{ "data": { "a": { "slug": "google-imagen", "name": "Google Imagen", "vendor": "Google", "vendorUrl": "https://ai.google.dev", "kind": "model", "category": "image-generation", "summary": "Discontinued Google image generation models, formerly available through the Gemini API and Vertex AI.", "url": "https://www.anchorterminal.com/tools/google-imagen", "markdownUrl": "https://www.anchorterminal.com/tools/google-imagen.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/google-imagen.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/google-imagen.json", "transports": [ "http" ], "remoteUrl": "https://generativelanguage.googleapis.com/v1beta", "packages": [ { "registry": "pypi", "name": "google-genai" }, { "registry": "npm", "name": "@google/genai" } ], "auth": "api-key", "authNotes": "Gemini API used an `x-goog-api-key` key. Vertex AI used Google Cloud IAM with OAuth access tokens.", "pricing": "usage", "pricingNotes": "Per image before shutdown. Imagen 4 Fast $0.02, Imagen 4 $0.04, Imagen 4 Ultra $0.06, Imagen 4 upscaling $0.06. The Vertex AI pricing page still lists these rates, but the models are discontinued (https://cloud.google.com/vertex-ai/generative-ai/pricing).", "priceSummary": "Pay per use", "where": "hosted", "x402": { "level": "no", "evidence": "No machine payment. Access needed a Google Cloud or AI Studio billing account.", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": null, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-09-30" }, "docsUrl": "https://ai.google.dev/gemini-api/docs/imagen", "capabilities": [ "image.generate", "image.edit", "image.upscale" ], "tags": [ "retired", "hosted", "closed-source", "python", "typescript", "watermark" ], "lastRelease": "2025-08-14", "graded": true, "anchor": { "graded": true, "score": 6.8, "grade": "F", "agentReady": false, "rank": 0, "ranked": false, "notRankedWhy": "Shut down 2026-08-17, so out of the ranking", "rankOf": 950, "categoryRank": 12, "methodology": "0.4", "run": "2026-10-01", "scores": { "ergonomics": 0, "maintenance": 5, "payments": 0, "reliability": 0, "schema": 25, "security": 0, "transparency": 60 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "high", "date": "2026-10-01" }, "negative": -3, "negativeNotes": [ "Since 2026-06-30 the Vertex AI generative AI pricing page still lists Imagen 4, Imagen 4 Fast and Imagen 4 Ultra at $0.02 to $0.06 an image with no discontinuation note, three months after the endpoints were discontinued (https://cloud.google.com/vertex-ai/generative-ai/pricing, seen 2026-10-01). -3, the low end, because the model pages and release notes do carry the date." ], "verdict": "Shutdown dates were published in the Gemini API changelog and the Vertex AI release notes, with replacements named. Discontinued. Calls to imagen model names fail on both the Gemini API and Vertex AI.", "strengths": [ "Shutdown dates were published in the Gemini API changelog and the Vertex AI release notes, with replacements named", "The Gemini API Imagen page now states the shutdown and the three migration changes", "Imagen 4 outputs carried a SynthID watermark, and C2PA on Imagen 4 and Fast" ], "weaknesses": [ "Discontinued. Calls to imagen model names fail on both the Gemini API and Vertex AI", "Notice was 63 days on the Gemini API and 98 days on Vertex AI, for a model GA since August 2025", "Mask-based editing from imagen-3.0-capability-001 has no Google replacement", "The Vertex AI pricing page still lists Imagen 4 rates with no discontinuation note" ], "agentNotes": [ "Replace `client.models.generate_images` with `client.models.generate_content` and a `gemini-3.1-flash-image` model", "Read images from the response content parts, not from `generated_images`", "Don't budget from the Vertex Imagen price rows, they describe a retired product", "If the job needs a mask-based inpaint, use another vendor's fill endpoint, since Gemini image editing is prompt-based" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 2, "avgRating": 1, "history": [ { "basis": "public evidence", "confidence": "high", "grade": "F", "methodology": "0.4", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 6.8 } ], "editorialScores": { "ergonomics": 0, "maintenance": 5, "payments": 0, "reliability": 0, "schema": 25, "security": 0, "transparency": 30 }, "provenanceScore": 89 }, "connect": { "http": "curl \"https://generativelanguage.googleapis.com/v1beta/models/imagen-4.0-generate-001:predict\" \\\n -H \"x-goog-api-key: $GEMINI_API_KEY\" -H \"content-type: application/json\" \\\n -d '{\"instances\":[{\"prompt\":\"A robot holding a red