{ "data": { "a": { "slug": "google-veo", "name": "Google Veo", "vendor": "Google", "vendorUrl": "https://ai.google.dev", "kind": "model", "category": "video-generation", "summary": "Google's Veo video models through the Gemini API (predictLongRunning) and Vertex AI.", "url": "https://www.anchorterminal.com/tools/google-veo", "markdownUrl": "https://www.anchorterminal.com/tools/google-veo.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/google-veo.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/google-veo.json", "repo": "https://github.com/googleapis/python-genai", "license": "Apache-2.0 (SDKs)", "transports": [ "http" ], "remoteUrl": "https://generativelanguage.googleapis.com/v1beta", "packages": [ { "registry": "pypi", "name": "google-genai" }, { "registry": "npm", "name": "@google/genai" } ], "auth": "api-key", "authNotes": "`x-goog-api-key` header with a key from AI Studio on the Gemini API. Vertex AI uses Google Cloud OAuth (service account or gcloud token) instead.", "pricing": "usage", "pricingNotes": "No free tier for Veo. Billed per second of video with audio. Veo 3.1 $0.40 a second at 720p and 1080p, $0.60 at 4K. Veo 3.1 Fast $0.10 at 720p, $0.12 at 1080p, $0.30 at 4K. Veo 3.1 Lite $0.05 at 720p, $0.08 at 1080p. You're charged only when a video is generated (https://ai.google.dev/gemini-api/docs/pricing).", "priceSummary": "Pay per use", "where": "hosted", "x402": { "level": "no", "evidence": "No machine payment. Needs billing on a Google Cloud project (checked 2026-09-30).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": 4000, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-09-30" }, "docsUrl": "https://ai.google.dev/gemini-api/docs/veo", "rateLimitsUrl": "https://ai.google.dev/gemini-api/docs/rate-limits", "llmsTxt": "https://ai.google.dev/gemini-api/docs/llms.txt", "capabilities": [ "video.generate", "video.image-to-video", "video.audio", "video.extend" ], "tags": [ "official", "hosted", "closed-source", "card-required", "llms-txt", "async-jobs", "python", "typescript", "watermark" ], "lastRelease": "2026-09-22", "graded": true, "anchor": { "graded": true, "score": 60.4, "grade": "C", "agentReady": false, "rank": 465, "ranked": true, "rankOf": 842, "categoryRank": 6, "methodology": "0.4", "run": "2026-10-01", "scores": { "ergonomics": 64, "maintenance": 77, "payments": 20, "reliability": 45, "schema": 71, "security": 78, "transparency": 75 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-01" }, "negative": 0, "verdict": "Audio on every Veo 3.1 clip, up to 4K on Veo 3.1 and Fast. All three Veo 3.1 previews shut down on the Gemini API on 2026-10-22.", "bestFor": "Teams already on Google Cloud who want sound with every clip and a choice between cheap (Lite) and top quality (Veo 3.1, 4K).", "strengths": [ "Audio on every Veo 3.1 clip, up to 4K on Veo 3.1 and Fast", "Lite at $0.05 a second for 720p with audio", "Keys restrictable to the Gemini API and by IP or app, with OAuth and IAM on Vertex AI", "Paid-tier prompts and outputs aren't used to improve Google's products", "Deprecations page dates every Veo shutdown and names the replacement" ], "weaknesses": [ "All three Veo 3.1 previews shut down on the Gemini API on 2026-10-22", "Veo 2.0 and 3.0 already shut down on 2026-06-30", "No free tier and no per-model rate limits published", "Clips are 4, 6 or 8 seconds per call, and 1080p and 4K need 8", "The Veo endpoint isn't covered by Google's SLA" ], "agentNotes": [ "Move off `veo-3.1-*-preview` before 2026-10-22. Use `gemini-omni-1.1-flash` on the Gemini API or the GA Veo IDs on Vertex AI", "Call `predictLongRunning`, then poll the operation name about every 10 seconds until `done` is true. Jobs take 11 seconds to 6 minutes", "Download the video within 2 days. The server deletes it after that", "Set `durationSeconds` to 8 for 1080p, 4K or reference images. Shorter clips aren't supported there", "In the EU, UK, Switzerland and MENA image-to-video only accepts `personGeneration` set to `allow_adult`" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 2, "avgRating": 2.5, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "C", "methodology": "0.4", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 60.4 } ], "editorialScores": { "ergonomics": 64, "maintenance": 77, "payments": 20, "reliability": 45, "schema": 71, "security": 78, "transparency": 60 }, "provenanceScore": 89 }, "connect": { "install": "pip install google-genai # or: npm i @google/genai", "http": "curl -X POST \"https://generativelanguage.googleapis.com/v1beta/models/veo-3.1-lite-generate-preview:predictLongRunning\" \\\n -H \"x-goog-api-key: $GEMINI_API_KEY\" -H \"Content-Type: application/json\" \\\n -d '{\"instances\":[{\"prompt\":\"a paper boat drifting down a rainy street\"}]}'" }, "letme": { "capability": "https://letme.dev/video.generate", "tool": "https://letme.dev/google-veo" }, "sameCompany": [ "gemini-api", "gemini-embedding", "vertex-ai-tuning", "google-model-armor", "google-imagen", "google-lyria", "google-speech-to-text", "gemini-live", "google-adk", "google-secret-manager", "google-weather-api", "chrome-devtools-mcp", "google-maps-platform", "google-cloud-translation", "google-calendar-api", "firebase-cloud-messaging", "google-drive-api", "gemini-cli", "google-search-console", "google-ads-api", "google-forms", "google-sheets-api", "gmail-api" ], "area": "content", "unitPrices": [ { "item": "Veo 3.1 720p or 1080p", "unit": "video-second", "usd": 0.4, "note": "with audio" }, { "item": "Veo 3.1 4K", "unit": "video-second", "usd": 0.6, "note": "with audio" }, { "item": "Veo 3.1 Fast 720p", "unit": "video-second", "usd": 0.1, "note": "with audio" }, { "item": "Veo 3.1 Fast 1080p", "unit": "video-second", "usd": 0.12, "note": "with audio" }, { "item": "Veo 3.1 Fast 4K", "unit": "video-second", "usd": 0.3, "note": "with audio" }, { "item": "Veo 3.1 Lite 720p", "unit": "video-second", "usd": 0.05, "note": "with audio" }, { "item": "Veo 3.1 Lite 1080p", "unit": "video-second", "usd": 0.08, "note": "with audio" } ], "provenance": { "legalEntity": "Google LLC", "domain": "google.com", "domainRegistered": "1997-09-15", "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": "2026-09-30", "notes": [ "The endpoint is on googleapis.com, Google's API domain. google.com was registered in 1997", "Vertex AI is now called Gemini Enterprise Agent Platform in Google's docs" ], "score": 89 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/google-veo.json", "live": { "slug": "google-veo", "probe": { "target": "https://generativelanguage.googleapis.com/v1beta", "method": "get", "lastAt": "2026-10-09T10:42:44.59728799Z", "lastOk": true, "lastStatus": 404, "lastMs": 11, "authRequired": false, "uptime24h": 100, "uptime30d": 100, "p50ms24h": 12, "p95ms24h": 27, "samples24h": 260, "samples30d": 2300, "days": [ { "date": "2026-09-30", "probes": 35, "ok": 35 }, { "date": "2026-10-01", "probes": 276, "ok": 276 }, { "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": 114, "ok": 114 } ] }, "versions": [ { "registry": "github", "name": "googleapis/python-genai", "version": "v2.29.0", "released": "2026-10-07", "seenAt": "2026-10-08T16:14:36.547058367Z" }, { "registry": "npm", "name": "@google/genai", "version": "2.28.0", "seenAt": "2026-10-08T16:14:33.588011152Z" }, { "registry": "pypi", "name": "google-genai", "version": "2.29.0", "released": "2026-10-07", "seenAt": "2026-10-08T16:14:33.460415673Z" } ], "githubStars": 4009, "npmWeekly": 29486957, "pypiWeekly": 34128301, "securityTxt": { "url": "https://google.com/.well-known/security.txt", "state": "valid", "expires": "2030-04-01T00:00:00z", "checkedAt": "2026-10-08T15:38:39.75078566Z" }, "llmsTxt": { "url": "https://ai.google.dev/gemini-api/docs/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-10-08T14:00:33.27867261Z" }, "domain": { "domain": "google.com", "registered": "1997-09-15", "source": "https://rdap.verisign.com/com/v1/domain/google.com", "checkedAt": "2026-10-04T13:05:50.737985829Z" }, "updatedAt": "2026-10-09T10:42:44.59728799Z" } }, "answer": "Replicate video models scores 62.1 (B) on agent readiness against Google Veo's 60.4 (C), and leads in 4 of 7 scored categories. Google Veo leads on security \u0026 auth and maintenance \u0026 community.", "b": { "slug": "replicate-video", "name": "Replicate video models", "vendor": "Replicate (Cloudflare)", "vendorUrl": "https://replicate.com", "kind": "platform", "category": "video-generation", "summary": "Replicate runs third-party and open video models, among them Veo 3.1, Kling 3.0, Runway Gen-4.5, Seedance 2.0 and Wan, through one predictions API with Python and JavaScript clients and an MCP server.", "url": "https://www.anchorterminal.com/tools/replicate-video", "markdownUrl": "https://www.anchorterminal.com/tools/replicate-video.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/replicate-video.