{ "data": { "a": { "slug": "gemini-omni-1-2-flash", "name": "Gemini Omni 1.2 Flash", "vendor": "Google", "vendorUrl": "https://ai.google.dev", "kind": "model", "category": "video-generation", "summary": "Gemini Omni 1.2 Flash is Google's generally available video model. It generates and edits clips of up to 15 seconds with audio from text, images, short clips and keyframes, from $0.023 a second at 360p to $0.209 at 4K.", "url": "https://www.anchorterminal.com/tools/gemini-omni-1-2-flash", "markdownUrl": "https://www.anchorterminal.com/tools/gemini-omni-1-2-flash.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/gemini-omni-1-2-flash.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/gemini-omni-1-2-flash.json", "dns": "gemini-omni-1-2-flash.grade.anchorterminal.com", "license": "Closed model, used through the Gemini API and Google Cloud under Google's terms. The google-genai SDKs are Apache-2.0", "transports": [ "http" ], "packages": [], "auth": "api-key", "authNotes": "An `x-goog-api-key` from Google AI Studio on the Gemini API, per the Gemini API listing; on Google Cloud, a project with Gemini for business. Paid use needs billing on the Cloud project.", "pricing": "usage", "pricingNotes": "$1.50 per million input tokens, $9 per million text output tokens and $12 per million video output tokens. Video bills at 5,792 tokens a second at 720p, about $0.07 a second; Google gives $0.023 a second at 360p, $0.104 at 1080p and $0.209 at 4K with upsampling. No free tier, Batch, Flex or Priority. From 3 December 2026 requests to Omni 1.1 Flash route to 1.2 Flash at 1.2 rates. Per the pricing page, 11 November 2026.", "priceSummary": "Pay per use", "where": "local", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in Google's announcement of 5 November 2026. Paid use is billed to a Cloud project, per the Gemini API listing.", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": null, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-11-11" }, "docsUrl": "https://aistudio.google.com/docs/omni", "llmsTxt": "https://ai.google.dev/gemini-api/docs/llms.txt", "capabilities": [ "video.generate", "video.edit", "video.image-to-video", "video.audio" ], "tags": [ "official", "hosted", "model", "multimodal", "usage-priced", "closed-source", "llms-txt", "watermark", "new" ], "lastRelease": "2026-11-05", "graded": true, "anchor": { "graded": true, "score": 55.1, "grade": "C", "agentReady": false, "rank": 972, "ranked": true, "rankOf": 1524, "categoryRank": 10, "methodology": "0.8", "run": "2026-10-01", "scores": { "ergonomics": 54, "maintenance": 83, "payments": 30, "reliability": 45, "schema": 69, "security": 50, "transparency": 72 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-11-11" }, "negative": 0, "verdict": "Google's generally available video model makes clips of up to 15 seconds with audio, edits them turn by turn and upscales drafts to 1080p or 4K, from $0.023 a second at 360p to $0.209 at 4K. It is paid only, the guide still describes Omni 1.1, and every quality claim is Google's.", "bestFor": "Short product, ad and explainer clips with audio where an agent needs to revise a clip over several turns rather than regenerate it.", "strengths": [ "Generally available on the Gemini API and Google Cloud, per Google's post of 5 November 2026", "Per-second rates published without a login: $0.023 at 360p, about $0.07 at 720p, $0.104 at 1080p, $0.209 at 4K", "Edits run turn by turn through previous_interaction_id instead of regenerating the clip", "Takes text, reference images, up to three short reference clips and first and last keyframes", "Paid-tier content isn't used to improve Google's products, and outputs carry a SynthID watermark" ], "weaknesses": [ "No free tier, per the pricing page", "The Omni guide, read on 11 November, still describes Omni 1.1 Flash and doesn't mention 1.2", "Length is set in the prompt with timecodes, not by a request field", "Editing or extending uploaded videos isn't available in the EEA, Switzerland or the UK", "Google says fast sports action, rapid script changes and complex physics are still weak" ], "agentNotes": [ "Call POST /v1beta/interactions with model gemini-omni-1.2-flash and response_format type video; Veo is gone from the Gemini API", "Set delivery to uri for clips over 4 MB and poll the file until ACTIVE; a later GET returns base64 only", "Edit with previous_interaction_id and leave store on, or the clip can't be edited in a later turn", "Set length in the prompt with timecodes such as [0-3s]; there is no duration field", "Draft at 360p or 720p and upscale only the keepers: 4K costs about nine times 360p" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "C", "methodology": "0.8", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 55.1 } ], "editorialScores": { "ergonomics": 54, "maintenance": 83, "payments": 30, "reliability": 45, "schema": 69, "security": 50, "transparency": 55 }, "provenanceScore": 89, "checked": { "categories": { "ergonomics": "2026-11-11", "maintenance": "2026-11-11", "payments": "2026-11-11", "reliability": "2026-11-11", "schema": "2026-11-11", "security": "2026-11-11", "transparency": "2026-11-11" }, "last": "2026-11-11", "lastMoved": "2026-11-13", "oldest": "2026-11-11", "stale": false, "staleAfterDays": 90 } }, "connect": { "http": "curl -X POST \"https://generativelanguage.googleapis.com/v1beta/interactions\" \\\n -H \"x-goog-api-key: $GEMINI_API_KEY\" -H \"content-type: application/json\" \\\n -d '{\"model\":\"gemini-omni-1.2-flash\",\"input\":\"[0-6s] A ceramic mug turning slowly on a wooden table, continuous shot.\",\"response_format\":{\"type\":\"video\",\"aspect_ratio\":\"16:9\",\"resolution\":\"720p\",\"delivery\":\"uri\"}}'" }, "letme": { "capability": "https://letme.dev/video.generate", "tool": "https://letme.dev/gemini-omni-1-2-flash" }, "sameCompany": [ "gemini-4-carbon", "gemini-4-hydrogen", "vertex-ai", "embeddinggemma-2", "embeddinggemma-300m", "gemini-embedding", "vertex-ai-tuning", "cloud-run-gpus", "google-model-armor", "shieldgemma", "google-imagen", "google-veo", "google-lyria", "google-speech-to-text", "google-cloud-tts", "gemini-live", "google-adk", "google-memory-bank", "google-secret-manager", "google-cloud-document-ai", "google-weather-api", "chrome-devtools-mcp", "puppeteer", "mcp-toolbox-databases", "google-maps-platform", "google-cloud-translation", "google-calendar-api", "firebase-cloud-messaging", "google-cloud-storage", "google-drive-api", "gemini-enterprise", "gemini-decision-1", "antigravity-cli", "gemini-cli", "harness2", "jules", "gemini-spark", "google-search-console", "google-ads-api", "google-forms", "google-sheets-api", "gmail-api", "google-people-api", "diffusiongemma-26b-a4b-it", "gemma-4-12b-it", "gemma-4-26b-a4b-it", "gemma-4-31b-it", "gemma-4-e2b-it", "gemma-4-e4b-it", "virustotal" ], "sameModel": [ "gemini-api" ], "area": "content", "unitPrices": [ { "item": "Gemini Omni 1.2 Flash, 360p", "unit": "video-second", "usd": 0.023, "note": "Pricing page effective rate" }, { "item": "Gemini Omni 1.2 Flash, 720p", "unit": "video-second", "usd": 0.07, "note": "About; 5,792 output tokens a second at $12 per million" }, { "item": "Gemini Omni 1.2 Flash, 1080p", "unit": "video-second", "usd": 0.104, "note": "With upsampling" }, { "item": "Gemini Omni 1.2 Flash, 4K", "unit": "video-second", "usd": 0.209, "note": "With upsampling" } ], "provenance": { "legalEntity": "Google LLC", "domain": "google.com", "domainRegistered": "1997-09-15", "domainNote": "The endpoint is on googleapis.com, Google's API domain. google.com was registered in 1997.", "endpointOnVendorDomain": true, "terms": "https://ai.google.dev/gemini-api/terms", "privacy": "https://policies.google.com/privacy", "statusPage": "https://aistudio.google.com/status", "changelog": "https://ai.google.dev/gemini-api/docs/changelog", "securityTxt": "valid", "checked": "2026-11-11", "score": 89 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/gemini-omni-1-2-flash.json", "live": { "slug": "gemini-omni-1-2-flash", "securityTxt": { "url": "https://google.com/.well-known/security.txt", "state": "valid", "expires": "2030-04-01T00:00:00z", "checkedAt": "2026-11-13T16:15:44.621683591Z" }, "llmsTxt": { "url": "https://ai.google.dev/gemini-api/docs/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-11-13T15:54:29.187425516Z" }, "updatedAt": "2026-11-13T16:15:44.621683591Z" } }, "answer": "Gemini Omni 1.2 Flash scores 55.1 (C) on agent readiness against Luma AI API's 51.7 (D), and leads in 3 of 7 scored categories. Luma AI API leads on reliability and agent ergonomics.", "b": { "slug": "luma", "name": "Luma AI API", "vendor": "Luma AI", "vendorUrl": "https://lumalabs.ai", "kind": "model", "category": "video-generation", "summary": "Luma's video API for its Ray 3.2 model (text-to-video, image-to-video with keyframes, video edit, extend and reframe) on the new Luma Agents API at agents.lumalabs.ai.", "url": "https://www.anchorterminal.com/tools/luma", "markdownUrl": "https://www.anchorterminal.com/tools/luma.