skateboard\"}],\"parameters\":{\"sampleCount\":1}}' # retired, kept for reference" }, "letme": { "capability": "https://letme.dev/image.generate", "tool": "https://letme.dev/google-imagen" }, "supersededBy": [ "gemini-api" ], "sameCompany": [ "gemini-api", "gemini-embedding", "vertex-ai-tuning", "google-model-armor", "google-veo", "google-lyria", "google-speech-to-text", "gemini-live", "google-adk", "google-secret-manager", "google-cloud-document-ai", "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", "retired": "2026-08-17", "unitPrices": [ { "item": "Imagen 4 Fast", "unit": "image", "usd": 0.02, "note": "retired, last listed price" }, { "item": "Imagen 4", "unit": "image", "usd": 0.04, "note": "retired, last listed price" }, { "item": "Imagen 4 Ultra", "unit": "image", "usd": 0.06, "note": "retired, last listed price" } ], "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": "2026-09-30", "score": 89 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/google-imagen.json" }, "answer": "Seedream on BytePlus ModelArk scores 53.8 (D) on agent readiness against Google Imagen's 6.8 (F), and leads in 6 of 7 scored categories.", "b": { "slug": "seedream-on-byteplus-modelark", "name": "Seedream on BytePlus ModelArk", "vendor": "BytePlus Pte. Ltd. (ByteDance)", "vendorUrl": "https://www.byteplus.com", "kind": "model", "category": "image-generation", "summary": "BytePlus ModelArk's hosted API for ByteDance's Seedream image models. One endpoint handles text-to-image, reference-image editing, batches of related images and layer decomposition, billed per generated image.", "url": "https://www.anchorterminal.com/tools/seedream-on-byteplus-modelark", "markdownUrl": "https://www.anchorterminal.com/tools/seedream-on-byteplus-modelark.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/seedream-on-byteplus-modelark.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/seedream-on-byteplus-modelark.json", "repo": "https://github.com/volcengine/ark-runtime-go", "license": "Proprietary service under the BytePlus Customer Agreement and Service Specific Terms. The Go and Python SDK repositories are Apache-2.0", "transports": [ "http" ], "remoteUrl": "https://ark.ap-southeast.bytepluses.com/api/v3", "packages": [ { "registry": "pypi", "name": "arkruntime" }, { "registry": "pypi", "name": "byteplus-python-sdk-v2" }, { "registry": "go", "name": "github.com/volcengine/ark-runtime-go" } ], "auth": "api-key", "authNotes": "The image endpoint takes a ModelArk API key as a Bearer token and, per its reference, no other credential. Keys are created in the console after a browser sign-up, belong to one resource project and one region, and can be limited to named model IDs or custom inference endpoints and to an IP allowlist. A key can be disabled, re-enabled or deleted, and a primary account holds up to 50. Each model must be activated in the console before use.", "pricing": "usage", "pricingNotes": "Pay as you go per successfully generated image, in US dollars, published without a login. Seedream 5.0 flash $0.018, 4.0 $0.03, 5.0 lite $0.035, 4.5 $0.04, 5.0 pro $0.045 up to 2.61 million pixels and $0.09 above. Input images are free except on 5.0 pro, which charges $0.003 from the second. No free image quota is listed for Seedream, and an account in arrears for two hours is suspended (https://docs.byteplus.com/en/docs/modelark/model-pricing).", "priceSummary": "Pay per use", "where": "hosted", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the API reference, the pricing page or the error codes (checked 2026-10-09).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": null, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-10-09" }, "docsUrl": "https://docs.byteplus.com/en/docs/modelark/image-generation-api", "capabilities": [ "image.generate", "image.edit", "image.reference" ], "tags": [ "hosted", "closed-source", "api-key", "python", "go", "java", "openai-compatible", "watermark", "streaming", "regional-endpoints" ], "lastRelease": "2026-09-17", "graded": true, "anchor": { "graded": true, "score": 53.8, "grade": "D", "agentReady": false, "rank": 700, "ranked": true, "rankOf": 950, "categoryRank": 5, "methodology": "0.4", "run": "2026-10-01", "scores": { "ergonomics": 72, "maintenance": 73, "payments": 20, "reliability": 43, "schema": 62, "security": 70, "transparency": 60 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-09" }, "negative": -3, "negativeNotes": [ "The model list (updated 28 September 2026) says `seedream-5-0-lite` is supported in eu-west-1, while the deprecation page says the model was deactivated in that region on 10 September 2026 and the region page lists only `seed-2-0-lite` for the EU. The batch that carries the notice is dated 8 September 2026, two days earlier, against the page's own 30-day minimum. We made no call to confirm which page is right. 