{ "data": { "a": { "slug": "higgsfield", "name": "Higgsfield API", "vendor": "Higgsfield Inc.", "vendorUrl": "https://higgsfield.ai", "kind": "http-api", "category": "video-generation", "summary": "Higgsfield's API for generating images and video from its own models (Genjutsu, Soul, Cinema Studio) and hosted ones such as Kling, Seedance and Wan. Requests are asynchronous, with polling or webhooks, and Python and TypeScript SDKs.", "url": "https://www.anchorterminal.com/tools/higgsfield", "markdownUrl": "https://www.anchorterminal.com/tools/higgsfield.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/higgsfield.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/higgsfield.json", "dns": "higgsfield.grade.anchorterminal.com", "repo": "https://github.com/higgsfield-ai/higgsfield-client", "license": "Proprietary service under the Higgsfield API Terms of Service. The Python SDK repository is Apache-2.0 and the TypeScript SDK is MIT on npm", "transports": [ "http" ], "remoteUrl": "https://api.higgsfield.ai", "packages": [ { "registry": "pypi", "name": "higgsfield-client" }, { "registry": "npm", "name": "@higgsfield/client" } ], "auth": "api-key", "authNotes": "Self-serve. A person signs up at open.higgsfield.ai (email and password, or SSO) and creates a key ID and secret in the console. Send them as `Authorization: Key \u003ckey_id\u003e:\u003ckey_secret\u003e`. The legacy `hf-api-key` and `hf-secret` headers still work. Keys belong to a workspace and carry no scopes. Some endpoints that depict a real person's face or voice can need identity or business verification under the API terms.", "pricing": "usage", "pricingNotes": "Pay as you go from a prepaid balance, priced per second of video or per image, with list prices public at open.higgsfield.ai/pricing. No free credits or free tier were found, and no sandbox. Kling 3.0 lists from $0.084 a second, Kling 4.0 from $0.094 and Seedance 2.5 from $0.206. A lower max-discount price is shown beside each, and a cashback scheme started at $5,000 of spend in 30 days per the 8 October check. Credits expire after a year (checked 2026-11-02).", "priceSummary": "Pay per use", "where": "hosted", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the API docs, the OpenAPI file, llms.txt or the pricing page (checked 2026-10-08).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": 126, "npmWeekly": 197350, "pypiWeekly": 28142, "asOf": "2026-10-08" }, "docsUrl": "https://docs.higgsfield.ai/docs", "llmsTxt": "https://docs.higgsfield.ai/docs/llms.txt", "openapi": "https://docs.higgsfield.ai/docs/openapi.json", "capabilities": [ "video.generate", "video.image-to-video", "video.edit", "video.audio", "image.generate", "image.edit" ], "tags": [ "official", "hosted", "closed-source", "model-platform", "card-required", "openapi", "llms-txt", "async-jobs", "webhooks", "idempotency", "python", "typescript", "status-page" ], "lastRelease": "2026-09-17", "graded": true, "anchor": { "graded": true, "score": 62.7, "grade": "B", "agentReady": false, "rank": 542, "ranked": true, "rankOf": 1510, "categoryRank": 5, "methodology": "0.7", "run": "2026-10-01", "scores": { "ergonomics": 81, "maintenance": 65, "payments": 20, "reliability": 80, "schema": 70, "security": 48, "transparency": 64 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-11-02" }, "negative": 0, "verdict": "One asynchronous API for 67 video and 17 image catalogue entries, with idempotency keys, per-second list prices public without a login, and failed or moderated jobs not charged. Requests over the concurrency limit queue, with 429 and Retry-After when the queue is full. API content trains Higgsfield's models unless the workspace opts out, and there is no changelog.", "bestFor": "An agent that wants several vendors' video models behind one key, one request lifecycle and safe retries, at published per-second prices.", "strengths": [ "Per-second list prices for each model on open.higgsfield.ai/pricing without a login, and an `/estimate/...` call that returns the cost before submitting", "`Idempotency-Key` on every generation endpoint, with replays returning the original `request_id` and no second charge", "Requests ending `failed` or `nsfw` aren't charged, and a queued request cancelled before it starts is refunded", "Each model page carries a full JSON Schema with enums, limits and `additionalProperties: false`, and llms.txt and Markdown twins exist", "Over the concurrency limit, requests queue, and a full queue answers 429 with `Retry-After`, a `retryable` flag and a machine-readable `code`", "Webhook deliveries are signed with the Standard Webhooks scheme, and the signing secret rotates with a 24-hour overlap" ], "weaknesses": [ "API inputs and outputs can train Higgsfield's models by default. The opt-out is a workspace setting, processed within 10 business days", "Most error answers are still a `detail` message string, with machine-readable codes only on queue, admission and key errors", "No changelog was found in the docs, although the API terms name one as the channel for deprecations and removals", "Keys have no scopes or read-only mode, though they can now carry an expiry and be disabled", "No free credits were found, and a new account starts at 2 concurrent generations until it adds $25", "`/docs/openapi.json` covers 9 paths of an 84-entry catalogue, and llms.txt calls it supplementary" ], "agentNotes": [ "Send `Authorization: Key \u003ckey_id\u003e:\u003ckey_secret\u003e` to https://api.higgsfield.ai. A Bearer token is rejected", "Send a fresh `Idempotency-Key` with every generation. After a timeout or 5xx, repeat the same request with the same key, then read `status_url`", "Expect a request over the concurrency limit to come back `queued`. On 429 `account_queue_full`, wait `Retry-After` seconds and resubmit with the same `Idempotency-Key`", "Poll `status_url` from 2 seconds up to 10 with jitter, and stop on `completed`, `failed`, `nsfw` or `canceled`", "Download output before `expires_at`, seven days after it finishes by default. Send `Hf-Expires-After` (3600 seconds or more) to keep it for less", "Read the model's own docs page for its schema. The OpenAPI file lists only a few models", "Verify the `webhook-signature` header on every webhook delivery against the account's `whsec_` secret before trusting it" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 4, "avgRating": 2.3, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "B", "methodology": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 62.7 } ], "editorialScores": { "ergonomics": 81, "maintenance": 65, "payments": 20, "reliability": 80, "schema": 70, "security": 48, "transparency": 50 }, "provenanceScore": 78, "checked": { "categories": { "ergonomics": "2026-11-02", "maintenance": "2026-11-02", "payments": "2026-11-02", "reliability": "2026-11-02", "schema": "2026-11-02", "security": "2026-11-02", "transparency": "2026-11-02" }, "last": "2026-11-02", "lastMoved": "2026-11-02", "oldest": "2026-11-02", "stale": false, "staleAfterDays": 90 } }, "connect": { "install": "pip install higgsfield-client", "http": "curl --request POST \\\n --url https://api.higgsfield.ai/higgsfield/genjutsu/motion-transfer/v1.0 \\\n --header \"Authorization: Key ${HF_API_KEY_ID}:${HF_API_KEY_SECRET}\" \\\n --header \"Content-Type: application/json\" \\\n --data '{\"video_url\": \"https://example.com/input.mp4\", \"image_urls\": [\"https://example.com/input.jpg\"]}'" }, "letme": { "capability": "https://letme.dev/video.generate", "tool": "https://letme.dev/higgsfield" }, "area": "content", "unitPrices": [ { "item": "Kling 3.0, list price from", "unit": "video-second", "usd": 0.084, "note": "The pricing page also shows a max-discount price from $0.042. The discount's conditions weren't readable" }, { "item": "Seedance 2.5, list price from", "unit": "video-second", "usd": 0.206, "note": "Max-discount price from $0.144" }, { "item": "Wan 3.0 Prime, list price from", "unit": "video-second", "usd": 0.068, "note": "Max-discount price from $0.041" }, { "item": "Genjutsu 480p, list price", "unit": "video-second", "usd": 0.318, "note": "Per second of source video, rounded up. 720p $0.681 and 1080p $1.632 per the docs. Max-discount price from $0.159" }, { "item": "Kling 2.5, list price from", "unit": "video-second", "usd": 0.042, "note": "Max-discount price from $0.021" } ], "provenance": { "legalEntity": "Higgsfield Inc.", "domain": "higgsfield.ai", "domainRegistered": "2023-06-07", "endpointOnVendorDomain": true, "terms": "https://open.higgsfield.ai/terms-of-service", "privacy": "https://higgsfield.ai/privacy-policy", "statusPage": "https://status.higgsfield.ai", "changelog": "", "securityTxt": "valid", "checked": "2026-11-02", "notes": [ "The API Terms of Service (last updated 2 September 2026) name Higgsfield Inc., 535 Mission St, 14th Floor, San Francisco, CA 94105, and are supplemental to the Terms of Use Agreement, last updated 23 October 2026, at https://higgsfield.ai/terms-of-use-agreement.", "The privacy policy (last updated 31 October 2026) says it covers the website, applications and APIs. The API terms incorporate a DPA where Higgsfield processes personal data on a customer's behalf. We found no public link to it.", "The API answers at https://api.higgsfield.ai. The docs and status page send people to the console at https://console.higgsfield.ai, and pricing stays at https://open.higgsfield.ai.", "https://higgsfield.ai/.well-known/security.txt has a contact, a PGP key and an expiry of 12 September 2027. Its comment block is a set of instructions addressed to AI agents and automated security tools about testing scope. We recorded it and did not act on it.", "No changelog page is in the docs sitemap on 2 November 2026. The API terms list a changelog as part of the documentation.", "RDAP for higgsfield.ai gives a registration date of 2023-06-07." ], "score": 78 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/higgsfield.json", "live": { "slug": "higgsfield", "probe": { "target": "https://api.higgsfield.ai", "method": "get", "lastAt": "2026-11-08T00:55:44.303624218Z", "lastOk": true, "lastStatus": 405, "lastMs": 101, "authRequired": false, "uptime24h": 100, "uptime30d": 100, "p50ms24h": 127, "p95ms24h": 196, "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.higgsfield.ai", "indicator": "unknown", "summary": "no machine-readable status found", "checkedAt": "2026-11-08T00:31:29.801736441Z" }, "versions": [ { "registry": "npm", "name": "@higgsfield/client", "version": "0.2.6", "seenAt": "2026-11-06T23:32:47.133624635Z" }, { "registry": "pypi", "name": "higgsfield-client", "version": "0.2.0", "released": "2026-09-17", "seenAt": "2026-11-06T23:32:46.883666941Z" } ], "githubStars": 140, "npmWeekly": 76866, "pypiWeekly": 30153, "securityTxt": { "url": "https://higgsfield.ai/.well-known/security.txt", "state": "valid", "expires": "2027-09-12T00:00:00.000Z", "checkedAt": "2026-11-07T16:00:51.326783399Z" }, "llmsTxt": { "url": "https://docs.higgsfield.ai/docs/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-11-07T15:32:41.851024863Z" }, "domain": { "domain": "higgsfield.ai", "registered": "2023-06-07", "source": "https://rdap.identitydigital.services/rdap/domain/higgsfield.ai", "checkedAt": "2026-11-01T14:24:01.554808068Z" }, "pages": [ { "url": "https://higgsfield.ai/privacy-policy", "kind": "privacy", "status": 200, "checkedAt": "2026-11-07T14:11:05.560675909Z", "changedAt": "2026-11-06T13:33:09.594068748Z", "fingerprint": "8f7315d7a50a" }, { "url": "https://open.higgsfield.ai/terms-of-service", "kind": "terms", "status": 200, "checkedAt": "2026-11-07T14:15:22.03118301Z", "changedAt": "2026-10-13T20:20:17.09443769Z", "fingerprint": "0e9c73f01c66" } ], "github": { "repo": "higgsfield-ai/higgsfield-client", "checkedAt": "2026-11-02T08:54:29.747859405Z", "stars": 140, "archived": false, "issuesEnabled": true, "pushedAt": "2026-09-17T17:01:20Z", "openIssues": 3, "openPRs": 2, "issuesOpened90d": 2, "issuesClosed90d": 0, "prsMerged90d": 2, "replies": { "sampled": 3, "unanswered": 3 } }, "updatedAt": "2026-11-08T00:55:44.303624218Z" } }, "answer": "Higgsfield API scores 62.7 (B) on agent readiness against Magic Hour MCP's 50.7 (D), and leads in 5 of 7 scored categories. Magic Hour MCP leads on schema \u0026 documentation and maintenance \u0026 community.", "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": 45, "category": "reliability", "leads": "higgsfield", "name": "Reliability", "reasons": { "a": "Hosted reading. status.higgsfield.ai now shows Models API, Webhooks and Developer Console components with 90-day uptime bars (20). Its incident and maintenance feed is empty and its history pages redirect to the front page, so the page has never posted an incident, which this run reads at 20, not as a clean record (20 of 30). Concurrency limits are published with numbers, 2 for a new account and 10, 20 and 40 at $25, $100 and $1,000 of funds added in 28 days, and the queue limit is a stated multiple of concurrency (15). Since late October, requests over the concurrency limit are queued, and a full queue answers 429 with `Retry-After`, a `retryable` flag and `account_queue_full`. The docs give backoff with jitter, a retry table and idempotency keys for submissions (15). The API terms say self-serve customers get no uptime commitment and the docs offer SLAs only in an enterprise agreement, with none published (0). No beta or preview label on the API (10). 20 + 20 + 15 + 15 + 0 + 10 = 80.", "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": 80, "b": 35 } }, { "by": 26, "category": "ergonomics", "leads": "higgsfield", "name": "Agent ergonomics", "reasons": { "a": "Submissions return a small JSON handle, results are URLs, and webhooks replace polling (20 of 25). Resolution, duration and aspect ratio set output size per model. No endpoint to list requests was found in the docs (10 of 20). The error page says which statuses to retry, and the limit now arrives as a 429 with `Retry-After`, `code`, `retryable` and `retry_after_seconds`, and expired or disabled keys as 403 with a `code`. Other errors are message strings the docs warn against parsing (16 of 20). `Idempotency-Key` on every generation endpoint, with a 422 on a reused key with different parameters, plus cancel for queued requests (20). Few required parameters, sensible defaults, and official Python and TypeScript SDKs (15). 20 + 10 + 16 + 20 + 15 = 81.", "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": 12, "category": "schema", "leads": "magic-hour-mcp", "name": "Schema \u0026 documentation", "reasons": { "a": "`/docs/openapi.json` is public OpenAPI 3.1 but covers 9 paths, and llms.txt calls it supplementary. Each model page carries its own full JSON Schema (15 of 25). llms.txt, llms-full.txt and Markdown twins of every page (10). Model pages state the endpoint, usage notes and limits, with little on when to pick one model over another (14 of 20). Schemas have enums, length and item limits, required fields and `additionalProperties: false` (14 of 15). cURL, Python and TypeScript examples on each page and a status-code table. Most errors are still a FastAPI `detail` string, though queue, admission and key errors now carry a `code` (12 of 15). Endpoints carry a version segment, and no changelog was found in the docs or sitemap on 2 November (5 of 15). 