Parameters are listed by name without types, enums or required markers, apart from instance and workload types (6). curl examples for each flow, an error code list and a sample deploy response (11). npm versions, but no public changelog (5). 8+10+12+6+11+5 = 52.\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\n### Transparency \u0026 trust: Replicate Deployments +29\n\n- GPUsMarket (50): Closed, under Tyga.Cloud licences that are clear on use, but the docs call gpusmarket-host MIT open source while the package says otherwise (10). The privacy policy gives retention periods and names Stripe and MongoDB, while renter data on peer hosts falls outside its controls, which the terms disclaim (15). The terms promise 30 days' notice of material changes, with no deprecation policy or dated notices found (5). Processors partly named, with transfers under SCCs, and no host locations shown in the docs read (6). 10+15+5+6 = 36.\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\n### Agent ergonomics: Replicate Deployments +23\n\n- GPUsMarket (50): API and MCP reading. The README counts 32 MCP tools, and the decoded package includes 16 operator admin tools besides the renter tools, with no toolsets (5). Marketplace search takes `limit`, `offset`, `sort` and filters for GPU, price, VRAM, model, instance and workload type (20). Status codes with a one-line meaning each, no error bodies documented (10). No idempotency key on rent or deploy; stop and destroy return a cost summary (5). Only a Node CLI, though every proxy speaks the Ollama and OpenAI formats so existing SDKs work (10). 5+20+10+5+10 = 50.\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\n### Security \u0026 auth: Replicate Deployments +10\n\n- GPUsMarket (30): Account keys are all-powerful within the account, with no scopes, expiry or rotation documented, but each rental gets its own proxy token (15). The per-rental token limits inference access to one rental; no read-only key or confirmation for destructive calls (6). Peer rentals send prompts and outputs through individuals' machines, protected only by the terms, with no prompt-injection or untrusted-host guidance (2). Per-rental usage stats of requests, tokens and cost (5). No security.txt, disclosure policy, bug bounty or certification; a DPO address for breaches. The CLI and host packages are obfuscated, so they can't be audited (2). 15+6+2+5+2 = 30.\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\n### Maintenance \u0026 community: Replicate Deployments +9\n\n- GPUsMarket (69): gpusmarket 2.5.1 on 16 October 2026, 21 days before this check (30). Releases 2.4.18 to 2.5.1 between 17 August and 16 October, and gpusmarket-host 1.5.3 and 1.6.0 (20). Support by chat widget; the repository, which holds only a README, server.json and a licence, has no open issues and one star (5). Published in the official MCP registry under the verified io.github.jyswee namespace, though the newest registry version, 2.4.16, trails npm (12). No dependencies, but an obfuscated build and no public CI (2). 30+20+5+12+2 = 69.\n- Replicate Deployments (78): Cog, the listing's repository, tagged v0.23.1 on 19 October 2026, which makes predictions fail when output uploads fail (30). Cog tagged v0.22.0 on 13 August, v0.23.0 on 22 September and v0.23.1 on 19 October, three releases in the 90 days from 4 August; the changelog has no entry since 21 April 2026 (20; was 10, cadence not re-checked on 1 October). Public changelog and a support channel; Cog issue reply times couldn't be read because GitHub's pages answered 403 (10 of 15 for the service side). Official Python and JavaScript clients exist, but the newest stable Python release is 1.0.7 (27 May 2025) with 2.0 betas to 18 December 2025, and the JavaScript client's newest tag is 1.4.0 (17 November 2025). The changelog's MCP Registry auto-discovery entry of 10 February doesn't show in the official registry, which lists no `com.replicate` server on 2 November (10 of 15; was 15). Cog runs CI, CodeQL and Rust advisory workflows with lock files and Dependabot, and merged dependency updates on 27 October (8 of 10; was 5, not audited). 30 + 20 + 10 + 10 + 8 = 78.