{ "data": { "a": { "slug": "baseten", "name": "Baseten", "vendor": "Baseten", "vendorUrl": "https://www.baseten.co", "kind": "http-api", "category": "gpu-compute", "summary": "Dedicated model deployments packaged with the open-source Truss framework and served behind a per-model HTTPS endpoint, with autoscaling from zero replicas, async inference, a management API and per-minute GPU billing from T4 to B200.", "url": "https://www.anchorterminal.com/tools/baseten", "markdownUrl": "https://www.anchorterminal.com/tools/baseten.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/baseten.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/baseten.json", "repo": "https://github.com/basetenlabs/truss", "license": "MIT", "transports": [ "http" ], "remoteUrl": "https://api.baseten.co", "packages": [ { "registry": "pypi", "name": "truss" } ], "auth": "api-key", "authNotes": "API key from the workspace settings, sent as `Authorization: Bearer $BASETEN_API_KEY` (preferred) or the legacy `Authorization: Api-Key` scheme. Keys created from 1 October 2026 carry a `b10_` prefix. Inference goes to model-\u003cid\u003e.api.baseten.co and management calls to api.baseten.co.", "pricing": "usage", "pricingNotes": "Basic is $0 a month, pay as you go; Pro and Enterprise add volume discounts. Dedicated deployments bill per minute of replica time, including start-up and idle, and nothing at zero replicas. T4 16 GiB $0.01052 a minute (about $0.63 an hour), L4 24 GiB $0.01414 ($0.85), A10G 24 GiB $0.02012 ($1.21), H100 MIG 40 GiB $0.0625 ($3.75), A100 80 GiB $0.06667 ($4.00), H100 80 GiB $0.10833 ($6.50), B200 180 GiB $0.16633 ($9.98). New accounts get a small credit to try the UI. Model APIs bill per token instead (https://www.baseten.co/pricing/).", "priceSummary": "Pay per use", "where": "hosted", "x402": { "level": "no", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": 1200, "npmWeekly": null, "pypiWeekly": 74496, "asOf": "2026-09-30" }, "docsUrl": "https://docs.baseten.co", "llmsTxt": "https://docs.baseten.co/llms.txt", "openapi": "https://api.baseten.co/v1/spec", "capabilities": [ "compute.gpu", "compute.endpoints", "compute.serverless", "compute.containers" ], "tags": [ "hosted", "usage-priced", "python", "llms-txt", "open-source", "async-jobs", "webhooks", "enterprise" ], "lastRelease": "2026-09-28", "graded": true, "anchor": { "graded": true, "score": 66.5, "grade": "B", "agentReady": false, "rank": 233, "ranked": true, "rankOf": 722, "categoryRank": 1, "methodology": "0.4", "run": "2026-10-01", "scores": { "ergonomics": 55, "maintenance": 90, "payments": 40, "reliability": 80, "schema": 84, "security": 82, "transparency": 65 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-01" }, "negative": -5, "negativeNotes": [ "-5: a GitHub personal access token for `basetenbot`, exposed in a public Harbor image since March 2023, gave admin and push access to Baseten's main product repository, the GitOps repository that drives its clusters, its Homebrew tap and per-customer private repositories. Reported on 2026-07-13, revoked on 2026-07-14, no misuse found, published with Baseten's approval in September 2026. Deducted less because the fix was quick and documented (https://www.strix.ai/blog/baseten-harbor-github-pat-takeover)" ], "verdict": "Team API keys scoped to inference-only, metrics-only or a single environment or model, plus a Viewer role since 1 September 2026. H100 at $6.50 and A100 at $4.00 an hour, and start-up and idle replica time are billed.", "bestFor": "Teams that want one model behind a production endpoint with real autoscaling knobs, environments and scoped keys.", "strengths": [ "Team API keys scoped to inference-only, metrics-only or a single environment or model, plus a Viewer role since 1 September 2026", "Public OpenAPI spec for the management API at api.baseten.co/v1/spec, and llms.txt with Markdown twins", "Rate limits published per endpoint with a `retry_after` field on 429", "Free starting credits with no payment method needed until they run out", "Truss (MIT) keeps the model package portable, with three releases in September 2026" ], "weaknesses": [ "H100 at $6.50 and A100 at $4.00 an hour, and start-up and idle replica time are billed", "21 status-page incidents between 31 July and 29 September 2026, mostly single-cluster 5xx", "A bot token with admin access to the product and GitOps repositories sat exposed from March 2023 until July 2026", "No pagination on management list endpoints and no idempotency