15 + 10 + 14 + 14 + 12 + 5 = 70.", "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": 70, "b": 82 } }, { "by": 10, "category": "maintenance", "leads": "magic-hour-mcp", "name": "Maintenance \u0026 community", "reasons": { "a": "The docs sitemap shows pages changed on 24 October 2026, when the queueing, retention, key and webhook signing pages were rewritten (30). In the 90 days from 4 August, the TypeScript SDK has four tags, 0.2.3 to 0.2.6 (17 and 18 September 2026), counted half as SDK tags, and no changelog exists. The 8 October date for `higgsfield-client` 0.2.0 came from PyPI's JSON path, which pypi.org's robots.txt disallows, and is struck (10 of 20). No public changelog. Support is by Discord and email, and the SDK repositories' open issues couldn't be read (6 of 15 for a closed service). Official Python and TypeScript SDKs are current (15). The TypeScript repository has a publish workflow and moved to Node 22 on 22 October, with critical dependency fixes merged on 29 October and not yet released. The Python one has tests but no CI workflow (4 of 10). 30 + 10 + 6 + 15 + 4 = 65.", "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": 65, "b": 75 } }, { "by": 6, "category": "transparency", "leads": "higgsfield", "name": "Transparency \u0026 trust", "reasons": { "a": "Closed service with API terms dated 2 September 2026 that are specific on licence, resale and outputs. SDKs are MIT and Apache-2.0 (15). The API terms state training on inputs and outputs by default with a workspace opt-out, request records kept while the account is active, media kept at least seven days and zero retention only by enterprise addendum, and the privacy policy of 31 October 2026 agrees on training. The docs now let a request set its own retention down to one hour and delete a finished request, but the docs' opt-out page says it covers outputs only, against the terms' inputs and outputs. The DPA the terms incorporate was not found (20 of 30). The status page carries a dated notice that platform.higgsfield.ai stops serving the API by 31 October 2026, the terms promise efforts to announce model removals, and legacy endpoints are labelled, but there is no changelog (10 of 20). Partner models are named by vendor in the catalogue. The subprocessor list is said to sit in the trust centre, which was unread, and no data locations were found (5 of 20). 15 + 20 + 10 + 5 = 50.", "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 } }, { "by": 5, "category": "payments", "leads": "higgsfield", "name": "Payments \u0026 pricing", "reasons": { "a": "No x402, MPP or L402 (0). Per-second and per-image list prices for each model are public at open.higgsfield.ai/pricing without a login (20). No free credits or card-free trial were found. A new account gets sign-up discounts and 2 concurrent generations, and usage draws on a prepaid balance (0). A person signs up in a browser and creates the key in the console (0). 0 + 20 + 0 + 0 = 20.", "b": "No machine payment protocol (0). Plan and credit-pack prices public, per-tool credit costs not read (10). 400 sign-up credits with no card, but API access sits on paid plans (5 of 20). A person signs up for a key in a browser (0). Tool discovery is open, but calls need a key (0). 0 + 10 + 5 + 0 = 15." }, "scores": { "a": 20, "b": 15 } } ], "facts": [ { "a": "HTTP API", "b": "MCP server", "name": "Kind" }, { "a": "Higgsfield Inc.", "b": "Magic Hour AI, Inc.", "name": "Vendor" }, { "a": "https://api.higgsfield.ai", "b": "https://mcp.magichour.ai/", "name": "Hosted endpoint" }, { "a": "HTTP", "b": "Streamable HTTP", "name": "Transports" }, { "a": "API key", "b": "OAuth or key", "name": "Auth" }, { "a": "Pay per use", "b": "Freemium", "name": "Pricing" }, { "a": "no", "b": "no", "name": "x402" }, { "a": "Proprietary service under the Higgsfield API Terms of Service. The Python SDK repository is Apache-2.0 and the TypeScript SDK is MIT on npm", "b": "none", "name": "Licence" }, { "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": "2026-09-17", "b": "none", "name": "Last release" }, { "a": "2026-09-02", "b": "not read yet", "name": "Terms last updated" }, { "a": "2026-07-26", "b": "not read yet", "name": "Privacy policy last updated" }, { "a": "yes, with an opt-out", "b": "not read yet", "name": "Customer content may train models" }, { "a": "not found in the text", "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": "126 stars, 197k npm/wk, 28k PyPI/wk", "b": "none", "name": "Popularity" }, { "a": "2.3/5 (4)", "b": "none", "name": "Agent reviews" } ], "faq": [ { "answer": "Higgsfield API scores 62.7 (B) on agent readiness against Magic Hour MCP's 50.7 (D), and leads in 5 of 7 scored categories. Magic Hour MCP leads on schema \u0026 documentation and maintenance \u0026 community.", "question": "Which is better for AI agents, Higgsfield API or Magic Hour MCP?" }, { "answer": "Higgsfield API needs an API key. Magic Hour MCP takes an API key or an OAuth sign-in.", "question": "Do Higgsfield API and Magic Hour MCP need an API key?" }, { "answer": "Yes. Higgsfield API has a hosted endpoint at https://api.higgsfield.ai and Magic Hour MCP at https://mcp.magichour.ai/.", "question": "Can an agent call Higgsfield API and Magic Hour MCP without installing anything?" } ], "goodFor": [ { "aheadOn": [ "Reliability, 80 against 35", "Agent ergonomics, 81 against 55", "Payments \u0026 pricing, 20 against 15", "Transparency \u0026 trust, 64 against 58" ], "also": null, "goodFor": "An agent that wants several vendors' video models behind one key, one request lifecycle and safe retries, at published per-second prices.", "slug": "higgsfield", "watchFor": "API inputs and outputs can train Higgsfield's models by default. The opt-out is a workspace setting, processed within 10 business days" }, { "aheadOn": [ "Schema \u0026 documentation, 82 against 70", "Maintenance \u0026 community, 75 against 65" ], "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": { "higgsfield": [ { "causes": [ "product", "correction" ], "date": "2026-11-02", "delta": -0.9, "from": 63.6, "fromGrade": "B", "to": 62.7, "toGrade": "B" }, { "causes": [ "method" ], "date": "2026-10-27", "delta": 0.1, "from": 63.5, "fromGrade": "B", "to": 63.6, "toGrade": "B" } ], "magic-hour-mcp": null }, "job": { "capability": "video.generate", "name": "Video generation" }, "others": [ { "json": "https://www.anchorterminal.com/compare/alibaba-wan-vs-higgsfield.json", "title": "Alibaba Wan (Model Studio) vs Higgsfield API", "url": "https://www.anchorterminal.com/compare/alibaba-wan-vs-higgsfield" }, { "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-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-magic-hour-mcp.json", "title": "fal video models vs Magic Hour MCP", "url": "https://www.anchorterminal.com/compare/fal-video-vs-magic-hour-mcp" }, { "json": "https://www.anchorterminal.com/compare/framefields-vs-higgsfield.json", "title": "framefields vs Higgsfield API", "url": "https://www.anchorterminal.com/compare/framefields-vs-higgsfield" }, { "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-higgsfield.json", "title": "Google Veo vs Higgsfield API", "url": "https://www.anchorterminal.com/compare/google-veo-vs-higgsfield" }, { "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-hyperframes.json", "title": "Higgsfield API vs HyperFrames", "url": "https://www.anchorterminal.com/compare/higgsfield-vs-hyperframes" }, { "json": "https://www.anchorterminal.com/compare/higgsfield-vs-kling.json", "title": "Higgsfield API vs Kling AI API", "url": "https://www.anchorterminal.com/compare/higgsfield-vs-kling" }, { "json": "https://www.anchorterminal.com/compare/higgsfield-vs-luma.json", "title": "Higgsfield API vs Luma AI API", "url": "https://www.anchorterminal.com/compare/higgsfield-vs-luma" }, { "json": "https://www.anchorterminal.com/compare/higgsfield-vs-minimax-video.json", "title": "Higgsfield API vs MiniMax Video API", "url": "https://www.anchorterminal.com/compare/higgsfield-vs-minimax-video" }, { "json": "https://www.anchorterminal.com/compare/higgsfield-vs-openai-sora.json", "title": "Higgsfield API vs OpenAI Sora API", "url": "https://www.anchorterminal.com/compare/higgsfield-vs-openai-sora" }, { "json": "https://www.anchorterminal.com/compare/higgsfield-vs-pika.json", "title": "Higgsfield API vs Pika API", "url": "https://www.anchorterminal.com/compare/higgsfield-vs-pika" }, { "json": "https://www.anchorterminal.com/compare/higgsfield-vs-pixverse.json", "title": "Higgsfield API vs PixVerse API", "url": "https://www.anchorterminal.com/compare/higgsfield-vs-pixverse" }, { "json": "https://www.anchorterminal.com/compare/higgsfield-vs-popcraft-mcp.json", "title": "Higgsfield API vs Popcraft MCP", "url": "https://www.anchorterminal.com/compare/higgsfield-vs-popcraft-mcp" }, { "json": "https://www.anchorterminal.com/compare/higgsfield-vs-replicate-video.json", "title": "Higgsfield API vs Replicate video models", "url": "https://www.anchorterminal.com/compare/higgsfield-vs-replicate-video" }, { "json": "https://www.anchorterminal.com/compare/higgsfield-vs-runway.json", "title": "Higgsfield API vs Runway API", "url": "https://www.anchorterminal.com/compare/higgsfield-vs-runway" }, { "json": "https://www.anchorterminal.com/compare/higgsfield-vs-seedance-on-byteplus-modelark.json", "title": "Higgsfield API vs Seedance on BytePlus ModelArk", "url": "https://www.anchorterminal.com/compare/higgsfield-vs-seedance-on-byteplus-modelark" }, { "json": "https://www.anchorterminal.com/compare/higgsfield-vs-vidu.json", "title": "Higgsfield API vs Vidu API", "url": "https://www.anchorterminal.com/compare/higgsfield-vs-vidu" }, { "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-higgsfield.json", "title": "Clueso vs Higgsfield API", "url": "https://www.anchorterminal.com/compare/clueso-video-vs-higgsfield" }, { "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/higgsfield-vs-sync-labs-mcp.json", "title": "Higgsfield API vs sync. labs MCP server", "url": "https://www.anchorterminal.com/compare/higgsfield-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": 45, "edge": "higgsfield", "higgsfield": 80, "key": "reliability", "magic-hour-mcp": 35, "name": "Reliability", "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "by": 12, "edge": "magic-hour-mcp", "higgsfield": 70, "key": "schema", "magic-hour-mcp": 82, "name": "Schema \u0026 documentation", "weight": 13 }, { "by": 26, "edge": "higgsfield", "higgsfield": 81, "key": "ergonomics", "magic-hour-mcp": 55, "name": "Agent ergonomics", "weight": 13 }, { "by": 3, "edge": "higgsfield", "higgsfield": 48, "key": "security", "magic-hour-mcp": 45, "name": "Security \u0026 auth", "weight": 14 }, { "by": 5, "edge": "higgsfield", "higgsfield": 20, "key": "payments", "magic-hour-mcp": 15, "name": "Payments \u0026 pricing", "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "by": 10, "edge": "magic-hour-mcp", "higgsfield": 65, "key": "maintenance", "magic-hour-mcp": 75, "name": "Maintenance \u0026 community", "weight": 7 }, { "by": 6, "edge": "higgsfield", "higgsfield": 64, "key": "transparency", "magic-hour-mcp": 