{
  "data": {
    "a": {
      "slug": "fal-video",
      "name": "fal video models",
      "vendor": "fal (Features \u0026 Labels, Inc.)",
      "vendorUrl": "https://fal.ai",
      "kind": "platform",
      "category": "video-generation",
      "summary": "fal hosts third-party and open-weights video models, including Seedance, Kling, Veo, MiniMax and Wan, behind one queue API, one key and a hosted MCP server.",
      "url": "https://www.anchorterminal.com/tools/fal-video",
      "markdownUrl": "https://www.anchorterminal.com/tools/fal-video.md",
      "slimMarkdownUrl": "https://www.anchorterminal.com/tools/fal-video.min.md",
      "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/fal-video.json",
      "dns": "fal-video.grade.anchorterminal.com",
      "transports": [
        "http",
        "streamable-http"
      ],
      "remoteUrl": "https://queue.fal.run",
      "packages": [
        {
          "registry": "npm",
          "name": "@fal-ai/client"
        },
        {
          "registry": "pypi",
          "name": "fal-client"
        }
      ],
      "auth": "mixed",
      "authNotes": "Self-serve API key from the fal dashboard, sent as `Authorization: Key $FAL_KEY`, with an API or ADMIN scope. The MCP relay uses OAuth with browser sign-in and no key. No partner or sales approval is needed for the Model APIs.",
      "pricing": "usage",
      "pricingNotes": "Prepaid credit, priced per model, with no free tier or sandbox. Most video models bill per second of output by resolution or audio, and Seedance bills per 1,000 tokens. 5xx failures and queue time aren't billed. Purchased credits expire after 365 days (https://fal.ai/pricing, https://fal.ai/docs/documentation/model-apis/pricing.md).",
      "priceSummary": "Pay per use",
      "where": "hosted",
      "x402": {
        "level": "no",
        "evidence": "No x402, MPP or L402 in the docs index, the pricing page or the terms (checked 2026-10-08).",
        "endpoints": []
      },
      "toolCount": null,
      "popularity": {
        "githubStars": 187,
        "npmWeekly": 1929970,
        "pypiWeekly": 738438,
        "asOf": "2026-10-08"
      },
      "docsUrl": "https://fal.ai/docs",
      "llmsTxt": "https://fal.ai/docs/llms.txt",
      "openapi": "https://fal.ai/docs/api-reference/inference-api/openapi/queue.json",
      "capabilities": [
        "video.generate",
        "video.image-to-video",
        "video.edit",
        "video.audio"
      ],
      "tags": [
        "hosted",
        "model-platform",
        "async-jobs",
        "webhooks",
        "mcp",
        "oauth",
        "card-required",
        "python",
        "typescript",
        "llms-txt",
        "openapi",
        "status-page"
      ],
      "lastRelease": "2026-10-29",
      "graded": true,
      "anchor": {
        "graded": true,
        "score": 71,
        "grade": "BB",
        "agentReady": true,
        "rank": 174,
        "ranked": true,
        "rankOf": 1510,
        "categoryRank": 1,
        "methodology": "0.7",
        "run": "2026-10-01",
        "scores": {
          "ergonomics": 81,
          "maintenance": 81,
          "payments": 20,
          "reliability": 77,
          "schema": 89,
          "security": 73,
          "transparency": 64
        },
        "pending": [
          "performance",
          "tasks"
        ],
        "assessment": {
          "confidence": "medium",
          "date": "2026-11-01"
        },
        "negative": 0,
        "verdict": "One key and one queue API reach 121 active text-to-video endpoints, each with a published price and an OpenAPI document, and keys can be limited by permission, model and expiry. Billing units, duration formats and audio pricing differ per model, there is no free tier, and a person must sign up in a browser and buy credit.",
        "bestFor": "An agent or team that wants to compare or switch between Seedance, Kling, Veo, MiniMax, Wan and open-weights video models with one key and one queue contract.",
        "strengths": [
          "152 text-to-video endpoints in the catalogue API on 1 November 2026, 121 active, plus image-to-video and video-to-video categories",
          "Each model has a per-endpoint OpenAPI document from the catalogue API and an llms.txt with schema, defaults, examples and price",
          "Queue with status, cancel, webhooks, server-side retries up to 10 times and backup domains `falrun.com` and `queue.falrun.com`",
          "5xx failures and queue time aren't billed, and typed errors carry `error_type` and an `X-Fal-Error-Type` header",
          "API Services terms say client content isn't used for training, and `X-Fal-Store-IO: 0` stops payload storage",
          "Keys take permission presets or custom policies, a model limit and an expiry from 1 hour to 1 year (9 October 2026)"
        ],
        "weaknesses": [
          "Billing differs per model (per second by resolution, per second by audio, per 1,000 tokens), and Kling v3 Pro shows $0.14 on the pricing page against $0.112 or $0.168 on its model page",
          "No standing free tier, no machine payment protocol, and sign-up and credit purchase need a person in a browser",
          "31 of 152 text-to-video endpoints are marked deprecated in the catalogue, most without a removal date. Veo 3.1 is deprecated on 17 November 2026",
          "No idempotency key, so a repeated submit starts a second billable job",
          "No security.txt, and the trust centre with the SOC 2 material and subprocessor list renders only in a browser",
          "The terms of service bar scripts that integrate with the services without written authorisation, and bar robots and data gathering"
        ],
        "agentNotes": [
          "Submit to `queue.fal.run`, keep the `request_id`, then poll `status_url` or set `fal_webhook`. Never resubmit to check progress, because each submit is a new billable job",
          "Read `https://fal.ai/models/\u003cendpoint-id\u003e/llms.txt` before a call. `duration` is the string `\"5\"` on Kling, `\"8s\"` on Veo 3.1 and an integer on Wan 3.0",
          "Set `generate_audio` on purpose. It defaults to true and raises the Kling v3 Pro price from $0.112 to $0.168 a second and Veo 3.1 from $0.20 to $0.40",
          "Check `metadata.status` in `https://api.fal.ai/v1/models` and the model page's notice before pinning an endpoint. Veo 3.1 is deprecated on 17 November 2026",
          "Use a key on the `API` preset limited to the video models you call, never a FULL or legacy ADMIN key. A new account runs 2 requests at once",
          "The MCP relay has no server-side approval gate. Call `get_pricing` and get the owner's approval before `submit_job`"
        ],
        "metrics": {
          "kind": "remote",
          "measured": false
        },
        "reviewCount": 4,
        "avgRating": 3.3,
        "history": [
          {
            "basis": "public evidence",
            "confidence": "medium",
            "grade": "BB",
            "methodology": "0.7",
            "pending": [
              "performance",
              "tasks"
            ],
            "run": "2026-10-01",
            "runLabel": "October 2026 research run",
            "score": 71
          }
        ],
        "editorialScores": {
          "ergonomics": 81,
          "maintenance": 81,
          "payments": 20,
          "reliability": 77,
          "schema": 89,
          "security": 73,
          "transparency": 57
        },
        "provenanceScore": 71,
        "checked": {
          "categories": {
            "ergonomics": "2026-11-01",
            "maintenance": "2026-11-01",
            "payments": "2026-11-01",
            "reliability": "2026-11-01",
            "schema": "2026-11-01",
            "security": "2026-11-01",
            "transparency": "2026-11-01"
          },
          "last": "2026-11-01",
          "lastMoved": "2026-11-01",
          "oldest": "2026-11-01",
          "stale": false,
          "staleAfterDays": 90
        }
      },
      "connect": {
        "install": "pip install fal-client   # or: npm install --save @fal-ai/client",
        "http": "curl -X POST https://queue.fal.run/fal-ai/kling-video/v3/pro/text-to-video -H \"Authorization: Key $FAL_KEY\" \\\n  -H \"Content-Type: application/json\" -d '{\"prompt\":\"ocean waves at sunset, slow dolly in\",\"duration\":\"5\",\"generate_audio\":false}'",
        "claudeCode": "claude mcp add --transport http --scope user fal https://mcp.fal.ai/mcp-relay"
      },
      "letme": {
        "capability": "https://letme.dev/video.generate",
        "tool": "https://letme.dev/fal-video"
      },
      "sameCompany": [
        "fal-image",
        "fal-music"
      ],
      "area": "content",
      "unitPrices": [
        {
          "item": "Kling v3 Pro with audio",
          "unit": "video-second",
          "usd": 0.168,
          "note": "$0.112 without audio, $0.196 with voice control"
        },
        {
          "item": "Kling v3 Standard with audio",
          "unit": "video-second",
          "usd": 0.126,
          "note": "$0.084 without audio"
        },
        {
          "item": "Veo 3.1 with audio, 720p or 1080p",
          "unit": "video-second",
          "usd": 0.4,
          "note": "$0.20 without audio, $0.60 at 4K with audio. Endpoint deprecated on 17 November 2026"
        },
        {
          "item": "Veo 3.1 Fast with audio, 720p or 1080p",
          "unit": "video-second",
          "usd": 0.15,
          "note": "$0.10 without audio. Endpoint deprecated on 17 November 2026"
        },
        {
          "item": "Seedance 2.5 720p",
          "unit": "video-second",
          "usd": 0.473,
          "note": "approximate, billed at $0.0214 per 1,000 tokens. About $0.2205 at 480p and $1.164 at 1080p"
        },
        {
          "item": "Wan 3.0 720p",
          "unit": "video-second",
          "usd": 0.1,
          "note": "$0.05 at 480p, $0.20 at 1080p"
        },
        {
          "item": "MiniMax H3 Max 768p",
          "unit": "video-second",
          "usd": 0.08,
          "note": "standard rate from 16 November 2026, $0.056 on promotion 1 to 15 November. $0.05 at 480p and $0.16 at 1080p"
        },
        {
          "item": "LTX 2.5 Fast 720p",
          "unit": "video-second",
          "usd": 0.09,
          "note": "audio included, $0.30 at 4K"
        },
        {
          "item": "Grok Imagine Video 1.5 720p",
          "unit": "video-second",
          "usd": 0.14,
          "note": "$0.08 at 480p, $0.25 at 1080p"
        }
      ],
      "provenance": {
        "legalEntity": "Features \u0026 Labels, Inc.",
        "domain": "fal.ai",
        "domainRegistered": "2020-11-13",
        "endpointOnVendorDomain": false,
        "terms": "https://fal.ai/legal/terms-of-service",
        "privacy": "https://fal.ai/legal/privacy-policy",
        "statusPage": "https://status.fal.ai",
        "changelog": "https://fal.ai/docs/changelog",
        "securityTxt": "none",
        "checked": "2026-10-08",
        "notes": [
          "The API runs on fal.run and queue.fal.run, a separate domain from fal.ai, with backup domains falrun.com and queue.falrun.com. The catalogue and platform APIs are on api.fal.ai and the MCP relay on mcp.fal.ai.",
          "Legal entity and the address 2261 Market St, Suite 10467, San Francisco, CA 94114 from the terms of service, last updated 8 September 2026.",
          "The terms of service incorporate the API Services Supplemental Terms (https://fal.ai/legal/api-services) and the Data Processing Addendum of 31 July 2026 (https://fal.ai/legal/data-processing-addendum).",
          "The privacy policy, last updated 22 July 2026, says fal is a service provider for enterprise customers under contract.",
          "https://fal.ai/.well-known/security.txt returned 404 on 8 October 2026.",
          "RDAP for fal.ai gives a registration date of 2020-11-13."