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/replicate-video.json", "repo": "https://github.com/replicate/replicate-python", "license": "Proprietary service under Replicate's terms of service. The Python and JavaScript clients and `replicate-mcp` are Apache-2.0, and each model carries its own licence", "transports": [ "http", "sse", "stdio" ], "remoteUrl": "https://api.replicate.com/v1", "packages": [ { "registry": "npm", "name": "replicate" }, { "registry": "pypi", "name": "replicate" }, { "registry": "npm", "name": "replicate-mcp" } ], "auth": "api-key", "authNotes": "Self-serve. A person signs up in a browser and creates a bearer API token (40 characters, prefix `r8_`) at replicate.com/account/api-tokens. An account can hold several named tokens and disable any of them. Tokens have no scopes or expiry. The hosted MCP server at https://mcp.replicate.com/sse takes the token in a browser flow, and the local `replicate-mcp` package reads `REPLICATE_API_TOKEN`.", "pricing": "usage", "pricingNotes": "Pay as you go from prepaid credit (valid one year, not refundable) or monthly in arrears. Official video models bill per second of output video, with tiers by resolution, mode and audio shown on each model page. Community models bill per second of hardware time. Failed runs aren't charged, and a cancelled official-model run may be. The try-for-free collection lets a new account run `minimax/video-01` a limited number of times before buying credit (https://replicate.com/collections/try-for-free).", "priceSummary": "Pay per use", "where": "both", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the docs index, the HTTP API reference or the pricing page (checked 2026-10-08).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": 917, "npmWeekly": 704939, "pypiWeekly": 356876, "asOf": "2026-10-08" }, "docsUrl": "https://replicate.com/docs", "llmsTxt": "https://replicate.com/docs/llms.txt", "openapi": "https://api.replicate.com/openapi.json", "capabilities": [ "video.generate", "video.image-to-video", "video.audio", "video.edit", "video.extend" ], "tags": [ "hosted", "model-platform", "mcp", "llms-txt", "openapi", "python", "typescript", "async-jobs", "webhooks", "open-weights", "status-page" ], "lastRelease": "2026-09-15", "graded": true, "anchor": { "graded": true, "score": 62.1, "grade": "B", "agentReady": false, "rank": 402, "ranked": true, "rankOf": 842, "categoryRank": 4, "methodology": "0.4", "run": "2026-10-01", "scores": { "ergonomics": 72, "maintenance": 48, "payments": 30, "reliability": 75, "schema": 86, "security": 41, "transparency": 72 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-08" }, "negative": 0, "verdict": "One bearer token reaches more than twenty official video models at published per-second prices, each with a typed input schema, and failed runs aren't charged. Tokens have no scopes or spend cap, no SLA is published, and the terms let Replicate withdraw any model without notice.", "bestFor": "An agent that wants several vendors' video models behind one token and one request shape, or open models such as Wan next to closed ones.", "strengths": [ "Official video models bill per second of output at prices shown on each model page, from $0.10 for Wan 2.7 to $0.40 for Veo 3.1 with audio", "Every model publishes a typed input schema, and the four we read require only `prompt`", "Failed runs aren't charged, and a `Cancel-After` header ends a job after a set time", "API inputs, outputs, files and logs are deleted after one hour by default", "Public OpenAPI document with 36 operations, llms.txt and Markdown docs pages" ], "weaknesses": [ "Tokens have no scopes, expiry or spend cap, and any token can run every model and delete account resources", "No SLA is published and the terms disclaim service levels. Replicate may withdraw a model without notice", "No idempotency key on prediction creates, and a 429 carries a wait time in the body with no `Retry-After` header documented", "The public changelog's newest entry is 21 April 2026, and the stable npm and PyPI clients date from November and May 2025", "No security.txt, and no certification is named on the pages we read" ], "agentNotes": [ "Call official models at `POST /v1/models/{owner}/{name}/predictions` with no version, then poll `GET /v1/predictions/{id}` or pass `webhook`. Video jobs usually outlast the 60-second `Prefer: wait` window", "Download the output file within the hour. API predictions lose inputs, outputs and logs after 60 minutes", "Read the model's price tiers before setting `resolution`, `mode` or `generate_audio`. Kling 3.0 runs from $0.168 to $0.42 a second and Veo 3.1 doubles with audio", "Send `Cancel-After` on every create. There is no idempotency key, so a blind retry is a second paid video", "Keep credit above $20 or enable auto-reload. Low balances are throttled, and granted credit with no card is held to 6 requests a minute" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "B", "methodology": "0.4", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 