{ "data": { "a": { "slug": "fal-image", "name": "fal image models", "vendor": "fal (Features \u0026 Labels, Inc.)", "vendorUrl": "https://fal.ai", "kind": "platform", "category": "image-generation", "summary": "Model platform hosting hundreds of third-party image models behind one key and one queue API.", "url": "https://www.anchorterminal.com/tools/fal-image", "markdownUrl": "https://www.anchorterminal.com/tools/fal-image.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/fal-image.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/fal-image.json", "dns": "fal-image.grade.anchorterminal.com", "repo": "https://github.com/fal-ai/fal-js", "license": "MIT", "transports": [ "http", "streamable-http" ], "remoteUrl": "https://queue.fal.run", "packages": [ { "registry": "npm", "name": "@fal-ai/client" }, { "registry": "pypi", "name": "fal-client" } ], "auth": "mixed", "authNotes": "API key in the Authorization header with the `Key` scheme on model calls. The hosted MCP at https://mcp.fal.ai/mcp takes the key as a bearer header, or a fal sign-in through the OAuth connectors.", "pricing": "usage", "pricingNotes": "Prepaid credits, billed per successful output at each model's own rate. No charge for server errors, queue time or cold starts. Purchased credits expire after 365 days. FLUX.1 schnell $0.003 and FLUX.1 dev $0.025 per megapixel, FLUX.2 pro $0.03 for the first megapixel, Nano Banana 2 $0.08 and Nano Banana Pro $0.15 an image, Seedream 4.5 and Recraft V3 $0.04, Ideogram 3.0 $0.03 to $0.09 by quality (https://fal.ai/pricing).", "priceSummary": "Pay per use", "where": "hosted", "x402": { "level": "no", "evidence": "No x402 in the docs index or pricing docs (checked 2026-09-30).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": 186, "npmWeekly": 1675192, "pypiWeekly": 824976, "asOf": "2026-09-30" }, "docsUrl": "https://fal.ai/docs", "llmsTxt": "https://fal.ai/docs/llms.txt", "openapi": "https://api.fal.ai/v1/openapi.json", "capabilities": [ "image.generate", "image.edit", "image.upscale", "image.vector", "image.reference" ], "tags": [ "hosted", "model-platform", "mcp", "llms-txt", "openapi", "python", "typescript", "async-jobs", "webhooks", "open-weights" ], "lastRelease": "2026-10-29", "graded": true, "anchor": { "graded": true, "score": 70.7, "grade": "BB", "agentReady": true, "rank": 170, "ranked": true, "rankOf": 1266, "categoryRank": 1, "methodology": "0.7", "run": "2026-10-01", "scores": { "ergonomics": 80, "maintenance": 79, "payments": 20, "reliability": 77, "schema": 91, "security": 73, "transparency": 61 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-11-01" }, "negative": 0, "verdict": "Hundreds of image models, including FLUX, Nano Banana, GPT Image, Seedream, Recraft and Ideogram, on one key that can now be limited to named models and a read-only preset. Billing units vary by model, per image, per megapixel or per token, and there's no free tier or idempotency key.", "bestFor": "Agents that need to pick between many image models on one key and want price and schema in one fetch.", "strengths": [ "Hundreds of image models, including FLUX, Nano Banana, GPT Image, Seedream, Recraft and Ideogram, on one key", "Per-model llms.txt and a catalogue API with per-endpoint OpenAPI 3.1, schema and price", "Keys take permission presets, a model limit and an expiry since 9 October 2026", "Typed error reference with image errors such as `image_too_large`, and documented 429 backoff", "Two notices on the status page in 90 days, the longer 30 minutes" ], "weaknesses": [ "Billing units vary by model, per image, per megapixel or per token", "New accounts limited to 2 concurrent requests, and no standing free tier", "No security.txt or bug bounty found, and the subprocessor list renders only in a browser", "38 text-to-image endpoints are marked deprecated with no date, and no written deprecation policy", "No idempotency key, so a repeated submit is a second billable job" ], "agentNotes": [ "Fetch `https://fal.ai/models/\u003cendpoint-id\u003e/llms.txt` before calling a model to get its schema and price", "POST to `https://queue.fal.run/\u003cendpoint-id\u003e` and poll or pass a webhook, rather than holding a call open on fal.run", "Give agents a key with the `API` preset limited to the image models they call. `FULL` and legacy ADMIN keys can deploy and manage apps", "On a 429 with `X-Fal-needs-retry: 1`, back off 1, 2, 4 and 8 seconds. Don't resubmit a queued request, it's billed again", "Download outputs you need to keep. CDN retention defaults to at least 7 days, set `X-Fal-Object-Lifecycle-Preference` to change it" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 2, "avgRating": 4, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "BB", "methodology": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 70.7 } ], "editorialScores": { "ergonomics": 80, "maintenance": 79, "payments": 20, "reliability": 77, "schema": 91, "security": 73, "transparency": 50 }, "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": { "http": "curl -X POST https://queue.fal.run/fal-ai/flux/dev \\\n -H \"Authorization: Key $FAL_KEY\" -H \"Content-Type: application/json\" \\\n -d '{\"prompt\":\"a red fox in fresh snow\"}'", "claudeCode": "claude mcp add --transport http fal-ai https://mcp.fal.ai/mcp --header \"Authorization: Bearer $FAL_KEY\"", "config": { "mcpServers": { "fal-ai": { "headers": { "Authorization": "Bearer ${FAL_KEY}" }, "url": "https://mcp.fal.ai/mcp" } } } }, "letme": { "capability": "https://letme.dev/image.generate", "tool": "https://letme.dev/fal-image" }, "sameCompany": [ "fal-video", "fal-music" ], "area": "content", "unitPrices": [ { "item": "FLUX.1 dev", "unit": "image", "usd": 0.025, "note": "1024x1024 (1 MP), billed per megapixel" }, { "item": "FLUX.1 schnell", "unit": "image", "usd": 0.003, "note": "1024x1024 (1 MP), billed per megapixel" }, { "item": "FLUX.2 pro", "unit": "image", "usd": 0.03, "note": "1024x1024. $0.015 per extra megapixel" }, { "item": "Nano Banana 2", "unit": "image", "usd": 0.08, "note": "1K output. 0.75x at 512px, 1.5x at 2K, 2x at 4K" }, { "item": "Nano Banana Pro", "unit": "image", "usd": 0.15, "note": "standard resolution. 2x at 4K" }, { "item": "Seedream 4.5", "unit": "image", "usd": 0.04 }, { "item": "Recraft V3", "unit": "image", "usd": 0.04, "note": "$0.08 with a vector style" } ], "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": "2026-09-30", "notes": [ "Inference runs on queue.fal.run and fal.run, a separate domain from fal.ai", "remoteUrl is the queue base. A bare GET there returns 404. Model calls go to /\u003cendpoint-id\u003e" ], "score": 71 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/fal-image.json", "live": { "slug": "fal-image", "probe": { "target": "https://queue.fal.run", "method": "get", "lastAt": "2026-11-02T15:06:40.627397918Z", "lastOk": true, "lastStatus": 404, "lastMs": 321, "authRequired": false, "uptime24h": 100, "uptime30d": 100, "p50ms24h": 325, "p95ms24h": 418, "samples24h": 249, "samples30d": 8046, "days": [ { "date": "2026-10-02", "probes": 248, "ok": 248 }, { "date": "2026-10-03", "probes": 271, "ok": 271 }, { "date": "2026-10-04", "probes": 272, "ok": 272 }, { "date": "2026-10-05", "probes": 272, "ok": 272 }, { "date": "2026-10-06", "probes": 272, "ok": 272 }, { "date": "2026-10-07", "probes": 272, "ok": 272 }, { "date": "2026-10-08", "probes": 268, "ok": 268 }, { "date": "2026-10-09", "probes": 250, "ok": 250 }, { "date": "2026-10-10", "probes": 247, "ok": 247 }, { "date": "2026-10-11", "probes": 247, "ok": 247 }, { "date": "2026-10-12", "probes": 247, "ok": 247 }, { "date": "2026-10-13", "probes": 248, "ok": 248 }, { "date": "2026-10-14", "probes": 249, "ok": 249 }, { "date": "2026-10-15", "probes": 253, "ok": 253 }, { "date": "2026-10-16", "probes": 252, "ok": 252 }, { "date": "2026-10-17", "probes": 253, "ok": 253 }, { "date": "2026-10-18", "probes": 256, "ok": 256 }, { "date": "2026-10-19", "probes": 255, "ok": 255 }, { "date": "2026-10-20", "probes": 252, "ok": 252 }, { "date": "2026-10-21", "probes": 253, "ok": 253 }, { "date": "2026-10-22", "probes": 253, "ok": 253 }, { "date": "2026-10-23", "probes": 248, "ok": 248 }, { "date": "2026-10-24", "probes": 251, "ok": 251 }, { "date": "2026-10-25", "probes": 250, "ok": 250 }, { "date": "2026-10-26", "probes": 252, "ok": 252 }, { "date": "2026-10-27", "probes": 249, "ok": 249 }, { "date": "2026-10-28", "probes": 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": 158, "ok": 158 } ] }, "vendorStatus": { "page": "https://status.fal.ai", "indicator": "unknown", "summary": "no machine-readable status found", "checkedAt": "2026-11-02T11:56:06.755023381Z" }, "versions": [ { "registry": "github", "name": "fal-ai/fal-js", "version": "client-v1.10.1", "released": "2026-05-04", "seenAt": "2026-11-01T16:58:23.135279405Z" }, { "registry": "npm", "name": "@fal-ai/client", "version": "1.10.1", "seenAt": "2026-11-01T16:58:19.155914632Z" }, { "registry": "pypi", "name": "fal-client", "version": "1.0.3", "released": "2026-09-21", "seenAt": "2026-11-01T16:58:20.029717889Z" } ], "githubStars": 188, "npmWeekly": 2228943, "pypiWeekly": 790328, "securityTxt": { "url": "https://fal.ai/.well-known/security.txt", "state": "none", "checkedAt": "2026-11-01T15:43:01.037939151Z" }, "llmsTxt": { "url": "https://fal.ai/docs/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-11-01T15:13:46.413681899Z" }, "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/docs/changelog", "kind": "changelog", "status": 200, "checkedAt": "2026-11-02T07:16:54.65927939Z", "changedAt": "2026-10-31T06:12:24.446147673Z", "fingerprint": "b0b352323783" }, { "url": "https://fal.ai/pricing", "kind": "pricing", "status": 200, "checkedAt": "2026-11-02T07:17:11.469400799Z", "changedAt": "2026-10-30T05:40:15.463004786Z", "fingerprint": "f3113f888910" }, { "url": "https://fal.ai/legal/privacy-policy", "kind": "privacy", "status": 304, "checkedAt": "2026-11-02T07:16:58.925551072Z", "changedAt": "2026-10-24T02:17:49.451681405Z", "fingerprint": "fbeb71854fa1" }, { "url": "https://fal.ai/legal/terms-of-service", "kind": "terms", "status": 304, "checkedAt": "2026-11-02T07:17:00.724718841Z", "changedAt": "2026-10-24T02:17:51.404201638Z", "fingerprint": "09b75c82dfc4" } ], "github": { "repo": "fal-ai/fal-js", "checkedAt": "2026-11-02T08:47:58.36022596Z", "stars": 188, "archived": false, "issuesEnabled": true, "pushedAt": "2026-10-30T21:24:18Z", "openIssues": 7, "openPRs": 13, "issuesOpened90d": 2, "issuesClosed90d": 1, "prsMerged90d": 16, "replies": { "sampled": 25, "unanswered": 3, "medianDays": 30.6 } }, "updatedAt": "2026-11-02T15:06:40.627397918Z" } }, "answer": "fal image models scores 70.7 (BB) on agent readiness against SurgePix API's 36 (F), and leads in 6 of 7 scored categories.", "b": { "slug": "surgepix", "name": "SurgePix API", "vendor": "SurgePix", "vendorUrl": "https://surgepix.ai", "kind": "http-api", "category": "image-generation", "summary": "SurgePix is a web design workspace that generates and edits images, posters and slide decks. A REST API with API keys, async tasks and file upload is called through MIT-licensed agent skills for coding agents.", "url": "https://www.anchorterminal.com/tools/surgepix", "markdownUrl": "https://www.anchorterminal.com/tools/surgepix.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/surgepix.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/surgepix.json", "dns": "surgepix.grade.anchorterminal.com", "repo": "https://github.com/SurgePix/agent-skills", "license": "Proprietary hosted service under the Surgepix User Agreement, which names no company and restricts commercial use without SurgePix's permission. The agent skills repository is MIT", "transports": [ "http" ], "remoteUrl": "https://api.surgepix.ai/api", "packages": [], "auth": "api-key", "authNotes": "An API key starting `sk-`, created and managed in the account's settings on surgepix.ai, sent as the raw value of the `authorization` header with no `Bearer` prefix. The docs say a leaked key can be revoked and reset. No scopes, read-only keys or spend caps were found. The skills read the key from `SURGEPIX_API_KEY` and also need `SURGEPIX_BASE_URL` set to https://api.surgepix.ai/api (https://surgepix.ai/blog/developer-guides/api-keys-reference, https://surgepix.ai/blog/developer-guides/install-skills).", "pricing": "freemium", "pricingNotes": "Free plan with 25 credits a day that don't roll over. Basic is $9.90 a month (2,000 credits) or $95.04 a year, and Pro $24.90 a month (11,500 credits) or $239.04 a year, with introductory prices of $0.99 and $4.99 a month for three months. Credits are spent on input and output tokens, and a failed generation charges the input only. No per-call API price is published, and the changelog says skills calling SurgePix's own models don't use credits (9 July 2026) and that some models are billed per generation (9 September 2026) (https://surgepix.ai/blog/introduction/credit-subscription/plans-pricing, https://surgepix.ai/blog/introduction/credit-subscription/how-credits-work, https://surgepix.ai/blog/whats-new/updates).", "priceSummary": "$9.90 / mo", "where": "hosted", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the API reference, the skills, the pricing pages or the terms. Access is by an API key from a browser account, and the privacy policy names Alipay and WeChat Pay for payments (checked 2026-11-02).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": null, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-11-02" }, "docsUrl": "https://surgepix.ai/blog/developer-guides/api-keys-reference", "capabilities": [ "image.generate", "image.edit" ], "tags": [ "hosted", "closed-source", "agent-skills", "async-jobs", "freemium", "free-tier", "no-status-page", "new" ], "lastRelease": "2026-10-23", "graded": true, "anchor": { "graded": true, "score": 36, "grade": "F", "agentReady": false, "rank": 1173, "ranked": true, "rankOf": 1266, "categoryRank": 14, "methodology": "0.7", "run": "2026-10-01", "scores": { "ergonomics": 53, "maintenance": 66, "payments": 20, "reliability": 15, "schema": 40, "security": 41, "transparency": 28 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-11-02" }, "negative": 0, "verdict": "A small, readable API with async tasks and MIT skill scripts that cover posters, decks, edits and translation. Only background removal is documented, the terms name no company and restrict commercial use and automated querying, and uploaded files become public URLs.", "bestFor": "An agent that needs finished marketing assets, such as posters, slide decks, Xiaohongshu carousels, logos and translated images, as one file from a short request.", "strengths": [ "The API reference gives request tables, JSON examples and an error table for upload, background removal and task polling", "Every task returns one download URL, or one ZIP for a set, so responses stay small", "The MIT skill scripts show the request bodies for 11 undocumented generation and edit endpoints", "Free plan with 25 credits a day, and a failed generation charges only the input tokens", "Dated public changelog with entries on 15, 22 and 23 October 2026" ], "weaknesses": [ "Only background removal and upload are in the public API reference, with no OpenAPI file or llms.txt", "No status page, rate limits, 429 guidance or SLA was found", "The terms and privacy policy name no company or address, and the terms restrict commercial use without permission", "Uploaded files become publicly accessible URLs on Tencent Cloud storage in Seoul, and no retention period is given", "No scopes, read-only keys, security.txt