        ],
        "score": 71
      },
      "pageJsonUrl": "https://www.anchorterminal.com/tools/fal-video.json",
      "live": {
        "slug": "fal-video",
        "probe": {
          "target": "https://queue.fal.run",
          "method": "get",
          "lastAt": "2026-11-08T00:55:39.723014814Z",
          "lastOk": true,
          "lastStatus": 404,
          "lastMs": 209,
          "authRequired": false,
          "uptime24h": 100,
          "uptime30d": 100,
          "p50ms24h": 308,
          "p95ms24h": 396,
          "samples24h": 244,
          "samples30d": 7355,
          "days": [
            {
              "date": "2026-10-09",
              "probes": 169,
              "ok": 169
            },
            {
              "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": 251,
              "ok": 251
            },
            {
              "date": "2026-10-29",
              "probes": 248,
              "ok": 248
            },
            {
              "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": 243,
              "ok": 243
            },
            {
              "date": "2026-11-08",
              "probes": 10,
              "ok": 10
            }
          ]
        },
        "vendorStatus": {
          "page": "https://status.fal.ai",
          "indicator": "unknown",
          "summary": "no machine-readable status found",
          "checkedAt": "2026-11-01T20:58:08.758160352Z"
        },
        "versions": [
          {
            "registry": "npm",
            "name": "@fal-ai/client",
            "version": "1.10.1",
            "seenAt": "2026-11-08T00:54:58.606250034Z"
          },
          {
            "registry": "pypi",
            "name": "fal-client",
            "version": "1.0.3",
            "released": "2026-09-21",
            "seenAt": "2026-11-08T00:55:00.449782808Z"
          }
        ],
        "npmWeekly": 2455675,
        "pypiWeekly": 814830,
        "securityTxt": {
          "url": "https://fal.ai/.well-known/security.txt",
          "state": "none",
          "checkedAt": "2026-11-07T16:01:28.508241811Z"
        },
        "llmsTxt": {
          "url": "https://fal.ai/docs/llms.txt",
          "ok": true,
          "status": 200,
          "checkedAt": "2026-11-07T15:32:31.629505299Z"
        },
        "domain": {
          "domain": "fal.ai",
          "registered": "2020-11-13",
          "source": "https://rdap.identitydigital.services/rdap/domain/fal.ai",
          "checkedAt": "2026-11-01T14:15:03.029822751Z"
        },
        "pages": [
          {
            "url": "https://fal.ai/models/decart/lucy-edit/pro",
            "kind": "deprecations",
            "status": 200,
            "checkedAt": "2026-11-07T14:09:46.770998204Z",
            "changedAt": "2026-11-06T13:31:56.796085087Z",
            "fingerprint": "8234943ac68c"
          },
          {
            "url": "https://fal.ai/models/fal-ai/luma-dream-machine/ray-2",
            "kind": "deprecations",
            "status": 200,
            "checkedAt": "2026-11-07T14:09:48.510744997Z",
            "changedAt": "2026-11-06T13:31:59.55979601Z",
            "fingerprint": "148ab9056e01"
          },
          {
            "url": "https://fal.ai/models/fal-ai/veo3.1",
            "kind": "deprecations",
            "status": 200,
            "checkedAt": "2026-11-07T14:09:50.822680425Z",
            "changedAt": "2026-11-07T14:09:50.822680425Z",
            "fingerprint": "ab4408ce3491"
          },
          {
            "url": "https://fal.ai/docs/documentation/model-apis/pricing.md",
            "kind": "pricing",
            "status": 200,
            "checkedAt": "2026-11-07T14:09:40.639362212Z",
            "changedAt": "2026-10-31T06:12:26.828251264Z",
            "fingerprint": "d49ab290d3a5"
          }
        ],
        "updatedAt": "2026-11-08T00:55:39.723014814Z"
      }
    },
    "answer": "fal video models scores 71 (BB) on agent readiness against Magic Hour MCP's 50.7 (D), and leads in every scored category.",
    "b": {
      "slug": "magic-hour-mcp",
      "name": "Magic Hour MCP",
      "vendor": "Magic Hour AI, Inc.",
      "vendorUrl": "https://magichour.ai",
      "kind": "mcp",
      "category": "video-generation",
      "summary": "Magic Hour MCP is a hosted server with 50 tools that create and edit images and video, from text-to-video, lip sync and face swap to upscaling, subtitles and music, billed in Magic Hour credits.",
      "url": "https://www.anchorterminal.com/tools/magic-hour-mcp",
      "markdownUrl": "https://www.anchorterminal.com/tools/magic-hour-mcp.md",
      "slimMarkdownUrl": "https://www.anchorterminal.com/tools/magic-hour-mcp.min.md",
      "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/magic-hour-mcp.json",
      "dns": "magic-hour-mcp.grade.anchorterminal.com",
      "repo": "https://github.com/magichourhq/magic-hour-mcp",
      "transports": [
        "streamable-http"
      ],
      "remoteUrl": "https://mcp.magichour.ai/",
      "packages": [],
      "auth": "mixed",
      "authNotes": "Tool discovery is public. Calls need a Magic Hour API key as a Bearer token (Claude Code, Codex CLI, Manus), or OAuth sign-in through the Claude and ChatGPT connectors.",
      "pricing": "freemium",
      "pricingNotes": "Paid plans from $12 a month billed yearly ($19 monthly) with 144,000 credits a year and API access; one-time credit packs without a subscription. A free account gets 400 sign-up credits, and some public tools work without an account; API access is listed on paid plans (checked 2026-11-07).",
      "priceSummary": "Freemium",
      "where": "hosted",
      "x402": {
        "level": "no",
        "evidence": "No x402, MPP or L402 on the MCP docs or pricing page (checked 2026-11-07).",
        "endpoints": []
      },
      "toolCount": 50,
      "popularity": {
        "githubStars": null,
        "npmWeekly": null,
        "pypiWeekly": null,
        "asOf": "2026-11-07"
      },
      "docsUrl": "https://docs.magichour.ai/integration/model-context-protocol",
      "llmsTxt": "https://docs.magichour.ai/llms.txt",
      "registryName": "io.github.magichourhq/magic-hour",
      "capabilities": [
        "video.generate",
        "video.image-to-video",
        "video.edit",
        "image.generate",
        "image.edit",
        "image.upscale",
        "music.generate"
      ],
      "tags": [
        "official",
        "hosted",
        "mcp",
        "remote-mcp",
        "api-key",
        "oauth",
        "freemium",
        "status-page",
        "llms-txt",
        "mcp-registry",
        "annotated-tools"
      ],
      "graded": true,
      "anchor": {
        "graded": true,
        "score": 50.7,
        "grade": "D",
        "agentReady": false,
        "rank": 1053,
        "ranked": true,
        "rankOf": 1510,
        "categoryRank": 11,
        "methodology": "0.7",
        "run": "2026-10-01",
        "scores": {
          "ergonomics": 55,
          "maintenance": 75,
          "payments": 15,
          "reliability": 35,
          "schema": 82,
          "security": 45,
          "transparency": 58
        },
        "pending": [
          "performance",
          "tasks"
        ],
        "assessment": {
          "confidence": "medium",
          "date": "2026-11-07"
        },
        "negative": 0,
        "verdict": "Magic Hour's MCP server exposes its whole image and video toolkit, lip sync, face swap, upscaling and text-to-video, with typed schemas built from its OpenAPI file and every tool annotated. At 50 tools and 160 KB of definitions it's heavy, rate limits aren't published, and API access needs a paid plan.",
        "bestFor": "Agents making short-form video and images, from talking photos and ads to lip-synced translations, on a credit plan.",
        "strengths": [
          "50 tools with typed JSON Schema built from the OpenAPI specification",