62.1 } ], "editorialScores": { "ergonomics": 72, "maintenance": 48, "payments": 30, "reliability": 75, "schema": 86, "security": 41, "transparency": 56 }, "provenanceScore": 87 }, "connect": { "http": "curl -X POST https://api.replicate.com/v1/models/google/veo-3.1/predictions \\\n -H \"Authorization: Bearer $REPLICATE_API_TOKEN\" -H \"Content-Type: application/json\" \\\n -d '{\"input\":{\"prompt\":\"a red fox running through fresh snow\",\"duration\":4,\"resolution\":\"720p\"}}'", "claudeCode": "claude mcp add replicate https://mcp.replicate.com/sse --transport sse --scope user", "config": { "mcpServers": { "replicate": { "args": [ "-y", "replicate-mcp@latest" ], "command": "npx", "env": { "REPLICATE_API_TOKEN": "${REPLICATE_API_TOKEN}" } } } } }, "letme": { "capability": "https://letme.dev/video.generate", "tool": "https://letme.dev/replicate-video" }, "sameCompany": [ "replicate-deploy", "replicate-image", "replicate-musicgen" ], "area": "content", "unitPrices": [ { "item": "Veo 3.1 with audio", "unit": "video-second", "usd": 0.4, "note": "$0.20 without audio" }, { "item": "Veo 3.1 Fast with audio", "unit": "video-second", "usd": 0.15, "note": "$0.10 without audio" }, { "item": "Kling 3.0 pro (1080p)", "unit": "video-second", "usd": 0.224, "note": "$0.336 with audio, standard 720p $0.168, 4K $0.42" }, { "item": "Runway Gen-4.5", "unit": "video-second", "usd": 0.12 }, { "item": "Seedance 2.0 720p", "unit": "video-second", "usd": 0.18, "note": "without video input. 480p $0.08, 1080p $0.45, 4K $1.00, more with video input" }, { "item": "Wan 2.7 text-to-video", "unit": "video-second", "usd": 0.1 }, { "item": "Wan 3.0 1080p", "unit": "video-second", "usd": 0.1, "note": "billing table on 8 October 2026 during a promotion. README lists $0.20" }, { "item": "Hailuo 2.3 768p", "unit": "video-second", "usd": 0.0467, "note": "$0.28 per 6-second video, $0.56 for 10 seconds, $0.49 for 6 seconds at 1080p" } ], "provenance": { "legalEntity": "Replicate, LLC", "domain": "replicate.com", "domainRegistered": "1998-05-26", "domainNote": "replicate.com was registered in 1998, long before Replicate the company existed.", "endpointOnVendorDomain": true, "terms": "https://replicate.com/terms", "privacy": "https://replicate.com/privacy", "statusPage": "https://replicatestatus.com", "changelog": "https://replicate.com/changelog", "securityTxt": "none", "checked": "2026-10-08", "notes": [ "The terms of service (last update 1 April 2026) name Replicate, LLC, 101 Townsend St, San Francisco, as the contracting party and govern use of the API and the models.", "The privacy policy was last updated on 1 April 2026.", "replicatestatus.com redirects to https://www.cloudflarestatus.com/services?search=replicate, where Replicate is one component of Cloudflare's status page.", "https://replicate.com/.well-known/security.txt returned 404 on 8 October 2026.", "RDAP gives a registration date of 1998-05-26 for replicate.com.", "Replicate's image and music models and its deployments are listed separately." ], "score": 87 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/replicate-video.json", "live": { "slug": "replicate-video", "probe": { "target": "https://api.replicate.com/v1", "method": "get", "lastAt": "2026-10-09T10:42:54.63874248Z", "lastOk": true, "lastStatus": 401, "lastMs": 111, "lastNote": "asks for credentials", "authRequired": true, "uptime24h": 100, "uptime30d": 100, "p50ms24h": 249, "p95ms24h": 279, "samples24h": 33, "samples30d": 33, "days": [ { "date": "2026-10-09", "probes": 33, "ok": 33 } ] }, "updatedAt": "2026-10-09T10:42:54.63874248Z" } }, "facts": [ { "a": "Model API", "b": "Model platform", "name": "Kind" }, { "a": "Google", "b": "Replicate (Cloudflare)", "name": "Vendor" }, { "a": "https://generativelanguage.googleapis.com/v1beta", "b": "https://api.replicate.com/v1", "name": "Hosted endpoint" }, { "a": "HTTP", "b": "HTTP, SSE (legacy), stdio", "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": "Apache-2.0 (SDKs)", "b": "Proprietary service under Replicate's terms of service. The Python and JavaScript clients and `replicate-mcp` are Apache-2.0, and each model carries its own licence", "name": "Licence" }, { "a": "no", "b": "no", "name": "Read-only variant documented" }, { "a": "yes", "b": "yes", "name": "llms.txt" }, { "a": "2026-09-22", "b": "2026-09-15", "name": "Last release" }, { "a": "2026-04-28", "b": "2026-04-01", "name": "Terms last updated" }, { "a": "2026-10-01", "b": "2026-04-01", "name": "Privacy policy last updated" }, { "a": "yes", "b": "not found in the text", "name": "Customer content