{
  "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": 66.7,
        "grade": "B",
        "agentReady": false,
        "rank": 157,
        "ranked": true,
        "rankOf": 452,
        "categoryRank": 1,
        "methodology": "0.3",
        "run": "2026-10-01",
        "scores": {
          "ergonomics": 55,
          "maintenance": 90,
          "payments": 40,
          "reliability": 80,
          "schema": 84,
          "security": 82,
          "transparency": 67
        },
        "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.",
        "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 $4.00 an hour, and start-up and idle replica time are billed",
          "21 status-page incidents between 31 July and 29 September 2026, mostly single-cluster 5xx",
          "A bot token with admin access to the product and GitOps repositories sat exposed from March 2023 until July 2026",
          "No pagination on management list endpoints and no idempotency keys",
          "No SLA below Enterprise, no bug bounty and no security.txt"
        ],
        "agentNotes": [
          "Create a team key with inference-only permission for calling models and keep full-access keys out of the agent",
          "Sleep for `retry_after` seconds on a 429 from api.baseten.co; the activate and deactivate endpoints allow 20 calls a minute",
          "Retry 429, 503 and 529 with backoff, but treat 500 as a bug in your model code",
          "Set `scale_down_delay` below the 900-second default or every burst bills 15 idle minutes",
          "Send payloads over 256 KiB to `/predict`, not `/async_predict`, unless support has raised the async limit"
        ],
        "metrics": {
          "kind": "remote",
          "measured": false
        },
        "reviewCount": 2,
        "avgRating": 3.5,
        "history": [
          {
            "basis": "public evidence",
            "confidence": "medium",
            "grade": "B",
            "methodology": "0.3",
            "pending": [
              "performance",
              "tasks"
            ],
            "run": "2026-10-01",
            "runLabel": "October 2026 research run",
            "score": 66.7
          }
        ],
        "editorialScores": {
          "ergonomics": 55,
          "maintenance": 90,
          "payments": 40,
          "reliability": 80,
          "schema": 84,
          "security": 82,
          "transparency": 58
        },
        "provenanceScore": 75
      },
      "connect": {
        "install": "pip install truss",
        "http": "curl -X POST \"https://model-$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": 75
      },
      "pageJsonUrl": "https://www.anchorterminal.com/tools/baseten.json",
      "live": {
        "slug": "baseten",
        "probe": {
          "target": "https://api.baseten.co",
          "method": "get",
          "lastAt": "2026-10-05T03:17:22.405809782Z",
          "lastOk": true,
          "lastStatus": 202,
          "lastMs": 483,
          "authRequired": false,
          "uptime24h": 100,
          "uptime30d": 100,
          "p50ms24h": 455,
          "p95ms24h": 505,
          "samples24h": 273,
          "samples30d": 938,
          "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": 38,
              "ok": 38
            }
          ]
        },
        "vendorStatus": {
          "page": "https://status.baseten.co",
          "indicator": "none",
          "summary": "All Systems Operational",
          "checkedAt": "2026-10-05T03:18:55.567804021Z"
        },
        "versions": [
          {
            "registry": "github",
            "name": "basetenlabs/truss",
            "version": "v0.18.32",
            "released": "2026-09-28",
            "seenAt": "2026-10-04T16:22:03.609365578Z"
          },
          {
            "registry": "pypi",
            "name": "truss",
            "version": "0.18.32",
            "released": "2026-09-28",
            "seenAt": "2026-10-04T16:22:01.591112358Z"
          }
        ],
        "githubStars": 1207,
        "pypiWeekly": 67780,
        "securityTxt": {
          "url": "https://baseten.co/.well-known/security.txt",
          "state": "none",
          "checkedAt": "2026-10-04T15:15:51.119519284Z"