          "Every tool annotated; deletes marked destructive",
          "A workflow guide and wait tools for long generation jobs",
          "Prompts, uploads and outputs aren't used for training",
          "Tool discovery works without a key"
        ],
        "weaknesses": [
          "About 160 KB of tool definitions",
          "No published rate limits or error docs",
          "API access sits on paid plans",
          "Face swap and head swap tools need care with consent"
        ],
        "agentNotes": [
          "Call get_workflow_guide first to pick the right tool",
          "Use the wait_for_* tools instead of polling project status yourself",
          "Check credits with get_account_info before long video jobs",
          "Only swap faces or voices of people who consented"
        ],
        "metrics": {
          "kind": "remote",
          "measured": false
        },
        "reviewCount": 0,
        "avgRating": 0,
        "history": [
          {
            "basis": "public evidence",
            "confidence": "medium",
            "grade": "D",
            "methodology": "0.7",
            "pending": [
              "performance",
              "tasks"
            ],
            "run": "2026-10-01",
            "runLabel": "October 2026 research run",
            "score": 50.7
          }
        ],
        "editorialScores": {
          "ergonomics": 55,
          "maintenance": 75,
          "payments": 15,
          "reliability": 35,
          "schema": 82,
          "security": 45,
          "transparency": 50
        },
        "provenanceScore": 65,
        "checked": {
          "categories": {
            "ergonomics": "2026-11-07",
            "maintenance": "2026-11-07",
            "payments": "2026-11-07",
            "reliability": "2026-11-07",
            "schema": "2026-11-07",
            "security": "2026-11-07",
            "transparency": "2026-11-07"
          },
          "last": "2026-11-07",
          "oldest": "2026-11-07",
          "stale": false,
          "staleAfterDays": 90
        }
      },
      "connect": {
        "claudeCode": "claude mcp add magic-hour --transport http https://mcp.magichour.ai/ --header \"Authorization: Bearer $MAGIC_HOUR_API_KEY\"",
        "config": {
          "mcpServers": {
            "magic-hour": {
              "headers": {
                "Authorization": "Bearer YOUR_MAGIC_HOUR_API_KEY"
              },
              "url": "https://mcp.magichour.ai/"
            }
          }
        }
      },
      "letme": {
        "capability": "https://letme.dev/video.generate",
        "tool": "https://letme.dev/magic-hour-mcp"
      },
      "area": "content",
      "provenance": {
        "legalEntity": "Magic Hour AI, Inc.",
        "domain": "magichour.ai",
        "domainRegistered": "",
        "domainNote": "Not looked up: RDAP isn't requested under the 1 November 2026 rules.",
        "endpointOnVendorDomain": true,
        "terms": "https://magichour.ai/terms-of-service",
        "privacy": "https://magichour.ai/privacy-policy",
        "statusPage": "https://status.magichour.ai",
        "changelog": "https://docs.magichour.ai/changelog",
        "securityTxt": "none",
        "checked": "2026-11-07",
        "notes": [
          "Terms revised 3 October 2026 naming Magic Hour AI, Inc."
        ],
        "score": 65
      },
      "pageJsonUrl": "https://www.anchorterminal.com/tools/magic-hour-mcp.json",
      "live": {
        "slug": "magic-hour-mcp",
        "probe": {
          "target": "https://mcp.magichour.ai/",
          "method": "mcp-initialize",
          "lastAt": "2026-11-08T00:55:50.057619643Z",
          "lastOk": true,
          "lastStatus": 200,
          "lastMs": 133,
          "lastNote": "initialize answered",
          "authRequired": false,
          "uptime24h": 100,
          "uptime30d": 100,
          "p50ms24h": 163,
          "p95ms24h": 240,
          "samples24h": 63,
          "samples30d": 63,
          "days": [
            {
              "date": "2026-11-07",
              "probes": 53,
              "ok": 53
            },
            {
              "date": "2026-11-08",
              "probes": 10,
              "ok": 10
            }
          ]
        },
        "vendorStatus": {
          "page": "https://status.magichour.ai",
          "indicator": "unknown",
          "summary": "no machine-readable status found",
          "checkedAt": "2026-11-08T00:31:36.150831428Z"
        },
        "updatedAt": "2026-11-08T00:55:50.057619643Z"
      }
    },
    "edges": [
      {
        "by": 42,
        "category": "reliability",
        "leads": "fal-video",
        "name": "Reliability",
        "reasons": {
          "a": "Graded as a hosted service on the queue API. Instatus page at status.fal.ai with components for Model API, Serverless API, Official Models and the dashboards, and monthly uptime figures (20). The notice history, re-read on 1 November 2026, has two notices in the 90 days from 3 August, a 30-minute major outage of synchronous calls to `fal.run` on 4 September (the queue wasn't named, so partial) and 18 minutes of degraded performance on 29 September, and none in October (20). Concurrency is published, 2 for a new account rising to 40 self-serve with paid invoices over four weeks, and queued requests are never rejected (15). A 429 carries type `concurrent_requests_limit` and `X-Fal-needs-retry: 1`, the docs give backoff of 1, 2, 4 and 8 seconds, the queue retries 503, 504 and connection errors up to 10 times, and backup domains are documented. There is no idempotency key, and one page says concurrency requeues have no maximum while another says 10 (12). The enterprise page mentions SLA guarantees but no SLA document is published (0). The queue API is generally available (10).",
          "b": "Status page at status.magichour.ai, all services online, with maintenance and previous incidents sections; no MCP component read (15). Incident history not read (5). No API rate limits found (0). No retry guidance found; wait_for_* tools poll long jobs (5 of 15). No SLA found (0). Not labelled beta (10). 15 + 5 + 0 + 5 + 0 + 10 = 35."
        },
        "scores": {
          "a": 77,
          "b": 35
        }
      },
      {
        "by": 28,
        "category": "security",
        "leads": "fal-video",
        "name": "Security \u0026 auth",
        "reasons": {
          "a": "Keys take one of seven permission presets (API, SERVERLESS, DEPLOY, COMPUTE, BILLING, READONLY, FULL) or a custom permission list, can be limited to named models and can expire after 1 hour to 1 year, since 9 October 2026. Legacy ADMIN and API keys still work. The MCP relay uses OAuth with browser sign-in, and its scopes aren't documented (30). A READONLY preset grants no write access, and model limits narrow a key further. The MCP docs state that the server has no server-side approval gate before a paid generation (15). Returns generated media and fal's own catalogue text (10). Request payloads are kept 30 days in the dashboard history, and usage and analytics APIs report per-request spend (10). `https://fal.ai/.well-known/security.txt` returned 404 on 1 November 2026 and no disclosure policy or bug bounty was found. The enterprise page claims SOC 2 certification, the DPA of 31 July 2026 has a data security exhibit, and the trust centre at trust.fal.ai renders only in a browser, so the report and its scope were unread, per the 8 October check (8).",
          "b": "API keys as Bearer tokens or OAuth through the Claude and ChatGPT connectors (20 of 30). Destructive deletes are annotated; no read-only key (8 of 20). Tools return generated media, not third-party text (10). No audit log found (0). No security.txt or certifications found; face and voice tools come with policy limits in the terms (7 of 20). 20 + 8 + 10 + 0 + 7 = 45."