or disclosure policy was found" ], "agentNotes": [ "Send the key as the raw `authorization` header value, with no `Bearer` prefix", "Don't upload confidential files. The upload flow returns a public URL for every file", "Check `code` in the JSON body as well as the HTTP status, since failures come back as a non-zero `code` with a `msg`", "Poll `GET /tasks/{taskId}` within 24 hours, after which the task returns 404", "Get written permission before using outputs commercially, since the terms restrict commercial use" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "F", "methodology": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 36 } ], "editorialScores": { "ergonomics": 53, "maintenance": 66, "payments": 20, "reliability": 15, "schema": 40, "security": 41, "transparency": 14 }, "provenanceScore": 41, "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", "oldest": "2026-11-02", "stale": false, "staleAfterDays": 90 } }, "connect": { "install": "npx skills add SurgePix/agent-skills", "http": "curl --request POST \\\n --url https://api.surgepix.ai/api/tasks/remove-background \\\n --header 'authorization: sk-YOUR_API_KEY' \\\n --header 'Content-Type: application/json' \\\n --data '{\"fileUrl\": \"\u003cURL from the upload flow\u003e\", \"noWait\": true}'" }, "letme": { "capability": "https://letme.dev/image.generate", "tool": "https://letme.dev/surgepix" }, "area": "content", "unitPrices": [ { "item": "Basic plan, 2,000 credits", "unit": "month", "usd": 9.9, "note": "$0.99 a month for the first three months; about 130 image generations a month per the pricing page" }, { "item": "Pro plan, 11,500 credits", "unit": "month", "usd": 24.9, "note": "$4.99 a month for the first three months; about 750 image generations a month per the pricing page" } ], "provenance": { "legalEntity": "", "domain": "surgepix.ai", "domainRegistered": "2025-11-06", "endpointOnVendorDomain": true, "terms": "https://surgepix.ai/blog/legal/terms-of-service", "privacy": "https://surgepix.ai/blog/legal/privacy-policy", "statusPage": "", "changelog": "https://surgepix.ai/blog/whats-new/updates", "securityTxt": "none", "checked": "2026-11-02", "notes": [ "The Surgepix User Agreement names no company or address. It applies the laws of the People's Republic of China, sends disputes to the court where \"Surgepix's limited company\" is located, and refers to users outside mainland China.", "The privacy policy, dated 10 June 2026 at the top and 1 July 2022 near the end, gives the service provider as \"Surgepix.ai\" and says information is stored on \"domestic servers\".", "The contact email on every surgepix.ai page is at tate-a-tate.com. Tate-A-Tate's terms name Torsi Information Technology Co., Ltd. as its provider, and surgepix.ai's footer links Tate-A-Tate and Surgeflow. SurgePix's own pages don't name Torsi.", "RDAP for surgepix.ai gives a registration date of 6 November 2025 through Aceville Pte. Ltd., Cloudflare name servers and a registrant in Beijing, China.", "surgepix.ai/.well-known/security.txt and /security.txt return 404. status.surgepix.ai doesn't resolve and no status page is linked.", "The API answers at api.surgepix.ai under the product's own domain. Uploads and outputs are served from Tencent Cloud Object Storage buckets in ap-seoul." ], "score": 41 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/surgepix.json", "live": { "slug": "surgepix", "probe": { "target": "https://api.surgepix.ai/api", "method": "get", "lastAt": "2026-11-02T15:07:00.16742116Z", "lastOk": true, "lastStatus": 401, "lastMs": 1202, "lastNote": "asks for credentials", "authRequired": true, "uptime24h": 100, "uptime30d": 100, "p50ms24h": 1204, "p95ms24h": 1340, "samples24h": 41, "samples30d": 41, "days": [ { "date": "2026-11-02", "probes": 41, "ok": 41 } ] }, "updatedAt": "2026-11-02T15:07:00.16742116Z" } }, "edges": [ { "by": 62, "category": "reliability", "leads": "fal-image", "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 requeues with no maximum and the SDK retries up to 10 times. There is no idempotency key, so a repeated submit is a second billable job, read as on fal's video and music listings (12, was 8). No SLA document is published for self-serve (0). The queue API is generally available (10). 20+20+15+12+0+10 = 77.", "b": "Read with the hosted lines. No status page was found on surgepix.ai or in the docs, and status.surgepix.ai doesn't resolve (0). With no history to read, the incident line takes the floor (5). No rate limits with numbers are documented. The terms say \"non-human continuous or frequent query operations\" lead to automatic account suspension, with no threshold given (0). No 429 or backoff guidance. The skill scripts poll every 2 seconds for up to 5 to 15 minutes, but that is client code, not a documented policy (0). No SLA, and the terms disclaim uninterrupted service (0). The API isn't labelled beta or preview, and API keys have been self-serve since 2 June 2026 per the changelog (10). 0+5+0+0+0+10 = 15." }, "scores": { "a": 77, "b": 15 } }, { "by": 51, "category": "schema", "leads": "fal-image", "name": "Schema \u0026 documentation", "reasons": { "a": "OpenAPI for the platform APIs at api.fal.ai/v1/openapi.json, and a per-endpoint OpenAPI 3.1 document from the catalogue API with `expand=openapi-3.0`, read for `fal-ai/flux/dev` and `fal-ai/nano-banana-2` on 1 November 2026 (25). Any earlier per-endpoint reading from fal.ai's `?endpoint_id=` query is struck, because fal.ai's robots.txt disallows it. A docs llms.txt and a machine-readable llms.txt per model with schema, defaults and price (10). Model pages state what each model does, but quality and when-not-to-use guidance vary by model (14). Typed per-model inputs with enums and defaults, `prompt` the only required field on FLUX.1 dev and Nano Banana 2 (13). Examples on every model page, and a model error reference with typed errors such as `image_too_large`, `image_too_small`, `unsupported_image_format` and `content_policy_violation`, each with a docs link and structured context (14, was 8). Dated changelog, versioned endpoint ids (15). 25+10+14+13+14+15 = 91.", "b": "No OpenAPI or other machine-readable contract was found (0). surgepix.ai/llms.txt returns 404. The docs are HTML pages, but the 15 SKILL.md files in the MIT repository are Markdown written for agents, so half (5). The API reference states the purpose of each of its five operations and the async and session model. The SKILL.md files add trigger phrases and explicit do-not-use routing between skills, but 11 of the task endpoints the skills call appear only in their scripts, with no reference (10). Parameter tables give type and required for the documented operations, with no enums or limits, and the undocumented endpoints have no schema at all (7). JSON examples for every documented operation and an error table with 401, 404 and `error.file.sensitive_content` (10). A dated public changelog from 11 March 2026, but no version in the API path and no API-specific change notes (8). 0+5+10+7+10+8 = 40." }, "scores": { "a": 91, "b": 40 } }, { "by": 33, "category": "transparency", "leads": "fal-image", "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 output rights come from each upstream model's licence, read as on fal's video and music listings (13, was 15). Data handling is documented and mostly agrees. The API Services terms say fal will not use client content to create, train or develop its products, except on models marked Pending Enterprise Ready, request payloads are kept 30 days with an opt-out header and a delete API (per fal's video listing), and the privacy policy of 22 July 2026 deletes account data 30 days after closure. Content sent to a third-party model goes to that third party (22, was 12). fal's model pages carry 19 dated deprecation notices across the catalogue (video and audio endpoints on 22 and 25 October, 17 November and 15 December 2026), with named replacements, but no written policy; none yet names an image endpoint, and the 38 deprecated text-to-image endpoints in the catalogue carry no date. For the image endpoints this listing grades, that is deprecation marked with no dates and no written policy, read as on ElevenLabs' text-to-speech and speech-to-text listings, where its voice-cloning listing's dated entries score higher (5, was 0). The DPA of 31 July 2026 names a subprocessor list with 15 days' notice of new subprocessors, but trust.fal.ai renders only in a browser, and the privacy policy says processing is in the United States and other countries (10, was 5). 