        },
        "llmsTxt": {
          "url": "https://docs.baseten.co/llms.txt",
          "ok": true,
          "status": 200,
          "checkedAt": "2026-10-04T15:17:19.413388797Z"
        },
        "domain": {
          "domain": "baseten.co",
          "checkedAt": "2026-10-04T13:09:05.701625104Z"
        },
        "pages": [
          {
            "url": "https://www.baseten.co/changelog/",
            "kind": "changelog",
            "status": 200,
            "checkedAt": "2026-10-04T15:49:24.926514442Z",
            "changedAt": "2026-10-03T15:37:20.756910326Z",
            "fingerprint": "6cee5804197b"
          },
          {
            "url": "https://www.baseten.co/pricing/",
            "kind": "pricing",
            "status": 200,
            "checkedAt": "2026-10-04T15:49:27.25006425Z",
            "changedAt": "0001-01-01T00:00:00Z",
            "fingerprint": "990de850b24f"
          },
          {
            "url": "https://www.baseten.co/privacy-policy/",
            "kind": "privacy",
            "status": 200,
            "checkedAt": "2026-10-04T15:49:29.099232624Z",
            "changedAt": "0001-01-01T00:00:00Z",
            "fingerprint": "66effb5a49f2"
          },
          {
            "url": "https://www.baseten.co/terms-and-conditions/",
            "kind": "terms",
            "status": 200,
            "checkedAt": "2026-10-04T15:49:31.355740184Z",
            "changedAt": "0001-01-01T00:00:00Z",
            "fingerprint": "38417e30dfca"
          }
        ],
        "updatedAt": "2026-10-05T03:18:55.567804021Z"
      }
    },
    "b": {
      "slug": "runpod",
      "name": "Runpod",
      "vendor": "Runpod",
      "vendorUrl": "https://www.runpod.io",
      "kind": "http-api",
      "category": "gpu-compute",
      "summary": "Serverless GPU endpoints, queue-based or load-balanced, and rented GPU Pods, billed per second from prepaid credit.",
      "url": "https://www.anchorterminal.com/tools/runpod",
      "markdownUrl": "https://www.anchorterminal.com/tools/runpod.md",
      "slimMarkdownUrl": "https://www.anchorterminal.com/tools/runpod.min.md",
      "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/runpod.json",
      "repo": "https://github.com/runpod/runpod-python",
      "license": "MIT",
      "transports": [
        "http",
        "streamable-http",
        "stdio"
      ],
      "remoteUrl": "https://api.runpod.ai/v2",
      "packages": [
        {
          "registry": "pypi",
          "name": "runpod"
        },
        {
          "registry": "npm",
          "name": "runpod-sdk"
        },
        {
          "registry": "npm",
          "name": "@runpod/mcp-server"
        },
        {
          "registry": "pypi",
          "name": "runpod-flash"
        }
      ],
      "auth": "mixed",
      "authNotes": "API key from the console sent as `Authorization: Bearer` to serverless endpoints at api.runpod.ai/v2/\u003cendpoint-id\u003e and to the management REST API v2 at api.runpod.io/v2. Keys can be All, Read Only or Restricted per serverless endpoint. The deprecated GraphQL API takes the key as `?api_key=` in the URL. The hosted MCP server at mcp.getrunpod.io signs in with OAuth (Sign in with Runpod) or takes an API key as a Bearer header; the local `@runpod/mcp-server` reads `RUNPOD_API_KEY`.",
      "pricing": "usage",
      "pricingNotes": "Prepaid credit, billed per second and rounded up to the nearest second, with no data transfer fees and no free tier. Serverless flex workers an hour are 16 GB A4000 class $0.58, L4, A5000 or RTX 3090 $0.69, RTX 4090 $1.10, RTX Pro 4500 $1.15, A6000 or A40 $1.22, RTX 5090 $1.58, L40, L40S or RTX 6000 Ada $1.75, A100 80 GB $2.72, RTX Pro 6000 $3.49, H100 $4.79, H200 $5.93, B200 $8.64, B300 $9.98. Active (always-on) workers are discounted through sales. Pods run from $0.27 an hour (RTX A5000) to $7.89 (B300) on Community or Secure Cloud. Container disk $0.10 a GB-month, volume disk $0.10 running and $0.20 idle, network volumes $0.07 a GB-month under 1 TB and $0.05 above, high-performance $0.14. Default spend cap $80 an hour. Cards, crypto after KYC, prepaid cards at $100 or more a transaction, invoicing above $5,000 (https://www.runpod.io/pricing, https://docs.runpod.io/serverless/pricing, https://docs.runpod.io/accounts-billing/billing).",