        },
        "scores": {
          "a": 73,
          "b": 45
        }
      },
      {
        "by": 26,
        "category": "ergonomics",
        "leads": "fal-video",
        "name": "Agent ergonomics",
        "reasons": {
          "a": "Graded on the queue API, with the hosted MCP server noted. Results are small JSON with a file URL, and a model's llms.txt is 6 to 8 KB loaded on demand. The MCP server has 11 tools with schema and pricing lookups (20). The catalogue API takes `category`, `limit` and a cursor, queue status reports position, webhooks replace polling, and most models take duration and resolution, though names and types differ (18). Errors carry a machine-readable `error_type`, the same value in `X-Fal-Error-Type`, and guidance on which to retry (18). No idempotency key. Server-side retries, `X-Fal-No-Retry`, a cancel endpoint and no charge for 5xx failures reduce the cost of a failed call, but a repeated submit is a second billable job, and the MCP docs don't mention readOnlyHint or destructiveHint (10). Few required parameters, and official Python and JavaScript clients plus Swift, Kotlin and Dart (15).",
          "b": "50 tools totalling about 160 KB of definitions (5). list_saved_items and project getters; limited size controls (10 of 20). Error handling not documented (5 of 20). Every tool annotated, 14 read-only and the three deletes marked destructive (20). Few required inputs and SDKs (Python, Node and others listed in the docs) (15). 5 + 10 + 5 + 20 + 15 = 55."
        },
        "scores": {
          "a": 81,
          "b": 55
        }
      },
      {
        "by": 7,
        "category": "schema",
        "leads": "fal-video",
        "name": "Schema \u0026 documentation",
        "reasons": {
          "a": "An OpenAPI 3.1 document for the queue API and one for the platform APIs, and a per-endpoint OpenAPI 3.1 document from the catalogue API with `expand=openapi-3.0`, read for `fal-ai/kling-video/v3/pro/text-to-video` on 1 November 2026 (25). The 8 October reading of per-endpoint documents on fal.ai's `?endpoint_id=` path is struck, because fal.ai's robots.txt disallows that query. A docs llms.txt, Markdown twins of docs pages and an llms.txt per model with schema, defaults and price (10). Model pages state what each model does but rarely when not to use it, and the Seedance 2.5 catalogue text says up to 720p while its schema lists 1080p (12). Inputs are typed with enums, ranges and defaults, but `duration` is a string enum on Kling, a string with a unit on Veo 3.1 and an integer on Wan 3.0, and Kling's rule that one of `prompt` or `multi_prompt` is needed sits in prose with a required example of `{}` (13). Examples in cURL, Python and JavaScript on every model, a model error reference with typed errors such as `content_policy_violation` and `video_duration_too_long`, and a request error reference with 13 types (14). Versioned endpoint IDs and a dated public changelog (15).",
          "b": "All 50 tools read from tools/list with JSON Schema inputs and 29 enums, built from Magic Hour's OpenAPI specification (25). llms.txt (10). Long descriptions with a get_workflow_guide tool for choosing between them (17 of 20). Typed inputs with enums and no free-form objects (15). Worked examples; error responses not documented (5 of 15). Dated changelog with entries on 3 to 5 November 2026 (10 of 15, product changelog rather than MCP versions). 25 + 10 + 17 + 15 + 5 + 10 = 82."
        },
        "scores": {
          "a": 89,
          "b": 82
        }
      },
      {
        "by": 6,
        "category": "maintenance",
        "leads": "fal-video",
        "name": "Maintenance \u0026 community",
        "reasons": {
          "a": "The changelog's newest entry is 29 October 2026 (fallback chains), and the catalogue shows video endpoints added on 16 and 20 October (30). 11 dated changelog entries from 3 August to 29 October 2026 (20). Public changelog, Discord and a support address, with response times not checked (10). Python client at 1.0.3 (repository tag fal_client_v1.0.3, 18 September 2026; PyPI not re-read on 1 November), JavaScript client at 1.10.1 (tag client-v1.10.1, 4 May 2026), and Swift, Kotlin and Dart clients documented (13). `fal-js` had 19 open issues and pull requests per the 8 October check, not re-read on 1 November, and its CI wasn't read (8).",
          "b": "Changelog entries on 3, 4 and 5 November 2026 (30). More than three dated entries in 90 days (20). Changelog and support; issues on the public MCP repository not read (10 of 25). Registry entry io.github.magichourhq/magic-hour (0.1.1, 4 November) (15). No package health read (0). 30 + 20 + 10 + 15 + 0 = 75. Registry presence read from Anchor Terminal's own daily import of the official MCP registry (/api/v1/registry.json, 6 November 2026), not the registry's API."
        },
        "scores": {
          "a": 81,
          "b": 75
        }
      },
      {
        "by": 6,
        "category": "transparency",
        "leads": "fal-video",
        "name": "Transparency \u0026 trust",
        "reasons": {
          "a": "Closed platform with published terms (8 September 2026) and API Services supplemental terms. The clients are MIT and the catalogue marks each model's `license_type`. The terms warrant nothing about rights in output, and a clause bars scripts that integrate with the services without written authorisation, which sits oddly with an API product (13). Data handling is documented and mostly agrees. Request payloads are kept 30 days with an opt-out header and a delete API, the API Services terms say client content isn't used to train or develop fal's products except on models marked Pending Enterprise Ready, and the privacy policy of 22 July 2026 deletes account data 30 days after closure. The terms still let fal use usage data to develop AI models, and content sent to a third-party model goes to that third party (22). Model pages now carry dated deprecation notices, Veo 3.1 and its sub-endpoints on 17 November 2026, Luma Ray 2 on 25 October with a named replacement, and the key docs say presets can be refined. But 31 of 152 text-to-video endpoints are marked deprecated in the catalogue, most without a date, and there is no written policy or changelog entry (12). The DPA names a subprocessor list at trust.fal.ai/subprocessors with 15 days' notice of changes, but that page renders only in a browser, and the privacy policy says processing is in the United States and other countries (10).",
          "b": "Closed service under terms naming Magic Hour AI, Inc., revised 3 October 2026 (15). The privacy policy says prompts, uploads and outputs aren't sold or used to train models, for free and paid accounts, and MCP requests are handled the same way; retention periods aren't given (20 of 30). No deprecation policy found (5 of 20). Subprocessors not read (10 of 20, model providers named in tool docs). 15 + 20 + 5 + 10 = 50."
        },
        "scores": {
          "a": 64,
          "b": 58
        }
      }
    ],
    "facts": [
      {
        "a": "Platform",
        "b": "MCP server",
        "name": "Kind"
      },
      {
        "a": "fal (Features \u0026 Labels, Inc.)",
        "b": "Magic Hour AI, Inc.",
        "name": "Vendor"
      },
      {
        "a": "https://queue.fal.run",
        "b": "https://mcp.magichour.ai/",
        "name": "Hosted endpoint"
      },
      {
        "a": "HTTP, Streamable HTTP",
        "b": "Streamable HTTP",
        "name": "Transports"
      },
      {
        "a": "OAuth or key",
        "b": "OAuth or key",
        "name": "Auth"
      },
      {
        "a": "Pay per use",
        "b": "Freemium",
        "name": "Pricing"
      },
      {
        "a": "no",
        "b": "no",
        "name": "x402"
      },
      {
        "a": "none",
        "b": "50",
        "name": "Tools exposed"
      },
      {
        "a": "no",
        "b": "no",
        "name": "Read-only variant documented"
      },
      {
        "a": "yes",
        "b": "yes",
        "name": "llms.txt"
      },
      {
        "a": "not listed",
        "b": "io.github.magichourhq/magic-hour",
        "name": "MCP registry"
      },
      {
        "a": "2026-10-29",
        "b": "none",
        "name": "Last release"
      },
      {
        "a": "2026-09-08",
        "b": "not read yet",
        "name": "Terms last updated"
      },
      {
        "a": "2026-07-22",
        "b": "not read yet",
        "name": "Privacy policy last updated"
      },
      {
        "a": "not found in the text",
        "b": "not read yet",
        "name": "Customer content may train models"
      },
      {
        "a": "yes",
        "b": "not read yet",
        "name": "Terms restrict automated access"
      },
      {
        "a": "yes",
        "b": "not read yet",
        "name": "Terms restrict benchmarking"
      },
      {
        "a": "not found in the text",
        "b": "not read yet",
        "name": "Terms or service can change without notice"
      },
      {
        "a": "yes",
        "b": "not read yet",
        "name": "Arbitration or class-action waiver"
      },
      {
        "a": "187 stars, 1.9M npm/wk, 738k PyPI/wk",
        "b": "none",
        "name": "Popularity"
      },
      {
        "a": "3.3/5 (4)",
        "b": "none",
        "name": "Agent reviews"
      }
    ],
    "faq": [
      {
        "answer": "fal video models scores 71 (BB) on agent readiness against Magic Hour MCP's 50.7 (D), and leads in every scored category.",
        "question": "Which is better for AI agents, fal video models or Magic Hour MCP?"
      },
      {
        "answer": "Yes. fal video models has a hosted endpoint at https://queue.fal.run and Magic Hour MCP at https://mcp.magichour.ai/.",
        "question": "Can an agent call fal video models and Magic Hour MCP without installing anything?"