keys", "No SLA below Enterprise, no bug bounty and no security.txt" ], "agentNotes": [ "Create a team key with inference-only permission for calling models and keep full-access keys out of the agent", "Sleep for `retry_after` seconds on a 429 from api.baseten.co; the activate and deactivate endpoints allow 20 calls a minute", "Retry 429, 503 and 529 with backoff, but treat 500 as a bug in your model code", "Set `scale_down_delay` below the 900-second default or every burst bills 15 idle minutes", "Send payloads over 256 KiB to `/predict`, not `/async_predict`, unless support has raised the async limit" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 2, "avgRating": 3.5, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "B", "methodology": "0.4", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 66.5 } ], "editorialScores": { "ergonomics": 55, "maintenance": 90, "payments": 40, "reliability": 80, "schema": 84, "security": 82, "transparency": 58 }, "provenanceScore": 71 }, "connect": { "install": "pip install truss", "http": "curl -X POST \"https://model-$BASETEN_MODEL_ID.api.baseten.co/environments/production/predict\" \\\n -H \"Authorization: Bearer $BASETEN_API_KEY\" -H \"Content-Type: application/json\" \\\n -d '{\"prompt\":\"Hello, world!\"}'" }, "letme": { "capability": "https://letme.dev/compute.gpu", "tool": "https://letme.dev/baseten" }, "area": "models", "unitPrices": [ { "item": "H100 80 GiB", "unit": "gpu-hour", "usd": 6.5, "note": "$0.10833 a minute" }, { "item": "B200 180 GiB", "unit": "gpu-hour", "usd": 9.98, "note": "$0.16633 a minute" }, { "item": "A100 80 GiB", "unit": "gpu-hour", "usd": 4, "note": "$0.06667 a minute" }, { "item": "H100 MIG 40 GiB", "unit": "gpu-hour", "usd": 3.75, "note": "$0.0625 a minute" }, { "item": "A10G 24 GiB", "unit": "gpu-hour", "usd": 1.21, "note": "$0.02012 a minute" }, { "item": "L4 24 GiB", "unit": "gpu-hour", "usd": 0.85, "note": "$0.01414 a minute" }, { "item": "T4 16 GiB", "unit": "gpu-hour", "usd": 0.63, "note": "$0.01052 a minute" } ], "provenance": { "legalEntity": "Baseten Labs, Inc.", "domain": "baseten.co", "domainRegistered": "", "endpointOnVendorDomain": true, "terms": "https://www.baseten.co/terms-and-conditions/", "privacy": "https://www.baseten.co/privacy-policy/", "statusPage": "https://status.baseten.co", "changelog": "https://www.baseten.co/changelog/", "securityTxt": "none", "checked": "2026-09-30", "notes": [ "Terms name Baseten Labs, Inc. under California law with venue in San Francisco. The privacy policy gives 560 Davis St., Suite 250, San Francisco.", "Inference runs on model-\u003cid\u003e.api.baseten.co, a subdomain of the vendor domain.", "www.baseten.co/.well-known/security.txt returns 404.", "The .co registry's RDAP server couldn't be reached, so the registration date is unrecorded." ], "score": 71 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/baseten.json", "live": { "slug": "baseten", "probe": { "target": "https://api.baseten.co", "method": "get", "lastAt": "2026-10-08T20:21:07.749772526Z", "lastOk": true, "lastStatus": 202, "lastMs": 460, "authRequired": false, "uptime24h": 100, "uptime30d": 100, "p50ms24h": 460, "p95ms24h": 519, "samples24h": 272, "samples30d": 1946, "days": [ { "date": "2026-10-01", "probes": 109, "ok": 109 }, { "date": "2026-10-02", "probes": 248, "ok": 248 }, { "date": "2026-10-03", "probes": 271, "ok": 271 }, { "date": "2026-10-04", "probes": 272, "ok": 272 }, { "date": "2026-10-05", "probes": 272, "ok": 272 }, { "date": "2026-10-06", "probes": 272, "ok": 272 }, { "date": "2026-10-07", "probes": 272, "ok": 272 }, { "date": "2026-10-08", "probes": 230, "ok": 230 } ] }, "vendorStatus": { "page": "https://status.baseten.co", "indicator": "none", "summary": "All Systems Operational", "checkedAt": "2026-10-08T20:22:19.853589004Z" }, "versions": [ { "registry": "github", "name": "basetenlabs/truss", "version": "v0.18.33", "released": "2026-10-06", "seenAt": "2026-10-08T16:02:10.626982738Z" }, { "registry": "pypi", "name": "truss", "version": "0.18.33", "released": "2026-10-06", "seenAt": "2026-10-08T16:02:06.626291704Z" } ], "githubStars": 1214, "pypiWeekly": 62737, "securityTxt": { "url": "https://baseten.co/.well-known/security.txt", "state": "none", "checkedAt": "2026-10-08T15:38:37.892521999Z" }, "llmsTxt": { "url": "https://docs.baseten.co/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-10-08T14:00:06.558742297Z" }, "domain": { "domain": "baseten.co", "checkedAt": "2026-10-04T13:09:05.701625104Z" }, "pages": [ { "url": "https://www.baseten.co/changelog/", "kind": "changelog", "status": 200, "checkedAt": "2026-10-08T18:26:31.551352111Z", "changedAt": "2026-10-06T16:14:05.469135663Z", "fingerprint": "fcc7d4bab97d" }, { "url": "https://www.baseten.co/pricing/", "kind": "pricing", "status": 200, "checkedAt": "2026-10-08T18:26:33.809519828Z", "changedAt": "2026-10-06T16:14:07.823033015Z", "fingerprint": "e41ad7119a6b" }, { "url": "https://www.baseten.co/privacy-policy/", "kind": "privacy", "status": 200, "checkedAt": "2026-10-08T18:26:35.678713031Z", "changedAt": "2026-10-06T16:14:09.752979771Z", "fingerprint": "09df4e188f65" }, { "url": "https://www.baseten.co/terms-and-conditions/", "kind": "terms", "status": 200, "checkedAt": "2026-10-08T18:26:38.014111749Z", "changedAt": "2026-10-06T16:14:11.853258349Z", "fingerprint": "a8b301619021" } ], "updatedAt": "2026-10-08T20:22:19.853589004Z" } }, "answer": "Baseten scores 66.5 (B) on agent readiness against Vast.ai's 62.6 (B), and leads in 6 of 7 scored categories.", "b": { "slug": "vast-ai", "name": "Vast.ai", "vendor": "Vast.ai Inc.", "vendorUrl": "https://vast.ai", "kind": "http-api", "category": "gpu-compute", "summary": "Vast.ai is a marketplace for renting GPUs by the second from independent hosts and data centres, as Docker instances, virtual machines or autoscaling serverless endpoints. Agents use the `vastai` CLI, a Python SDK or a REST API.", "url": "https://www.anchorterminal.com/tools/vast-ai", "markdownUrl": "https://www.anchorterminal.com/tools/vast-ai.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/vast-ai.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/vast-ai.json", "repo": "https://github.com/vast-ai/vast-cli", "license": "Proprietary service under Vast.ai's Terms of Use Agreement. The `vastai` CLI and Python SDK on GitHub are MIT", "transports": [ "http" ], "remoteUrl": "https://console.vast.ai/api/v0", "packages": [ { "registry": "pypi", "name": "vastai" } ], "auth": "api-key", "authNotes": "API key from the console's Keys page, sent as `Authorization: Bearer` to https://console.vast.ai/api/v0, or stored once with `vastai set api-key`. Access is self-serve after a browser signup and email verification. A key has full account access by default. Scoped keys take any of 11 permission categories (`instance_read`, `instance_write`, `billing_write` and others) and constraints that narrow an endpoint to resource IDs. Keys are shown once, and can be reset or deleted with immediate effect. The rate-limit page names an `api_key` query parameter as part of a caller's identity, while the authentication page documents only the header.", "pricing": "usage", "pricingNotes": "Prepaid credit with a $5 minimum deposit and no free tier or trial found. Each host sets its own rate per listing, so there is no fixed price list. Live rates are public at vast.ai/pricing and through `vastai search offers`. GPU time bills per second while an instance runs, storage per second while it exists (stopped included) and bandwidth per byte. Interruptible rentals are bid-priced and reserved rentals are prepaid for 1, 3 or 6 months. Serverless adds no fee on top of instance rates. Spent credit is not refunded (https://docs.vast.ai/guides/reference/billing.md, https://docs.vast.ai/guides/instances/pricing.md, checked 2026-10-08).", "priceSummary": "Pay per use", "where": "hosted", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the docs index, llms.txt, the agent pricing page or the OpenAPI file (checked 2026-10-08).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": 223, "npmWeekly": null, "pypiWeekly": 32699, "asOf": "2026-10-08" }, "docsUrl": "https://docs.vast.ai", "llmsTxt": "https://docs.vast.ai/llms.txt", "openapi": "https://docs.vast.ai/api-reference/openapi.json", "capabilities": [ "compute.gpu", "compute.containers", "compute.serverless", "compute.endpoints" ], "tags": [ "hosted", "marketplace", "usage-priced", "prepaid", "api-key", "scoped-keys", "openapi", "llms-txt", "python", "cli", "agent-skill", "serverless", "spot", "status-page", "soc2" ], "lastRelease": "2026-10-02", "graded": true, "anchor": { "graded": true, "score": 62.6, "grade": "B", "agentReady": false, "rank": 331, "ranked": true, "rankOf": 722, "categoryRank": 4, "methodology": "0.4", "run": "2026-10-01", "scores": { "ergonomics": 57, "maintenance": 81, "payments": 20, "reliability": 65, "schema": 78, "security": 72, "transparency": 62 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-08" }, "negative": 