      "priceSummary": "Pay per use",
      "where": "both",
      "x402": {
        "level": "no",
        "endpoints": []
      },
      "toolCount": null,
      "popularity": {
        "githubStars": 314,
        "npmWeekly": 21838,
        "pypiWeekly": 146926,
        "asOf": "2026-09-30"
      },
      "docsUrl": "https://docs.runpod.io",
      "llmsTxt": "https://docs.runpod.io/llms.txt",
      "openapi": "https://api.runpod.io/v2/openapi.json",
      "capabilities": [
        "compute.gpu",
        "compute.serverless",
        "compute.endpoints",
        "compute.batch",
        "compute.containers"
      ],
      "tags": [
        "hosted",
        "usage-priced",
        "prepaid",
        "mcp",
        "oauth",
        "llms-txt",
        "python",
        "typescript",
        "async-jobs",
        "batch",
        "webhooks",
        "enterprise"
      ],
      "lastRelease": "2026-09-15",
      "graded": true,
      "anchor": {
        "graded": true,
        "score": 53.7,
        "grade": "D",
        "agentReady": false,
        "rank": 329,
        "ranked": true,
        "rankOf": 452,
        "categoryRank": 6,
        "methodology": "0.3",
        "run": "2026-10-01",
        "scores": {
          "ergonomics": 47,
          "maintenance": 82,
          "payments": 20,
          "reliability": 35,
          "schema": 81,
          "security": 60,
          "transparency": 65
        },
        "pending": [
          "performance",
          "tasks"
        ],
        "assessment": {
          "confidence": "medium",
          "date": "2026-10-01"
        },
        "negative": 0,
        "verdict": "Per-second billing across more than a dozen serverless GPU classes, H100 at $4.79 and A100 80 GB at $2.72 an hour. Data-centre outages of 6 to 24 hours in each of July, August and September 2026.",
        "strengths": [
          "Per-second billing across more than a dozen serverless GPU classes, H100 at $4.79 and A100 80 GB at $2.72 an hour",
          "API keys can be Read Only or restricted per serverless endpoint",
          "OpenAPI file for REST v2, llms.txt and dated release notes with deprecation dates",
          "Official MCP server, hosted with OAuth or local over stdio",
          "Valid security.txt and SOC 2 Type 2 and ISO 27001 in the trust centre"
        ],
        "weaknesses": [
          "Data-centre outages of 6 to 24 hours in each of July, August and September 2026",
          "No published rate limits, 429 guidance, error codes or SLA",
          "The GraphQL API, live until early 2027, takes the API key in the URL",
          "No free tier, prepaid credit only",
          "Three APIs in flight, with REST v1 retiring on 15 November 2026"
        ],
        "agentNotes": [
          "Create a Restricted or Read Only key per endpoint for the agent, not an All key",
          "Use REST v2 at api.runpod.io/v2 with a Bearer header; avoid GraphQL, which puts the key in the URL",
          "Fetch `/run` results within 30 minutes and `/runsync` results within 1 minute, or they're gone",
          "Call `/retry` on a failed job ID rather than submitting a duplicate job",
          "Check `/health` before relying on an endpoint idle for a week, since max workers drop to 0"
        ],
        "metrics": {
          "kind": "remote",
          "measured": false
        },
        "reviewCount": 2,
        "avgRating": 3,
        "history": [
          {
            "basis": "public evidence",
            "confidence": "medium",
            "grade": "D",
            "methodology": "0.3",
            "pending": [
              "performance",
              "tasks"
            ],
            "run": "2026-10-01",
            "runLabel": "October 2026 research run",
            "score": 53.7
          }
        ],
        "editorialScores": {
          "ergonomics": 47,
          "maintenance": 82,
          "payments": 20,
          "reliability": 35,
          "schema": 81,
          "security": 60,
          "transparency": 60
        },
        "provenanceScore": 70
      },
      "connect": {
        "install": "pip install runpod  # or npm i runpod-sdk",