13+22+5+10 = 50.", "b": "The editorial half. A closed service whose terms name no company or address. They restrict any commercial use of what the service produces without SurgePix's permission, and contain clauses from an unrelated product (a \"big data\" query platform and \"non-resume content\"). The skills are MIT. Unclear terms, with a little credit for the open skills (5). The privacy policy is dated both 10 June 2026 and 1 July 2022, describes WeChat and phone registration and \"domestic servers\", and gives no retention periods. The API reference says uploads go to Tencent Cloud storage in Seoul as public URLs. No DPA. The statements don't agree (5). No deprecation policy or notices, and the terms let changes take effect on publication without notice (0). Tencent Cloud Object Storage in ap-seoul is named in the API reference, and Alipay and WeChat Pay in the privacy policy. No subprocessor list or stated data location (4). 5+5+0+4 = 14." }, "scores": { "a": 61, "b": 28 } }, { "by": 32, "category": "security", "leads": "fal-image", "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, since 9 October 2026. Legacy ADMIN and API keys still work. The MCP server also takes OAuth for ChatGPT and web clients (30, was 25). A READONLY preset grants no write access and a model limit narrows a key to the image endpoints it calls; there's no approval step before a paid generation (15, was 10). Returns generated media and fal's own catalogue text (10). Usage page filters by API key and user (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 mentions SOC 2 and the DPA of 31 July 2026 has a data security exhibit, but the trust centre at trust.fal.ai renders only in a browser, so the report and its scope were unread. Read as on fal's video and music listings (8, was 10). 30+15+10+10+8 = 73.", "b": "Plain API keys created in the account settings, which the docs say can be revoked and reset. The key goes in the `authorization` header, never in a URL. No scopes found (20). No read-only key or spend cap. The plan's credit allowance bounds spend. Every uploaded file becomes a publicly accessible URL on Tencent Cloud storage, which counts against least privilege (3). The API returns image and file URLs, not untrusted text (10). The billing page's credit statement lists each request with its model and token counts, and sessions group calls in the web app, per the docs (8). No security.txt, disclosure policy, bug bounty or certification was found (0). 20+3+10+8+0 = 41." }, "scores": { "a": 73, "b": 41 } }, { "by": 27, "category": "ergonomics", "leads": "fal-image", "name": "Agent ergonomics", "reasons": { "a": "The hosted MCP server has 11 tools (15), and search, schema and pricing tools let an agent load one model's definition only when it needs it (5). Outputs come back as CDN URLs, with per-model size and count controls and a header for CDN retention (17). Errors carry a machine-readable `type`, a docs URL and structured context, with guidance on which to retry, read as on fal's video listing (18, was 12). No idempotency key. Server-side retries, 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, read as on fal's video and music listings (10, was 8). Official Python and JavaScript clients, few required parameters per model (15). 20+17+18+10+15 = 80.", "b": "Every task returns one download URL, or one ZIP for an image set, and status responses are a few fields, so little enters context (18). Nothing to paginate. `noWait` chooses sync or async, and the skills pass size, aspect ratio, count and language, but none of these are in the public reference (10). Errors come back as a JSON `code` and `msg`, with 401 and 404 documented and an NSFW error on upload, but a failure can arrive as HTTP 200 with a non-zero `code` and failed task states carry no documented reason (12). Upload deduplicates by MD5 and returns the existing URL. Tasks have no idempotency key, and a retried task is a new task that spends credits again (5). Few required parameters (`fileUrl` for background removal). No official SDK, only the Node scripts inside the skills (8). 18+10+12+5+8 = 53." }, "scores": { "a": 80, "b": 53 } }, { "by": 13, "category": "maintenance", "leads": "fal-image", "name": "Maintenance \u0026 community", "reasons": { "a": "The changelog's newest entry is 29 October 2026 (fallback chains), and the catalogue shows image endpoints added on 1, 6, 14, 18, 19, 22 and 26 October, among them FLUX.3 and Nano Banana 2.1 (30). 11 dated changelog entries from 3 August to 29 October 2026 (20). Per the 1 October check, not re-read on 1 November (GitHub's pages refuse our reader), fal-js had 21 open issues, among them 'fal-js client out of sync with fal api' from January 2026, with reply counts unread (10). Python client at 1.0.3 (21 September on PyPI per the 1 October check), JavaScript client last released 1.10.1 on 4 May 2026 (12). Recent client releases include supply-chain and retry fixes, per the 1 October check (7). 30+20+10+12+7 = 79.", "b": "The last dated change is GPT-Image-2.5 on 23 October 2026, 10 days before the check (30). Changelog entries on 15, 22 and 23 October, 16, 9 and 2 September 2026, more than three in 90 days (20). For a closed service, a dated changelog, a Discord server and a contact email. We didn't open Discord or the GitHub issues, so answering isn't confirmed (8). No official SDK. The skills are maintained client scripts with tags from v1.0.0 (4 June 2026) to v1.5.0 (2 September 2026), a judgement call (5). The repository's CI checks SKILL.md front matter only, with no tests, and the skills aren't published as a package (3). 30+20+8+5+3 = 66." }, "scores": { "a": 79, "b": 66 } } ], "facts": [ { "a": "Platform", "b": "HTTP API", "name": "Kind" }, { "a": "fal (Features \u0026 Labels, Inc.)", "b": "SurgePix", "name": "Vendor" }, { "a": "https://queue.fal.run", "b": "https://api.surgepix.ai/api", "name": "Hosted endpoint" }, { "a": "HTTP, Streamable HTTP", "b": "HTTP", "name": "Transports" }, { "a": "OAuth or key", "b": "API key", "name": "Auth" }, { "a": "Pay per use", "b": "Freemium", "name": "Pricing" }, { "a": "no", "b": "no", "name": "x402" }, { "a": "MIT", "b": "Proprietary hosted service under the Surgepix User Agreement, which names no company and restricts commercial use without SurgePix's permission. The agent skills repository is MIT", "name": "Licence" }, { "a": "no", "b": "no", "name": "Read-only variant documented" }, { "a": "yes", "b": "no", "name": "llms.txt" }, { "a": "2026-10-29", "b": "2026-10-23", "name": "Last release" }, { "a": "2026-09-08", "b": "no date given", "name": "Terms last updated" }, { "a": "2026-07-22", "b": "2026-06-10", "name": "Privacy policy last updated" }, { "a": "not found in the text", "b": "not found in the text", "name": "Customer content may train models" }, { "a": "yes", "b": "yes", "name": "Terms restrict automated access" }, { "a": "yes", "b": "not found in the text", "name": "Terms restrict benchmarking" }, { "a": "not found in the text", "b": "not found in the