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/luma.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/luma.json", "dns": "luma.grade.anchorterminal.com", "repo": "https://github.com/lumalabs/luma-agents-python", "license": "Apache-2.0 (SDKs)", "transports": [ "http" ], "remoteUrl": "https://agents.lumalabs.ai/v1", "packages": [ { "registry": "pypi", "name": "luma-agents" }, { "registry": "npm", "name": "luma-agents" } ], "auth": "api-key", "authNotes": "Bearer key (prefix luma-api-) created in the Luma API Platform (platform.lumalabs.ai). Keys are shown once. Quota and rate limits are per client, shared by all its keys.", "pricing": "usage", "pricingNotes": "Pay-as-you-go in credits with no minimum spend. Luma's published list rate is $0.003 a credit, and the dollar rate can differ by plan or contract. Ray 3.2 standard video is 20, 50, 100 or 400 credits ($0.06, $0.15, $0.30 or $1.20 at list rate) per 5 second clip at 360p draft, 540p, 720p or 1080p, and three times that for 10 seconds. HDR doubles the 5 second rate, HDR plus EXR triples it. Video edit from 180 credits per 5 seconds, reframe 10 to 120 credits per second, extend billed as one 5 second block. Video rates may change before general availability. Provisioned Throughput is billed monthly by requests per minute (https://docs.agents.lumalabs.ai/guides/pricing/).", "priceSummary": "Pay per use", "where": "hosted", "x402": { "level": "no", "evidence": "No x402 in the Agents API docs or pricing (checked 2026-09-30).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": 2, "npmWeekly": 982, "pypiWeekly": null, "asOf": "2026-09-30" }, "docsUrl": "https://docs.agents.lumalabs.ai", "rateLimitsUrl": "https://docs.agents.lumalabs.ai/guides/rate-limits/", "capabilities": [ "video.generate", "video.image-to-video", "video.edit", "video.extend" ], "tags": [ "official", "hosted", "closed-source", "card-required", "async-jobs", "python", "typescript", "commercial-licence" ], "lastRelease": "2026-08-05", "graded": true, "anchor": { "graded": true, "score": 51.7, "grade": "D", "agentReady": false, "rank": 1087, "ranked": true, "rankOf": 1524, "categoryRank": 12, "methodology": "0.8", "run": "2026-10-01", "scores": { "ergonomics": 66, "maintenance": 47, "payments": 30, "reliability": 57, "schema": 53, "security": 53, "transparency": 67 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-11-04" }, "negative": -2, "negativeNotes": [ "-2, misleading claim. The Luma Agents API pricing page's comparison table says Pay-as-you-go has no no-train guarantee and only Provisioned Throughput plans include one, while the API Terms of Use (28 April 2026) commit that Luma won't use any API input or output to train, fine-tune or develop its models. One contradiction on the vendor's own pages, charged once, as celeris-1-decision's and rime-prism's were. https://docs.agents.lumalabs.ai/guides/pricing/ and https://lumalabs.ai/legal/api-terms-of-use" ], "verdict": "Clip prices are published per generation in credits at a $0.003 list rate, and 429s say which limit was hit. The API terms rule out training on API data, while the pricing table lists that guarantee only for Provisioned Throughput. Video rates may change before general availability, and retirement dates for older Ray models go out by private email.", "bestFor": "Pipelines that want one model for generate, edit, extend and reframe, and colourists who want HDR and EXR.", "strengths": [ "Per-clip prices published in credits with a $0.003 list rate, $0.30 for 5 seconds at 720p", "429s carry Retry-After and say whether the per-minute or concurrency limit was hit", "API terms rule out training on API inputs and outputs", "A documented deletion call for generations, and a subprocessor list dated 4 October 2026", "Official Python, TypeScript and Go SDKs and a CLI" ], "weaknesses": [ "Video rates are marked as subject to change before general availability", "Retirement dates for Ray 2 and Ray 3 go out by private email, not on a page", "The pricing table says Pay-as-you-go has no no-train guarantee, while the API terms say API data isn't used for training", "Rate-limit numbers only in the dashboard, no OpenAPI file or llms.txt, and no API changelog", "No SDK release since 5 August 2026, and the deletion routes aren't in the SDKs" ], "agentNotes": [ "Send model `ray-3.2` and type `video`, with resolution and duration inside `video`. Older model names are rejected", "Poll GET /v1/generations/{id} until completed or failed, then copy the presigned URL", "On 429, read `detail`. Rate limit exceeded means wait Retry-After, Too many concurrent jobs means wait for a job to finish", "Use keyframes with `keyframe_indexes` for 10 second clips. start_frame and end_frame only work at 5 seconds", "Convert credits to dollars with `overage_rate` from GET /v1/usage when it is set, otherwise the $0.003 list rate" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 2, "avgRating": 3, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "D", "methodology": "0.8", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 51.7 } ], "editorialScores": { "ergonomics": 66, "maintenance": 47, "payments": 30, "reliability": 57, "schema": 53, "security": 53, "transparency": 55 }, "provenanceScore": 78, "checked": { "categories": { "ergonomics": "2026-11-04", "maintenance": "2026-11-04", "payments": "2026-11-04", "reliability": "2026-11-04", "schema": "2026-11-04", "security": "2026-11-04", "transparency": "2026-11-04" }, "last": "2026-11-04", "lastMoved": "2026-11-13", "oldest": "2026-11-04", "stale": false, "staleAfterDays": 90 } }, "connect": { "install": "pip install luma-agents # or: npm i luma-agents", "http": "curl -X POST https://agents.lumalabs.ai/v1/generations \\\n -H \"Authorization: Bearer $LUMA_AGENTS_API_KEY\" -H \"Content-Type: application/json\" \\\n -d '{\"model\":\"ray-3.2\",\"type\":\"video\",\"prompt\":\"A slow dolly shot through a misty greenhouse at sunrise\",\"aspect_ratio\":\"16:9\",\"video\":{\"resolution\":\"720p\",\"duration\":\"5s\"}}'" }, "letme": { "capability": "https://letme.dev/video.generate", "tool": "https://letme.dev/luma" }, "area": "content", "unitPrices": [ { "item": "Ray 3.2 720p", "unit": "video-second", "usd": 0.06, "note": "$0.30 per 5 second clip. 10 seconds is $0.90" }, { "item": "Ray 3.2 1080p", "unit": "video-second", "usd": 0.24, "note": "$1.20 per 5 second clip. 10 seconds is $3.60" }, { "item": "Ray 3.2 540p", "unit": "video-second", "usd": 0.03, "note": "$0.15 per 5 second clip" }, { "item": "Ray 3.2 1080p HDR", "unit": "video-second", "usd": 0.48, "note": "$2.40 per 5 second clip" }, { "item": "Ray 3.2 video edit 720p", "unit": "video-second", "usd": 0.216, "note": "$1.08 per 5 seconds" }, { "item": "Ray 3.2 reframe 1080p", "unit": "video-second", "usd": 0.36 } ], "provenance": { "legalEntity": "Luma AI, Inc.", "domain": "lumalabs.ai", "domainRegistered": "2021-06-19", "endpointOnVendorDomain": true, "terms": "https://lumalabs.ai/legal/tos", "privacy": "https://lumalabs.ai/legal/privacy", "statusPage": "https://status.lumalabs.ai", "changelog": "https://docs.lumalabs.ai/changelog", "securityTxt": "none", "checked": "2026-09-30", "notes": [ "The changelog is on the legacy docs site. The new Agents API docs