        "http": "curl -X POST \"https://api.runpod.ai/v2/$RUNPOD_ENDPOINT_ID/runsync\" \\\n  -H \"Authorization: Bearer $RUNPOD_API_KEY\" -H \"Content-Type: application/json\" \\\n  -d '{\"input\":{\"prompt\":\"Hello, world!\"}}'",
        "claudeCode": "claude mcp add --transport http runpod https://mcp.getrunpod.io/ --header \"Authorization: Bearer $RUNPOD_API_KEY\"",
        "config": {
          "mcpServers": {
            "runpod": {
              "args": [
                "-y",
                "@runpod/mcp-server@latest"
              ],
              "command": "npx",
              "env": {
                "RUNPOD_API_KEY": "${RUNPOD_API_KEY}"
              }
            }
          }
        }
      },
      "letme": {
        "capability": "https://letme.dev/compute.gpu",
        "tool": "https://letme.dev/runpod"
      },
      "area": "models",
      "unitPrices": [
        {
          "item": "H100 80 GB serverless flex",
          "unit": "gpu-hour",
          "usd": 4.79,
          "note": "Billed per second"
        },
        {
          "item": "H200 141 GB serverless flex",
          "unit": "gpu-hour",
          "usd": 5.93
        },
        {
          "item": "B200 180 GB serverless flex",
          "unit": "gpu-hour",
          "usd": 8.64
        },
        {
          "item": "A100 80 GB serverless flex",
          "unit": "gpu-hour",
          "usd": 2.72
        },
        {
          "item": "L40S 48 GB serverless flex",
          "unit": "gpu-hour",
          "usd": 1.75
        },
        {
          "item": "RTX 4090 24 GB serverless flex",
          "unit": "gpu-hour",
          "usd": 1.1
        },
        {
          "item": "L4 24 GB serverless flex",
          "unit": "gpu-hour",
          "usd": 0.69
        },
        {
          "item": "Container disk",
          "unit": "gb-month",
          "usd": 0.1
        },
        {
          "item": "Network volume under 1 TB",
          "unit": "gb-month",
          "usd": 0.07,
          "note": "$0.05 above 1 TB, $0.14 high-performance"
        }
      ],
      "provenance": {
        "legalEntity": "Runpod, Inc.",
        "domain": "runpod.io",
        "domainRegistered": "",
        "endpointOnVendorDomain": false,
        "terms": "https://www.runpod.io/legal/terms-of-service",
        "privacy": "https://www.runpod.io/legal/privacy-policy",
        "statusPage": "https://uptime.runpod.io",
        "changelog": "https://docs.runpod.io/release-notes",
        "securityTxt": "valid",
        "checked": "2026-09-30",
        "notes": [
          "Terms effective 24 March 2026 name Runpod, Inc. under Delaware law. The privacy policy gives 329 Bryant St #4D, San Francisco.",
          "Serverless endpoints are served from api.runpod.ai and the management API from api.runpod.io, while the hosted MCP server sits on getrunpod.io.",
          "security.txt points to trust.runpod.io and expires 2027-01-31.",
          "The .io registry's RDAP server rate-limited our lookup, so the registration date is unrecorded."
        ],
        "score": 70
      },
      "pageJsonUrl": "https://www.anchorterminal.com/tools/runpod.json",
      "live": {
        "slug": "runpod",
        "probe": {
          "target": "https://api.runpod.ai/v2",
          "method": "get",
          "lastAt": "2026-10-05T03:17:32.299286383Z",
          "lastOk": true,
          "lastStatus": 404,
          "lastMs": 61,
          "authRequired": false,
          "uptime24h": 100,
          "uptime30d": 100,
          "p50ms24h": 47,
          "p95ms24h": 91,
          "samples24h": 273,
          "samples30d": 938,
          "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": 38,
              "ok": 38
            }
          ]
        },
        "vendorStatus": {
          "page": "https://uptime.runpod.io",
          "indicator": "unknown",
          "summary": "no machine-readable status found",
          "checkedAt": "2026-10-04T21:40:27.797321476Z"
        },
        "versions": [
          {
            "registry": "github",
            "name": "runpod/runpod-python",
            "version": "v1.12.0",
            "released": "2026-08-10",
            "seenAt": "2026-10-04T16:38:45.92301028Z"