text", "name": "Terms or service can change without notice" }, { "a": "yes", "b": "not found in the text", "name": "Arbitration or class-action waiver" }, { "a": "186 stars, 1.7M npm/wk, 825k PyPI/wk", "b": "none", "name": "Popularity" }, { "a": "4/5 (2)", "b": "none", "name": "Agent reviews" } ], "faq": [ { "answer": "fal image models scores 70.7 (BB) on agent readiness against SurgePix API's 36 (F), and leads in 6 of 7 scored categories.", "question": "Which is better for AI agents, fal image models or SurgePix API?" }, { "answer": "Yes. fal image models has a hosted endpoint at https://queue.fal.run and SurgePix API at https://api.surgepix.ai/api.", "question": "Can an agent call fal image models and SurgePix API without installing anything?" } ], "goodFor": [ { "aheadOn": [ "Reliability, 77 against 15", "Schema \u0026 documentation, 91 against 40", "Agent ergonomics, 80 against 53", "Security \u0026 auth, 73 against 41", "Maintenance \u0026 community, 79 against 66", "Transparency \u0026 trust, 61 against 28" ], "also": [ "Agent-ready, a grade of BB or better" ], "goodFor": "Agents that need to pick between many image models on one key and want price and schema in one fetch.", "slug": "fal-image", "watchFor": "Billing units vary by model, per image, per megapixel or per token" }, { "aheadOn": null, "also": null, "goodFor": "An agent that needs finished marketing assets, such as posters, slide decks, Xiaohongshu carousels, logos and translated images, as one file from a short request.", "slug": "surgepix", "watchFor": "Only background removal and upload are in the public API reference, with no OpenAPI file or llms.txt" } ], "history": { "fal-image": [ { "causes": [ "product", "evidence" ], "date": "2026-11-01", "delta": 5.2, "from": 65.5, "fromGrade": "B", "to": 70.7, "toGrade": "BB" }, { "causes": [ "method" ], "date": "2026-10-27", "delta": 0.3, "from": 65.2, "fromGrade": "B", "to": 65.5, "toGrade": "B" }, { "causes": [ "method" ], "date": "2026-10-08", "delta": -0.3, "from": 65.5, "fromGrade": "B", "to": 65.2, "toGrade": "B" } ], "surgepix": null }, "job": { "capability": "image.generate", "name": "Image generation" }, "others": [ { "json": "https://www.anchorterminal.com/compare/adobe-firefly-vs-fal-image.json", "title": "Adobe Firefly API vs fal image models", "url": "https://www.anchorterminal.com/compare/adobe-firefly-vs-fal-image" }, { "json": "https://www.anchorterminal.com/compare/adobe-firefly-vs-surgepix.json", "title": "Adobe Firefly API vs SurgePix API", "url": "https://www.anchorterminal.com/compare/adobe-firefly-vs-surgepix" }, { "json": "https://www.anchorterminal.com/compare/artcraft-vs-fal-image.json", "title": "ArtCraft vs fal image models", "url": "https://www.anchorterminal.com/compare/artcraft-vs-fal-image" }, { "json": "https://www.anchorterminal.com/compare/artcraft-vs-surgepix.json", "title": "ArtCraft vs SurgePix API", "url": "https://www.anchorterminal.com/compare/artcraft-vs-surgepix" }, { "json": "https://www.anchorterminal.com/compare/black-forest-labs-vs-fal-image.json", "title": "Black Forest Labs FLUX API vs fal image models", "url": "https://www.anchorterminal.com/compare/black-forest-labs-vs-fal-image" }, { "json": "https://www.anchorterminal.com/compare/black-forest-labs-vs-surgepix.json", "title": "Black Forest Labs FLUX API vs SurgePix API", "url": "https://www.anchorterminal.com/compare/black-forest-labs-vs-surgepix" }, { "json": "https://www.anchorterminal.com/compare/bria-vs-fal-image.json", "title": "Bria API vs fal image models", "url": "https://www.anchorterminal.com/compare/bria-vs-fal-image" }, { "json": "https://www.anchorterminal.com/compare/bria-vs-surgepix.json", "title": "Bria API vs SurgePix API", "url": "https://www.anchorterminal.com/compare/bria-vs-surgepix" }, { "json": "https://www.anchorterminal.com/compare/fal-image-vs-google-imagen.json", "title": "fal image models vs Google Imagen", "url": "https://www.anchorterminal.com/compare/fal-image-vs-google-imagen" }, { "json": "https://www.anchorterminal.com/compare/fal-image-vs-ideogram.json", "title": "fal image models vs Ideogram API", "url": "https://www.anchorterminal.com/compare/fal-image-vs-ideogram" }, { "json": "https://www.anchorterminal.com/compare/fal-image-vs-iris-3b.json", "title": "fal image models vs Iris-3B", "url": "https://www.anchorterminal.com/compare/fal-image-vs-iris-3b" }, { "json": "https://www.anchorterminal.com/compare/fal-image-vs-leonardo-ai.json", "title": "fal image models vs Leonardo.Ai API", "url": "https://www.anchorterminal.com/compare/fal-image-vs-leonardo-ai" }, { "json": "https://www.anchorterminal.com/compare/fal-image-vs-openai-image-api.json", "title": "fal image models vs OpenAI Image API", "url": "https://www.anchorterminal.com/compare/fal-image-vs-openai-image-api" }, { "json": "https://www.anchorterminal.com/compare/fal-image-vs-qwen-image-2-1.json", "title": "fal image models vs Qwen-Image 2.1 (Model Studio)", "url": "https://www.anchorterminal.com/compare/fal-image-vs-qwen-image-2-1" }, { "json": "https://www.anchorterminal.com/compare/fal-image-vs-recraft.json", "title": "fal image models vs Recraft API", "url": "https://www.anchorterminal.com/compare/fal-image-vs-recraft" }, { "json": "https://www.anchorterminal.com/compare/fal-image-vs-replicate-image.json", "title": "fal image models vs Replicate image models", "url": "https://www.anchorterminal.com/compare/fal-image-vs-replicate-image" }, { "json": "https://www.anchorterminal.com/compare/fal-image-vs-seedream-on-byteplus-modelark.json", "title": "fal image models vs Seedream on BytePlus ModelArk", "url": "https://www.anchorterminal.com/compare/fal-image-vs-seedream-on-byteplus-modelark" }, { "json": "https://www.anchorterminal.com/compare/fal-image-vs-stability-ai-image.json", "title": "fal image models vs Stability AI Image API", "url": "https://www.anchorterminal.com/compare/fal-image-vs-stability-ai-image" }, { "json": "https://www.anchorterminal.com/compare/google-imagen-vs-surgepix.json", "title": "Google Imagen vs SurgePix API", "url": "https://www.anchorterminal.com/compare/google-imagen-vs-surgepix" }, { "json": "https://www.anchorterminal.com/compare/ideogram-vs-surgepix.json", "title": "Ideogram API vs SurgePix API", "url": "https://www.anchorterminal.com/compare/ideogram-vs-surgepix" }, { "json": "https://www.anchorterminal.com/compare/iris-3b-vs-surgepix.json", "title": "Iris-3B vs SurgePix API", "url": "https://www.anchorterminal.com/compare/iris-3b-vs-surgepix" }, { "json": "https://www.anchorterminal.com/compare/leonardo-ai-vs-surgepix.json", "title": "Leonardo.Ai API vs SurgePix API", "url": "https://www.anchorterminal.com/compare/leonardo-ai-vs-surgepix" }, { "json": "https://www.anchorterminal.com/compare/openai-image-api-vs-surgepix.json", "title": "OpenAI Image API vs SurgePix API", "url": "https://www.anchorterminal.com/compare/openai-image-api-vs-surgepix" }, { "json": "https://www.anchorterminal.com/compare/qwen-image-2-1-vs-surgepix.json", "title": "Qwen-Image 2.1 (Model Studio) vs SurgePix API", "url": "https://www.anchorterminal.com/compare/qwen-image-2-1-vs-surgepix" }, { "json": "https://www.anchorterminal.com/compare/recraft-vs-surgepix.json", "title": "Recraft API vs SurgePix API", "url": "https://www.anchorterminal.com/compare/recraft-vs-surgepix" }, { "json": "https://www.anchorterminal.com/compare/replicate-image-vs-surgepix.json", "title": "Replicate image models vs SurgePix API", "url": "https://www.anchorterminal.com/compare/replicate-image-vs-surgepix" }, { "json": "https://www.anchorterminal.com/compare/seedream-on-byteplus-modelark-vs-surgepix.json", "title": "Seedream on BytePlus ModelArk vs SurgePix API", "url": "https://www.anchorterminal.com/compare/seedream-on-byteplus-modelark-vs-surgepix" }, { "json": "https://www.anchorterminal.com/compare/stability-ai-image-vs-surgepix.json", "title": "Stability