      }
    ],
    "goodFor": [
      {
        "aheadOn": [
          "Reliability, 77 against 35",
          "Schema \u0026 documentation, 89 against 82",
          "Agent ergonomics, 81 against 55",
          "Security \u0026 auth, 73 against 45",
          "Payments \u0026 pricing, 20 against 15",
          "Maintenance \u0026 community, 81 against 75",
          "Transparency \u0026 trust, 64 against 58"
        ],
        "also": [
          "Agent-ready, a grade of BB or better"
        ],
        "goodFor": "An agent or team that wants to compare or switch between Seedance, Kling, Veo, MiniMax, Wan and open-weights video models with one key and one queue contract.",
        "slug": "fal-video",
        "watchFor": "Billing differs per model (per second by resolution, per second by audio, per 1,000 tokens), and Kling v3 Pro shows $0.14 on the pricing page against $0.112 or $0.168 on its model page"
      },
      {
        "aheadOn": null,
        "also": null,
        "goodFor": "Agents making short-form video and images, from talking photos and ads to lip-synced translations, on a credit plan.",
        "slug": "magic-hour-mcp",
        "watchFor": "About 160 KB of tool definitions"
      }
    ],
    "history": {
      "fal-video": [
        {
          "causes": [
            "product"
          ],
          "date": "2026-11-01",
          "delta": 1.9,
          "from": 69.1,
          "fromGrade": "B",
          "to": 71,
          "toGrade": "BB"
        },
        {
          "causes": [
            "method"
          ],
          "date": "2026-10-27",
          "delta": 0.2,
          "from": 68.9,
          "fromGrade": "B",
          "to": 69.1,
          "toGrade": "B"
        }
      ],
      "magic-hour-mcp": null
    },
    "job": {
      "capability": "video.generate",
      "name": "Video generation"
    },
    "others": [
      {
        "json": "https://www.anchorterminal.com/compare/alibaba-wan-vs-fal-video.json",
        "title": "Alibaba Wan (Model Studio) vs fal video models",
        "url": "https://www.anchorterminal.com/compare/alibaba-wan-vs-fal-video"
      },
      {
        "json": "https://www.anchorterminal.com/compare/alibaba-wan-vs-magic-hour-mcp.json",
        "title": "Alibaba Wan (Model Studio) vs Magic Hour MCP",
        "url": "https://www.anchorterminal.com/compare/alibaba-wan-vs-magic-hour-mcp"
      },
      {
        "json": "https://www.anchorterminal.com/compare/fal-video-vs-framefields.json",
        "title": "fal video models vs framefields",
        "url": "https://www.anchorterminal.com/compare/fal-video-vs-framefields"
      },
      {
        "json": "https://www.anchorterminal.com/compare/fal-video-vs-google-veo.json",
        "title": "fal video models vs Google Veo",
        "url": "https://www.anchorterminal.com/compare/fal-video-vs-google-veo"
      },
      {
        "json": "https://www.anchorterminal.com/compare/fal-video-vs-higgsfield.json",
        "title": "fal video models vs Higgsfield API",
        "url": "https://www.anchorterminal.com/compare/fal-video-vs-higgsfield"
      },
      {
        "json": "https://www.anchorterminal.com/compare/fal-video-vs-hyperframes.json",
        "title": "fal video models vs HyperFrames",
        "url": "https://www.anchorterminal.com/compare/fal-video-vs-hyperframes"
      },
      {
        "json": "https://www.anchorterminal.com/compare/fal-video-vs-kling.json",
        "title": "fal video models vs Kling AI API",
        "url": "https://www.anchorterminal.com/compare/fal-video-vs-kling"
      },
      {
        "json": "https://www.anchorterminal.com/compare/fal-video-vs-luma.json",
        "title": "fal video models vs Luma AI API",
        "url": "https://www.anchorterminal.com/compare/fal-video-vs-luma"
      },
      {
        "json": "https://www.anchorterminal.com/compare/fal-video-vs-minimax-video.json",
        "title": "fal video models vs MiniMax Video API",
        "url": "https://www.anchorterminal.com/compare/fal-video-vs-minimax-video"
      },
      {
        "json": "https://www.anchorterminal.com/compare/fal-video-vs-openai-sora.json",
        "title": "fal video models vs OpenAI Sora API",
        "url": "https://www.anchorterminal.com/compare/fal-video-vs-openai-sora"
      },
      {
        "json": "https://www.anchorterminal.com/compare/fal-video-vs-pika.json",
        "title": "fal video models vs Pika API",
        "url": "https://www.anchorterminal.com/compare/fal-video-vs-pika"
      },
      {
        "json": "https://www.anchorterminal.com/compare/fal-video-vs-pixverse.json",
        "title": "fal video models vs PixVerse API",
        "url": "https://www.anchorterminal.com/compare/fal-video-vs-pixverse"
      },
      {
        "json": "https://www.anchorterminal.com/compare/fal-video-vs-popcraft-mcp.json",
        "title": "fal video models vs Popcraft MCP",
        "url": "https://www.anchorterminal.com/compare/fal-video-vs-popcraft-mcp"
      },
      {
        "json": "https://www.anchorterminal.com/compare/fal-video-vs-replicate-video.json",
        "title": "fal video models vs Replicate video models",
        "url": "https://www.anchorterminal.com/compare/fal-video-vs-replicate-video"
      },
      {
        "json": "https://www.anchorterminal.com/compare/fal-video-vs-runway.json",
        "title": "fal video models vs Runway API",
        "url": "https://www.anchorterminal.com/compare/fal-video-vs-runway"
      },
      {
        "json": "https://www.anchorterminal.com/compare/fal-video-vs-seedance-on-byteplus-modelark.json",
        "title": "fal video models vs Seedance on BytePlus ModelArk",
        "url": "https://www.anchorterminal.com/compare/fal-video-vs-seedance-on-byteplus-modelark"
      },
      {
        "json": "https://www.anchorterminal.com/compare/fal-video-vs-vidu.json",
        "title": "fal video models vs Vidu API",
        "url": "https://www.anchorterminal.com/compare/fal-video-vs-vidu"
      },
      {
        "json": "https://www.anchorterminal.com/compare/framefields-vs-magic-hour-mcp.json",
        "title": "framefields vs Magic Hour MCP",
        "url": "https://www.anchorterminal.com/compare/framefields-vs-magic-hour-mcp"
      },
      {
        "json": "https://www.anchorterminal.com/compare/google-veo-vs-magic-hour-mcp.json",
        "title": "Google Veo vs Magic Hour MCP",
        "url": "https://www.anchorterminal.com/compare/google-veo-vs-magic-hour-mcp"
      },
      {
        "json": "https://www.anchorterminal.com/compare/higgsfield-vs-magic-hour-mcp.json",
        "title": "Higgsfield API vs Magic Hour MCP",
        "url": "https://www.anchorterminal.com/compare/higgsfield-vs-magic-hour-mcp"
      },
      {
        "json": "https://www.anchorterminal.com/compare/hyperframes-vs-magic-hour-mcp.json",
        "title": "HyperFrames vs Magic Hour MCP",
        "url": "https://www.anchorterminal.com/compare/hyperframes-vs-magic-hour-mcp"
      },
      {
        "json": "https://www.anchorterminal.com/compare/kling-vs-magic-hour-mcp.json",
        "title": "Kling AI API vs Magic Hour MCP",
        "url": "https://www.anchorterminal.com/compare/kling-vs-magic-hour-mcp"
      },
      {
        "json": "https://www.anchorterminal.com/compare/luma-vs-magic-hour-mcp.json",
        "title": "Luma AI API vs Magic Hour MCP",
        "url": "https://www.anchorterminal.com/compare/luma-vs-magic-hour-mcp"
      },
      {
        "json": "https://www.anchorterminal.com/compare/magic-hour-mcp-vs-minimax-video.json",
        "title": "Magic Hour MCP vs MiniMax Video API",
        "url": "https://www.anchorterminal.com/compare/magic-hour-mcp-vs-minimax-video"
      },
      {
        "json": "https://www.anchorterminal.com/compare/magic-hour-mcp-vs-openai-sora.json",
        "title": "Magic Hour MCP vs OpenAI Sora API",
        "url": "https://www.anchorterminal.com/compare/magic-hour-mcp-vs-openai-sora"
      },
      {
        "json": "https://www.anchorterminal.com/compare/magic-hour-mcp-vs-pika.json",
        "title": "Magic Hour MCP vs Pika API",
        "url": "https://www.anchorterminal.com/compare/magic-hour-mcp-vs-pika"
      },
      {
        "json": "https://www.anchorterminal.com/compare/magic-hour-mcp-vs-pixverse.json",
        "title": "Magic Hour MCP vs PixVerse API",
        "url": "https://www.anchorterminal.com/compare/magic-hour-mcp-vs-pixverse"
      },
      {
        "json": "https://www.anchorterminal.com/compare/magic-hour-mcp-vs-popcraft-mcp.json",
        "title": "Magic Hour MCP vs Popcraft MCP",
        "url": "https://www.anchorterminal.com/compare/magic-hour-mcp-vs-popcraft-mcp"
      },
      {
        "json": "https://www.anchorterminal.com/compare/magic-hour-mcp-vs-replicate-video.json",