3 points (https://docs.byteplus.com/en/docs/modelark/model-deprecation-notice)." ], "verdict": "Per-image prices from $0.018 are public, and API keys can be limited to named models and an IP allowlist. No status page, SLA or OpenAPI file was found, onboarding needs a browser sign-up, and BytePlus says its model services are not available in the United States.", "bestFor": "Agents that need ByteDance's Seedream models first-hand, multi-reference edits, 4K output or layered PNG output at a published per-image price, for users outside the United States.", "strengths": [ "Per-image prices are public for five Seedream models, from $0.018 (5.0 flash) to $0.09 (5.0 pro above 1.5K), and failed or moderated images are not billed", "API keys are scoped to a project and can be limited to named model IDs or endpoints and to an IP allowlist", "Up to 14 reference images on Seedream 5.0 lite, 4.5 and 4.0, and up to 4K output (4096x4096) on those models", "The error reference lists 15 distinct 429 codes, and a burst-traffic guide gives backoff code with jitter", "The service terms say customer data is not used for training unless the customer opts in", "A written deprecation process promises at least 30 calendar days' notice, with dated batches and named replacements" ], "weaknesses": [ "No status page, incident history or ModelArk SLA was found in the pages read", "No OpenAPI file, llms.txt or Markdown docs for agents were found. The docs site is drawn by script", "The model list says `seedream-5-0-lite` runs in eu-west-1, while the deprecation page says it was deactivated there on 10 September 2026", "The Service Specific Terms say BytePlus Model Services are not available in the United States", "No idempotency key was found, so a retried request that succeeded is a second paid generation", "Image URLs expire 24 hours after generation, and a watermark is added unless `watermark` is set to false" ], "agentNotes": [ "POST to `https://ark.ap-southeast.bytepluses.com/api/v3/images/generations` with `Authorization: Bearer $ARK_API_KEY`. Keys and model activation are per region", "Set `watermark` to false if the image must not carry the AI-generated mark. The default is true", "Download `data[].url` within 24 hours, or ask for `response_format` `b64_json`", "Check each `data[].error` in a sequential batch. One moderated image does not fail the others, and only `usage.generated_images` is billed", "Stay under 500 images a minute per model and back off with jitter on 429. Layer decomposition reserves 17 against that limit per request" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "D", "methodology": "0.4", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 53.8 } ], "editorialScores": { "ergonomics": 72, "maintenance": 73, "payments": 20, "reliability": 43, "schema": 62, "security": 70, "transparency": 61 }, "provenanceScore": 59 }, "connect": { "install": "python -m pip install --upgrade arkruntime", "http": "curl https://ark.ap-southeast.bytepluses.com/api/v3/images/generations \\\n -H \"Content-Type: application/json\" \\\n -H \"Authorization: Bearer $ARK_API_KEY\" \\\n -d '{\"model\":\"seedream-5-0-lite-260128\",\"prompt\":\"A lighthouse at dusk\",\"size\":\"2K\",\"output_format\":\"png\",\"watermark\":false}'" }, "letme": { "capability": "https://letme.dev/image.generate", "tool": "https://letme.dev/seedream-on-byteplus-modelark" }, "sameCompany": [ "seedance-on-byteplus-modelark" ], "area": "content", "unitPrices": [ { "item": "Seedream 5.0 flash", "unit": "image", "usd": 0.018 }, { "item": "Seedream 4.0", "unit": "image", "usd": 0.03 }, { "item": "Seedream 5.0 lite", "unit": "image", "usd": 0.035 }, { "item": "Seedream 4.5", "unit": "image", "usd": 0.04 }, { "item": "Seedream 5.0 pro", "unit": "image", "usd": 0.045, "note": "up to 2.61 million pixels (1.5K or lower)" }, { "item": "Seedream 5.0 pro above 1.5K", "unit": "image", "usd": 0.09, "note": "more than 2.61 million pixels" } ], "provenance": { "legalEntity": "BytePlus Pte. Ltd.", "domain": "byteplus.com", "domainRegistered": "2002-09-07", "endpointOnVendorDomain": false, "terms": "https://docs.byteplus.com/en/docs/legal/docs-customer-agreement", "privacy": "https://docs.byteplus.com/en/docs/legal/docs-privacy-policy", "statusPage": "", "changelog": "https://docs.byteplus.com/en/docs/modelark/model-release-announcement", "securityTxt": "none", "checked": "2026-10-09", "notes": [ "The Customer Agreement (effective 30 September 2026) is made with BytePlus Pte. Ltd. or another BytePlus affiliate named as the contracting entity. The Service Specific Terms, which hold the ModelArk and Model Services sections, rank above it.", "The API answers at ark.ap-southeast.bytepluses.com and ark.eu-west.bytepluses.com, a different domain from byteplus.com. BytePlus's own docs name both hosts.", "The Privacy Policy names Byteplus Pte. Ltd. in Singapore as controller and says it does not cover personal data processed on behalf of corporate customers. That processing falls under the Data Processing Addendum, which we did not read.", "https://www.byteplus.com/.well-known/security.txt returns the site's HTML shell, not a security.txt file. The SDK repositories carry a SECURITY.md that sends reports to ByteDance's security centre.", "No status page was found in the docs or on the pages of www.byteplus.com that we could read.", "RDAP for byteplus.com gives a registration date of 2002-09-07 and Gandi SAS as registrar." ], "score": 59 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/seedream-on-byteplus-modelark.json", "live": { "slug": "seedream-on-byteplus-modelark", "probe": { "target": "https://ark.ap-southeast.bytepluses.com/api/v3", "method": "get", "lastAt": "2026-10-10T04:41:02.921829271Z", "lastOk": true, "lastStatus": 401, "lastMs": 457, "lastNote": "asks for credentials", "authRequired": true, "uptime24h": 100, "uptime30d": 100, "p50ms24h": 507, "p95ms24h": 595, "samples24h": 133, "samples30d": 133, "days": [ { "date": "2026-10-09", "probes": 85, "ok": 85 }, { "date": "2026-10-10", "probes": 48, "ok": 48 } ] }, "versions": [ { "registry": "pypi", "name": "arkruntime", "version": "0.8.0", "released": "2026-09-17", "seenAt": "2026-10-09T17:19:00.477962822Z" }, { "registry": "pypi", "name": "byteplus-python-sdk-v2", "version": "3.0.61", "released": "2026-09-17", "seenAt": "2026-10-09T17:19:00.589058252Z" } ], "githubStars": 1, "pypiWeekly": 1265, "pages": [ { "url": "https://docs.byteplus.com/en/docs/modelark/model-release-announcement", "kind": "changelog", "status": 200, "checkedAt": "2026-10-09T18:36:54.525658153Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "2c972ac5021a" }, { "url": "https://docs.byteplus.com/en/docs/modelark/model-pricing", "kind": "pricing", "status": 200, "checkedAt": "2026-10-09T18:36:52.663758009Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "faaf238183a5" } ], "updatedAt": "2026-10-10T04:41:02.921829271Z" } }, "facts": [ { "a": "Model API", "b": "Model API", "name": "Kind" }, { "a": "Google", "b": "BytePlus Pte. Ltd. (ByteDance)", "name": "Vendor" }, { "a": "https://generativelanguage.googleapis.com/v1beta", "b": "https://ark.ap-southeast.bytepluses.com/api/v3", "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": "none", "b": "Proprietary service under the BytePlus Customer Agreement and Service Specific Terms. The Go and Python SDK repositories are Apache-2.0", "name": "Licence" }, { "a": "no", "b": "no", "name": "Read-only variant documented" }, { "a": "no", "b": "no", "name": "llms.txt" }, { "a": "2025-08-14", "b": "2026-09-17", "name": "Last release" }, { "a": "2026-04-28", "b": "couldn't be read", "name": "Terms last updated" }, { "a": "2026-10-01", "b": "couldn't be read", "name": "Privacy policy last updated" }, { "a": "yes", "b": "couldn't be read", "name": "Customer content may train models" }, { "a": "yes", "b": "couldn't be read", "name": "Terms restrict automated access" }, { "a": "yes", "b": "couldn't be read", "name": "Terms restrict benchmarking" }, { "a": "not found in the text", "b": "couldn't be read", "name": "Terms or service can change without notice" }, { "a": "not found in the text", "b": "couldn't be read", "name": "Arbitration or class-action waiver" }, { "a": "1/5 (2)", "b": "none", "name": "Agent reviews" } ], "faq": [ { "answer": "Seedream on BytePlus ModelArk scores 53.8 (D) on agent readiness against Google Imagen's 6.8 (F), and leads in 6 of 7 scored categories.", "question": "Which is better for AI agents, Google Imagen or Seedream on BytePlus ModelArk?" }, { "answer": "Both need an API key.", "question": "Do Google Imagen and Seedream on BytePlus ModelArk need an API key?" }, { "answer": "Yes. Google Imagen has a hosted endpoint at https://generativelanguage.googleapis.com/v1beta and Seedream on BytePlus ModelArk at https://ark.ap-southeast.bytepluses.com/api/v3.", "question": "Can an agent call Google Imagen and Seedream on BytePlus ModelArk without installing anything?" } ], "goodFor": [ { "aheadOn": null, "also": null, "goodFor": "Nothing