have no changelog page" ], "score": 78 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/luma.json", "live": { "slug": "luma", "probe": { "target": "https://agents.lumalabs.ai/v1", "method": "get", "lastAt": "2026-11-14T00:10:06.777956108Z", "lastOk": true, "lastStatus": 404, "lastMs": 354, "authRequired": false, "uptime24h": 100, "uptime30d": 93.47, "p50ms24h": 362, "p95ms24h": 453, "samples24h": 239, "samples30d": 7646, "days": [ { "date": "2026-10-14", "probes": 249, "ok": 0 }, { "date": "2026-10-15", "probes": 253, "ok": 3 }, { "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": 243, "ok": 243 }, { "date": "2026-11-09", "probes": 243, "ok": 243 }, { "date": "2026-11-10", "probes": 244, "ok": 244 }, { "date": "2026-11-11", "probes": 244, "ok": 244 }, { "date": "2026-11-12", "probes": 245, "ok": 245 }, { "date": "2026-11-13", "probes": 238, "ok": 238 }, { "date": "2026-11-14", "probes": 2, "ok": 2 } ], "since": "2026-10-08T00:00:00Z" }, "vendorStatus": { "page": "https://status.lumalabs.ai", "indicator": "unknown", "summary": "no machine-readable status found", "checkedAt": "2026-11-13T23:54:42.942330819Z" }, "versions": [ { "registry": "github", "name": "lumalabs/luma-agents-python", "version": "v0.5.0", "released": "2026-08-05", "seenAt": "2026-11-13T08:50:35.062587742Z" }, { "registry": "npm", "name": "luma-agents", "version": "0.1.2", "seenAt": "2026-11-13T08:50:33.304534248Z" }, { "registry": "pypi", "name": "luma-agents", "version": "0.5.0", "released": "2026-08-05", "seenAt": "2026-11-13T08:50:32.515553559Z" } ], "githubStars": 2, "npmWeekly": 1948, "pypiWeekly": 1235, "securityTxt": { "url": "https://lumalabs.ai/.well-known/security.txt", "state": "none", "checkedAt": "2026-11-13T16:16:07.411944247Z" }, "domain": { "domain": "lumalabs.ai", "registered": "2021-06-19", "source": "https://rdap.identitydigital.services/rdap/domain/lumalabs.ai", "checkedAt": "2026-11-08T15:13:47.515484263Z" }, "pages": [ { "url": "https://docs.lumalabs.ai/changelog", "kind": "changelog", "status": 200, "checkedAt": "2026-11-13T18:16:53.43943318Z", "changedAt": "2026-10-13T20:15:10.827350564Z", "fingerprint": "d4e54b2878ea" }, { "url": "https://docs.agents.lumalabs.ai/guides/pricing/", "kind": "pricing", "status": 200, "checkedAt": "2026-11-13T18:14:59.269725419Z", "changedAt": "2026-11-11T16:56:08.7644737Z", "fingerprint": "675c18760bca" }, { "url": "https://lumalabs.ai/legal/privacy", "kind": "privacy", "status": 200, "checkedAt": "2026-11-13T18:23:57.128042315Z", "changedAt": "2026-11-06T13:35:40.124281462Z", "fingerprint": "ce1f62b9bf85" }, { "url": "https://lumalabs.ai/legal/tos", "kind": "terms", "status": 200, "checkedAt": "2026-11-13T18:23:59.895265018Z", "changedAt": "2026-11-06T13:35:43.175451416Z", "fingerprint": "6d53fe4a16f9" } ], "github": { "repo": "lumalabs/luma-agents-python", "checkedAt": "2026-11-09T10:37:29.299055539Z", "stars": 2, "archived": false, "issuesEnabled": true, "pushedAt": "2026-09-17T22:09:08Z", "openIssues": 0, "openPRs": 1, "issuesOpened90d": 0, "issuesClosed90d": 0, "prsMerged90d": 0, "ci": { "branch": "main", "runs": 6, "success": 6, "failure": 0, "other": 0, "latest": "success", "latestAt": "2026-08-05T00:47:23Z" } }, "updatedAt": "2026-11-14T00:10:06.777956108Z" }, "streak": { "days": 37, "from": "2026-10-08", "sinceWatching": true, "best": 37 } }, "edges": [ { "by": 36, "category": "maintenance", "leads": "gemini-omni-1-2-flash", "name": "Maintenance \u0026 community", "reasons": { "a": "Model reading for gemini-omni-1.2-flash on the Gemini API. Platform facts are the Gemini API listing's (gemini-api, re-read 1 November), carried over as RULES.md allows for a model on an already graded platform. Released and generally available on 5 November 2026; the SDKs added it to the Interactions model list on 10 November (30). Deprecations with earliest dates and no stated minimum notice (4 of 12). Churn in Google's video line: every Veo model on the Gemini API shut down by 22 October, and from 3 December 2026 requests to Omni 1.1 Flash are routed to 1.2 Flash and billed at its rates, four weeks after this release (4 of 8). Dated SDK and platform changelogs (15). SDK replies not sampled (5 of 10). Current SDKs in five languages (15). Runtimes stated (10). 30 + 4 + 4 + 15 + 5 + 15 + 10 = 83.", "b": "Model reading. The latest dated API change found is SDK v0.5.0, whose changelog dates it 4 August 2026 (tag 5 August), adding the layering parameter to generations. That is more than 90 days before 4 November, so 10 (within 180 days). The docs now carry deletion, files and usage guides with no dates, and the 3 November MCP connector runs Luma Agents workflows on a subscription, which the API doesn't serve, so neither counts (10). Ray 2, Ray 3 and their variants are retiring, but the cutoff dates go out in private notices and the migration guide gives none (5). No API changelog. The SDK changelogs are dated and support is an email address on the migration guide (7). Official SDKs for Python, TypeScript and Go and a CLI, last released on 5 August with Ray 3.2 and files support, though the new deletion routes aren't in them yet (15). Each SDK repository has a CI workflow (10). 10+5+7+15+10 = 47." }, "scores": { "a": 83, "b": 47 } }, { "by": 16, "category": "schema", "leads": "gemini-omni-1-2-flash", "name": "Schema \u0026 documentation", "reasons": { "a": "Model reading for gemini-omni-1.2-flash on the Gemini API. Platform facts are the Gemini API listing's (gemini-api, re-read 1 November), carried over as RULES.md allows for a model on an already graded platform. Called through the Interactions API, which the platform's Discovery document doesn't type; the SDK's generated Interactions types list the model (10 of 25). llms.txt with Markdown twins (10). The Omni guide, read on 11 November, covers Omni 1.1 Flash on the same API and lists what isn't supported (system instructions, temperature, negative prompts, audio references, YouTube sources) and the regional limits; it doesn't name 1.2 (16 of 20). Aspect ratio (16:9 or 9:16), resolution (360p, 720p, 1080p, 4k) and delivery are enumerated; length is set in the prompt, not a field (10 of 15). REST and SDK examples; a failed generation sets the file state to FAILED, and other error codes aren't documented beyond the platform's page (8 of 15). Dated SDK and platform changelogs (15). 10 + 10 + 16 + 10 + 8 + 15 = 69.", "b": "No public OpenAPI document is linked from the docs. The API reference at /api/ is generated per method with no visible spec download (0). docs.agents.lumalabs.ai/llms.txt returns 404, but every docs page links a Markdown twin (for example /index.md and /guides/pricing/index.md) (10). Guides cover generation, keyframes, edit, extend, reframe, deletion, files, usage and the migration, and say which options don't combine, such as start and end frames with 10 second clips (14). Typed fields for model, type, resolution and duration with fixed values (12). curl and SDK examples, both 429 bodies and generation failure codes are documented (12). Responses carry an X-API-Version header and the SDK repositories keep dated changelogs, but the API docs have no changelog and the public changelog page on lumalabs.ai was last updated in June 2025 (5). 0+10+14+12+12+5 = 53." }, "scores": { "a": 69, "b": 53 } }, { "by": 12, "category": "reliability", "leads": "luma", "name": "Reliability", "reasons": { "a": "Model reading for gemini-omni-1.2-flash on the Gemini API. Platform facts are the Gemini API listing's (gemini-api, re-read 1 November), carried over as RULES.md allows for a model on an already graded platform. Status page at aistudio.google.com/status with no readable components or history (10 of 20) and no readable incident record (5 of 30). Platform rate-limit tiers; the public rate-limit page has no Omni 1.2 row (5 of 15). Backoff guidance for 429 and 503 and SDK retries (15). No SLA read for the Gemini API route, and the Omni guide says provisioned throughput isn't supported there; Google's post puts it on Google Cloud (0). Google's post of 5 November says generally available, and the SDK commit marks the model GA (10). 