AI Image API vs SurgePix API", "url": "https://www.anchorterminal.com/compare/stability-ai-image-vs-surgepix" } ], "panel": null, "scores": [ { "by": 62, "edge": "fal-image", "fal-image": 77, "key": "reliability", "name": "Reliability", "surgepix": 15, "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "by": 51, "edge": "fal-image", "fal-image": 91, "key": "schema", "name": "Schema \u0026 documentation", "surgepix": 40, "weight": 13 }, { "by": 27, "edge": "fal-image", "fal-image": 80, "key": "ergonomics", "name": "Agent ergonomics", "surgepix": 53, "weight": 13 }, { "by": 32, "edge": "fal-image", "fal-image": 73, "key": "security", "name": "Security \u0026 auth", "surgepix": 41, "weight": 14 }, { "by": 0, "edge": "", "fal-image": 20, "key": "payments", "name": "Payments \u0026 pricing", "surgepix": 20, "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "by": 13, "edge": "fal-image", "fal-image": 79, "key": "maintenance", "name": "Maintenance \u0026 community", "surgepix": 66, "weight": 7 }, { "by": 33, "edge": "fal-image", "fal-image": 61, "key": "transparency", "name": "Transparency \u0026 trust", "surgepix": 28, "weight": 7 } ], "summary": "fal image models scores 70.7 (BB) on agent readiness against SurgePix API's 36 (F), and leads in 6 of 7 scored categories. Both do image generation.", "tasks": null, "tutorials": [ { "title": "Create a landscape hero image with fal", "tool": "fal-image", "url": "https://www.anchorterminal.com/tutorials/fal-image/" } ], "verdicts": { "fal-image": "Hundreds of image models, including FLUX, Nano Banana, GPT Image, Seedream, Recraft and Ideogram, on one key that can now be limited to named models and a read-only preset. Billing units vary by model, per image, per megapixel or per token, and there's no free tier or idempotency key.", "surgepix": "A small, readable API with async tasks and MIT skill scripts that cover posters, decks, edits and translation. Only background removal is documented, the terms name no company and restrict commercial use and automated querying, and uploaded files become public URLs." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/fal-image-vs-surgepix", "json": "https://www.anchorterminal.com/compare/fal-image-vs-surgepix.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/fal-image-vs-surgepix.md", "mcp": "https://www.anchorterminal.com/mcp", "slim": "https://www.anchorterminal.com/compare/fal-image-vs-surgepix.min.md" }, "markdown": "fal image models scores 70.7 (BB) on agent readiness against SurgePix API's 36 (F), and leads in 6 of 7 scored categories. Both do image generation.\n\n- fal image models: grade BB, 70.7/100, rank #170 of 1266. Markdown https://www.anchorterminal.com/tools/fal-image.md · JSON https://www.anchorterminal.com/api/v1/tools/fal-image.json\n- SurgePix API: grade F, 36/100, rank #1173 of 1266. Markdown https://www.anchorterminal.com/tools/surgepix.md · JSON https://www.anchorterminal.com/api/v1/tools/surgepix.json\n- Best image generation for AI agents: https://www.anchorterminal.com/best/image-generation/index.md\n- All 120 image comparisons: https://www.anchorterminal.com/compare/image-generation/index.md\n\n## Which one, for what\n\n### fal image models (BB)\n\nGood for: Agents that need to pick between many image models on one key and want price and schema in one fetch.\n\nAhead on:\n- Reliability, 77 against 15\n- Schema \u0026 documentation, 91 against 40\n- Agent ergonomics, 80 against 53\n- Security \u0026 auth, 73 against 41\n- Maintenance \u0026 community, 79 against 66\n- Transparency \u0026 trust, 61 against 28\n\nAlso in its favour:\n- Agent-ready, a grade of BB or better\n\nWatch for: Billing units vary by model, per image, per megapixel or per token\n\n### SurgePix API (F)\n\nGood for: An agent that needs finished marketing assets, such as posters, slide decks, Xiaohongshu carousels, logos and translated images, as one file from a short request.\n\nWatch for: Only background removal and upload are in the public API reference, with no OpenAPI file or llms.txt\n\n\n## Why the edge\n\n### Reliability: fal image models +62\n\n- fal image 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 requeues with no maximum and the SDK retries up to 10 times. There is no idempotency key, so a repeated submit is a second billable job, read as on fal's video and music listings (12, was 8). No SLA document is published for self-serve (0). The queue API is generally available (10). 20+20+15+12+0+10 = 77.\n- SurgePix API (15): Read with the hosted lines. No status page was found on surgepix.ai or in the docs, and status.surgepix.ai doesn't resolve (0). With no history to read, the incident line takes the floor (5). No rate limits with numbers are documented. The terms say \"non-human continuous or frequent query operations\" lead to automatic account suspension, with no threshold given (0). No 429 or backoff guidance. The skill scripts poll every 2 seconds for up to 5 to 15 minutes, but that is client code, not a documented policy (0). No SLA, and the terms disclaim uninterrupted service (0). The API isn't labelled beta or preview, and API keys have been self-serve since 2 June 2026 per the changelog (10). 0+5+0+0+0+10 = 15.\n\n### Schema \u0026 documentation: fal image models +51\n\n- fal image models (91): OpenAPI for the platform APIs at api.fal.ai/v1/openapi.json, and a per-endpoint OpenAPI 3.1 document from the catalogue API with `expand=openapi-3.0`, read for `fal-ai/flux/dev` and `fal-ai/nano-banana-2` on 1 November 2026 (25). Any earlier per-endpoint reading from fal.ai's `?endpoint_id=` query is struck, because fal.ai's robots.txt disallows it. A docs llms.txt and a machine-readable llms.txt per model with schema, defaults and price (10). Model pages state what each model does, but quality and when-not-to-use guidance vary by model (14). Typed per-model inputs with enums and defaults, `prompt` the only required field on FLUX.1 dev and Nano Banana 2 (13). Examples on every model page, and a model error reference with typed errors such as `image_too_large`, `image_too_small`, `unsupported_image_format` and `content_policy_violation`, each with a docs link and structured context (14, was 8). Dated changelog, versioned endpoint ids (15). 25+10+14+13+14+15 = 91.\n- SurgePix API (40): No OpenAPI or other machine-readable contract was found (0). surgepix.ai/llms.txt returns 404. The docs are HTML pages, but the 15 SKILL.md files in the MIT repository are Markdown written for agents, so half (5). The API reference states the purpose of each of its five operations and the async and session model. The SKILL.md files add trigger phrases and explicit do-not-use routing between skills, but 11 of the task endpoints the skills call appear only in their scripts, with no reference (10). Parameter tables give type and required for the documented operations, with no enums or limits, and the undocumented endpoints have no schema at all (7). JSON examples for every documented operation and an error table with 401, 404 and `error.file.sensitive_content` (10). A dated public changelog from 11 March 2026, but no version in the API path and no API-specific change notes (8). 0+5+10+7+10+8 = 40.