may train models" }, { "a": "yes", "b": "not found in the text", "name": "Terms restrict automated access" }, { "a": "yes", "b": "not found in the text", "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": "4k stars", "b": "917 stars, 705k npm/wk, 357k PyPI/wk", "name": "Popularity" }, { "a": "2.5/5 (2)", "b": "none", "name": "Agent reviews" } ], "faq": [ { "answer": "Replicate video models scores 62.1 (B) on agent readiness against Google Veo's 60.4 (C), and leads in 4 of 7 scored categories. Google Veo leads on security \u0026 auth and maintenance \u0026 community.", "question": "Which is better for AI agents, Google Veo or Replicate video models?" }, { "answer": "Yes. Google Veo has a hosted endpoint at https://generativelanguage.googleapis.com/v1beta and Replicate video models at https://api.replicate.com/v1.", "question": "Can an agent call Google Veo and Replicate video models without installing anything?" } ], "goodFor": [ { "aheadOn": [ "Security \u0026 auth, 78 against 41", "Maintenance \u0026 community, 77 against 48" ], "also": null, "goodFor": "Teams already on Google Cloud who want sound with every clip and a choice between cheap (Lite) and top quality (Veo 3.1, 4K).", "slug": "google-veo", "watchFor": "All three Veo 3.1 previews shut down on the Gemini API on 2026-10-22" }, { "aheadOn": [ "Reliability, 75 against 45", "Schema \u0026 documentation, 86 against 71", "Agent ergonomics, 72 against 64", "Payments \u0026 pricing, 30 against 20" ], "also": [ "Runs on your own machine" ], "goodFor": "An agent that wants several vendors' video models behind one token and one request shape, or open models such as Wan next to closed ones.", "slug": "replicate-video", "watchFor": "Tokens have no scopes, expiry or spend cap, and any token can run every model and delete account resources" } ], "job": { "capability": "video.generate", "name": "Video generate" }, "others": [ { "json": "https://www.anchorterminal.com/compare/alibaba-wan-vs-google-veo.json", "title": "Alibaba Wan (Model Studio) vs Google Veo", "url": "https://www.anchorterminal.com/compare/alibaba-wan-vs-google-veo" }, { "json": "https://www.anchorterminal.com/compare/alibaba-wan-vs-replicate-video.json", "title": "Alibaba Wan (Model Studio) vs Replicate video models", "url": "https://www.anchorterminal.com/compare/alibaba-wan-vs-replicate-video" }, { "json": "https://www.anchorterminal.com/compare/fal-video-vs-google-veo.json", "title": "fal video models vs Google Veo", "url": "https://www.anchorterminal.com/compare/fal-video-vs-google-veo" }, { "json": "https://www.anchorterminal.com/compare/fal-video-vs-replicate-video.json", "title": "fal video models vs Replicate video models", "url": "https://www.anchorterminal.com/compare/fal-video-vs-replicate-video" }, { "json": "https://www.anchorterminal.com/compare/google-veo-vs-higgsfield.json", "title": "Google Veo vs Higgsfield API", "url": "https://www.anchorterminal.com/compare/google-veo-vs-higgsfield" }, { "json": "https://www.anchorterminal.com/compare/google-veo-vs-kling.json", "title": "Google Veo vs Kling AI API", "url": "https://www.anchorterminal.com/compare/google-veo-vs-kling" }, { "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/google-veo-vs-minimax-video.json", "title": "Google Veo vs MiniMax Video API", "url": "https://www.anchorterminal.com/compare/google-veo-vs-minimax-video" }, { "json": "https://www.anchorterminal.com/compare/google-veo-vs-openai-sora.json", "title": "Google Veo vs OpenAI Sora API", "url": "https://www.anchorterminal.com/compare/google-veo-vs-openai-sora" }, { "json": "https://www.anchorterminal.com/compare/google-veo-vs-pika.json", "title": "Google Veo vs Pika API", "url": "https://www.anchorterminal.com/compare/google-veo-vs-pika" }, { "json": "https://www.anchorterminal.com/compare/google-veo-vs-pixverse.json", "title": "Google Veo vs PixVerse API", "url": "https://www.anchorterminal.com/compare/google-veo-vs-pixverse" }, { "json": "https://www.anchorterminal.com/compare/google-veo-vs-runway.json", "title": "Google Veo vs Runway API", "url": "https://www.anchorterminal.com/compare/google-veo-vs-runway" }, { "json": "https://www.anchorterminal.com/compare/google-veo-vs-vidu.json", "title": "Google Veo vs Vidu API", "url": "https://www.anchorterminal.com/compare/google-veo-vs-vidu" }, { "json": "https://www.anchorterminal.com/compare/higgsfield-vs-replicate-video.json", "title": "Higgsfield API vs Replicate video models", "url": "https://www.anchorterminal.com/compare/higgsfield-vs-replicate-video" }, { "json": "https://www.anchorterminal.com/compare/kling-vs-replicate-video.json", "title": "Kling