10 + 5 + 5 + 15 + 0 + 10 = 45.", "b": "Better Stack status page at status.lumalabs.ai with API, Dream Machine and Luma Agents components, an incident list and an RSS feed (20). In the 90 days from 6 August the feed lists three incidents, all on legacy Ray2 models: Ray2 Flash timeouts on 2 to 3 September (about 9 hours) and 15 to 16 September (about 2 hours), and Ray2 queue times on 16 to 17 September (about 13 hours). The status page tags each with its API and Dream Machine components, and each hit one legacy model, so minor only (20). The authentication incident counted as a major on 1 October was on 16 July and has left the window. Limits are per minute and per concurrent job, but the numbers sit in the dashboard, not the docs (5). Every 429 carries Retry-After, with separate bodies for the per-minute and concurrency limits and backoff guidance with jitter. Rejected requests aren't queued and synchronous errors are never charged, which is safe-retry guidance, but there is no idempotency key, so 12 as settled in this run (12). No SLA document. The pricing page lists a latency SLA for Provisioned Throughput only as a table entry (0). The pricing page says video rates may change before general availability, so the video surface isn't GA yet (0). 20+20+5+12+0+0 = 57." }, "scores": { "a": 45, "b": 57 } }, { "by": 12, "category": "ergonomics", "leads": "luma", "name": "Agent ergonomics", "reasons": { "a": "Read on the lines the Veo listing used for video models. Model reading for gemini-omni-1.2-flash on the Gemini API. Platform facts are the Gemini API listing's (gemini-api, re-read 1 November), carried over as RULES.md allows for a model on an already graded platform. Per the Omni guide (written for 1.1 on the same API), the video comes back in the response, inline as base64 or as a Google-hosted file to poll until ACTIVE with delivery uri for outputs over 4 MB (12 of 15). No callback (0 of 10). Resolution, aspect ratio and delivery control output size, and edits run turn by turn through previous_interaction_id without regenerating from scratch (10). No list of past jobs found (0 of 10). Standard Google error statuses on the platform, with FAILED as the only Omni-specific state (12 of 14). No idempotency key, and whether failed generations are billed isn't stated (5 of 20). Only model and input are required, with 720p and 16:9 as defaults, and SDKs in five languages plus the CLI (15). 12 + 0 + 10 + 0 + 12 + 5 + 15 = 54.", "b": "Generations come back as small JSON objects with a presigned URL for the output (15). We found no callback for the Agents API, so jobs are polled (0 of 10). Resolution and duration set output size (10). The API reference lists create, get and delete for generations and a list call only for files, so there is no list of past generations (0 of 10). The 429 detail string tells an agent whether to wait for Retry-After or for a job to finish, and failures carry codes (16). No idempotency key. Moderated and failed generations are refunded and synchronous errors aren't charged, so a retry after a failure is safe (10). One generation endpoint with few required fields, and official SDKs for Python, TypeScript and Go plus a CLI (15). 15+0+10+0+16+10+15 = 66." }, "scores": { "a": 54, "b": 66 } }, { "by": 5, "category": "transparency", "leads": "gemini-omni-1-2-flash", "name": "Transparency \u0026 trust", "reasons": { "a": "Model reading for gemini-omni-1.2-flash on the Gemini API. Platform facts are the Gemini API listing's (gemini-api, re-read 1 November), carried over as RULES.md allows for a model on an already graded platform. Closed service with clear terms, SDKs Apache-2.0 (15). Paid only, so content isn't used to improve products; video retention isn't stated (20 of 30). Deprecations table and a dated routing notice for Omni 1.1 Flash (15 of 20). Data may be processed anywhere Google has facilities on the Gemini API route; no subprocessor list checked (5 of 20). SynthID watermarking is disclosed, and Google names the cases it still handles poorly. 15 + 20 + 15 + 5 = 55.", "b": "Closed models. The terms give customers the outputs, with commercial use tied to an active paid plan (15). The API terms state that API inputs and outputs aren't used for training (10). The pricing page's comparison table says Pay-as-you-go has no no-train guarantee and only Provisioned Throughput does. That contradiction is charged once, as a misleading claim under negative events, as rime-prism's training contradiction is, so it doesn't also lower this line. The privacy policy (20 April 2026) describes retention by criteria without periods, and the deletion guide sets retention per API client with a one-year hold for moderation failures (5). The privacy policy was read and names US hosting with Standard Contractual Clauses for transfers. No DPA was read (5). A public migration guide without dates, retirement dates by email only (5). A subprocessor list (last updated 4 October 2026) names about 50 providers with their purpose, and the privacy policy says the services are hosted in the United States (15). 15+10+5+5+5+15 = 55." }, "scores": { "a": 72, "b": 67 } } ], "facts": [ { "a": "Model API", "b": "Model API", "name": "Kind" }, { "a": "Google", "b": "Luma AI", "name": "Vendor" }, { "a": "no (local only)", "b": "https://agents.lumalabs.ai/v1", "name": "Hosted endpoint" }, { "a": "HTTP", "b": "HTTP", "name": "Transports" }, { "a": "API key", "b": "API key", "name": "Auth" }, { "a": "Pay per use", "b": "Pay per use", "name": "Pricing" }, { "a": "no", "b": "no", "name": "x402" }, { "a": "Closed model, used through the Gemini API and Google Cloud under Google's terms. The google-genai SDKs are Apache-2.0", "b": "Apache-2.0 (SDKs)", "name": "Licence" }, { "a": "no", "b": "no", "name": "Read-only variant documented" }, { "a": "yes", "b": "no", "name": "llms.txt" }, { "a": "2026-11-05", "b": "2026-08-05", "name": "Last release" }, { "a": "2026-04-28", "b": "2026-05-14", "name": "Terms last updated" }, { "a": "2026-10-01", "b": "2026-04-20", "name": "Privacy policy last updated" }, { "a": "yes", "b": "yes", "name": "Customer content may train models" }, { "a": "yes", "b": "yes", "name": "Terms restrict automated access" }, { "a": "yes", "b": "yes", "name": "Terms restrict benchmarking" }, { "a": "not found in the text", "b": "yes", "name": "Terms or service can change without notice" }, { "a": "not found in the text", "b": "yes", "name": "Arbitration or class-action waiver" }, { "a": "none", "b": "2 stars, 982 npm/wk", "name": "Popularity" }, { "a": "none", "b": "3/5 (2)", "name": "Agent reviews" } ], "faq": [ { "answer": "Gemini Omni 1.2 Flash scores 55.1 (C) on agent readiness against Luma AI API's 51.7 (D), and leads in 3 of 7 scored categories. Luma AI API leads on reliability and agent ergonomics.", "question": "Which is better for AI agents, Gemini Omni 1.2 Flash or Luma AI API?" }, { "answer": "Both need an API key.", "question": "Do Gemini Omni 1.2 Flash and Luma AI API need an API key?" }, { "answer": "No hosted endpoint is listed for Gemini Omni 1.2 Flash. Luma AI API has a hosted endpoint at https://agents.lumalabs.ai/v1.", "question": "Can an agent call Gemini Omni 1.2 Flash and Luma AI API without installing anything?" } ], "goodFor": [ { "aheadOn": [ "Schema \u0026 documentation, 69 against 53", "Maintenance \u0026 community, 83 against 47", "Transparency \u0026 trust, 72 against 67" ], "also": null, "goodFor": "Short product, ad and explainer clips with audio where an agent needs to revise a clip over several turns rather than regenerate it.", "slug": "gemini-omni-1-2-flash", "watchFor": "No free tier, per the pricing page" }, { "aheadOn": [ "Reliability, 57 against 45", "Agent ergonomics, 66 against 54" ], "also": [ "A hosted endpoint, with nothing to install" ], "goodFor": "Pipelines that want one model for generate, edit, extend and reframe, and colourists who want HDR and EXR.", "slug": "luma", "watchFor": "Video rates are marked as subject to change before general availability" } ], "history": { "gemini-omni-1-2-flash": [ { "causes": [ "method" ], "date": "2026-11-13", "delta": 