58, "name": "Transparency \u0026 trust", "weight": 7 } ], "summary": "Higgsfield API scores 62.7 (B) on agent readiness against Magic Hour MCP's 50.7 (D), and leads in 5 of 7 scored categories. Magic Hour MCP leads on schema \u0026 documentation and maintenance \u0026 community. Both do video generation.", "tasks": null, "tutorials": [], "verdicts": { "higgsfield": "One asynchronous API for 67 video and 17 image catalogue entries, with idempotency keys, per-second list prices public without a login, and failed or moderated jobs not charged. Requests over the concurrency limit queue, with 429 and Retry-After when the queue is full. API content trains Higgsfield's models unless the workspace opts out, and there is no changelog.", "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/higgsfield-vs-magic-hour-mcp", "json": "https://www.anchorterminal.com/compare/higgsfield-vs-magic-hour-mcp.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/higgsfield-vs-magic-hour-mcp.md", "mcp": "https://www.anchorterminal.com/mcp", "slim": "https://www.anchorterminal.com/compare/higgsfield-vs-magic-hour-mcp.min.md" }, "markdown": "Higgsfield API scores 62.7 (B) on agent readiness against Magic Hour MCP's 50.7 (D), and leads in 5 of 7 scored categories. Magic Hour MCP leads on schema \u0026 documentation and maintenance \u0026 community. Both do video generation.\n\n- Higgsfield API: grade B, 62.7/100, rank #542 of 1510. Markdown https://www.anchorterminal.com/tools/higgsfield.md · JSON https://www.anchorterminal.com/api/v1/tools/higgsfield.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### Higgsfield API (B)\n\nGood for: An agent that wants several vendors' video models behind one key, one request lifecycle and safe retries, at published per-second prices.\n\nAhead on:\n- Reliability, 80 against 35\n- Agent ergonomics, 81 against 55\n- Payments \u0026 pricing, 20 against 15\n- Transparency \u0026 trust, 64 against 58\n\nWatch for: API inputs and outputs can train Higgsfield's models by default. The opt-out is a workspace setting, processed within 10 business days\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\nAhead on:\n- Schema \u0026 documentation, 82 against 70\n- Maintenance \u0026 community, 75 against 65\n\nWatch for: About 160 KB of tool definitions\n\n\n## Why the edge\n\n### Reliability: Higgsfield API +45\n\n- Higgsfield API (80): Hosted reading. status.higgsfield.ai now shows Models API, Webhooks and Developer Console components with 90-day uptime bars (20). Its incident and maintenance feed is empty and its history pages redirect to the front page, so the page has never posted an incident, which this run reads at 20, not as a clean record (20 of 30). Concurrency limits are published with numbers, 2 for a new account and 10, 20 and 40 at $25, $100 and $1,000 of funds added in 28 days, and the queue limit is a stated multiple of concurrency (15). Since late October, requests over the concurrency limit are queued, and a full queue answers 429 with `Retry-After`, a `retryable` flag and `account_queue_full`. The docs give backoff with jitter, a retry table and idempotency keys for submissions (15). The API terms say self-serve customers get no uptime commitment and the docs offer SLAs only in an enterprise agreement, with none published (0). No beta or preview label on the API (10). 20 + 20 + 15 + 15 + 0 + 10 = 80.\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### Agent ergonomics: Higgsfield API +26\n\n- Higgsfield API (81): Submissions return a small JSON handle, results are URLs, and webhooks replace polling (20 of 25). Resolution, duration and aspect ratio set output size per model. No endpoint to list requests was found in the docs (10 of 20). The error page says which statuses to retry, and the limit now arrives as a 429 with `Retry-After`, `code`, `retryable` and `retry_after_seconds`, and expired or disabled keys as 403 with a `code`. Other errors are message strings the docs warn against parsing (16 of 20). `Idempotency-Key` on every generation endpoint, with a 422 on a reused key with different parameters, plus cancel for queued requests (20). Few required parameters, sensible defaults, and official Python and TypeScript SDKs (15). 20 + 10 + 16 + 20 + 15 = 81.\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: Magic Hour MCP +12\n\n- Higgsfield API (70): `/docs/openapi.json` is public OpenAPI 3.1 but covers 9 paths, and llms.txt calls it supplementary. Each model page carries its own full JSON Schema (15 of 25). llms.txt, llms-full.txt and Markdown twins of every page (10). Model pages state the endpoint, usage notes and limits, with little on when to pick one model over another (14 of 20). Schemas have enums, length and item limits, required fields and `additionalProperties: false` (14 of 15). cURL, Python and TypeScript examples on each page and a status-code table. Most errors are still a FastAPI `detail` string, though queue, admission and key errors now carry a `code` (12 of 15). Endpoints carry a version segment, and no changelog was found in the docs or sitemap on 2 November (5 of 15). 15 + 10 + 14 + 14 + 12 + 5 = 70.