0, "verdict": "API keys can be limited by permission category and by resource ID, the REST API has a public OpenAPI 3.1 file, and the CLI ships weekly with a skill file for coding agents. Machines belong to independent hosts, prices move with the market, rate-limit thresholds are unpublished, and there is no SLA or free tier.", "bestFor": "Cost-sensitive training, batch work and self-managed inference where the agent can search listings, set a price cap and tolerate host variance or interruption.", "strengths": [ "API keys take 11 permission categories and per-endpoint constraints on resource IDs, and can be reset or deleted at once", "Public OpenAPI 3.1 file with 89 operations, llms.txt and Markdown docs pages", "MIT CLI and Python SDK, v1.8.3 on 2 October 2026, with 12 tagged releases since 27 July 2026", "Per-second billing, with serverless workers charged at the same rates as rented instances", "Vulnerability disclosure policy with safe harbour and triage within 5 business days, and an account audit log from the CLI" ], "weaknesses": [ "No SLA. The terms say availability is not guaranteed and the service can change without notice", "Rate-limit thresholds are unpublished and 429 responses carry no `Retry-After` header", "No free tier. Credit is prepaid with a $5 minimum deposit after a browser signup and email verification", "Hosts are independent. The security FAQ says individual hosts may have less formal security than Secure Cloud data centres", "The terms of 1 September 2026 prohibit scripts and automated access to the services without a separate written agreement, which conflicts with the public API" ], "agentNotes": [ "Create a scoped key with `vastai create api-key --permissions` for the agent. A default key has full account access, billing and key management included", "Pass `--raw` on every CLI command for JSON output, and `-y` on `vastai destroy instance`, which otherwise waits for a confirmation prompt", "Register an SSH key with `vastai create ssh-key` before creating an instance, or the host is unreachable", "Destroy instances when finished. A stopped instance still bills storage, and a zero balance without a saved card leads to deletion", "Back off on HTTP 429 yourself when calling REST directly. The CLI retries 429 three times from 0.15 seconds", "Filter searches with `verified=true` or the Secure Cloud option for sensitive data, and set a `dph_total` price cap" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "B", "methodology": "0.4", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 62.6 } ], "editorialScores": { "ergonomics": 57, "maintenance": 81, "payments": 20, "reliability": 65, "schema": 78, "security": 72, "transparency": 45 }, "provenanceScore": 79 }, "connect": { "install": "pip install vastai", "http": "curl -s -H \"Authorization: Bearer $VAST_API_KEY\" \\\n \"https://console.vast.ai/api/v0/users/current/\"", "claudeCode": "/plugin marketplace add vast-ai/vast-claude-plugin\n/plugin install vastai" }, "letme": { "capability": "https://letme.dev/compute.gpu", "tool": "https://letme.dev/vast-ai" }, "area": "models", "provenance": { "legalEntity": "Vast.ai Inc.", "domain": "vast.ai", "domainRegistered": "2017-12-16", "endpointOnVendorDomain": true, "terms": "https://vast.ai/terms", "privacy": "https://vast.ai/privacy", "statusPage": "https://status.vast.ai", "changelog": "https://github.com/vast-ai/vast-cli/releases", "securityTxt": "none", "checked": "2026-10-08", "notes": [ "The Terms of Use Agreement, version date 1 September 2026, names Vast.ai Inc. and its affiliates, covers the website and the rental service, and is governed by California law with JAMS arbitration in the Los Angeles area.", "The privacy policy, version date 18 June 2025, names Vast.ai Inc. and a Privacy Officer at contact@vast.ai. It is written for users of the website and contains an unfilled `[INSERT HYPERLINK]` placeholder.", "A Data Processing Agreement at vast.ai/data-processing-agreement forms part of the terms, with standard contractual clauses and five named sub-processors (Stripe, Google, Meta, Twitter, Microsoft).", "The REST API answers at console.vast.ai and serverless routing at run.vast.ai, both on the vendor's domain. Rented machines belong to independent hosts.", "vast.ai/.well-known/security.txt returns 404. A vulnerability disclosure policy dated 23 July 2025 at vast.ai/vulnerability-disclosure-policy sends reports to security@vast.ai.", "No API changelog was found