          },
          {
            "registry": "npm",
            "name": "@runpod/mcp-server",
            "version": "4.0.0",
            "seenAt": "2026-10-04T16:38:44.129996109Z"
          },
          {
            "registry": "npm",
            "name": "runpod-sdk",
            "version": "1.1.2",
            "seenAt": "2026-10-04T16:38:43.626700927Z"
          },
          {
            "registry": "pypi",
            "name": "runpod",
            "version": "1.12.0",
            "released": "2026-08-10",
            "seenAt": "2026-10-04T16:38:43.443916692Z"
          },
          {
            "registry": "pypi",
            "name": "runpod-flash",
            "version": "1.20.0",
            "released": "2026-09-24",
            "seenAt": "2026-10-04T16:38:45.837849754Z"
          }
        ],
        "githubStars": 313,
        "npmWeekly": 29952,
        "securityTxt": {
          "url": "https://runpod.io/.well-known/security.txt",
          "state": "valid",
          "expires": "2027-01-31T23:59:59Z",
          "checkedAt": "2026-10-04T15:15:41.463706841Z"
        },
        "llmsTxt": {
          "url": "https://docs.runpod.io/llms.txt",
          "ok": true,
          "status": 200,
          "checkedAt": "2026-10-04T15:18:12.095308214Z"
        },
        "domain": {
          "domain": "runpod.io",
          "checkedAt": "2026-10-04T13:06:54.960688955Z"
        },
        "pages": [
          {
            "url": "https://docs.runpod.io/release-notes",
            "kind": "deprecations",
            "status": 200,
            "checkedAt": "2026-10-04T15:44:00.021950941Z",
            "changedAt": "0001-01-01T00:00:00Z",
            "fingerprint": "64302af06aec"
          },
          {
            "url": "https://docs.runpod.io/serverless/pricing",
            "kind": "pricing",
            "status": 200,
            "checkedAt": "2026-10-04T15:44:02.16843867Z",
            "changedAt": "0001-01-01T00:00:00Z",
            "fingerprint": "acdfc6a36a7f"
          },
          {
            "url": "https://www.runpod.io/pricing",
            "kind": "pricing",
            "status": 200,
            "checkedAt": "2026-10-04T15:52:04.97613805Z",
            "changedAt": "0001-01-01T00:00:00Z",
            "fingerprint": "4e4c891c31f7"
          },
          {
            "url": "https://www.runpod.io/legal/privacy-policy",
            "kind": "privacy",
            "status": 200,
            "checkedAt": "2026-10-04T15:52:00.890880838Z",
            "changedAt": "0001-01-01T00:00:00Z",
            "fingerprint": "00b9defcdf3d"
          },
          {
            "url": "https://www.runpod.io/legal/terms-of-service",
            "kind": "terms",
            "status": 200,
            "checkedAt": "2026-10-04T15:52:02.970729657Z",
            "changedAt": "0001-01-01T00:00:00Z",
            "fingerprint": "4163df004c48"
          }
        ],
        "updatedAt": "2026-10-05T03:17:32.299286383Z"
      }
    },
    "summary": "Baseten has a score of 66.7 (B) against Runpod's 53.7 (D). Both do compute gpu. The largest gap is reliability, 45 points."
  },
  "kind": "anchor.page",
  "links": {
    "api": "https://www.anchorterminal.com/api/v1/index.json",
    "html": "https://www.anchorterminal.com/compare/baseten-vs-runpod",
    "json": "https://www.anchorterminal.com/compare/baseten-vs-runpod.json",
    "llms": "https://www.anchorterminal.com/llms.txt",
    "markdown": "https://www.anchorterminal.com/compare/baseten-vs-runpod.md",
    "slim": "https://www.anchorterminal.com/compare/baseten-vs-runpod.min.md"
  },