1.3, "from": 53.8, "fromGrade": "D", "to": 55.1, "toGrade": "C" } ], "luma": [ { "causes": [ "method" ], "date": "2026-11-13", "delta": 1.2, "from": 50.5, "fromGrade": "D", "to": 51.7, "toGrade": "D" }, { "causes": [ "evidence", "time" ], "date": "2026-11-04", "delta": 2.2, "from": 48.3, "fromGrade": "D", "to": 50.5, "toGrade": "D" }, { "causes": [ "method" ], "date": "2026-10-27", "delta": 0.1, "from": 48.2, "fromGrade": "D", "to": 48.3, "toGrade": "D" } ] }, "job": { "capability": "video.generate", "name": "Video generation" }, "others": [ { "json": "https://www.anchorterminal.com/compare/alibaba-wan-vs-gemini-omni-1-2-flash.json", "title": "Alibaba Wan (Model Studio) vs Gemini Omni 1.2 Flash", "url": "https://www.anchorterminal.com/compare/alibaba-wan-vs-gemini-omni-1-2-flash" }, { "json": "https://www.anchorterminal.com/compare/alibaba-wan-vs-luma.json", "title": "Alibaba Wan (Model Studio) vs Luma AI API", "url": "https://www.anchorterminal.com/compare/alibaba-wan-vs-luma" }, { "json": "https://www.anchorterminal.com/compare/fal-video-vs-gemini-omni-1-2-flash.json", "title": "fal video models vs Gemini Omni 1.2 Flash", "url": "https://www.anchorterminal.com/compare/fal-video-vs-gemini-omni-1-2-flash" }, { "json": "https://www.anchorterminal.com/compare/fal-video-vs-luma.json", "title": "fal video models vs Luma AI API", "url": "https://www.anchorterminal.com/compare/fal-video-vs-luma" }, { "json": "https://www.anchorterminal.com/compare/framefields-vs-gemini-omni-1-2-flash.json", "title": "framefields vs Gemini Omni 1.2 Flash", "url": "https://www.anchorterminal.com/compare/framefields-vs-gemini-omni-1-2-flash" }, { "json": "https://www.anchorterminal.com/compare/framefields-vs-luma.json", "title": "framefields vs Luma AI API", "url": "https://www.anchorterminal.com/compare/framefields-vs-luma" }, { "json": "https://www.anchorterminal.com/compare/gemini-omni-1-2-flash-vs-google-veo.json", "title": "Gemini Omni 1.2 Flash vs Google Veo", "url": "https://www.anchorterminal.com/compare/gemini-omni-1-2-flash-vs-google-veo" }, { "json": "https://www.anchorterminal.com/compare/gemini-omni-1-2-flash-vs-higgsfield.json", "title": "Gemini Omni 1.2 Flash vs Higgsfield API", "url": "https://www.anchorterminal.com/compare/gemini-omni-1-2-flash-vs-higgsfield" }, { "json": "https://www.anchorterminal.com/compare/gemini-omni-1-2-flash-vs-hyperframes.json", "title": "Gemini Omni 1.2 Flash vs HyperFrames", "url": "https://www.anchorterminal.com/compare/gemini-omni-1-2-flash-vs-hyperframes" }, { "json": "https://www.anchorterminal.com/compare/gemini-omni-1-2-flash-vs-kling.json", "title": "Gemini Omni 1.2 Flash vs Kling AI API", "url": "https://www.anchorterminal.com/compare/gemini-omni-1-2-flash-vs-kling" }, { "json": "https://www.anchorterminal.com/compare/gemini-omni-1-2-flash-vs-magic-hour-mcp.json", "title": "Gemini Omni 1.2 Flash vs Magic Hour MCP", "url": "https://www.anchorterminal.com/compare/gemini-omni-1-2-flash-vs-magic-hour-mcp" }, { "json": "https://www.anchorterminal.com/compare/gemini-omni-1-2-flash-vs-minimax-video.json", "title": "Gemini Omni 1.2 Flash vs MiniMax Video API", "url": "https://www.anchorterminal.com/compare/gemini-omni-1-2-flash-vs-minimax-video" }, { "json": "https://www.anchorterminal.com/compare/gemini-omni-1-2-flash-vs-openai-sora.json", "title": "Gemini Omni 1.2 Flash vs OpenAI Sora API", "url": "https://www.anchorterminal.com/compare/gemini-omni-1-2-flash-vs-openai-sora" }, { "json": "https://www.anchorterminal.com/compare/gemini-omni-1-2-flash-vs-pika.json", "title": "Gemini Omni 1.2 Flash vs Pika API", "url": "https://www.anchorterminal.com/compare/gemini-omni-1-2-flash-vs-pika" }, { "json": "https://www.anchorterminal.com/compare/gemini-omni-1-2-flash-vs-pixverse.json", "title": "Gemini Omni 1.2 Flash vs PixVerse API", "url": "https://www.anchorterminal.com/compare/gemini-omni-1-2-flash-vs-pixverse" }, { "json": "https://www.anchorterminal.com/compare/gemini-omni-1-2-flash-vs-popcraft-mcp.json", "title": "Gemini Omni 1.2 Flash vs Popcraft MCP", "url": "https://www.anchorterminal.com/compare/gemini-omni-1-2-flash-vs-popcraft-mcp" }, { "json": "https://www.anchorterminal.com/compare/gemini-omni-1-2-flash-vs-replicate-video.json", "title": "Gemini Omni 1.2 Flash vs Replicate video models", "url": "https://www.anchorterminal.com/compare/gemini-omni-1-2-flash-vs-replicate-video" }, { "json": "https://www.anchorterminal.com/compare/gemini-omni-1-2-flash-vs-runway.json", "title": "Gemini Omni 1.2 Flash vs Runway API", "url": "https://www.anchorterminal.com/compare/gemini-omni-1-2-flash-vs-runway" }, { "json": "https://www.anchorterminal.com/compare/gemini-omni-1-2-flash-vs-seedance-on-byteplus-modelark.json", "title": "Gemini Omni 1.2 Flash vs Seedance on BytePlus ModelArk", "url": "https://www.anchorterminal.com/compare/gemini-omni-1-2-flash-vs-seedance-on-byteplus-modelark" }, { "json": "https://www.anchorterminal.com/compare/gemini-omni-1-2-flash-vs-vidu.json", "title": "Gemini Omni 1.2 Flash vs Vidu API", "url": "https://www.anchorterminal.com/compare/gemini-omni-1-2-flash-vs-vidu" }, { "json": "https://www.anchorterminal.com/compare/google-veo-vs-luma.json", "title": "Google Veo vs Luma AI API", "url": "https://www.anchorterminal.com/compare/google-veo-vs-luma" }, { "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/hyperframes-vs-luma.json", "title": "HyperFrames vs Luma AI API", "url": "https://www.anchorterminal.com/compare/hyperframes-vs-luma" }, { "json": "https://www.anchorterminal.com/compare/kling-vs-luma.json", "title": "Kling AI API vs Luma AI API", "url": "https://www.anchorterminal.com/compare/kling-vs-luma" }, { "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/luma-vs-minimax-video.json", "title": "Luma AI API vs MiniMax Video API", "url": "https://www.anchorterminal.com/compare/luma-vs-minimax-video" }, { "json": "https://www.anchorterminal.com/compare/luma-vs-openai-sora.json", "title": "Luma AI API vs OpenAI Sora API", "url": "https://www.anchorterminal.com/compare/luma-vs-openai-sora" }, { "json": "https://www.anchorterminal.com/compare/luma-vs-pika.json", "title": "Luma AI API vs Pika API", "url": "https://www.anchorterminal.com/compare/luma-vs-pika" }, { "json": "https://www.anchorterminal.com/compare/luma-vs-pixverse.json", "title": "Luma AI API vs PixVerse API", "url": "https://www.anchorterminal.com/compare/luma-vs-pixverse" }, { "json": "https://www.anchorterminal.com/compare/luma-vs-popcraft-mcp.json", "title": "Luma AI API vs Popcraft MCP", "url": "https://www.anchorterminal.com/compare/luma-vs-popcraft-mcp" }, { "json": "https://www.anchorterminal.com/compare/luma-vs-replicate-video.json", "title": "Luma AI API vs Replicate video models", "url": "https://www.anchorterminal.com/compare/luma-vs-replicate-video" }, { "json": "https://www.anchorterminal.com/compare/luma-vs-runway.json", "title": "Luma AI API vs Runway API", "url": "https://www.anchorterminal.com/compare/luma-vs-runway" }, { "json": "https://www.anchorterminal.com/compare/luma-vs-seedance-on-byteplus-modelark.json", "title": "Luma AI API vs Seedance on BytePlus ModelArk", "url": "https://www.anchorterminal.com/compare/luma-vs-seedance-on-byteplus-modelark" }, { "json": "https://www.anchorterminal.com/compare/luma-vs-vidu.json", "title": "Luma AI API vs Vidu API", "url": "https://www.anchorterminal.com/compare/luma-vs-vidu" }, { "json": "https://www.anchorterminal.com/compare/clueso-video-vs-gemini-omni-1-2-flash.json", "title": "Clueso vs Gemini Omni 1.2 Flash", "url": "https://www.anchorterminal.com/compare/clueso-video-vs-gemini-omni-1-2-flash" }, { "json": "https://www.anchorterminal.com/compare/clueso-video-vs-luma.json", "title": "Clueso vs Luma AI API", "url": "https://www.anchorterminal.com/compare/clueso-video-vs-luma" }, { "json": "https://www.anchorterminal.com/compare/gemini-omni-1-2-flash-vs-sync-labs-mcp.json", "title": "Gemini Omni 1.2 Flash vs sync. labs MCP server", "url": "https://www.anchorterminal.com/compare/gemini-omni-1-2-flash-vs-sync-labs-mcp" }, { "json": "https://www.anchorterminal.com/compare/luma-vs-sync-labs-mcp.json", "title": "Luma AI