new. It shut down on 2026-08-17.", "slug": "google-imagen", "watchFor": "Discontinued. Calls to imagen model names fail on both the Gemini API and Vertex AI" }, { "aheadOn": [ "Reliability, 43 against 0", "Schema \u0026 documentation, 62 against 25", "Agent ergonomics, 72 against 0", "Security \u0026 auth, 70 against 0", "Payments \u0026 pricing, 20 against 0", "Maintenance \u0026 community, 73 against 5" ], "also": [ "Still running. Google Imagen has shut down" ], "goodFor": "Agents that need ByteDance's Seedream models first-hand, multi-reference edits, 4K output or layered PNG output at a published per-image price, for users outside the United States.", "slug": "seedream-on-byteplus-modelark", "watchFor": "No status page, incident history or ModelArk SLA was found in the pages read" } ], "job": { "capability": "image.generate", "name": "Image generation" }, "others": [ { "json": "https://www.anchorterminal.com/compare/adobe-firefly-vs-google-imagen.json", "title": "Adobe Firefly API vs Google Imagen", "url": "https://www.anchorterminal.com/compare/adobe-firefly-vs-google-imagen" }, { "json": "https://www.anchorterminal.com/compare/adobe-firefly-vs-seedream-on-byteplus-modelark.json", "title": "Adobe Firefly API vs Seedream on BytePlus ModelArk", "url": "https://www.anchorterminal.com/compare/adobe-firefly-vs-seedream-on-byteplus-modelark" }, { "json": "https://www.anchorterminal.com/compare/black-forest-labs-vs-google-imagen.json", "title": "Black Forest Labs FLUX API vs Google Imagen", "url": "https://www.anchorterminal.com/compare/black-forest-labs-vs-google-imagen" }, { "json": "https://www.anchorterminal.com/compare/black-forest-labs-vs-seedream-on-byteplus-modelark.json", "title": "Black Forest Labs FLUX API vs Seedream on BytePlus ModelArk", "url": "https://www.anchorterminal.com/compare/black-forest-labs-vs-seedream-on-byteplus-modelark" }, { "json": "https://www.anchorterminal.com/compare/bria-vs-google-imagen.json", "title": "Bria API vs Google Imagen", "url": "https://www.anchorterminal.com/compare/bria-vs-google-imagen" }, { "json": "https://www.anchorterminal.com/compare/bria-vs-seedream-on-byteplus-modelark.json", "title": "Bria API vs Seedream on BytePlus ModelArk", "url": "https://www.anchorterminal.com/compare/bria-vs-seedream-on-byteplus-modelark" }, { "json": "https://www.anchorterminal.com/compare/fal-image-vs-google-imagen.json", "title": "fal image models vs Google Imagen", "url": "https://www.anchorterminal.com/compare/fal-image-vs-google-imagen" }, { "json": "https://www.anchorterminal.com/compare/fal-image-vs-seedream-on-byteplus-modelark.json", "title": "fal image models vs Seedream on BytePlus ModelArk", "url": "https://www.anchorterminal.com/compare/fal-image-vs-seedream-on-byteplus-modelark" }, { "json": "https://www.anchorterminal.com/compare/google-imagen-vs-ideogram.json", "title": "Google Imagen vs Ideogram API", "url": "https://www.anchorterminal.com/compare/google-imagen-vs-ideogram" }, { "json": "https://www.anchorterminal.com/compare/google-imagen-vs-leonardo-ai.json", "title": "Google Imagen vs Leonardo.Ai API", "url": "https://www.anchorterminal.com/compare/google-imagen-vs-leonardo-ai" }, { "json": "https://www.anchorterminal.com/compare/google-imagen-vs-openai-image-api.json", "title": "Google Imagen vs OpenAI Image API", "url": "https://www.anchorterminal.com/compare/google-imagen-vs-openai-image-api" }, { "json": "https://www.anchorterminal.com/compare/google-imagen-vs-recraft.json", "title": "Google Imagen vs Recraft API", "url": "https://www.anchorterminal.com/compare/google-imagen-vs-recraft" }, { "json": "https://www.anchorterminal.com/compare/google-imagen-vs-replicate-image.json", "title": "Google Imagen vs Replicate image models", "url": "https://www.anchorterminal.com/compare/google-imagen-vs-replicate-image" }, { "json": "https://www.anchorterminal.com/compare/google-imagen-vs-stability-ai-image.json", "title": "Google Imagen vs Stability AI Image API", "url": "https://www.anchorterminal.com/compare/google-imagen-vs-stability-ai-image" }, { "json": "https://www.anchorterminal.com/compare/ideogram-vs-seedream-on-byteplus-modelark.json", "title": "Ideogram API vs Seedream on BytePlus ModelArk", "url": "https://www.anchorterminal.com/compare/ideogram-vs-seedream-on-byteplus-modelark" }, { "json": "https://www.anchorterminal.com/compare/leonardo-ai-vs-seedream-on-byteplus-modelark.json", "title": "Leonardo.Ai API vs Seedream on BytePlus ModelArk", "url": "https://www.anchorterminal.com/compare/leonardo-ai-vs-seedream-on-byteplus-modelark" }, { "json": "https://www.anchorterminal.com/compare/openai-image-api-vs-seedream-on-byteplus-modelark.json", "title": "OpenAI