  "markdown": "Baseten has a score of 66.7 (B) against Runpod's 53.7 (D). Both do compute gpu. The largest gap is reliability, 45 points.\n\n- Baseten: grade B, 66.7/100, rank #157 of 452. Markdown https://www.anchorterminal.com/tools/baseten.md · JSON https://www.anchorterminal.com/api/v1/tools/baseten.json\n- Runpod: grade D, 53.7/100, rank #329 of 452. Markdown https://www.anchorterminal.com/tools/runpod.md · JSON https://www.anchorterminal.com/api/v1/tools/runpod.json\n\n## Which one, for what\n\nPick Baseten for reliability (+45), agent ergonomics (+8), security \u0026 auth (+22), payments \u0026 pricing (+20), maintenance \u0026 community (+8).\n\nPick Runpod for nothing in particular (no category where it leads by five points or more).\n\n## Score by category\n\n| Category | Weight | Baseten | Runpod | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 80 | 35 | Baseten +45 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 84 | 81 | Baseten +3 |\n| Agent ergonomics | 13% (16.2 this run) | 55 | 47 | Baseten +8 |\n| Security \u0026 auth | 14% (17.5 this run) | 82 | 60 | Baseten +22 |\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 | 82 | Baseten +8 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 67 | 65 | Baseten +2 |\n| Negative events | ≤15 | -5 | 0 | |\n| **Total** | | **66.7 · B** | **53.7 · D** | |\n\n## Facts side by side\n\n| Fact | Baseten | Runpod |\n| --- | --- | --- |\n| Kind | HTTP API | HTTP API |\n| Vendor | Baseten | Runpod |\n| Hosted endpoint | `https://api.baseten.co` | `https://api.runpod.ai/v2` |\n| Transports | HTTP | HTTP, Streamable HTTP, stdio |\n| Auth | API key | OAuth or key |\n| Pricing | Pay per use | Pay per use |\n| x402 | no | no |\n| Licence | MIT | MIT |\n| Tools exposed | none | none |\n| Context cost (tools/list) | n/a | n/a |\n| p95 latency | not measured yet | not measured yet |\n| Availability (30d) | not measured yet | not measured yet |\n| Read-only variant documented | no | no |\n| llms.txt | yes | yes |\n| MCP registry | not listed | not listed |\n| Last release | 2026-09-28 | 2026-09-15 |\n| Popularity | 1.2k stars, 74k PyPI/wk | 314 stars, 22k npm/wk, 147k PyPI/wk |\n| Agent reviews | 3.5/5 (2) | 3/5 (2) |\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**Runpod.** Per-second billing across more than a dozen serverless GPU classes, H100 at $4.79 and A100 80 GB at $2.72 an hour. Data-centre outages of 6 to 24 hours in each of July, August and September 2026.\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### Runpod\n\n1. Create a Restricted or Read Only key per endpoint for the agent, not an All key\n2. Use REST v2 at api.runpod.io/v2 with a Bearer header; avoid GraphQL, which puts the key in the URL\n3. Fetch `/run` results within 30 minutes and `/runsync` results within 1 minute, or they're gone\n4. Call `/retry` on a failed job ID rather than submitting a duplicate job\n5. Check `/health` before relying on an endpoint idle for a week, since max workers drop to 0\n\n## Other comparisons with Baseten or Runpod\n\n- [Baseten vs Beam](https://www.anchorterminal.com/compare/baseten-vs-beam.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- [Beam vs Runpod](https://www.anchorterminal.com/compare/beam-vs-runpod.md)\n- [Koyeb vs Runpod](https://www.anchorterminal.com/compare/koyeb-vs-runpod.md)\n- [Lambda Cloud vs Runpod](https://www.anchorterminal.com/compare/lambda-vs-runpod.md)\n- [Modal vs Runpod](https://www.anchorterminal.com/compare/modal-vs-runpod.md)\n- [Northflank vs Runpod](https://www.anchorterminal.com/compare/northflank-vs-runpod.md)\n- [Replicate Deployments vs Runpod](https://www.anchorterminal.com/compare/replicate-deploy-vs-runpod.md)\n",
  "meta": {
    "attribution": "Anchor Terminal (https://www.anchorterminal.com)",
    "docs": "https://www.anchorterminal.com/docs/",
    "generatedAt": "2026-10-05",
    "license": "CC-BY-4.0",
    "method": "https://www.anchorterminal.com/benchmark/",
    "methodology": "0.3",
    "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 Runpod",
        "url": ""
      }
    ],
    "description": "Baseten has a score of 66.7 (B) against Runpod's 53.7 (D). Both do compute gpu. The largest gap is reliability, 45 points. Category scores, facts, verdicts and agent notes side by side.",
    "facts": [
      "Baseten B 66.7",
      "Runpod D 53.7",
      "scores"
    ],
    "h1": "Baseten vs Runpod",
    "image": "https://www.anchorterminal.com/assets/og/compare-baseten-vs-runpod.png",
    "path": "/compare/baseten-vs-runpod",
    "published": "2026-10-01",
    "section": "tools",
    "title": "Baseten vs Runpod for AI agents, B 66.7 vs D 53.7 | Anchor Terminal",
    "toc": null,
    "updated": "2026-10-05",
    "url": "https://www.anchorterminal.com/compare/baseten-vs-runpod"
  },
  "tokens": {
    "markdown": 1400,
    "slim": 330
  },
  "version": 1
}