API vs sync. labs MCP server", "url": "https://www.anchorterminal.com/compare/luma-vs-sync-labs-mcp" } ], "panel": null, "scores": [ { "by": 12, "edge": "luma", "gemini-omni-1-2-flash": 45, "key": "reliability", "luma": 57, "name": "Reliability", "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "by": 16, "edge": "gemini-omni-1-2-flash", "gemini-omni-1-2-flash": 69, "key": "schema", "luma": 53, "name": "Schema \u0026 documentation", "weight": 13 }, { "by": 12, "edge": "luma", "gemini-omni-1-2-flash": 54, "key": "ergonomics", "luma": 66, "name": "Agent ergonomics", "weight": 13 }, { "by": 3, "edge": "luma", "gemini-omni-1-2-flash": 50, "key": "security", "luma": 53, "name": "Security \u0026 auth", "weight": 14 }, { "by": 0, "edge": "", "gemini-omni-1-2-flash": 30, "key": "payments", "luma": 30, "name": "Payments \u0026 pricing", "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "by": 36, "edge": "gemini-omni-1-2-flash", "gemini-omni-1-2-flash": 83, "key": "maintenance", "luma": 47, "name": "Maintenance \u0026 community", "weight": 7 }, { "by": 5, "edge": "gemini-omni-1-2-flash", "gemini-omni-1-2-flash": 72, "key": "transparency", "luma": 67, "name": "Transparency \u0026 trust", "weight": 7 } ], "summary": "Gemini Omni 1.2 Flash scores 55.1 (C) on agent readiness against Luma AI API's 51.7 (D), and leads in 3 of 7 scored categories. Luma AI API leads on reliability and agent ergonomics. Both do video generation.", "tasks": [ { "a": "$0.69 to $6.27", "b": "$0.90 to $14.40", "cheaper": "gemini-omni-1-2-flash", "task": "Make a 30-second video clip", "what": "30 seconds of generated video" } ], "tutorials": [], "verdicts": { "gemini-omni-1-2-flash": "Google's generally available video model makes clips of up to 15 seconds with audio, edits them turn by turn and upscales drafts to 1080p or 4K, from $0.023 a second at 360p to $0.209 at 4K. It is paid only, the guide still describes Omni 1.1, and every quality claim is Google's.", "luma": "Clip prices are published per generation in credits at a $0.003 list rate, and 429s say which limit was hit. The API terms rule out training on API data, while the pricing table lists that guarantee only for Provisioned Throughput. Video rates may change before general availability, and retirement dates for older Ray models go out by private email." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/gemini-omni-1-2-flash-vs-luma", "json": "https://www.anchorterminal.com/compare/gemini-omni-1-2-flash-vs-luma.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/gemini-omni-1-2-flash-vs-luma.md", "mcp": "https://www.anchorterminal.com/mcp", "slim": "https://www.anchorterminal.com/compare/gemini-omni-1-2-flash-vs-luma.min.md" }, "markdown": "Gemini Omni 1.2 Flash scores 55.1 (C) on agent readiness against Luma AI API's 51.7 (D), and leads in 3 of 7 scored categories. Luma AI API leads on reliability and agent ergonomics. Both do video generation.\n\n- Gemini Omni 1.2 Flash: grade C, 55.1/100, rank #972 of 1524. Markdown https://www.anchorterminal.com/tools/gemini-omni-1-2-flash.md · JSON https://www.anchorterminal.com/api/v1/tools/gemini-omni-1-2-flash.json\n- Luma AI API: grade D, 51.7/100, rank #1087 of 1524. Markdown https://www.anchorterminal.com/tools/luma.md · JSON https://www.anchorterminal.com/api/v1/tools/luma.json\n- Best video generation for AI agents: https://www.anchorterminal.com/best/video-generation/index.md\n- All 203 video comparisons: https://www.anchorterminal.com/compare/video-generation/index.md\n\n## Which one, for what\n\n### Gemini Omni 1.2 Flash (C)\n\nGood for: Short product, ad and explainer clips with audio where an agent needs to revise a clip over several turns rather than regenerate it.\n\nAhead on:\n- Schema \u0026 documentation, 69 against 53\n- Maintenance \u0026 community, 83 against 47\n- Transparency \u0026 trust, 72 against 67\n\nWatch for: No free tier, per the pricing page\n\n### Luma AI API (D)\n\nGood for: Pipelines that want one model for generate, edit, extend and reframe, and colourists who want HDR and EXR.\n\nAhead on:\n- Reliability, 57 against 45\n- Agent ergonomics, 66 against 54\n\nAlso in its favour:\n- A hosted endpoint, with nothing to install\n\nWatch for: Video rates are marked as subject to change before general availability\n\n\n## Why the edge\n\n### Maintenance \u0026 community: Gemini Omni 1.2 Flash +36\n\n- Gemini Omni 1.2 Flash (83): Model reading for gemini-omni-1.2-flash on the Gemini API. Platform facts are the Gemini API listing's (gemini-api, re-read 1 November), carried over as RULES.md allows for a model on an already graded platform. Released and generally available on 5 November 2026; the SDKs added it to the Interactions model list on 10 November (30). Deprecations with earliest dates and no stated minimum notice (4 of 12). Churn in Google's video line: every Veo model on the Gemini API shut down by 22 October, and from 3 December 2026 requests to Omni 1.1 Flash are routed to 1.2 Flash and billed at its rates, four weeks after this release (4 of 8). Dated SDK and platform changelogs (15). SDK replies not sampled (5 of 10). Current SDKs in five languages (15). Runtimes stated (10). 30 + 4 + 4 + 15 + 5 + 15 + 10 = 83.\n- Luma AI API (47): Model reading. The latest dated API change found is SDK v0.5.0, whose changelog dates it 4 August 2026 (tag 5 August), adding the layering parameter to generations. That is more than 90 days before 4 November, so 10 (within 180 days). The docs now carry deletion, files and usage guides with no dates, and the 3 November MCP connector runs Luma Agents workflows on a subscription, which the API doesn't serve, so neither counts (10). Ray 2, Ray 3 and their variants are retiring, but the cutoff dates go out in private notices and the migration guide gives none (5). No API changelog. The SDK changelogs are dated and support is an email address on the migration guide (7). Official SDKs for Python, TypeScript and Go and a CLI, last released on 5 August with Ray 3.2 and files support, though the new deletion routes aren't in them yet (15). Each SDK repository has a CI workflow (10). 10+5+7+15+10 = 47.\n\n### Schema \u0026 documentation: Gemini Omni 1.2 Flash +16\n\n- Gemini Omni 1.2 Flash (69): Model reading for gemini-omni-1.2-flash on the Gemini API. Platform facts are the Gemini API listing's (gemini-api, re-read 1 November), carried over as RULES.md allows for a model on an already graded platform. Called through the Interactions API, which the platform's Discovery document doesn't type; the SDK's generated Interactions types list the model (10 of 25). llms.txt with Markdown twins (10). The Omni guide, read on 11 November, covers Omni 1.1 Flash on the same API and lists what isn't supported (system instructions, temperature, negative prompts, audio references, YouTube sources) and the regional limits; it doesn't name 1.2 (16 of 20). Aspect ratio (16:9 or 9:16), resolution (360p, 720p, 1080p, 4k) and delivery are enumerated; length is set in the prompt, not a field (10 of 15). REST and SDK examples; a failed generation sets the file state to FAILED, and other error codes aren't documented beyond the platform's page (8 of 15). Dated SDK and platform changelogs (15). 10 + 10 + 16 + 10 + 8 + 15 = 69.\n- Luma AI API (53): No public OpenAPI document is linked from the docs. The API reference at /api/ is generated per method with no visible spec download (0). docs.agents.lumalabs.ai/llms.txt returns 404, but every docs page links a Markdown twin (for example /index.md and /guides/pricing/index.md) (10). Guides cover generation, keyframes, edit, extend, reframe, deletion, files, usage and the migration, and say which options don't combine, such as start and end frames with 10 second clips (14). Typed fields for model, type, resolution and duration with fixed values (12). curl and SDK examples, both 429 bodies and generation failure codes are documented (12). Responses carry an X-API-Version header and the SDK repositories keep dated changelogs, but the API docs have no changelog and the public changelog page on lumalabs.ai was last updated in June 2025 (5). 