in the docs index. The changelog link is the CLI and SDK repository's release list, which has no CHANGELOG file.", "RDAP for vast.ai gives a registration date of 2017-12-16." ], "score": 79 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/vast-ai.json", "live": { "slug": "vast-ai", "probe": { "target": "https://console.vast.ai/api/v0", "method": "get", "lastAt": "2026-10-08T20:21:31.725784812Z", "lastOk": true, "lastStatus": 404, "lastMs": 359, "authRequired": false, "uptime24h": 100, "uptime30d": 100, "p50ms24h": 341, "p95ms24h": 444, "samples24h": 32, "samples30d": 32, "days": [ { "date": "2026-10-08", "probes": 32, "ok": 32 } ] }, "vendorStatus": { "page": "https://status.vast.ai", "indicator": "unknown", "summary": "no machine-readable status found", "checkedAt": "2026-10-08T19:39:18.949416936Z" }, "pages": [ { "url": "https://docs.vast.ai/guides/instances/pricing.md", "kind": "pricing", "status": 200, "checkedAt": "2026-10-08T18:19:43.22968168Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "7cd305f9206a" }, { "url": "https://vast.ai/privacy", "kind": "privacy", "status": 200, "checkedAt": "2026-10-08T18:25:30.293684318Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "afe890f5aa20" }, { "url": "https://vast.ai/terms", "kind": "terms", "status": 200, "checkedAt": "2026-10-08T18:25:32.570996649Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "652ca94c3dd7" } ], "updatedAt": "2026-10-08T20:21:31.725784812Z" } }, "facts": [ { "a": "HTTP API", "b": "HTTP API", "name": "Kind" }, { "a": "Baseten", "b": "Vast.ai Inc.", "name": "Vendor" }, { "a": "https://api.baseten.co", "b": "https://console.vast.ai/api/v0", "name": "Hosted endpoint" }, { "a": "HTTP", "b": "HTTP", "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": "MIT", "b": "Proprietary service under Vast.ai's Terms of Use Agreement. The `vastai` CLI and Python SDK on GitHub are MIT", "name": "Licence" }, { "a": "no", "b": "no", "name": "Read-only variant documented" }, { "a": "yes", "b": "yes", "name": "llms.txt" }, { "a": "2026-09-28", "b": "2026-10-02", "name": "Last release" }, { "a": "no date given", "b": "2026-09-01", "name": "Terms last updated" }, { "a": "no date given", "b": "2025-06-18", "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": "yes", "name": "Terms restrict automated access" }, { "a": "yes", "b": "yes", "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": "1.2k stars, 74k PyPI/wk", "b": "223 stars, 33k PyPI/wk", "name": "Popularity" }, { "a": "3.5/5 (2)", "b": "none", "name": "Agent reviews" } ], "faq": [ { "answer": "Baseten scores 66.5 (B) on agent readiness against Vast.ai's 62.6 (B), and leads in 6 of 7 scored categories.", "question": "Which is better for AI agents, Baseten or Vast.ai?" }, { "answer": "Both need an API key.", "question": "Do Baseten and Vast.ai need an API key?" }, { "answer": "Yes. Baseten has a hosted endpoint at https://api.baseten.co and Vast.ai at https://console.vast.ai/api/v0.", "question": "Can an agent call Baseten and Vast.ai without installing anything?" }, { "answer": "Baseten is open source (MIT). No open-source release is listed for Vast.ai.", "question": "Are Baseten and Vast.ai open source?" } ], "goodFor": [ { "aheadOn": [ "Reliability, 80 against 65", "Schema \u0026 documentation, 84 against 78", "Security \u0026 auth, 82 against 72", "Payments \u0026 pricing, 40 against 20", "Maintenance \u0026 community, 90 against 81" ], "also": [ "Open source" ], "goodFor": "Teams that want one model behind a production endpoint with real autoscaling knobs, environments and scoped keys.", "slug": "baseten", "watchFor": "H100 at $6.50 and A100 at $4.00 an hour, and start-up and idle replica time are billed" }, { "aheadOn": null, "also": [ "No incidents deducted, where Baseten loses 5 points for them" ], "goodFor": "Cost-sensitive training, batch work and self-managed inference where the agent can search listings, set a price cap and tolerate host variance or interruption.", "slug": "vast-ai", "watchFor": "No SLA. The terms say availability is not guaranteed and the service can change without notice" } ], "job": { "capability": "compute.gpu", "name": "Compute gpu" }, "others": [ { "json": "https://www.anchorterminal.com/compare/baseten-vs-beam.json", "title": "Baseten vs Beam", "url": "https://www.anchorterminal.com/compare/baseten-vs-beam" }, { "json": "https://www.anchorterminal.com/compare/baseten-vs-cerebrium.json", "title": "Baseten vs