AI API vs Replicate video models", "url": "https://www.anchorterminal.com/compare/kling-vs-replicate-video" }, { "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/minimax-video-vs-replicate-video.json", "title": "MiniMax Video API vs Replicate video models", "url": "https://www.anchorterminal.com/compare/minimax-video-vs-replicate-video" }, { "json": "https://www.anchorterminal.com/compare/openai-sora-vs-replicate-video.json", "title": "OpenAI Sora API vs Replicate video models", "url": "https://www.anchorterminal.com/compare/openai-sora-vs-replicate-video" }, { "json": "https://www.anchorterminal.com/compare/pika-vs-replicate-video.json", "title": "Pika API vs Replicate video models", "url": "https://www.anchorterminal.com/compare/pika-vs-replicate-video" }, { "json": "https://www.anchorterminal.com/compare/pixverse-vs-replicate-video.json", "title": "PixVerse API vs Replicate video models", "url": "https://www.anchorterminal.com/compare/pixverse-vs-replicate-video" }, { "json": "https://www.anchorterminal.com/compare/replicate-video-vs-runway.json", "title": "Replicate video models vs Runway API", "url": "https://www.anchorterminal.com/compare/replicate-video-vs-runway" }, { "json": "https://www.anchorterminal.com/compare/replicate-video-vs-vidu.json", "title": "Replicate video models vs Vidu API", "url": "https://www.anchorterminal.com/compare/replicate-video-vs-vidu" } ], "scores": [ { "by": 30, "edge": "replicate-video", "google-veo": 45, "key": "reliability", "name": "Reliability", "replicate-video": 75, "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "by": 15, "edge": "replicate-video", "google-veo": 71, "key": "schema", "name": "Schema \u0026 documentation", "replicate-video": 86, "weight": 13 }, { "by": 8, "edge": "replicate-video", "google-veo": 64, "key": "ergonomics", "name": "Agent ergonomics", "replicate-video": 72, "weight": 13 }, { "by": 37, "edge": "google-veo", "google-veo": 78, "key": "security", "name": "Security \u0026 auth", "replicate-video": 41, "weight": 14 }, { "by": 10, "edge": "replicate-video", "google-veo": 20, "key": "payments", "name": "Payments \u0026 pricing", "replicate-video": 30, "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "by": 29, "edge": "google-veo", "google-veo": 77, "key": "maintenance", "name": "Maintenance \u0026 community", "replicate-video": 48, "weight": 7 }, { "by": 3, "edge": "google-veo", "google-veo": 75, "key": "transparency", "name": "Transparency \u0026 trust", "replicate-video": 72, "weight": 7 } ], "summary": "Replicate video models scores 62.1 (B) on agent readiness against Google Veo's 60.4 (C), and leads in 4 of 7 scored categories. Google Veo leads on security \u0026 auth and maintenance \u0026 community. Both do video generate.", "verdicts": { "google-veo": "Audio on every Veo 3.1 clip, up to 4K on Veo 3.1 and Fast. All three Veo 3.1 previews shut down on the Gemini API on 2026-10-22.", "replicate-video": "One bearer token reaches more than twenty official video models at published per-second prices, each with a typed input schema, and failed runs aren't charged. Tokens have no scopes or spend cap, no SLA is published, and the terms let Replicate withdraw any model without notice." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/google-veo-vs-replicate-video", "json": "https://www.anchorterminal.com/compare/google-veo-vs-replicate-video.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/google-veo-vs-replicate-video.md", "slim": "https://www.anchorterminal.com/compare/google-veo-vs-replicate-video.min.md" }, "markdown": "Replicate video models scores 62.1 (B) on agent readiness against Google Veo's 60.4 (C), and leads in 4 of 7 scored categories. Google Veo leads on security \u0026 auth and maintenance \u0026 community. Both do video generate.\n\n- Google Veo: grade C, 60.4/100, rank #465 of 842. Markdown https://www.anchorterminal.com/tools/google-veo.md · JSON https://www.anchorterminal.com/api/v1/tools/google-veo.json\n- Replicate video models: grade B, 62.1/100, rank #402 of 842. Markdown https://www.anchorterminal.com/tools/replicate-video.md · JSON https://www.anchorterminal.com/api/v1/tools/replicate-video.json\n\n## Which one, for what\n\n### Google Veo (C)\n\nGood for: Teams already on Google Cloud who want sound with every clip and a choice between cheap (Lite) and top quality (Veo 3.1, 4K).\n\nAhead on:\n- Security \u0026 auth, 78 against 41\n- Maintenance \u0026 community, 77 against 48\n\nWatch for: All three Veo 3.1 previews shut down on the Gemini API on 2026-10-22\n\n### Replicate video models (B)\n\nGood for: An agent that wants several vendors' video models behind one token and one request shape, or open models such as Wan next to closed ones.