0+10+14+12+12+5 = 53.\n\n### Reliability: Luma AI API +12\n\n- Gemini Omni 1.2 Flash (45): Model reading for gemini-omni-1.2-flash on the Gemini API. Platform facts are the Gemini API listing's (gemini-api, re-read 1 November), carried over as RULES.md allows for a model on an already graded platform. Status page at aistudio.google.com/status with no readable components or history (10 of 20) and no readable incident record (5 of 30). Platform rate-limit tiers; the public rate-limit page has no Omni 1.2 row (5 of 15). Backoff guidance for 429 and 503 and SDK retries (15). No SLA read for the Gemini API route, and the Omni guide says provisioned throughput isn't supported there; Google's post puts it on Google Cloud (0). Google's post of 5 November says generally available, and the SDK commit marks the model GA (10). 10 + 5 + 5 + 15 + 0 + 10 = 45.\n- Luma AI API (57): Better Stack status page at status.lumalabs.ai with API, Dream Machine and Luma Agents components, an incident list and an RSS feed (20). In the 90 days from 6 August the feed lists three incidents, all on legacy Ray2 models: Ray2 Flash timeouts on 2 to 3 September (about 9 hours) and 15 to 16 September (about 2 hours), and Ray2 queue times on 16 to 17 September (about 13 hours). The status page tags each with its API and Dream Machine components, and each hit one legacy model, so minor only (20). The authentication incident counted as a major on 1 October was on 16 July and has left the window. Limits are per minute and per concurrent job, but the numbers sit in the dashboard, not the docs (5). Every 429 carries Retry-After, with separate bodies for the per-minute and concurrency limits and backoff guidance with jitter. Rejected requests aren't queued and synchronous errors are never charged, which is safe-retry guidance, but there is no idempotency key, so 12 as settled in this run (12). No SLA document. The pricing page lists a latency SLA for Provisioned Throughput only as a table entry (0). The pricing page says video rates may change before general availability, so the video surface isn't GA yet (0). 20+20+5+12+0+0 = 57.\n\n### Agent ergonomics: Luma AI API +12\n\n- Gemini Omni 1.2 Flash (54): Read on the lines the Veo listing used for video models. Model reading for gemini-omni-1.2-flash on the Gemini API. Platform facts are the Gemini API listing's (gemini-api, re-read 1 November), carried over as RULES.md allows for a model on an already graded platform. Per the Omni guide (written for 1.1 on the same API), the video comes back in the response, inline as base64 or as a Google-hosted file to poll until ACTIVE with delivery uri for outputs over 4 MB (12 of 15). No callback (0 of 10). Resolution, aspect ratio and delivery control output size, and edits run turn by turn through previous_interaction_id without regenerating from scratch (10). No list of past jobs found (0 of 10). Standard Google error statuses on the platform, with FAILED as the only Omni-specific state (12 of 14). No idempotency key, and whether failed generations are billed isn't stated (5 of 20). Only model and input are required, with 720p and 16:9 as defaults, and SDKs in five languages plus the CLI (15). 12 + 0 + 10 + 0 + 12 + 5 + 15 = 54.\n- Luma AI API (66): Generations come back as small JSON objects with a presigned URL for the output (15). We found no callback for the Agents API, so jobs are polled (0 of 10). Resolution and duration set output size (10). The API reference lists create, get and delete for generations and a list call only for files, so there is no list of past generations (0 of 10). The 429 detail string tells an agent whether to wait for Retry-After or for a job to finish, and failures carry codes (16). No idempotency key. Moderated and failed generations are refunded and synchronous errors aren't charged, so a retry after a failure is safe (10). One generation endpoint with few required fields, and official SDKs for Python, TypeScript and Go plus a CLI (15). 15+0+10+0+16+10+15 = 66.\n\n### Transparency \u0026 trust: Gemini Omni 1.2 Flash +5\n\n- Gemini Omni 1.2 Flash (72): Model reading for gemini-omni-1.2-flash on the Gemini API. Platform facts are the Gemini API listing's (gemini-api, re-read 1 November), carried over as RULES.md allows for a model on an already graded platform. Closed service with clear terms, SDKs Apache-2.0 (15). Paid only, so content isn't used to improve products; video retention isn't stated (20 of 30). Deprecations table and a dated routing notice for Omni 1.1 Flash (15 of 20). Data may be processed anywhere Google has facilities on the Gemini API route; no subprocessor list checked (5 of 20). SynthID watermarking is disclosed, and Google names the cases it still handles poorly. 15 + 20 + 15 + 5 = 55.\n- Luma AI API (67): Closed models. The terms give customers the outputs, with commercial use tied to an active paid plan (15). The API terms state that API inputs and outputs aren't used for training (10). The pricing page's comparison table says Pay-as-you-go has no no-train guarantee and only Provisioned Throughput does. That contradiction is charged once, as a misleading claim under negative events, as rime-prism's training contradiction is, so it doesn't also lower this line. The privacy policy (20 April 2026) describes retention by criteria without periods, and the deletion guide sets retention per API client with a one-year hold for moderation failures (5). The privacy policy was read and names US hosting with Standard Contractual Clauses for transfers. No DPA was read (5). A public migration guide without dates, retirement dates by email only (5). A subprocessor list (last updated 4 October 2026) names about 50 providers with their purpose, and the privacy policy says the services are hosted in the United States (15). 15+10+5+5+5+15 = 55.\n\n## Score by category\n\n| Category | Weight | Gemini Omni 1.2 Flash | Luma AI API | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 45 | 57 | Luma AI API +12 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 69 | 53 | Gemini Omni 1.2 Flash +16 |\n| Agent ergonomics | 13% (16.2 this run) | 54 | 66 | Luma AI API +12 |\n| Security \u0026 auth | 14% (17.5 this run) | 50 | 53 | Luma AI API +3 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 30 | 30 | even |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 83 | 47 | Gemini Omni 1.2 Flash +36 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 72 | 67 | Gemini Omni 1.2 Flash +5 |\n| Negative events | ≤15 | 0 | -2 | |\n| **Total** | | **55.1 · C** | **51.7 · D** | |\n\n## Facts side by side\n\n| Fact | Gemini Omni 1.2 Flash | Luma AI API |\n| --- | --- | --- |\n| Kind | Model API | Model API |\n| Vendor | Google | Luma AI |\n| Hosted endpoint | no (local only) | `https://agents.lumalabs.ai/v1` |\n| Transports | HTTP | HTTP |\n| Auth | API key | API key |\n| Pricing | Pay per use | Pay per use |\n| x402 | no | no |\n| Licence | Closed model, used through the Gemini API and Google Cloud under Google's terms. The google-genai SDKs are Apache-2.0 | Apache-2.0 (SDKs) |\n| Read-only variant documented | no | no |\n| llms.txt | yes | no |\n| Last release | 2026-11-05 | 2026-08-05 |\n| Terms last updated | 2026-04-28 | 2026-05-14 |\n| Privacy policy last updated | 2026-10-01 | 2026-04-20 |\n| Customer content may train models | yes | yes |\n| Terms restrict automated access | yes | yes |\n| Terms restrict benchmarking | yes | yes |\n| Terms or service can change without notice | not found in the text | yes |\n| Arbitration or class-action waiver | not found in the text | yes |\n| Popularity | none | 2 stars, 982 npm/wk |\n| Agent reviews | none | 3/5 (2) |\n\n## What the same task costs\n\n| Task | Gemini Omni 1.2 Flash | Luma AI API |\n| --- | --- | --- |\n| Make a 30-second video clip | $0.69 to $6.27 | $0.90 to $14.40 |\n\n## How the scores have moved\n\n### Gemini Omni 1.2 Flash\n\n- +1.3 on 13 November 2026 (D to C): checklist\n\n### Luma AI API\n\n- +1.2 on 13 November 2026: checklist\n- +2.2 on 4 November 2026: new evidence, time\n- +0.1 on 27 October 2026: checklist\n\n## Verdicts\n\n**Gemini Omni 1.2 Flash.