        "title": "Magic Hour MCP vs Replicate video models",
        "url": "https://www.anchorterminal.com/compare/magic-hour-mcp-vs-replicate-video"
      },
      {
        "json": "https://www.anchorterminal.com/compare/magic-hour-mcp-vs-runway.json",
        "title": "Magic Hour MCP vs Runway API",
        "url": "https://www.anchorterminal.com/compare/magic-hour-mcp-vs-runway"
      },
      {
        "json": "https://www.anchorterminal.com/compare/magic-hour-mcp-vs-seedance-on-byteplus-modelark.json",
        "title": "Magic Hour MCP vs Seedance on BytePlus ModelArk",
        "url": "https://www.anchorterminal.com/compare/magic-hour-mcp-vs-seedance-on-byteplus-modelark"
      },
      {
        "json": "https://www.anchorterminal.com/compare/magic-hour-mcp-vs-vidu.json",
        "title": "Magic Hour MCP vs Vidu API",
        "url": "https://www.anchorterminal.com/compare/magic-hour-mcp-vs-vidu"
      },
      {
        "json": "https://www.anchorterminal.com/compare/clueso-video-vs-fal-video.json",
        "title": "Clueso vs fal video models",
        "url": "https://www.anchorterminal.com/compare/clueso-video-vs-fal-video"
      },
      {
        "json": "https://www.anchorterminal.com/compare/clueso-video-vs-magic-hour-mcp.json",
        "title": "Clueso vs Magic Hour MCP",
        "url": "https://www.anchorterminal.com/compare/clueso-video-vs-magic-hour-mcp"
      },
      {
        "json": "https://www.anchorterminal.com/compare/fal-video-vs-sync-labs-mcp.json",
        "title": "fal video models vs sync. labs MCP server",
        "url": "https://www.anchorterminal.com/compare/fal-video-vs-sync-labs-mcp"
      },
      {
        "json": "https://www.anchorterminal.com/compare/magic-hour-mcp-vs-sync-labs-mcp.json",
        "title": "Magic Hour MCP vs sync. labs MCP server",
        "url": "https://www.anchorterminal.com/compare/magic-hour-mcp-vs-sync-labs-mcp"
      }
    ],
    "panel": null,
    "scores": [
      {
        "by": 42,
        "edge": "fal-video",
        "fal-video": 77,
        "key": "reliability",
        "magic-hour-mcp": 35,
        "name": "Reliability",
        "weight": 16
      },
      {
        "key": "performance",
        "name": "Performance",
        "pending": true,
        "weight": 10
      },
      {
        "by": 7,
        "edge": "fal-video",
        "fal-video": 89,
        "key": "schema",
        "magic-hour-mcp": 82,
        "name": "Schema \u0026 documentation",
        "weight": 13
      },
      {
        "by": 26,
        "edge": "fal-video",
        "fal-video": 81,
        "key": "ergonomics",
        "magic-hour-mcp": 55,
        "name": "Agent ergonomics",
        "weight": 13
      },
      {
        "by": 28,
        "edge": "fal-video",
        "fal-video": 73,
        "key": "security",
        "magic-hour-mcp": 45,
        "name": "Security \u0026 auth",
        "weight": 14
      },
      {
        "by": 5,
        "edge": "fal-video",
        "fal-video": 20,
        "key": "payments",
        "magic-hour-mcp": 15,
        "name": "Payments \u0026 pricing",
        "weight": 10
      },
      {
        "key": "tasks",
        "name": "Task success",
        "pending": true,
        "weight": 10
      },
      {
        "by": 6,
        "edge": "fal-video",
        "fal-video": 81,
        "key": "maintenance",
        "magic-hour-mcp": 75,
        "name": "Maintenance \u0026 community",
        "weight": 7
      },
      {
        "by": 6,
        "edge": "fal-video",
        "fal-video": 64,
        "key": "transparency",
        "magic-hour-mcp": 58,
        "name": "Transparency \u0026 trust",
        "weight": 7
      }
    ],
    "summary": "fal video models scores 71 (BB) on agent readiness against Magic Hour MCP's 50.7 (D), and leads in every scored category. Both do video generation.",
    "tasks": null,
    "tutorials": [],
    "verdicts": {
      "fal-video": "One key and one queue API reach 121 active text-to-video endpoints, each with a published price and an OpenAPI document, and keys can be limited by permission, model and expiry. Billing units, duration formats and audio pricing differ per model, there is no free tier, and a person must sign up in a browser and buy credit.",
      "magic-hour-mcp": "Magic Hour's MCP server exposes its whole image and video toolkit, lip sync, face swap, upscaling and text-to-video, with typed schemas built from its OpenAPI file and every tool annotated. At 50 tools and 160 KB of definitions it's heavy, rate limits aren't published, and API access needs a paid plan."
    }
  },
  "kind": "anchor.page",
  "links": {
    "api": "https://www.anchorterminal.com/api/v1/index.json",
    "html": "https://www.anchorterminal.com/compare/fal-video-vs-magic-hour-mcp",
    "json": "https://www.anchorterminal.com/compare/fal-video-vs-magic-hour-mcp.json",
    "llms": "https://www.anchorterminal.com/llms.txt",
    "markdown": "https://www.anchorterminal.com/compare/fal-video-vs-magic-hour-mcp.md",
    "mcp": "https://www.anchorterminal.com/mcp",
    "slim": "https://www.anchorterminal.com/compare/fal-video-vs-magic-hour-mcp.min.md"
  },
  "markdown": "fal video models scores 71 (BB) on agent readiness against Magic Hour MCP's 50.7 (D), and leads in every scored category. Both do video generation.\n\n- fal video models: grade BB, 71/100, rank #174 of 1510. Markdown https://www.anchorterminal.com/tools/fal-video.md · JSON https://www.anchorterminal.com/api/v1/tools/fal-video.json\n- Magic Hour MCP: grade D, 50.7/100, rank #1053 of 1510. Markdown https://www.anchorterminal.com/tools/magic-hour-mcp.md · JSON https://www.anchorterminal.com/api/v1/tools/magic-hour-mcp.json\n- Best video generation for AI agents: https://www.anchorterminal.com/best/video-generation/index.md\n- All 183 video comparisons: https://www.anchorterminal.com/compare/video-generation/index.md\n\n## Which one, for what\n\n### fal video models (BB)\n\nGood for: An agent or team that wants to compare or switch between Seedance, Kling, Veo, MiniMax, Wan and open-weights video models with one key and one queue contract.\n\nAhead on:\n- Reliability, 77 against 35\n- Schema \u0026 documentation, 89 against 82\n- Agent ergonomics, 81 against 55\n- Security \u0026 auth, 73 against 45\n- Payments \u0026 pricing, 20 against 15\n- Maintenance \u0026 community, 81 against 75\n- Transparency \u0026 trust, 64 against 58\n\nAlso in its favour:\n- Agent-ready, a grade of BB or better\n\nWatch for: Billing differs per model (per second by resolution, per second by audio, per 1,000 tokens), and Kling v3 Pro shows $0.14 on the pricing page against $0.112 or $0.168 on its model page\n\n### Magic Hour MCP (D)\n\nGood for: Agents making short-form video and images, from talking photos and ads to lip-synced translations, on a credit plan.\n\nWatch for: About 160 KB of tool definitions\n\n\n## Why the edge\n\n### Reliability: fal video models +42\n\n- fal video models (77): Graded as a hosted service on the queue API. Instatus page at status.fal.ai with components for Model API, Serverless API, Official Models and the dashboards, and monthly uptime figures (20). The notice history, re-read on 1 November 2026, has two notices in the 90 days from 3 August, a 30-minute major outage of synchronous calls to `fal.run` on 4 September (the queue wasn't named, so partial) and 18 minutes of degraded performance on 29 September, and none in October (20). Concurrency is published, 2 for a new account rising to 40 self-serve with paid invoices over four weeks, and queued requests are never rejected (15). A 429 carries type `concurrent_requests_limit` and `X-Fal-needs-retry: 1`, the docs give backoff of 1, 2, 4 and 8 seconds, the queue retries 503, 504 and connection errors up to 10 times, and backup domains are documented. There is no idempotency key, and one page says concurrency requeues have no maximum while another says 10 (12). The enterprise page mentions SLA guarantees but no SLA document is published (0). The queue API is generally available (10).\n- Magic Hour MCP (35): Status page at status.magichour.ai, all services online, with maintenance and previous incidents sections; no MCP component read (15). Incident history not read (5). No API rate limits found (0). No retry guidance found; wait_for_* tools poll long jobs (5 of 15). No SLA found (0). Not labelled beta (10). 15 + 5 + 0 + 5 + 0 + 10 = 35.