Image API vs Seedream on BytePlus ModelArk", "url": "https://www.anchorterminal.com/compare/openai-image-api-vs-seedream-on-byteplus-modelark" }, { "json": "https://www.anchorterminal.com/compare/recraft-vs-seedream-on-byteplus-modelark.json", "title": "Recraft API vs Seedream on BytePlus ModelArk", "url": "https://www.anchorterminal.com/compare/recraft-vs-seedream-on-byteplus-modelark" }, { "json": "https://www.anchorterminal.com/compare/replicate-image-vs-seedream-on-byteplus-modelark.json", "title": "Replicate image models vs Seedream on BytePlus ModelArk", "url": "https://www.anchorterminal.com/compare/replicate-image-vs-seedream-on-byteplus-modelark" }, { "json": "https://www.anchorterminal.com/compare/seedream-on-byteplus-modelark-vs-stability-ai-image.json", "title": "Seedream on BytePlus ModelArk vs Stability AI Image API", "url": "https://www.anchorterminal.com/compare/seedream-on-byteplus-modelark-vs-stability-ai-image" } ], "scores": [ { "by": 43, "edge": "seedream-on-byteplus-modelark", "google-imagen": 0, "key": "reliability", "name": "Reliability", "seedream-on-byteplus-modelark": 43, "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "by": 37, "edge": "seedream-on-byteplus-modelark", "google-imagen": 25, "key": "schema", "name": "Schema \u0026 documentation", "seedream-on-byteplus-modelark": 62, "weight": 13 }, { "by": 72, "edge": "seedream-on-byteplus-modelark", "google-imagen": 0, "key": "ergonomics", "name": "Agent ergonomics", "seedream-on-byteplus-modelark": 72, "weight": 13 }, { "by": 70, "edge": "seedream-on-byteplus-modelark", "google-imagen": 0, "key": "security", "name": "Security \u0026 auth", "seedream-on-byteplus-modelark": 70, "weight": 14 }, { "by": 20, "edge": "seedream-on-byteplus-modelark", "google-imagen": 0, "key": "payments", "name": "Payments \u0026 pricing", "seedream-on-byteplus-modelark": 20, "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "by": 68, "edge": "seedream-on-byteplus-modelark", "google-imagen": 5, "key": "maintenance", "name": "Maintenance \u0026 community", "seedream-on-byteplus-modelark": 73, "weight": 7 }, { "by": 0, "edge": "", "google-imagen": 60, "key": "transparency", "name": "Transparency \u0026 trust", "seedream-on-byteplus-modelark": 60, "weight": 7 } ], "summary": "Google Imagen shut down on 2026-08-17. Seedream on BytePlus ModelArk scores 53.8 (D) on agent readiness against Google Imagen's 6.8 (F), and leads in 6 of 7 scored categories. Both do image generation.", "verdicts": { "google-imagen": "Shutdown dates were published in the Gemini API changelog and the Vertex AI release notes, with replacements named. Discontinued. Calls to imagen model names fail on both the Gemini API and Vertex AI.", "seedream-on-byteplus-modelark": "Per-image prices from $0.018 are public, and API keys can be limited to named models and an IP allowlist. No status page, SLA or OpenAPI file was found, onboarding needs a browser sign-up, and BytePlus says its model services are not available in the United States." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/google-imagen-vs-seedream-on-byteplus-modelark", "json": "https://www.anchorterminal.com/compare/google-imagen-vs-seedream-on-byteplus-modelark.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/google-imagen-vs-seedream-on-byteplus-modelark.md", "slim": "https://www.anchorterminal.com/compare/google-imagen-vs-seedream-on-byteplus-modelark.min.md" }, "markdown": "Google Imagen shut down on 2026-08-17. Seedream on BytePlus ModelArk scores 53.8 (D) on agent readiness against Google Imagen's 6.8 (F), and leads in 6 of 7 scored categories. Both do image generation.\n\n- Google Imagen: grade F, 6.8/100, rank retired, not ranked. Markdown https://www.anchorterminal.com/tools/google-imagen.md · JSON https://www.anchorterminal.com/api/v1/tools/google-imagen.json\n- Seedream on BytePlus ModelArk: grade D, 53.8/100, rank #700 of 950. Markdown https://www.anchorterminal.com/tools/seedream-on-byteplus-modelark.md · JSON https://www.anchorterminal.com/api/v1/tools/seedream-on-byteplus-modelark.json\n- Best image generation for AI agents: https://www.anchorterminal.com/best/image-generation/index.md\n- All 66 image comparisons: https://www.anchorterminal.com/compare/image-generation/index.md\n\n## Which one, for what\n\n### Google Imagen (F)\n\nGood for: Nothing new. It shut down on 2026-08-17.