** Google's generally available video model makes clips of up to 15 seconds with audio, edits them turn by turn and upscales drafts to 1080p or 4K, from $0.023 a second at 360p to $0.209 at 4K. It is paid only, the guide still describes Omni 1.1, and every quality claim is Google's.\n\n**Luma AI API.** Clip prices are published per generation in credits at a $0.003 list rate, and 429s say which limit was hit. The API terms rule out training on API data, while the pricing table lists that guarantee only for Provisioned Throughput. Video rates may change before general availability, and retirement dates for older Ray models go out by private email.\n\n## Before you call either\n\n### Gemini Omni 1.2 Flash\n\n1. Call POST /v1beta/interactions with model gemini-omni-1.2-flash and response_format type video; Veo is gone from the Gemini API\n2. Set delivery to uri for clips over 4 MB and poll the file until ACTIVE; a later GET returns base64 only\n3. Edit with previous_interaction_id and leave store on, or the clip can't be edited in a later turn\n4. Set length in the prompt with timecodes such as [0-3s]; there is no duration field\n5. Draft at 360p or 720p and upscale only the keepers: 4K costs about nine times 360p\n\n### Luma AI API\n\n1. Send model `ray-3.2` and type `video`, with resolution and duration inside `video`. Older model names are rejected\n2. Poll GET /v1/generations/{id} until completed or failed, then copy the presigned URL\n3. On 429, read `detail`. Rate limit exceeded means wait Retry-After, Too many concurrent jobs means wait for a job to finish\n4. Use keyframes with `keyframe_indexes` for 10 second clips. start_frame and end_frame only work at 5 seconds\n5. Convert credits to dollars with `overage_rate` from GET /v1/usage when it is set, otherwise the $0.003 list rate\n\n## Questions\n\n### Which is better for AI agents, Gemini Omni 1.2 Flash or Luma AI API?\n\nGemini Omni 1.2 Flash scores 55.1 (C) on agent readiness against Luma AI API's 51.7 (D), and leads in 3 of 7 scored categories. Luma AI API leads on reliability and agent ergonomics.\n\n### Do Gemini Omni 1.2 Flash and Luma AI API need an API key?\n\nBoth need an API key.\n\n### Can an agent call Gemini Omni 1.2 Flash and Luma AI API without installing anything?\n\nNo hosted endpoint is listed for Gemini Omni 1.2 Flash. Luma AI API has a hosted endpoint at https://agents.lumalabs.ai/v1.\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/gemini-omni-1-2-flash-vs-luma.json, and with the fewest tokens: https://www.anchorterminal.com/compare/gemini-omni-1-2-flash-vs-luma.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"gemini-omni-1-2-flash\", \"b\": \"luma\"}`. From a terminal: `anchor compare gemini-omni-1-2-flash luma`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/gemini-omni-1-2-flash.json and https://www.anchorterminal.com/api/v1/tools/luma.json\n\n## Other comparisons with Gemini Omni 1.2 Flash or Luma AI API\n\n- [Alibaba Wan (Model Studio) vs Gemini Omni 1.2 Flash](https://www.anchorterminal.com/compare/alibaba-wan-vs-gemini-omni-1-2-flash.md)\n- [Alibaba Wan (Model Studio) vs Luma AI API](https://www.anchorterminal.com/compare/alibaba-wan-vs-luma.md)\n- [fal video models vs Gemini Omni 1.2 Flash](https://www.anchorterminal.com/compare/fal-video-vs-gemini-omni-1-2-flash.md)\n- [fal video models vs Luma AI API](https://www.anchorterminal.com/compare/fal-video-vs-luma.md)\n- [framefields vs Gemini Omni 1.2 Flash](https://www.anchorterminal.com/compare/framefields-vs-gemini-omni-1-2-flash.md)\n- [framefields vs Luma AI API](https://www.anchorterminal.com/compare/framefields-vs-luma.md)\n- [Gemini Omni 1.2 Flash vs Google Veo](https://www.anchorterminal.com/compare/gemini-omni-1-2-flash-vs-google-veo.md)\n- [Gemini Omni 1.2 Flash vs Higgsfield API](https://www.anchorterminal.com/compare/gemini-omni-1-2-flash-vs-higgsfield.md)\n- [Gemini Omni 1.2 Flash vs HyperFrames](https://www.anchorterminal.com/compare/gemini-omni-1-2-flash-vs-hyperframes.md)\n- [Gemini Omni 1.2 Flash vs Kling AI API](https://www.anchorterminal.com/compare/gemini-omni-1-2-flash-vs-kling.md)\n- [Gemini Omni 1.2 Flash vs Magic Hour MCP](https://www.anchorterminal.com/compare/gemini-omni-1-2-flash-vs-magic-hour-mcp.md)\n- [Gemini Omni 1.2 Flash vs MiniMax Video API](https://www.anchorterminal.com/compare/gemini-omni-1-2-flash-vs-minimax-video.md)\n- [Gemini Omni 1.2 Flash vs OpenAI Sora API](https://www.anchorterminal.com/compare/gemini-omni-1-2-flash-vs-openai-sora.md)\n- [Gemini Omni 1.2 Flash vs Pika API](https://www.anchorterminal.com/compare/gemini-omni-1-2-flash-vs-pika.md)\n- [Gemini Omni 1.2 Flash vs PixVerse API](https://www.anchorterminal.com/compare/gemini-omni-1-2-flash-vs-pixverse.md)\n- [Gemini Omni 1.2 Flash vs Popcraft MCP](https://www.anchorterminal.com/compare/gemini-omni-1-2-flash-vs-popcraft-mcp.md)\n- [Gemini Omni 1.2 Flash vs Replicate video models](https://www.anchorterminal.com/compare/gemini-omni-1-2-flash-vs-replicate-video.md)\n- [Gemini Omni 1.2 Flash vs Runway API](https://www.anchorterminal.com/compare/gemini-omni-1-2-flash-vs-runway.md)\n- [Gemini Omni 1.2 Flash vs Seedance on BytePlus ModelArk](https://www.anchorterminal.com/compare/gemini-omni-1-2-flash-vs-seedance-on-byteplus-modelark.md)\n- [Gemini Omni 1.2 Flash vs Vidu API](https://www.anchorterminal.com/compare/gemini-omni-1-2-flash-vs-vidu.md)\n- [Google Veo vs Luma AI API](https://www.anchorterminal.com/compare/google-veo-vs-luma.md)\n- [Higgsfield API vs Luma AI API](https://www.anchorterminal.com/compare/higgsfield-vs-luma.md)\n- [HyperFrames vs Luma AI API](https://www.anchorterminal.com/compare/hyperframes-vs-luma.md)\n- [Kling AI API vs Luma AI API](https://www.anchorterminal.com/compare/kling-vs-luma.md)\n- [Luma AI API vs Magic Hour MCP](https://www.anchorterminal.com/compare/luma-vs-magic-hour-mcp.md)\n- [Luma AI API vs MiniMax Video API](https://www.anchorterminal.com/compare/luma-vs-minimax-video.md)\n- [Luma AI API vs OpenAI Sora API](https://www.anchorterminal.com/compare/luma-vs-openai-sora.md)\n- [Luma AI API vs Pika API](https://www.anchorterminal.com/compare/luma-vs-pika.md)\n- [Luma AI API vs PixVerse API](https://www.anchorterminal.com/compare/luma-vs-pixverse.md)\n- [Luma AI API vs Popcraft MCP](https://www.anchorterminal.com/compare/luma-vs-popcraft-mcp.md)\n- [Luma AI API vs Replicate video models](https://www.anchorterminal.com/compare/luma-vs-replicate-video.md)\n- [Luma AI API vs Runway API](https://www.anchorterminal.com/compare/luma-vs-runway.md)\n- [Luma AI API vs Seedance on BytePlus ModelArk](https://www.anchorterminal.com/compare/luma-vs-seedance-on-byteplus-modelark.md)\n- [Luma AI API vs Vidu API](https://www.anchorterminal.com/compare/luma-vs-vidu.md)\n- [Clueso vs Gemini Omni 1.2 Flash](https://www.anchorterminal.com/compare/clueso-video-vs-gemini-omni-1-2-flash.md)\n- [Clueso vs Luma AI API](https://www.anchorterminal.com/compare/clueso-video-vs-luma.md)\n- [Gemini Omni 1.2 Flash vs sync. labs MCP server](https://www.anchorterminal.com/compare/gemini-omni-1-2-flash-vs-sync-labs-mcp.md)\n- [Luma AI API vs sync. labs MCP server](https://www.anchorterminal.com/compare/luma-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": "2026-11-14", "license": "CC-BY-4.0", "method": "https://www.anchorterminal.com/benchmark/", "methodology": "0.8", "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": "Gemini Omni 1.2 Flash vs Luma AI API", "url": "" } ], "description": "Gemini Omni 1.2 Flash scores 55.1 (C) to Luma AI's 51.7 (D) for video generation. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "Gemini Omni 1.2 Flash C 55.1", "Luma AI API D 51.7", "scores" ], "h1": "Gemini Omni 1.2 Flash vs Luma AI API", "image": "https://www.anchorterminal.com/assets/og/default.png", "path": "/compare/gemini-omni-1-2-flash-vs-luma", "published": "2026-10-01", "section": "tools", "title": "Gemini Omni 1.2 Flash vs Luma AI for AI agents (2026)", "toc": null, "updated": "2026-11-13", "url": "https://www.anchorterminal.com/compare/gemini-omni-1-2-flash-vs-luma" }, "tokens": { "markdown": 5350, "slim": 930 }, "version": 1 }