\n\nAhead on:\n- Reliability, 75 against 45\n- Schema \u0026 documentation, 86 against 71\n- Agent ergonomics, 72 against 64\n- Payments \u0026 pricing, 30 against 20\n\nAlso in its favour:\n- Runs on your own machine\n\nWatch for: Tokens have no scopes, expiry or spend cap, and any token can run every model and delete account resources\n\n\n## Score by category\n\n| Category | Weight | Google Veo | Replicate video models | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 45 | 75 | Replicate video models +30 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 71 | 86 | Replicate video models +15 |\n| Agent ergonomics | 13% (16.2 this run) | 64 | 72 | Replicate video models +8 |\n| Security \u0026 auth | 14% (17.5 this run) | 78 | 41 | Google Veo +37 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 20 | 30 | Replicate video models +10 |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 77 | 48 | Google Veo +29 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 75 | 72 | Google Veo +3 |\n| Negative events | ≤15 | 0 | 0 | |\n| **Total** | | **60.4 · C** | **62.1 · B** | |\n\n## Facts side by side\n\n| Fact | Google Veo | Replicate video models |\n| --- | --- | --- |\n| Kind | Model API | Model platform |\n| Vendor | Google | Replicate (Cloudflare) |\n| Hosted endpoint | `https://generativelanguage.googleapis.com/v1beta` | `https://api.replicate.com/v1` |\n| Transports | HTTP | HTTP, SSE (legacy), stdio |\n| Auth | API key | API key |\n| Pricing | Pay per use | Pay per use |\n| x402 | no | no |\n| Licence | Apache-2.0 (SDKs) | Proprietary service under Replicate's terms of service. The Python and JavaScript clients and `replicate-mcp` are Apache-2.0, and each model carries its own licence |\n| Read-only variant documented | no | no |\n| llms.txt | yes | yes |\n| Last release | 2026-09-22 | 2026-09-15 |\n| Terms last updated | 2026-04-28 | 2026-04-01 |\n| Privacy policy last updated | 2026-10-01 | 2026-04-01 |\n| Customer content may train models | yes | not found in the text |\n| Terms restrict automated access | yes | not found in the text |\n| Terms restrict benchmarking | yes | not found in the text |\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 | 4k stars | 917 stars, 705k npm/wk, 357k PyPI/wk |\n| Agent reviews | 2.5/5 (2) | none |\n\n## Verdicts\n\n**Google Veo.** Audio on every Veo 3.1 clip, up to 4K on Veo 3.1 and Fast. All three Veo 3.1 previews shut down on the Gemini API on 2026-10-22.\n\n**Replicate video models.** One bearer token reaches more than twenty official video models at published per-second prices, each with a typed input schema, and failed runs aren't charged. Tokens have no scopes or spend cap, no SLA is published, and the terms let Replicate withdraw any model without notice.\n\n## Before you call either\n\n### Google Veo\n\n1. Move off `veo-3.1-*-preview` before 2026-10-22. Use `gemini-omni-1.1-flash` on the Gemini API or the GA Veo IDs on Vertex AI\n2. Call `predictLongRunning`, then poll the operation name about every 10 seconds until `done` is true. Jobs take 11 seconds to 6 minutes\n3. Download the video within 2 days. The server deletes it after that\n4. Set `durationSeconds` to 8 for 1080p, 4K or reference images. Shorter clips aren't supported there\n5. In the EU, UK, Switzerland and MENA image-to-video only accepts `personGeneration` set to `allow_adult`\n\n### Replicate video models\n\n1. Call official models at `POST /v1/models/{owner}/{name}/predictions` with no version, then poll `GET /v1/predictions/{id}` or pass `webhook`. Video jobs usually outlast the 60-second `Prefer: wait` window\n2. Download the output file within the hour. API predictions lose inputs, outputs and logs after 60 minutes\n3. Read the model's price tiers before setting `resolution`, `mode` or `generate_audio`. Kling 3.0 runs from $0.168 to $0.42 a second and Veo 3.1 doubles with audio\n4. Send `Cancel-After` on every create. There is no idempotency key, so a blind retry is a second paid video\n5. Keep credit above $20 or enable auto-reload. Low balances are throttled, and granted credit with no card is held to 6 requests a minute\n\n## Questions\n\n### Which is better for AI agents, Google Veo or Replicate video models?\n\nReplicate video models scores 62.1 (B) on agent readiness against Google Veo's 60.4 (C), and leads in 4 of 7 scored categories. Google Veo leads on security \u0026 auth and maintenance \u0026 community.\n\n### Can an agent call Google Veo and Replicate video models without installing anything?