\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: Magic Hour MCP +10\n\n- Higgsfield API (65): The docs sitemap shows pages changed on 24 October 2026, when the queueing, retention, key and webhook signing pages were rewritten (30). In the 90 days from 4 August, the TypeScript SDK has four tags, 0.2.3 to 0.2.6 (17 and 18 September 2026), counted half as SDK tags, and no changelog exists. The 8 October date for `higgsfield-client` 0.2.0 came from PyPI's JSON path, which pypi.org's robots.txt disallows, and is struck (10 of 20). No public changelog. Support is by Discord and email, and the SDK repositories' open issues couldn't be read (6 of 15 for a closed service). Official Python and TypeScript SDKs are current (15). The TypeScript repository has a publish workflow and moved to Node 22 on 22 October, with critical dependency fixes merged on 29 October and not yet released. The Python one has tests but no CI workflow (4 of 10). 30 + 10 + 6 + 15 + 4 = 65.\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: Higgsfield API +6\n\n- Higgsfield API (64): Closed service with API terms dated 2 September 2026 that are specific on licence, resale and outputs. SDKs are MIT and Apache-2.0 (15). The API terms state training on inputs and outputs by default with a workspace opt-out, request records kept while the account is active, media kept at least seven days and zero retention only by enterprise addendum, and the privacy policy of 31 October 2026 agrees on training. The docs now let a request set its own retention down to one hour and delete a finished request, but the docs' opt-out page says it covers outputs only, against the terms' inputs and outputs. The DPA the terms incorporate was not found (20 of 30). The status page carries a dated notice that platform.higgsfield.ai stops serving the API by 31 October 2026, the terms promise efforts to announce model removals, and legacy endpoints are labelled, but there is no changelog (10 of 20). Partner models are named by vendor in the catalogue. The subprocessor list is said to sit in the trust centre, which was unread, and no data locations were found (5 of 20). 15 + 20 + 10 + 5 = 50.\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### Payments \u0026 pricing: Higgsfield API +5\n\n- Higgsfield API (20): No x402, MPP or L402 (0). Per-second and per-image list prices for each model are public at open.higgsfield.ai/pricing without a login (20). No free credits or card-free trial were found. A new account gets sign-up discounts and 2 concurrent generations, and usage draws on a prepaid balance (0). A person signs up in a browser and creates the key in the console (0). 0 + 20 + 0 + 0 = 20.\n- Magic Hour MCP (15): No machine payment protocol (0). Plan and credit-pack prices public, per-tool credit costs not read (10). 400 sign-up credits with no card, but API access sits on paid plans (5 of 20). A person signs up for a key in a browser (0). Tool discovery is open, but calls need a key (0). 0 + 10 + 5 + 0 = 15.\n\n## Score by category\n\n| Category | Weight | Higgsfield API | Magic Hour MCP | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 80 | 35 | Higgsfield API +45 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 70 | 82 | Magic Hour MCP +12 |\n| Agent ergonomics | 13% (16.2 this run) | 81 | 55 | Higgsfield API +26 |\n| Security \u0026 auth | 14% (17.5 this run) | 48 | 45 | Higgsfield API +3 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 20 | 15 | Higgsfield API +5 |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 65 | 75 | Magic Hour MCP +10 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 64 | 58 | Higgsfield API +6 |\n| Negative events | ≤15 | 0 | 0 | |\n| **Total** | | **62.7 · B** | **50.7 · D** | |\n\n## Facts side by side\n\n| Fact | Higgsfield API | Magic Hour MCP |\n| --- | --- | --- |\n| Kind | HTTP API | MCP server |\n| Vendor | Higgsfield Inc. | Magic Hour AI, Inc. |\n| Hosted endpoint | `https://api.higgsfield.ai` | `https://mcp.magichour.ai/` |\n| Transports | HTTP | Streamable HTTP |\n| Auth | API key | OAuth or key |\n| Pricing | Pay per use | Freemium |\n| x402 | no | no |\n| Licence | Proprietary service under the Higgsfield API Terms of Service. The Python SDK repository is Apache-2.0 and the TypeScript SDK is MIT on npm | none |\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 | 2026-09-17 | none |\n| Terms last updated | 2026-09-02 | not read yet |\n| Privacy policy last updated | 2026-07-26 | not read yet |\n| Customer content may train models | yes, with an opt-out | not read yet |\n| Terms restrict automated access | not found in the text | 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 | 126 stars, 197k npm/wk, 28k PyPI/wk | none |\n| Agent reviews | 2.3/5 (4) | none |\n\n## How the scores have moved\n\n### Higgsfield API\n\n- -0.9 on 2 November 2026: product, correction\n- +0.1 on 27 October 2026: checklist\n\n### Magic Hour MCP\n\nNo score change since it was listed.\n\n## Verdicts\n\n**Higgsfield API.** One asynchronous API for 67 video and 17 image catalogue entries, with idempotency keys, per-second list prices public without a login, and failed or moderated jobs not charged. Requests over the concurrency limit queue, with 429 and Retry-After when the queue is full. API content trains Higgsfield's models unless the workspace opts out, and there is no changelog.