\n\nWatch for: Discontinued. Calls to imagen model names fail on both the Gemini API and Vertex AI\n\n### Seedream on BytePlus ModelArk (D)\n\nGood for: Agents that need ByteDance's Seedream models first-hand, multi-reference edits, 4K output or layered PNG output at a published per-image price, for users outside the United States.\n\nAhead on:\n- Reliability, 43 against 0\n- Schema \u0026 documentation, 62 against 25\n- Agent ergonomics, 72 against 0\n- Security \u0026 auth, 70 against 0\n- Payments \u0026 pricing, 20 against 0\n- Maintenance \u0026 community, 73 against 5\n\nAlso in its favour:\n- Still running. Google Imagen has shut down\n\nWatch for: No status page, incident history or ModelArk SLA was found in the pages read\n\n\n## Score by category\n\n| Category | Weight | Google Imagen | Seedream on BytePlus ModelArk | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 0 | 43 | Seedream on BytePlus ModelArk +43 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 25 | 62 | Seedream on BytePlus ModelArk +37 |\n| Agent ergonomics | 13% (16.2 this run) | 0 | 72 | Seedream on BytePlus ModelArk +72 |\n| Security \u0026 auth | 14% (17.5 this run) | 0 | 70 | Seedream on BytePlus ModelArk +70 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 0 | 20 | Seedream on BytePlus ModelArk +20 |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 5 | 73 | Seedream on BytePlus ModelArk +68 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 60 | 60 | even |\n| Negative events | ≤15 | -3 | -3 | |\n| **Total** | | **6.8 · F** | **53.8 · D** | |\n\n## Facts side by side\n\n| Fact | Google Imagen | Seedream on BytePlus ModelArk |\n| --- | --- | --- |\n| Kind | Model API | Model API |\n| Vendor | Google | BytePlus Pte. Ltd. (ByteDance) |\n| Hosted endpoint | `https://generativelanguage.googleapis.com/v1beta` | `https://ark.ap-southeast.bytepluses.com/api/v3` |\n| Transports | HTTP | HTTP |\n| Auth | API key | API key |\n| Pricing | Pay per use | Pay per use |\n| x402 | no | no |\n| Licence | none | Proprietary service under the BytePlus Customer Agreement and Service Specific Terms. The Go and Python SDK repositories are Apache-2.0 |\n| Read-only variant documented | no | no |\n| llms.txt | no | no |\n| Last release | 2025-08-14 | 2026-09-17 |\n| Terms last updated | 2026-04-28 | couldn't be read |\n| Privacy policy last updated | 2026-10-01 | couldn't be read |\n| Customer content may train models | yes | couldn't be read |\n| Terms restrict automated access | yes | couldn't be read |\n| Terms restrict benchmarking | yes | couldn't be read |\n| Terms or service can change without notice | not found in the text | couldn't be read |\n| Arbitration or class-action waiver | not found in the text | couldn't be read |\n| Agent reviews | 1/5 (2) | none |\n\n## Verdicts\n\n**Google Imagen.** Shutdown dates were published in the Gemini API changelog and the Vertex AI release notes, with replacements named. Discontinued. Calls to imagen model names fail on both the Gemini API and Vertex AI.\n\n**Seedream on BytePlus ModelArk.** Per-image prices from $0.018 are public, and API keys can be limited to named models and an IP allowlist. No status page, SLA or OpenAPI file was found, onboarding needs a browser sign-up, and BytePlus says its model services are not available in the United States.\n\n## Before you call either\n\n### Google Imagen\n\n1. Replace `client.models.generate_images` with `client.models.generate_content` and a `gemini-3.1-flash-image` model\n2. Read images from the response content parts, not from `generated_images`\n3. Don't budget from the Vertex Imagen price rows, they describe a retired product\n4. If the job needs a mask-based inpaint, use another vendor's fill endpoint, since Gemini image editing is prompt-based\n\n### Seedream on BytePlus ModelArk\n\n1. POST to `https://ark.ap-southeast.bytepluses.com/api/v3/images/generations` with `Authorization: Bearer $ARK_API_KEY`. Keys and model activation are per region\n2. Set `watermark` to false if the image must not carry the AI-generated mark. The default is true\n3. Download `data[].url` within 24 hours, or ask for `response_format` `b64_json`\n4. Check each `data[].error` in a sequential batch. One moderated image does not fail the others, and only `usage.generated_images` is billed\n5. Stay under 500 images a minute per model and back off with jitter on 429. Layer decomposition reserves 17 against that limit per request\n\n## Questions\n\n### Which is better for AI agents, Google Imagen or Seedream on BytePlus ModelArk?\n\nSeedream on BytePlus ModelArk scores 53.8 (D) on agent readiness against Google Imagen's 6.8 (F), and leads in 6 of 7 scored categories.\n\n### Do Google Imagen and Seedream on BytePlus ModelArk need an API key?