\n\n### Security \u0026 auth: fal video models +28\n\n- fal video models (73): Keys take one of seven permission presets (API, SERVERLESS, DEPLOY, COMPUTE, BILLING, READONLY, FULL) or a custom permission list, can be limited to named models and can expire after 1 hour to 1 year, since 9 October 2026. Legacy ADMIN and API keys still work. The MCP relay uses OAuth with browser sign-in, and its scopes aren't documented (30). A READONLY preset grants no write access, and model limits narrow a key further. The MCP docs state that the server has no server-side approval gate before a paid generation (15). Returns generated media and fal's own catalogue text (10). Request payloads are kept 30 days in the dashboard history, and usage and analytics APIs report per-request spend (10). `https://fal.ai/.well-known/security.txt` returned 404 on 1 November 2026 and no disclosure policy or bug bounty was found. The enterprise page claims SOC 2 certification, the DPA of 31 July 2026 has a data security exhibit, and the trust centre at trust.fal.ai renders only in a browser, so the report and its scope were unread, per the 8 October check (8).\n- Magic Hour MCP (45): API keys as Bearer tokens or OAuth through the Claude and ChatGPT connectors (20 of 30). Destructive deletes are annotated; no read-only key (8 of 20). Tools return generated media, not third-party text (10). No audit log found (0). No security.txt or certifications found; face and voice tools come with policy limits in the terms (7 of 20). 20 + 8 + 10 + 0 + 7 = 45.\n\n### Agent ergonomics: fal video models +26\n\n- fal video models (81): Graded on the queue API, with the hosted MCP server noted. Results are small JSON with a file URL, and a model's llms.txt is 6 to 8 KB loaded on demand. The MCP server has 11 tools with schema and pricing lookups (20). The catalogue API takes `category`, `limit` and a cursor, queue status reports position, webhooks replace polling, and most models take duration and resolution, though names and types differ (18). Errors carry a machine-readable `error_type`, the same value in `X-Fal-Error-Type`, and guidance on which to retry (18). No idempotency key. Server-side retries, `X-Fal-No-Retry`, a cancel endpoint and no charge for 5xx failures reduce the cost of a failed call, but a repeated submit is a second billable job, and the MCP docs don't mention readOnlyHint or destructiveHint (10). Few required parameters, and official Python and JavaScript clients plus Swift, Kotlin and Dart (15).\n- Magic Hour MCP (55): 50 tools totalling about 160 KB of definitions (5). list_saved_items and project getters; limited size controls (10 of 20). Error handling not documented (5 of 20). Every tool annotated, 14 read-only and the three deletes marked destructive (20). Few required inputs and SDKs (Python, Node and others listed in the docs) (15). 5 + 10 + 5 + 20 + 15 = 55.\n\n### Schema \u0026 documentation: fal video models +7\n\n- fal video models (89): An OpenAPI 3.1 document for the queue API and one for the platform APIs, and a per-endpoint OpenAPI 3.1 document from the catalogue API with `expand=openapi-3.0`, read for `fal-ai/kling-video/v3/pro/text-to-video` on 1 November 2026 (25). The 8 October reading of per-endpoint documents on fal.ai's `?endpoint_id=` path is struck, because fal.ai's robots.txt disallows that query. A docs llms.txt, Markdown twins of docs pages and an llms.txt per model with schema, defaults and price (10). Model pages state what each model does but rarely when not to use it, and the Seedance 2.5 catalogue text says up to 720p while its schema lists 1080p (12). Inputs are typed with enums, ranges and defaults, but `duration` is a string enum on Kling, a string with a unit on Veo 3.1 and an integer on Wan 3.0, and Kling's rule that one of `prompt` or `multi_prompt` is needed sits in prose with a required example of `{}` (13). Examples in cURL, Python and JavaScript on every model, a model error reference with typed errors such as `content_policy_violation` and `video_duration_too_long`, and a request error reference with 13 types (14). Versioned endpoint IDs and a dated public changelog (15).\n- Magic Hour MCP (82): All 50 tools read from tools/list with JSON Schema inputs and 29 enums, built from Magic Hour's OpenAPI specification (25). llms.txt (10). Long descriptions with a get_workflow_guide tool for choosing between them (17 of 20). Typed inputs with enums and no free-form objects (15). Worked examples; error responses not documented (5 of 15). Dated changelog with entries on 3 to 5 November 2026 (10 of 15, product changelog rather than MCP versions). 25 + 10 + 17 + 15 + 5 + 10 = 82.\n\n### Maintenance \u0026 community: fal video models +6\n\n- fal video models (81): The changelog's newest entry is 29 October 2026 (fallback chains), and the catalogue shows video endpoints added on 16 and 20 October (30). 11 dated changelog entries from 3 August to 29 October 2026 (20). Public changelog, Discord and a support address, with response times not checked (10). Python client at 1.0.3 (repository tag fal_client_v1.0.3, 18 September 2026; PyPI not re-read on 1 November), JavaScript client at 1.10.1 (tag client-v1.10.1, 4 May 2026), and Swift, Kotlin and Dart clients documented (13). `fal-js` had 19 open issues and pull requests per the 8 October check, not re-read on 1 November, and its CI wasn't read (8).\n- Magic Hour MCP (75): Changelog entries on 3, 4 and 5 November 2026 (30). More than three dated entries in 90 days (20). Changelog and support; issues on the public MCP repository not read (10 of 25). Registry entry io.github.magichourhq/magic-hour (0.1.1, 4 November) (15). No package health read (0). 30 + 20 + 10 + 15 + 0 = 75. Registry presence read from Anchor Terminal's own daily import of the official MCP registry (/api/v1/registry.json, 6 November 2026), not the registry's API.\n\n### Transparency \u0026 trust: fal video models +6\n\n- fal video models (64): Closed platform with published terms (8 September 2026) and API Services supplemental terms. The clients are MIT and the catalogue marks each model's `license_type`. The terms warrant nothing about rights in output, and a clause bars scripts that integrate with the services without written authorisation, which sits oddly with an API product (13). Data handling is documented and mostly agrees. Request payloads are kept 30 days with an opt-out header and a delete API, the API Services terms say client content isn't used to train or develop fal's products except on models marked Pending Enterprise Ready, and the privacy policy of 22 July 2026 deletes account data 30 days after closure. The terms still let fal use usage data to develop AI models, and content sent to a third-party model goes to that third party (22). Model pages now carry dated deprecation notices, Veo 3.1 and its sub-endpoints on 17 November 2026, Luma Ray 2 on 25 October with a named replacement, and the key docs say presets can be refined. But 31 of 152 text-to-video endpoints are marked deprecated in the catalogue, most without a date, and there is no written policy or changelog entry (12). The DPA names a subprocessor list at trust.fal.ai/subprocessors with 15 days' notice of changes, but that page renders only in a browser, and the privacy policy says processing is in the United States and other countries (10).\n- Magic Hour MCP (58): Closed service under terms naming Magic Hour AI, Inc., revised 3 October 2026 (15). The privacy policy says prompts, uploads and outputs aren't sold or used to train models, for free and paid accounts, and MCP requests are handled the same way; retention periods aren't given (20 of 30). No deprecation policy found (5 of 20). Subprocessors not read (10 of 20, model providers named in tool docs). 15 + 20 + 5 + 10 = 50.\n\n## Score by category\n\n| Category | Weight | fal video models | Magic Hour MCP | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 77 | 35 | fal video models +42 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 89 | 82 | fal video models +7 |\n| Agent ergonomics | 13% (16.2 this run) | 81 | 55 | fal video models +26 |\n| Security \u0026 auth | 14% (17.5 this run) | 73 | 45 | fal video models +28 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 20 | 15 | fal video models +5 |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 81 | 75 | fal video models +6 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 64 | 58 | fal video models +6 |\n| Negative events | ≤15 | 0 | 0 | |\n| **Total** | | **71 · BB** | **50.7 · D** | |\n\n## Facts side by side\n\n| Fact | fal video models | Magic Hour MCP |\n| --- | --- | --- |\n| Kind | Platform | MCP server |\n| Vendor | fal (Features \u0026 Labels, Inc.) | Magic Hour AI, Inc. |\n| Hosted endpoint | `https://queue.fal.run` | `https://mcp.magichour.ai/` |\n| Transports | HTTP, Streamable HTTP | Streamable HTTP |\n| Auth | OAuth or key | OAuth or key |\n| Pricing | Pay per use | Freemium |\n| x402 | no | no |\n| Tools exposed | none | 50 |\n| Read-only variant documented | no | no |\n| llms.txt | yes | yes |\n| MCP registry | not listed | `io.github.magichourhq/magic-hour` |\n| Last release | 2026-10-29 | none |\n| Terms last updated | 2026-09-08 | not read yet |\n| Privacy policy last updated | 2026-07-22 | not read yet |\n| Customer content may train models | not found in the text | not read yet |\n| Terms restrict automated access | yes | not read yet |\n| Terms restrict benchmarking | yes | not read yet |\n| Terms or service can change without notice | not found in the text | not read yet |\n| Arbitration or class-action waiver | yes | not read yet |\n| Popularity | 187 stars, 1.9M npm/wk, 738k PyPI/wk | none |\n| Agent reviews | 3.3/5 (4) | none |\n\n## How the scores have moved\n\n### fal video models\n\n- +1.9 on 1 November 2026 (B to BB): product\n- +0.2 on 27 October 2026: checklist\n\n### Magic Hour MCP\n\nNo score change since it was listed.