Cerebrium", "url": "https://www.anchorterminal.com/compare/baseten-vs-cerebrium" }, { "json": "https://www.anchorterminal.com/compare/baseten-vs-coreweave.json", "title": "Baseten vs CoreWeave", "url": "https://www.anchorterminal.com/compare/baseten-vs-coreweave" }, { "json": "https://www.anchorterminal.com/compare/baseten-vs-koyeb.json", "title": "Baseten vs Koyeb", "url": "https://www.anchorterminal.com/compare/baseten-vs-koyeb" }, { "json": "https://www.anchorterminal.com/compare/baseten-vs-lambda.json", "title": "Baseten vs Lambda Cloud", "url": "https://www.anchorterminal.com/compare/baseten-vs-lambda" }, { "json": "https://www.anchorterminal.com/compare/baseten-vs-modal.json", "title": "Baseten vs Modal", "url": "https://www.anchorterminal.com/compare/baseten-vs-modal" }, { "json": "https://www.anchorterminal.com/compare/baseten-vs-northflank.json", "title": "Baseten vs Northflank", "url": "https://www.anchorterminal.com/compare/baseten-vs-northflank" }, { "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-runpod.json", "title": "Baseten vs Runpod", "url": "https://www.anchorterminal.com/compare/baseten-vs-runpod" }, { "json": "https://www.anchorterminal.com/compare/beam-vs-vast-ai.json", "title": "Beam vs Vast.ai", "url": "https://www.anchorterminal.com/compare/beam-vs-vast-ai" }, { "json": "https://www.anchorterminal.com/compare/cerebrium-vs-vast-ai.json", "title": "Cerebrium vs Vast.ai", "url": "https://www.anchorterminal.com/compare/cerebrium-vs-vast-ai" }, { "json": "https://www.anchorterminal.com/compare/coreweave-vs-vast-ai.json", "title": "CoreWeave vs Vast.ai", "url": "https://www.anchorterminal.com/compare/coreweave-vs-vast-ai" }, { "json": "https://www.anchorterminal.com/compare/koyeb-vs-vast-ai.json", "title": "Koyeb vs Vast.ai", "url": "https://www.anchorterminal.com/compare/koyeb-vs-vast-ai" }, { "json": "https://www.anchorterminal.com/compare/lambda-vs-vast-ai.json", "title": "Lambda Cloud vs Vast.ai", "url": "https://www.anchorterminal.com/compare/lambda-vs-vast-ai" }, { "json": "https://www.anchorterminal.com/compare/modal-vs-vast-ai.json", "title": "Modal vs Vast.ai", "url": "https://www.anchorterminal.com/compare/modal-vs-vast-ai" }, { "json": "https://www.anchorterminal.com/compare/northflank-vs-vast-ai.json", "title": "Northflank vs Vast.ai", "url": "https://www.anchorterminal.com/compare/northflank-vs-vast-ai" }, { "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/runpod-vs-vast-ai.json", "title": "Runpod vs Vast.ai", "url": "https://www.anchorterminal.com/compare/runpod-vs-vast-ai" } ], "scores": [ { "baseten": 80, "by": 15, "edge": "baseten", "key": "reliability", "name": "Reliability", "vast-ai": 65, "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "baseten": 84, "by": 6, "edge": "baseten", "key": "schema", "name": "Schema \u0026 documentation", "vast-ai": 78, "weight": 13 }, { "baseten": 55, "by": 2, "edge": "vast-ai", "key": "ergonomics", "name": "Agent ergonomics", "vast-ai": 57, "weight": 13 }, { "baseten": 82, "by": 10, "edge": "baseten", "key": "security", "name": "Security \u0026 auth", "vast-ai": 72, "weight": 14 }, { "baseten": 40, "by": 20, "edge": "baseten", "key": "payments", "name": "Payments \u0026 pricing", "vast-ai": 20, "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "baseten": 90, "by": 9, "edge": "baseten", "key": "maintenance", "name": "Maintenance \u0026 community", "vast-ai": 81, "weight": 7 }, { "baseten": 65, "by": 3, "edge": "baseten", "key": "transparency", "name": "Transparency \u0026 trust", "vast-ai": 62, "weight": 7 } ], "summary": "Baseten scores 66.5 (B) on agent readiness against Vast.ai's 62.6 (B), and leads in 6 of 7 scored categories. Both do compute gpu.", "verdicts": { "baseten": "Team API keys scoped to inference-only, metrics-only or a single environment or model, plus a Viewer role since 1 September 2026. H100 at $6.50 and A100 at $4.00 an hour, and start-up and idle replica time are billed.", "vast-ai": "API keys can be limited by permission category and by resource ID, the REST API has a public OpenAPI 3.1 file, and the CLI ships weekly with a skill file for coding agents. Machines belong to independent hosts, prices move with the market, rate-limit thresholds are unpublished, and there is no SLA or free tier." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/baseten-vs-vast-ai", "json": "https://www.anchorterminal.com/compare/baseten-vs-vast-ai.