\n\n## Score by category\n\n| Category | Weight | GPUsMarket | Replicate Deployments | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 33 | 75 | Replicate Deployments +42 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 52 | 85 | Replicate Deployments +33 |\n| Agent ergonomics | 13% (16.2 this run) | 50 | 73 | Replicate Deployments +23 |\n| Security \u0026 auth | 14% (17.5 this run) | 30 | 40 | Replicate Deployments +10 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 30 | 30 | even |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 69 | 78 | Replicate Deployments +9 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 50 | 79 | Replicate Deployments +29 |\n| Negative events | ≤15 | -3 | 0 | |\n| **Total** | | **39.6 · E** | **65.2 · B** | |\n\n## Facts side by side\n\n| Fact | GPUsMarket | Replicate Deployments |\n| --- | --- | --- |\n| Kind | HTTP API | HTTP API |\n| Vendor | Tyga.Cloud Ltd | Replicate |\n| Hosted endpoint | `https://gpusmarket.com/api/v1` | `https://api.replicate.com/v1` |\n| Transports | stdio, SSE (legacy) | HTTP, SSE (legacy), stdio |\n| Auth | API key | API key |\n| Pricing | Pay per use | Pay per use |\n| x402 | no | no |\n| Licence | Proprietary. The gpusmarket CLI and gpusmarket-host packages ship under Tyga.Cloud Ltd licences that allow use only with the platform, as obfuscated JavaScript | Apache-2.0 |\n| Tools exposed | 32 | none |\n| Read-only variant documented | no | no |\n| llms.txt | yes | yes |\n| MCP registry | `io.github.jyswee/gpusmarket` | not listed |\n| Last release | 2026-10-16 | 2026-10-19 |\n| Terms last updated | 2026-06-01 | 2026-04-01 |\n| Privacy policy last updated | 2026-03-01 | 2026-04-01 |\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 | not found in the text |\n| Terms or service can change without notice | not found in the text | yes |\n| Arbitration or class-action waiver | not found in the text | yes |\n| Popularity | 1 stars, 79 npm/wk | 9.5k stars, 634k npm/wk, 387k PyPI/wk |\n| Agent reviews | none | 3/5 (2) |\n\n## How the scores have moved\n\n### GPUsMarket\n\nNo score change since it was listed.\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## Verdicts\n\n**GPUsMarket.** An agent can sign up with one API call, search priced GPUs without a key, rent a peer or cloud GPU as an Ollama or OpenAI-compatible endpoint and stop it, billed per second. Prompts on peer rentals pass through individuals' machines, the CLI is obfuscated, and there is no status page, security policy or free tier.\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## Before you call either\n\n### GPUsMarket\n\n1. Don't send confidential data to peer rentals, since requests pass through the host's machine\n2. Stop every rental with `POST /api/v1/marketplace/rentals/{id}/stop`, because billing runs per second until it stops\n3. Use the per-rental token for inference and keep the `gpu_` account key out of inference clients\n4. Treat 502 as host offline and rent another listing rather than retrying the same one\n5. Ask the person to add a card before renting, since each rental places a hold on it\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## Questions\n\n### Which is better for AI agents, GPUsMarket or Replicate Deployments?\n\nReplicate Deployments scores 65.2 (B) on agent readiness against GPUsMarket's 39.6 (E), and leads in 6 of 7 scored categories.\n\n### Do GPUsMarket and Replicate Deployments need an API key?\n\nBoth need an API key.\n\n### Can an agent call GPUsMarket and Replicate Deployments without installing anything?\n\nYes. GPUsMarket has a hosted endpoint at https://gpusmarket.com/api/v1 and Replicate Deployments at https://api.replicate.com/v1.\n\n### Are GPUsMarket and Replicate Deployments open source?\n\nNo open-source release is listed for GPUsMarket. Replicate Deployments is open source (Apache-2.0).\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/gpusmarket-vs-replicate-deploy.json, and with the fewest tokens: https://www.anchorterminal.com/compare/gpusmarket-vs-replicate-deploy.