\n\nYes. Google Veo has a hosted endpoint at https://generativelanguage.googleapis.com/v1beta and Replicate video models at https://api.replicate.com/v1.\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/google-veo-vs-replicate-video.json, and with the fewest tokens: https://www.anchorterminal.com/compare/google-veo-vs-replicate-video.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"google-veo\", \"b\": \"replicate-video\"}`. From a terminal: `anchor compare google-veo replicate-video`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/google-veo.json and https://www.anchorterminal.com/api/v1/tools/replicate-video.json\n\n## Other comparisons with Google Veo or Replicate video models\n\n- [Alibaba Wan (Model Studio) vs Google Veo](https://www.anchorterminal.com/compare/alibaba-wan-vs-google-veo.md)\n- [Alibaba Wan (Model Studio) vs Replicate video models](https://www.anchorterminal.com/compare/alibaba-wan-vs-replicate-video.md)\n- [fal video models vs Google Veo](https://www.anchorterminal.com/compare/fal-video-vs-google-veo.md)\n- [fal video models vs Replicate video models](https://www.anchorterminal.com/compare/fal-video-vs-replicate-video.md)\n- [Google Veo vs Higgsfield API](https://www.anchorterminal.com/compare/google-veo-vs-higgsfield.md)\n- [Google Veo vs Kling AI API](https://www.anchorterminal.com/compare/google-veo-vs-kling.md)\n- [Google Veo vs Luma AI API](https://www.anchorterminal.com/compare/google-veo-vs-luma.md)\n- [Google Veo vs MiniMax Video API](https://www.anchorterminal.com/compare/google-veo-vs-minimax-video.md)\n- [Google Veo vs OpenAI Sora API](https://www.anchorterminal.com/compare/google-veo-vs-openai-sora.md)\n- [Google Veo vs Pika API](https://www.anchorterminal.com/compare/google-veo-vs-pika.md)\n- [Google Veo vs PixVerse API](https://www.anchorterminal.com/compare/google-veo-vs-pixverse.md)\n- [Google Veo vs Runway API](https://www.anchorterminal.com/compare/google-veo-vs-runway.md)\n- [Google Veo vs Vidu API](https://www.anchorterminal.com/compare/google-veo-vs-vidu.md)\n- [Higgsfield API vs Replicate video models](https://www.anchorterminal.com/compare/higgsfield-vs-replicate-video.md)\n- [Kling AI API vs Replicate video models](https://www.anchorterminal.com/compare/kling-vs-replicate-video.md)\n- [Luma AI API vs Replicate video models](https://www.anchorterminal.com/compare/luma-vs-replicate-video.md)\n- [MiniMax Video API vs Replicate video models](https://www.anchorterminal.com/compare/minimax-video-vs-replicate-video.md)\n- [OpenAI Sora API vs Replicate video models](https://www.anchorterminal.com/compare/openai-sora-vs-replicate-video.md)\n- [Pika API vs Replicate video models](https://www.anchorterminal.com/compare/pika-vs-replicate-video.md)\n- [PixVerse API vs Replicate video models](https://www.anchorterminal.com/compare/pixverse-vs-replicate-video.md)\n- [Replicate video models vs Runway API](https://www.anchorterminal.com/compare/replicate-video-vs-runway.md)\n- [Replicate video models vs Vidu API](https://www.anchorterminal.com/compare/replicate-video-vs-vidu.md)\n", "meta": { "attribution": "Anchor Terminal (https://www.anchorterminal.com)", "docs": "https://www.anchorterminal.com/docs/", "generatedAt": "2026-10-09", "license": "CC-BY-4.0", "method": "https://www.anchorterminal.com/benchmark/", "methodology": "0.4", "openapi": "https://www.anchorterminal.com/openapi.json", "preview": false, "run": "2026-10-01", "runLabel": "October 2026 research run" }, "page": { "breadcrumbs": [ { "name": "Home", "url": "https://www.anchorterminal.com/" }, { "name": "Compare", "url": "https://www.anchorterminal.com/compare/" }, { "name": "Google Veo vs Replicate video models", "url": "" } ], "description": "Replicate video models scores 62.1 (B) on agent readiness against Google Veo's 60.4 (C), and leads in 4 of 7 scored categories. Google Veo leads on security \u0026 auth and maintenance \u0026 community. Both do video generate. Category scores, facts, verdicts and agent notes side by side.", "facts": [ "Google Veo C 60.4", "Replicate video models B 62.1", "scores" ], "h1": "Google Veo vs Replicate video models", "image": "https://www.anchorterminal.com/assets/og/compare-google-veo-vs-replicate-video.png", "path": "/compare/google-veo-vs-replicate-video", "published": "2026-10-01", "section": "tools", "title": "Google Veo vs Replicate video models for AI agents, C 60.4 vs B 62.1", "toc": null, "updated": "2026-10-09", "url": "https://www.anchorterminal.com/compare/google-veo-vs-replicate-video" }, "tokens": { "markdown": 2400, "slim": 730 }, "version": 1 }