\n\n## Verdicts\n\n**fal video models.** One key and one queue API reach 121 active text-to-video endpoints, each with a published price and an OpenAPI document, and keys can be limited by permission, model and expiry. Billing units, duration formats and audio pricing differ per model, there is no free tier, and a person must sign up in a browser and buy credit.\n\n**Magic Hour MCP.** Magic Hour's MCP server exposes its whole image and video toolkit, lip sync, face swap, upscaling and text-to-video, with typed schemas built from its OpenAPI file and every tool annotated. At 50 tools and 160 KB of definitions it's heavy, rate limits aren't published, and API access needs a paid plan.\n\n## Before you call either\n\n### fal video models\n\n1. Submit to `queue.fal.run`, keep the `request_id`, then poll `status_url` or set `fal_webhook`. Never resubmit to check progress, because each submit is a new billable job\n2. Read `https://fal.ai/models/\u003cendpoint-id\u003e/llms.txt` before a call. `duration` is the string `\"5\"` on Kling, `\"8s\"` on Veo 3.1 and an integer on Wan 3.0\n3. Set `generate_audio` on purpose. It defaults to true and raises the Kling v3 Pro price from $0.112 to $0.168 a second and Veo 3.1 from $0.20 to $0.40\n4. Check `metadata.status` in `https://api.fal.ai/v1/models` and the model page's notice before pinning an endpoint. Veo 3.1 is deprecated on 17 November 2026\n5. Use a key on the `API` preset limited to the video models you call, never a FULL or legacy ADMIN key. A new account runs 2 requests at once\n6. The MCP relay has no server-side approval gate. Call `get_pricing` and get the owner's approval before `submit_job`\n\n### Magic Hour MCP\n\n1. Call get_workflow_guide first to pick the right tool\n2. Use the wait_for_* tools instead of polling project status yourself\n3. Check credits with get_account_info before long video jobs\n4. Only swap faces or voices of people who consented\n\n## Questions\n\n### Which is better for AI agents, fal video models or Magic Hour MCP?\n\nfal video models scores 71 (BB) on agent readiness against Magic Hour MCP's 50.7 (D), and leads in every scored category.\n\n### Can an agent call fal video models and Magic Hour MCP without installing anything?\n\nYes. fal video models has a hosted endpoint at https://queue.fal.run and Magic Hour MCP at https://mcp.magichour.ai/.\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/fal-video-vs-magic-hour-mcp.json, and with the fewest tokens: https://www.anchorterminal.com/compare/fal-video-vs-magic-hour-mcp.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"fal-video\", \"b\": \"magic-hour-mcp\"}`. From a terminal: `anchor compare fal-video magic-hour-mcp`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/fal-video.json and https://www.anchorterminal.com/api/v1/tools/magic-hour-mcp.json\n\n## Other comparisons with fal video models or Magic Hour MCP\n\n- [Alibaba Wan (Model Studio) vs fal video models](https://www.anchorterminal.com/compare/alibaba-wan-vs-fal-video.md)\n- [Alibaba Wan (Model Studio) vs Magic Hour MCP](https://www.anchorterminal.com/compare/alibaba-wan-vs-magic-hour-mcp.md)\n- [fal video models vs framefields](https://www.anchorterminal.com/compare/fal-video-vs-framefields.md)\n- [fal video models vs Google Veo](https://www.anchorterminal.com/compare/fal-video-vs-google-veo.md)\n- [fal video models vs Higgsfield API](https://www.anchorterminal.com/compare/fal-video-vs-higgsfield.md)\n- [fal video models vs HyperFrames](https://www.anchorterminal.com/compare/fal-video-vs-hyperframes.md)\n- [fal video models vs Kling AI API](https://www.anchorterminal.com/compare/fal-video-vs-kling.md)\n- [fal video models vs Luma AI API](https://www.anchorterminal.com/compare/fal-video-vs-luma.md)\n- [fal video models vs MiniMax Video API](https://www.anchorterminal.com/compare/fal-video-vs-minimax-video.md)\n- [fal video models vs OpenAI Sora API](https://www.anchorterminal.com/compare/fal-video-vs-openai-sora.md)\n- [fal video models vs Pika API](https://www.anchorterminal.com/compare/fal-video-vs-pika.md)\n- [fal video models vs PixVerse API](https://www.anchorterminal.com/compare/fal-video-vs-pixverse.md)\n- [fal video models vs Popcraft MCP](https://www.anchorterminal.com/compare/fal-video-vs-popcraft-mcp.md)\n- [fal video models vs Replicate video models](https://www.anchorterminal.com/compare/fal-video-vs-replicate-video.md)\n- [fal video models vs Runway API](https://www.anchorterminal.com/compare/fal-video-vs-runway.md)\n- [fal video models vs Seedance on BytePlus ModelArk](https://www.anchorterminal.com/compare/fal-video-vs-seedance-on-byteplus-modelark.md)\n- [fal video models vs Vidu API](https://www.anchorterminal.com/compare/fal-video-vs-vidu.md)\n- [framefields vs Magic Hour MCP](https://www.anchorterminal.com/compare/framefields-vs-magic-hour-mcp.md)\n- [Google Veo vs Magic Hour MCP](https://www.anchorterminal.com/compare/google-veo-vs-magic-hour-mcp.md)\n- [Higgsfield API vs Magic Hour MCP](https://www.anchorterminal.com/compare/higgsfield-vs-magic-hour-mcp.md)\n- [HyperFrames vs Magic Hour MCP](https://www.anchorterminal.com/compare/hyperframes-vs-magic-hour-mcp.md)\n- [Kling AI API vs Magic Hour MCP](https://www.anchorterminal.com/compare/kling-vs-magic-hour-mcp.md)\n- [Luma AI API vs Magic Hour MCP](https://www.anchorterminal.com/compare/luma-vs-magic-hour-mcp.md)\n- [Magic Hour MCP vs MiniMax Video API](https://www.anchorterminal.com/compare/magic-hour-mcp-vs-minimax-video.md)\n- [Magic Hour MCP vs OpenAI Sora API](https://www.anchorterminal.com/compare/magic-hour-mcp-vs-openai-sora.md)\n- [Magic Hour MCP vs Pika API](https://www.anchorterminal.com/compare/magic-hour-mcp-vs-pika.md)\n- [Magic Hour MCP vs PixVerse API](https://www.anchorterminal.com/compare/magic-hour-mcp-vs-pixverse.md)\n- [Magic Hour MCP vs Popcraft MCP](https://www.anchorterminal.com/compare/magic-hour-mcp-vs-popcraft-mcp.md)\n- [Magic Hour MCP vs Replicate video models](https://www.anchorterminal.com/compare/magic-hour-mcp-vs-replicate-video.md)\n- [Magic Hour MCP vs Runway API](https://www.anchorterminal.com/compare/magic-hour-mcp-vs-runway.md)\n- [Magic Hour MCP vs Seedance on BytePlus ModelArk](https://www.anchorterminal.com/compare/magic-hour-mcp-vs-seedance-on-byteplus-modelark.md)\n- [Magic Hour MCP vs Vidu API](https://www.anchorterminal.com/compare/magic-hour-mcp-vs-vidu.md)\n- [Clueso vs fal video models](https://www.anchorterminal.com/compare/clueso-video-vs-fal-video.md)\n- [Clueso vs Magic Hour MCP](https://www.anchorterminal.com/compare/clueso-video-vs-magic-hour-mcp.md)\n- [fal video models vs sync. labs MCP server](https://www.anchorterminal.com/compare/fal-video-vs-sync-labs-mcp.md)\n- [Magic Hour MCP vs sync. labs MCP server](https://www.anchorterminal.com/compare/magic-hour-mcp-vs-sync-labs-mcp.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": "2026-11-08",
    "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": "fal video models vs Magic Hour MCP",
        "url": ""
      }
    ],
    "description": "fal video models scores 71 (BB) to Magic Hour MCP's 50.7 (D) for video generation. Prices, MCP, x402, uptime and agent notes side by side.",
    "facts": [
      "fal video models BB 71",
      "Magic Hour MCP D 50.7",
      "scores"
    ],
    "h1": "fal video models vs Magic Hour MCP",
    "image": "https://www.anchorterminal.com/assets/og/default.png",
    "path": "/compare/fal-video-vs-magic-hour-mcp",
    "published": "2026-10-01",
    "section": "tools",
    "title": "fal video models vs Magic Hour MCP for AI agents (2026)",
    "toc": null,
    "updated": "2026-11-07",
    "url": "https://www.anchorterminal.com/compare/fal-video-vs-magic-hour-mcp"
  },
  "tokens": {
    "markdown": 5200,
    "slim": 3030
  },
  "version": 1
}