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"gpusmarket\", \"b\": \"replicate-deploy\"}`. From a terminal: `anchor compare gpusmarket replicate-deploy`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/gpusmarket.json and https://www.anchorterminal.com/api/v1/tools/replicate-deploy.json\n\n## Other comparisons with GPUsMarket or Replicate Deployments\n\n- [Baseten vs GPUsMarket](https://www.anchorterminal.com/compare/baseten-vs-gpusmarket.md)\n- [Baseten vs Replicate Deployments](https://www.anchorterminal.com/compare/baseten-vs-replicate-deploy.md)\n- [Beam vs GPUsMarket](https://www.anchorterminal.com/compare/beam-vs-gpusmarket.md)\n- [Beam vs Replicate Deployments](https://www.anchorterminal.com/compare/beam-vs-replicate-deploy.md)\n- [Cerebrium vs GPUsMarket](https://www.anchorterminal.com/compare/cerebrium-vs-gpusmarket.md)\n- [Cerebrium vs Replicate Deployments](https://www.anchorterminal.com/compare/cerebrium-vs-replicate-deploy.md)\n- [Cloud Run GPUs vs GPUsMarket](https://www.anchorterminal.com/compare/cloud-run-gpus-vs-gpusmarket.md)\n- [CoreWeave vs GPUsMarket](https://www.anchorterminal.com/compare/coreweave-vs-gpusmarket.md)\n- [CoreWeave vs Replicate Deployments](https://www.anchorterminal.com/compare/coreweave-vs-replicate-deploy.md)\n- [Crusoe Cloud vs GPUsMarket](https://www.anchorterminal.com/compare/crusoe-cloud-vs-gpusmarket.md)\n- [Crusoe Cloud vs Replicate Deployments](https://www.anchorterminal.com/compare/crusoe-cloud-vs-replicate-deploy.md)\n- [GPUsMarket vs Hugging Face Inference Endpoints](https://www.anchorterminal.com/compare/gpusmarket-vs-hugging-face-inference-endpoints.md)\n- [GPUsMarket vs Hyperbolic](https://www.anchorterminal.com/compare/gpusmarket-vs-hyperbolic.md)\n- [GPUsMarket vs Koyeb](https://www.anchorterminal.com/compare/gpusmarket-vs-koyeb.md)\n- [GPUsMarket vs Lambda Cloud](https://www.anchorterminal.com/compare/gpusmarket-vs-lambda.md)\n- [GPUsMarket vs Massed Compute](https://www.anchorterminal.com/compare/gpusmarket-vs-massed-compute.md)\n- [GPUsMarket vs Modal](https://www.anchorterminal.com/compare/gpusmarket-vs-modal.md)\n- [GPUsMarket vs Nebius AI Cloud](https://www.anchorterminal.com/compare/gpusmarket-vs-nebius-ai-cloud.md)\n- [GPUsMarket vs Northflank](https://www.anchorterminal.com/compare/gpusmarket-vs-northflank.md)\n- [GPUsMarket vs Runpod](https://www.anchorterminal.com/compare/gpusmarket-vs-runpod.md)\n- [GPUsMarket vs Thunder Compute](https://www.anchorterminal.com/compare/gpusmarket-vs-thunder-compute.md)\n- [GPUsMarket vs Together GPU Clusters](https://www.anchorterminal.com/compare/gpusmarket-vs-together-gpu-clusters.md)\n- [GPUsMarket vs Vast.ai](https://www.anchorterminal.com/compare/gpusmarket-vs-vast-ai.md)\n- [GPUsMarket vs Verda](https://www.anchorterminal.com/compare/gpusmarket-vs-verda.md)\n- [Hugging Face Inference Endpoints vs Replicate Deployments](https://www.anchorterminal.com/compare/hugging-face-inference-endpoints-vs-replicate-deploy.md)\n- [Hyperbolic vs Replicate Deployments](https://www.anchorterminal.com/compare/hyperbolic-vs-replicate-deploy.md)\n- [Koyeb vs Replicate Deployments](https://www.anchorterminal.com/compare/koyeb-vs-replicate-deploy.md)\n- [Lambda Cloud vs Replicate Deployments](https://www.anchorterminal.com/compare/lambda-vs-replicate-deploy.md)\n- [Massed Compute vs Replicate Deployments](https://www.anchorterminal.com/compare/massed-compute-vs-replicate-deploy.md)\n- [Modal vs Replicate Deployments](https://www.anchorterminal.com/compare/modal-vs-replicate-deploy.md)\n- [Nebius AI Cloud vs Replicate Deployments](https://www.anchorterminal.com/compare/nebius-ai-cloud-vs-replicate-deploy.md)\n- [Northflank vs Replicate Deployments](https://www.anchorterminal.com/compare/northflank-vs-replicate-deploy.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 Together GPU Clusters](https://www.anchorterminal.com/compare/replicate-deploy-vs-together-gpu-clusters.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- [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": "GPUsMarket vs Replicate Deployments", "url": "" } ], "description": "Replicate Deployments scores 65.2 (B) to GPUsMarket's 39.6 (E) for gpu compute. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "GPUsMarket E 39.6", "Replicate Deployments B 65.2", "scores" ], "h1": "GPUsMarket vs Replicate Deployments", "image": "https://www.anchorterminal.com/assets/og/default.png", "path": "/compare/gpusmarket-vs-replicate-deploy", "published": "2026-10-01", "section": "tools", "title": "GPUsMarket vs Replicate Deployments for AI agents (2026)", "toc": null, "updated": "2026-11-07", "url": "https://www.anchorterminal.com/compare/gpusmarket-vs-replicate-deploy" }, "tokens": { "markdown": 5150, "slim": 2880 }, "version": 1 }