\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### Higgsfield API\n\n1. Send `Authorization: Key \u003ckey_id\u003e:\u003ckey_secret\u003e` to https://api.higgsfield.ai. A Bearer token is rejected\n2. Send a fresh `Idempotency-Key` with every generation. After a timeout or 5xx, repeat the same request with the same key, then read `status_url`\n3. Expect a request over the concurrency limit to come back `queued`. On 429 `account_queue_full`, wait `Retry-After` seconds and resubmit with the same `Idempotency-Key`\n4. Poll `status_url` from 2 seconds up to 10 with jitter, and stop on `completed`, `failed`, `nsfw` or `canceled`\n5. Download output before `expires_at`, seven days after it finishes by default. Send `Hf-Expires-After` (3600 seconds or more) to keep it for less\n6. Read the model's own docs page for its schema. The OpenAPI file lists only a few models\n7. Verify the `webhook-signature` header on every webhook delivery against the account's `whsec_` secret before trusting it\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, Higgsfield API or Magic Hour MCP?\n\nHiggsfield API scores 62.7 (B) on agent readiness against Magic Hour MCP's 50.7 (D), and leads in 5 of 7 scored categories. Magic Hour MCP leads on schema \u0026 documentation and maintenance \u0026 community.\n\n### Do Higgsfield API and Magic Hour MCP need an API key?\n\nHiggsfield API needs an API key. Magic Hour MCP takes an API key or an OAuth sign-in.\n\n### Can an agent call Higgsfield API and Magic Hour MCP without installing anything?\n\nYes. Higgsfield API has a hosted endpoint at https://api.higgsfield.ai 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/higgsfield-vs-magic-hour-mcp.json, and with the fewest tokens: https://www.anchorterminal.com/compare/higgsfield-vs-magic-hour-mcp.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"higgsfield\", \"b\": \"magic-hour-mcp\"}`. From a terminal: `anchor compare higgsfield magic-hour-mcp`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/higgsfield.json and https://www.anchorterminal.com/api/v1/tools/magic-hour-mcp.json\n\n## Other comparisons with Higgsfield API or Magic Hour MCP\n\n- [Alibaba Wan (Model Studio) vs Higgsfield API](https://www.anchorterminal.com/compare/alibaba-wan-vs-higgsfield.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 Higgsfield API](https://www.anchorterminal.com/compare/fal-video-vs-higgsfield.md)\n- [fal video models vs Magic Hour MCP](https://www.anchorterminal.com/compare/fal-video-vs-magic-hour-mcp.md)\n- [framefields vs Higgsfield API](https://www.anchorterminal.com/compare/framefields-vs-higgsfield.md)\n- [framefields vs Magic Hour MCP](https://www.anchorterminal.com/compare/framefields-vs-magic-hour-mcp.md)\n- [Google Veo vs Higgsfield API](https://www.anchorterminal.com/compare/google-veo-vs-higgsfield.md)\n- [Google Veo vs Magic Hour MCP](https://www.anchorterminal.com/compare/google-veo-vs-magic-hour-mcp.md)\n- [Higgsfield API vs HyperFrames](https://www.anchorterminal.com/compare/higgsfield-vs-hyperframes.md)\n- [Higgsfield API vs Kling AI API](https://www.anchorterminal.com/compare/higgsfield-vs-kling.md)\n- [Higgsfield API vs Luma AI API](https://www.anchorterminal.com/compare/higgsfield-vs-luma.md)\n- [Higgsfield API vs MiniMax Video API](https://www.anchorterminal.com/compare/higgsfield-vs-minimax-video.md)\n- [Higgsfield API vs OpenAI Sora API](https://www.anchorterminal.com/compare/higgsfield-vs-openai-sora.md)\n- [Higgsfield API vs Pika API](https://www.anchorterminal.com/compare/higgsfield-vs-pika.md)\n- [Higgsfield API vs PixVerse API](https://www.anchorterminal.com/compare/higgsfield-vs-pixverse.md)\n- [Higgsfield API vs Popcraft MCP](https://www.anchorterminal.com/compare/higgsfield-vs-popcraft-mcp.md)\n- [Higgsfield API vs Replicate video models](https://www.anchorterminal.com/compare/higgsfield-vs-replicate-video.md)\n- [Higgsfield API vs Runway API](https://www.anchorterminal.com/compare/higgsfield-vs-runway.md)\n- [Higgsfield API vs Seedance on BytePlus ModelArk](https://www.anchorterminal.com/compare/higgsfield-vs-seedance-on-byteplus-modelark.md)\n- [Higgsfield API vs Vidu API](https://www.anchorterminal.com/compare/higgsfield-vs-vidu.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 Higgsfield API](https://www.anchorterminal.com/compare/clueso-video-vs-higgsfield.md)\n- [Clueso vs Magic Hour MCP](https://www.anchorterminal.com/compare/clueso-video-vs-magic-hour-mcp.md)\n- [Higgsfield API vs sync. labs MCP server](https://www.anchorterminal.com/compare/higgsfield-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": "Higgsfield API vs Magic Hour MCP", "url": "" } ], "description": "Higgsfield scores 62.7 (B) to Magic Hour MCP's 50.7 (D) for video generation. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "Higgsfield API B 62.7", "Magic Hour MCP D 50.7", "scores" ], "h1": "Higgsfield API vs Magic Hour MCP", "image": "https://www.anchorterminal.com/assets/og/default.png", "path": "/compare/higgsfield-vs-magic-hour-mcp", "published": "2026-10-01", "section": "tools", "title": "Higgsfield vs Magic Hour MCP for AI agents in 2026: scores and prices", "toc": null, "updated": "2026-11-07", "url": "https://www.anchorterminal.com/compare/higgsfield-vs-magic-hour-mcp" }, "tokens": { "markdown": 4900, "slim": 2680 }, "version": 1 }