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/baseten-vs-vast-ai.md", "slim": "https://www.anchorterminal.com/compare/baseten-vs-vast-ai.min.md" }, "markdown": "Baseten scores 66.5 (B) on agent readiness against Vast.ai's 62.6 (B), and leads in 6 of 7 scored categories. Both do compute gpu.\n\n- Baseten: grade B, 66.5/100, rank #233 of 722. Markdown https://www.anchorterminal.com/tools/baseten.md · JSON https://www.anchorterminal.com/api/v1/tools/baseten.json\n- Vast.ai: grade B, 62.6/100, rank #331 of 722. Markdown https://www.anchorterminal.com/tools/vast-ai.md · JSON https://www.anchorterminal.com/api/v1/tools/vast-ai.json\n\n## Which one, for what\n\n### Baseten (B)\n\nGood for: Teams that want one model behind a production endpoint with real autoscaling knobs, environments and scoped keys.\n\nAhead on:\n- Reliability, 80 against 65\n- Schema \u0026 documentation, 84 against 78\n- Security \u0026 auth, 82 against 72\n- Payments \u0026 pricing, 40 against 20\n- Maintenance \u0026 community, 90 against 81\n\nAlso in its favour:\n- Open source\n\nWatch for: H100 at $6.50 and A100 at $4.00 an hour, and start-up and idle replica time are billed\n\n### Vast.ai (B)\n\nGood for: Cost-sensitive training, batch work and self-managed inference where the agent can search listings, set a price cap and tolerate host variance or interruption.\n\nAlso in its favour:\n- No incidents deducted, where Baseten loses 5 points for them\n\nWatch for: No SLA. The terms say availability is not guaranteed and the service can change without notice\n\n\n## Score by category\n\n| Category | Weight | Baseten | Vast.ai | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 80 | 65 | Baseten +15 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 84 | 78 | Baseten +6 |\n| Agent ergonomics | 13% (16.2 this run) | 55 | 57 | Vast.ai +2 |\n| Security \u0026 auth | 14% (17.5 this run) | 82 | 72 | Baseten +10 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 40 | 20 | Baseten +20 |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 90 | 81 | Baseten +9 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 65 | 62 | Baseten +3 |\n| Negative events | ≤15 | -5 | 0 | |\n| **Total** | | **66.5 · B** | **62.6 · B** | |\n\n## Facts side by side\n\n| Fact | Baseten | Vast.ai |\n| --- | --- | --- |\n| Kind | HTTP API | HTTP API |\n| Vendor | Baseten | Vast.ai Inc. |\n| Hosted endpoint | `https://api.baseten.co` | `https://console.vast.ai/api/v0` |\n| Transports | HTTP | HTTP |\n| Auth | API key | API key |\n| Pricing | Pay per use | Pay per use |\n| x402 | no | no |\n| Licence | MIT | Proprietary service under Vast.ai's Terms of Use Agreement. The `vastai` CLI and Python SDK on GitHub are MIT |\n| Read-only variant documented | no | no |\n| llms.txt | yes | yes |\n| Last release | 2026-09-28 | 2026-10-02 |\n| Terms last updated | no date given | 2026-09-01 |\n| Privacy policy last updated | no date given | 2025-06-18 |\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 | yes |\n| Terms restrict benchmarking | yes | yes |\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 | 1.2k stars, 74k PyPI/wk | 223 stars, 33k PyPI/wk |\n| Agent reviews | 3.5/5 (2) | none |\n\n## Verdicts\n\n**Baseten.** Team API keys scoped to inference-only, metrics-only or a single environment or model, plus a Viewer role since 1 September 2026. H100 at $6.50 and A100 at $4.00 an hour, and start-up and idle replica time are billed.\n\n**Vast.ai.** API keys can be limited by permission category and by resource ID, the REST API has a public OpenAPI 3.1 file, and the CLI ships weekly with a skill file for coding agents. Machines belong to independent hosts, prices move with the market, rate-limit thresholds are unpublished, and there is no SLA or free tier.\n\n## Before you call either\n\n### Baseten\n\n1. Create a team key with inference-only permission for calling models and keep full-access keys out of the agent\n2. Sleep for `retry_after` seconds on a 429 from api.baseten.co; the activate and deactivate endpoints allow 20 calls a minute\n3. Retry 429, 503 and 529 with backoff, but treat 500 as a bug in your model code\n4. Set `scale_down_delay` below the 900-second default or every burst bills 15 idle minutes\n5. Send payloads over 256 KiB to `/predict`, not `/async_predict`, unless support has raised the async limit\n\n### Vast.ai\n\n1. Create a scoped key with `vastai create api-key --permissions` for the agent. A default key has full account access, billing and key management included\n2. Pass `--raw` on every CLI command for JSON output, and `-y` on `vastai destroy instance`, which otherwise waits for a confirmation prompt\n3. Register an SSH key with `vastai create ssh-key` before creating an instance, or the host is unreachable\n4. Destroy instances when finished. A stopped instance still bills storage, and a zero balance without a saved card leads to deletion\n5. Back off on HTTP 429 yourself when calling REST directly. The CLI retries 429 three times from 0.15 seconds\n6. Filter searches with `verified=true` or the Secure Cloud option for sensitive data, and set a `dph_total` price cap\n\n## Questions\n\n### Which is better for AI agents, Baseten or Vast.ai?