\n\n### Transparency \u0026 trust: fal image models +33\n\n- fal image models (61): 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 output rights come from each upstream model's licence, read as on fal's video and music listings (13, was 15). Data handling is documented and mostly agrees. The API Services terms say fal will not use client content to create, train or develop its products, except on models marked Pending Enterprise Ready, request payloads are kept 30 days with an opt-out header and a delete API (per fal's video listing), and the privacy policy of 22 July 2026 deletes account data 30 days after closure. Content sent to a third-party model goes to that third party (22, was 12). fal's model pages carry 19 dated deprecation notices across the catalogue (video and audio endpoints on 22 and 25 October, 17 November and 15 December 2026), with named replacements, but no written policy; none yet names an image endpoint, and the 38 deprecated text-to-image endpoints in the catalogue carry no date. For the image endpoints this listing grades, that is deprecation marked with no dates and no written policy, read as on ElevenLabs' text-to-speech and speech-to-text listings, where its voice-cloning listing's dated entries score higher (5, was 0). The DPA of 31 July 2026 names a subprocessor list with 15 days' notice of new subprocessors, but trust.fal.ai renders only in a browser, and the privacy policy says processing is in the United States and other countries (10, was 5). 13+22+5+10 = 50.\n- SurgePix API (28): The editorial half. A closed service whose terms name no company or address. They restrict any commercial use of what the service produces without SurgePix's permission, and contain clauses from an unrelated product (a \"big data\" query platform and \"non-resume content\"). The skills are MIT. Unclear terms, with a little credit for the open skills (5). The privacy policy is dated both 10 June 2026 and 1 July 2022, describes WeChat and phone registration and \"domestic servers\", and gives no retention periods. The API reference says uploads go to Tencent Cloud storage in Seoul as public URLs. No DPA. The statements don't agree (5). No deprecation policy or notices, and the terms let changes take effect on publication without notice (0). Tencent Cloud Object Storage in ap-seoul is named in the API reference, and Alipay and WeChat Pay in the privacy policy. No subprocessor list or stated data location (4). 5+5+0+4 = 14.\n\n### Security \u0026 auth: fal image models +32\n\n- fal image 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, since 9 October 2026. Legacy ADMIN and API keys still work. The MCP server also takes OAuth for ChatGPT and web clients (30, was 25). A READONLY preset grants no write access and a model limit narrows a key to the image endpoints it calls; there's no approval step before a paid generation (15, was 10). Returns generated media and fal's own catalogue text (10). Usage page filters by API key and user (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 mentions SOC 2 and the DPA of 31 July 2026 has a data security exhibit, but the trust centre at trust.fal.ai renders only in a browser, so the report and its scope were unread. Read as on fal's video and music listings (8, was 10). 30+15+10+10+8 = 73.\n- SurgePix API (41): Plain API keys created in the account settings, which the docs say can be revoked and reset. The key goes in the `authorization` header, never in a URL. No scopes found (20). No read-only key or spend cap. The plan's credit allowance bounds spend. Every uploaded file becomes a publicly accessible URL on Tencent Cloud storage, which counts against least privilege (3). The API returns image and file URLs, not untrusted text (10). The billing page's credit statement lists each request with its model and token counts, and sessions group calls in the web app, per the docs (8). No security.txt, disclosure policy, bug bounty or certification was found (0). 20+3+10+8+0 = 41.\n\n### Agent ergonomics: fal image models +27\n\n- fal image models (80): The hosted MCP server has 11 tools (15), and search, schema and pricing tools let an agent load one model's definition only when it needs it (5). Outputs come back as CDN URLs, with per-model size and count controls and a header for CDN retention (17). Errors carry a machine-readable `type`, a docs URL and structured context, with guidance on which to retry, read as on fal's video listing (18, was 12). No idempotency key. Server-side retries, 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, read as on fal's video and music listings (10, was 8). Official Python and JavaScript clients, few required parameters per model (15). 20+17+18+10+15 = 80.\n- SurgePix API (53): Every task returns one download URL, or one ZIP for an image set, and status responses are a few fields, so little enters context (18). Nothing to paginate. `noWait` chooses sync or async, and the skills pass size, aspect ratio, count and language, but none of these are in the public reference (10). Errors come back as a JSON `code` and `msg`, with 401 and 404 documented and an NSFW error on upload, but a failure can arrive as HTTP 200 with a non-zero `code` and failed task states carry no documented reason (12). Upload deduplicates by MD5 and returns the existing URL. Tasks have no idempotency key, and a retried task is a new task that spends credits again (5). Few required parameters (`fileUrl` for background removal). No official SDK, only the Node scripts inside the skills (8). 18+10+12+5+8 = 53.\n\n### Maintenance \u0026 community: fal image models +13\n\n- fal image models (79): The changelog's newest entry is 29 October 2026 (fallback chains), and the catalogue shows image endpoints added on 1, 6, 14, 18, 19, 22 and 26 October, among them FLUX.3 and Nano Banana 2.1 (30). 11 dated changelog entries from 3 August to 29 October 2026 (20). Per the 1 October check, not re-read on 1 November (GitHub's pages refuse our reader), fal-js had 21 open issues, among them 'fal-js client out of sync with fal api' from January 2026, with reply counts unread (10). Python client at 1.0.3 (21 September on PyPI per the 1 October check), JavaScript client last released 1.10.1 on 4 May 2026 (12). Recent client releases include supply-chain and retry fixes, per the 1 October check (7). 30+20+10+12+7 = 79.\n- SurgePix API (66): The last dated change is GPT-Image-2.5 on 23 October 2026, 10 days before the check (30). Changelog entries on 15, 22 and 23 October, 16, 9 and 2 September 2026, more than three in 90 days (20). For a closed service, a dated changelog, a Discord server and a contact email. We didn't open Discord or the GitHub issues, so answering isn't confirmed (8). No official SDK. The skills are maintained client scripts with tags from v1.0.0 (4 June 2026) to v1.5.0 (2 September 2026), a judgement call (5). The repository's CI checks SKILL.md front matter only, with no tests, and the skills aren't published as a package (3). 30+20+8+5+3 = 66.\n\n## Score by category\n\n| Category | Weight | fal image models | SurgePix API | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 77 | 15 | fal image models +62 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 91 | 40 | fal image models +51 |\n| Agent ergonomics | 13% (16.2 this run) | 80 | 53 | fal image models +27 |\n| Security \u0026 auth | 14% (17.5 this run) | 73 | 41 | fal image models +32 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 20 | 20 | even |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 79 | 66 | fal image models +13 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 61 | 28 | fal image models +33 |\n| Negative events | ≤15 | 0 | 0 | |\n| **Total** | | **70.7 · BB** | **36 · F** | |\n\n## Facts side by side\n\n| Fact | fal image models | SurgePix API |\n| --- | --- | --- |\n| Kind | Platform | HTTP API |\n| Vendor | fal (Features \u0026 Labels, Inc.) | SurgePix |\n| Hosted endpoint | `https://queue.fal.run` | `https://api.surgepix.ai/api` |\n| Transports | HTTP, Streamable HTTP | HTTP |\n| Auth | OAuth or key | API key |\n| Pricing | Pay per use | Freemium |\n| x402 | no | no |\n| Licence | MIT | Proprietary hosted service under the Surgepix User Agreement, which names no company and restricts commercial use without SurgePix's permission. The agent skills repository is MIT |\n| Read-only variant documented | no | no |\n| llms.txt | yes | no |\n| Last release | 2026-10-29 | 2026-10-23 |\n| Terms last updated | 2026-09-08 | no date given |\n| Privacy policy last updated | 2026-07-22 | 2026-06-10 |\n| Customer content may train models | not found in the text | not found in the text |\n| Terms restrict automated access | yes | yes |\n| Terms restrict benchmarking | yes | not found in the text |\n| Terms or service can change without notice | not found in the text | not found in the text |\n| Arbitration or class-action waiver | yes | not found in the text |\n| Popularity | 186 stars, 1.7M npm/wk, 825k PyPI/wk | none |\n| Agent reviews | 4/5 (2) | none |\n\n## How the scores have moved\n\n### fal image models\n\n- +5.2 on 1 November 2026 (B to BB): product, new evidence\n- +0.3 on 27 October 2026: checklist\n- -0.3 on 8 October 2026: checklist\n\n### SurgePix API\n\nNo score change since it was listed.