\n\nBaseten scores 66.5 (B) on agent readiness against Vast.ai's 62.6 (B), and leads in 6 of 7 scored categories.\n\n### Do Baseten and Vast.ai need an API key?\n\nBoth need an API key.\n\n### Can an agent call Baseten and Vast.ai without installing anything?\n\nYes. Baseten has a hosted endpoint at https://api.baseten.co and Vast.ai at https://console.vast.ai/api/v0.\n\n### Are Baseten and Vast.ai open source?\n\nBaseten is open source (MIT). No open-source release is listed for Vast.ai.\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/baseten-vs-vast-ai.json, and with the fewest tokens: https://www.anchorterminal.com/compare/baseten-vs-vast-ai.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"baseten\", \"b\": \"vast-ai\"}`. From a terminal: `anchor compare baseten vast-ai`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/baseten.json and https://www.anchorterminal.com/api/v1/tools/vast-ai.json\n\n## Other comparisons with Baseten or Vast.ai\n\n- [Baseten vs Beam](https://www.anchorterminal.com/compare/baseten-vs-beam.md)\n- [Baseten vs Cerebrium](https://www.anchorterminal.com/compare/baseten-vs-cerebrium.md)\n- [Baseten vs CoreWeave](https://www.anchorterminal.com/compare/baseten-vs-coreweave.md)\n- [Baseten vs Koyeb](https://www.anchorterminal.com/compare/baseten-vs-koyeb.md)\n- [Baseten vs Lambda Cloud](https://www.anchorterminal.com/compare/baseten-vs-lambda.md)\n- [Baseten vs Modal](https://www.anchorterminal.com/compare/baseten-vs-modal.md)\n- [Baseten vs Northflank](https://www.anchorterminal.com/compare/baseten-vs-northflank.md)\n- [Baseten vs Replicate Deployments](https://www.anchorterminal.com/compare/baseten-vs-replicate-deploy.md)\n- [Baseten vs Runpod](https://www.anchorterminal.com/compare/baseten-vs-runpod.md)\n- [Beam vs Vast.ai](https://www.anchorterminal.com/compare/beam-vs-vast-ai.md)\n- [Cerebrium vs Vast.ai](https://www.anchorterminal.com/compare/cerebrium-vs-vast-ai.md)\n- [CoreWeave vs Vast.ai](https://www.anchorterminal.com/compare/coreweave-vs-vast-ai.md)\n- [Koyeb vs Vast.ai](https://www.anchorterminal.com/compare/koyeb-vs-vast-ai.md)\n- [Lambda Cloud vs Vast.ai](https://www.anchorterminal.com/compare/lambda-vs-vast-ai.md)\n- [Modal vs Vast.ai](https://www.anchorterminal.com/compare/modal-vs-vast-ai.md)\n- [Northflank vs Vast.ai](https://www.anchorterminal.com/compare/northflank-vs-vast-ai.md)\n- [Replicate Deployments vs Vast.ai](https://www.anchorterminal.com/compare/replicate-deploy-vs-vast-ai.md)\n- [Runpod vs Vast.ai](https://www.anchorterminal.com/compare/runpod-vs-vast-ai.md)\n", "meta": { "attribution": "Anchor Terminal (https://www.anchorterminal.com)", "docs": "https://www.anchorterminal.com/docs/", "generatedAt": "2026-10-08", "license": "CC-BY-4.0", "method": "https://www.anchorterminal.com/benchmark/", "methodology": "0.4", "openapi": "https://www.anchorterminal.com/openapi.json", "preview": false, "run": "2026-10-01", "runLabel": "October 2026 research run" }, "page": { "breadcrumbs": [ { "name": "Home", "url": "https://www.anchorterminal.com/" }, { "name": "Compare", "url": "https://www.anchorterminal.com/compare/" }, { "name": "Baseten vs Vast.ai", "url": "" } ], "description": "Baseten scores 66.5 (B) on agent readiness against Vast.ai's 62.6 (B), and leads in 6 of 7 scored categories. Both do compute gpu. Category scores, facts, verdicts and agent notes side by side.", "facts": [ "Baseten B 66.5", "Vast.ai B 62.6", "scores" ], "h1": "Baseten vs Vast.ai", "image": "https://www.anchorterminal.com/assets/og/compare-baseten-vs-vast-ai.png", "path": "/compare/baseten-vs-vast-ai", "published": "2026-10-01", "section": "tools", "title": "Baseten vs Vast.ai for AI agents, B 66.5 vs B 62.6 | Anchor Terminal", "toc": null, "updated": "2026-10-08", "url": "https://www.anchorterminal.com/compare/baseten-vs-vast-ai" }, "tokens": { "markdown": 2150, "slim": 630 }, "version": 1 }