\n\n## Verdicts\n\n**fal image models.** Hundreds of image models, including FLUX, Nano Banana, GPT Image, Seedream, Recraft and Ideogram, on one key that can now be limited to named models and a read-only preset. Billing units vary by model, per image, per megapixel or per token, and there's no free tier or idempotency key.\n\n**SurgePix API.** A small, readable API with async tasks and MIT skill scripts that cover posters, decks, edits and translation. Only background removal is documented, the terms name no company and restrict commercial use and automated querying, and uploaded files become public URLs.\n\n## Before you call either\n\n### fal image models\n\n1. Fetch `https://fal.ai/models/\u003cendpoint-id\u003e/llms.txt` before calling a model to get its schema and price\n2. POST to `https://queue.fal.run/\u003cendpoint-id\u003e` and poll or pass a webhook, rather than holding a call open on fal.run\n3. Give agents a key with the `API` preset limited to the image models they call. `FULL` and legacy ADMIN keys can deploy and manage apps\n4. On a 429 with `X-Fal-needs-retry: 1`, back off 1, 2, 4 and 8 seconds. Don't resubmit a queued request, it's billed again\n5. Download outputs you need to keep. CDN retention defaults to at least 7 days, set `X-Fal-Object-Lifecycle-Preference` to change it\n\n### SurgePix API\n\n1. Send the key as the raw `authorization` header value, with no `Bearer` prefix\n2. Don't upload confidential files. The upload flow returns a public URL for every file\n3. Check `code` in the JSON body as well as the HTTP status, since failures come back as a non-zero `code` with a `msg`\n4. Poll `GET /tasks/{taskId}` within 24 hours, after which the task returns 404\n5. Get written permission before using outputs commercially, since the terms restrict commercial use\n\n## Tutorials\n\n- [Create a landscape hero image with fal](https://www.anchorterminal.com/tutorials/fal-image/), for fal image models\n\n## Questions\n\n### Which is better for AI agents, fal image models or SurgePix API?\n\nfal image models scores 70.7 (BB) on agent readiness against SurgePix API's 36 (F), and leads in 6 of 7 scored categories.\n\n### Can an agent call fal image models and SurgePix API without installing anything?\n\nYes. fal image models has a hosted endpoint at https://queue.fal.run and SurgePix API at https://api.surgepix.ai/api.\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/fal-image-vs-surgepix.json, and with the fewest tokens: https://www.anchorterminal.com/compare/fal-image-vs-surgepix.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"fal-image\", \"b\": \"surgepix\"}`. From a terminal: `anchor compare fal-image surgepix`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/fal-image.json and https://www.anchorterminal.com/api/v1/tools/surgepix.json\n\n## Other comparisons with fal image models or SurgePix API\n\n- [Adobe Firefly API vs fal image models](https://www.anchorterminal.com/compare/adobe-firefly-vs-fal-image.md)\n- [Adobe Firefly API vs SurgePix API](https://www.anchorterminal.com/compare/adobe-firefly-vs-surgepix.md)\n- [ArtCraft vs fal image models](https://www.anchorterminal.com/compare/artcraft-vs-fal-image.md)\n- [ArtCraft vs SurgePix API](https://www.anchorterminal.com/compare/artcraft-vs-surgepix.md)\n- [Black Forest Labs FLUX API vs fal image models](https://www.anchorterminal.com/compare/black-forest-labs-vs-fal-image.md)\n- [Black Forest Labs FLUX API vs SurgePix API](https://www.anchorterminal.com/compare/black-forest-labs-vs-surgepix.md)\n- [Bria API vs fal image models](https://www.anchorterminal.com/compare/bria-vs-fal-image.md)\n- [Bria API vs SurgePix API](https://www.anchorterminal.com/compare/bria-vs-surgepix.md)\n- [fal image models vs Google Imagen](https://www.anchorterminal.com/compare/fal-image-vs-google-imagen.md)\n- [fal image models vs Ideogram API](https://www.anchorterminal.com/compare/fal-image-vs-ideogram.md)\n- [fal image models vs Iris-3B](https://www.anchorterminal.com/compare/fal-image-vs-iris-3b.md)\n- [fal image models vs Leonardo.Ai API](https://www.anchorterminal.com/compare/fal-image-vs-leonardo-ai.md)\n- [fal image models vs OpenAI Image API](https://www.anchorterminal.com/compare/fal-image-vs-openai-image-api.md)\n- [fal image models vs Qwen-Image 2.1 (Model Studio)](https://www.anchorterminal.com/compare/fal-image-vs-qwen-image-2-1.md)\n- [fal image models vs Recraft API](https://www.anchorterminal.com/compare/fal-image-vs-recraft.md)\n- [fal image models vs Replicate image models](https://www.anchorterminal.com/compare/fal-image-vs-replicate-image.md)\n- [fal image models vs Seedream on BytePlus ModelArk](https://www.anchorterminal.com/compare/fal-image-vs-seedream-on-byteplus-modelark.md)\n- [fal image models vs Stability AI Image API](https://www.anchorterminal.com/compare/fal-image-vs-stability-ai-image.md)\n- [Google Imagen vs SurgePix API](https://www.anchorterminal.com/compare/google-imagen-vs-surgepix.md)\n- [Ideogram API vs SurgePix API](https://www.anchorterminal.com/compare/ideogram-vs-surgepix.md)\n- [Iris-3B vs SurgePix API](https://www.anchorterminal.com/compare/iris-3b-vs-surgepix.md)\n- [Leonardo.Ai API vs SurgePix API](https://www.anchorterminal.com/compare/leonardo-ai-vs-surgepix.md)\n- [OpenAI Image API vs SurgePix API](https://www.anchorterminal.com/compare/openai-image-api-vs-surgepix.md)\n- [Qwen-Image 2.1 (Model Studio) vs SurgePix API](https://www.anchorterminal.com/compare/qwen-image-2-1-vs-surgepix.md)\n- [Recraft API vs SurgePix API](https://www.anchorterminal.com/compare/recraft-vs-surgepix.md)\n- [Replicate image models vs SurgePix API](https://www.anchorterminal.com/compare/replicate-image-vs-surgepix.md)\n- [Seedream on BytePlus ModelArk vs SurgePix API](https://www.anchorterminal.com/compare/seedream-on-byteplus-modelark-vs-surgepix.md)\n- [Stability AI Image API vs SurgePix API](https://www.anchorterminal.com/compare/stability-ai-image-vs-surgepix.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": "2026-11-02", "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 image models vs SurgePix API", "url": "" } ], "description": "fal image models scores 70.7 (BB) to SurgePix's 36 (F) for image generation. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "fal image models BB 70.7", "SurgePix API F 36", "scores" ], "h1": "fal image models vs SurgePix API", "image": "https://www.anchorterminal.com/assets/og/default.png", "path": "/compare/fal-image-vs-surgepix", "published": "2026-10-01", "section": "tools", "title": "fal image models vs SurgePix for AI agents in 2026: scores and prices", "toc": null, "updated": "2026-11-02", "url": "https://www.anchorterminal.com/compare/fal-image-vs-surgepix" }, "tokens": { "markdown": 5500, "slim": 3530 }, "version": 1 }