\n\nBoth need an API key.\n\n### Can an agent call Google Imagen and Seedream on BytePlus ModelArk without installing anything?\n\nYes. Google Imagen has a hosted endpoint at https://generativelanguage.googleapis.com/v1beta and Seedream on BytePlus ModelArk at https://ark.ap-southeast.bytepluses.com/api/v3.\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/google-imagen-vs-seedream-on-byteplus-modelark.json, and with the fewest tokens: https://www.anchorterminal.com/compare/google-imagen-vs-seedream-on-byteplus-modelark.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"google-imagen\", \"b\": \"seedream-on-byteplus-modelark\"}`. From a terminal: `anchor compare google-imagen seedream-on-byteplus-modelark`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/google-imagen.json and https://www.anchorterminal.com/api/v1/tools/seedream-on-byteplus-modelark.json\n\n## Other comparisons with Google Imagen or Seedream on BytePlus ModelArk\n\n- [Adobe Firefly API vs Google Imagen](https://www.anchorterminal.com/compare/adobe-firefly-vs-google-imagen.md)\n- [Adobe Firefly API vs Seedream on BytePlus ModelArk](https://www.anchorterminal.com/compare/adobe-firefly-vs-seedream-on-byteplus-modelark.md)\n- [Black Forest Labs FLUX API vs Google Imagen](https://www.anchorterminal.com/compare/black-forest-labs-vs-google-imagen.md)\n- [Black Forest Labs FLUX API vs Seedream on BytePlus ModelArk](https://www.anchorterminal.com/compare/black-forest-labs-vs-seedream-on-byteplus-modelark.md)\n- [Bria API vs Google Imagen](https://www.anchorterminal.com/compare/bria-vs-google-imagen.md)\n- [Bria API vs Seedream on BytePlus ModelArk](https://www.anchorterminal.com/compare/bria-vs-seedream-on-byteplus-modelark.md)\n- [fal image models vs Google Imagen](https://www.anchorterminal.com/compare/fal-image-vs-google-imagen.md)\n- [fal image models vs Seedream on BytePlus ModelArk](https://www.anchorterminal.com/compare/fal-image-vs-seedream-on-byteplus-modelark.md)\n- [Google Imagen vs Ideogram API](https://www.anchorterminal.com/compare/google-imagen-vs-ideogram.md)\n- [Google Imagen vs Leonardo.Ai API](https://www.anchorterminal.com/compare/google-imagen-vs-leonardo-ai.md)\n- [Google Imagen vs OpenAI Image API](https://www.anchorterminal.com/compare/google-imagen-vs-openai-image-api.md)\n- [Google Imagen vs Recraft API](https://www.anchorterminal.com/compare/google-imagen-vs-recraft.md)\n- [Google Imagen vs Replicate image models](https://www.anchorterminal.com/compare/google-imagen-vs-replicate-image.md)\n- [Google Imagen vs Stability AI Image API](https://www.anchorterminal.com/compare/google-imagen-vs-stability-ai-image.md)\n- [Ideogram API vs Seedream on BytePlus ModelArk](https://www.anchorterminal.com/compare/ideogram-vs-seedream-on-byteplus-modelark.md)\n- [Leonardo.Ai API vs Seedream on BytePlus ModelArk](https://www.anchorterminal.com/compare/leonardo-ai-vs-seedream-on-byteplus-modelark.md)\n- [OpenAI Image API vs Seedream on BytePlus ModelArk](https://www.anchorterminal.com/compare/openai-image-api-vs-seedream-on-byteplus-modelark.md)\n- [Recraft API vs Seedream on BytePlus ModelArk](https://www.anchorterminal.com/compare/recraft-vs-seedream-on-byteplus-modelark.md)\n- [Replicate image models vs Seedream on BytePlus ModelArk](https://www.anchorterminal.com/compare/replicate-image-vs-seedream-on-byteplus-modelark.md)\n- [Seedream on BytePlus ModelArk vs Stability AI Image API](https://www.anchorterminal.com/compare/seedream-on-byteplus-modelark-vs-stability-ai-image.md)\n", "meta": { "attribution": "Anchor Terminal (https://www.anchorterminal.com)", "docs": "https://www.anchorterminal.com/docs/", "generatedAt": "2026-10-10", "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 Imagen vs Seedream on BytePlus ModelArk", "url": "" } ], "description": "Seedream on BytePlus ModelArk scores 53.8 (D) to Google Imagen's 6.8 (F) for image generation. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "Google Imagen F 6.8", "Seedream on BytePlus ModelArk D 53.8", "scores" ], "h1": "Google Imagen vs Seedream on BytePlus ModelArk", "image": "https://www.anchorterminal.com/assets/og/compare-google-imagen-vs-seedream-on-byteplus-modelark.png", "path": "/compare/google-imagen-vs-seedream-on-byteplus-modelark", "published": "2026-10-01", "section": "tools", "title": "Google Imagen vs Seedream on BytePlus ModelArk for AI agents (2026)", "toc": null, "updated": "2026-10-09", "url": "https://www.anchorterminal.com/compare/google-imagen-vs-seedream-on-byteplus-modelark" }, "tokens": { "markdown": 2500, "slim": 730 }, "version": 1 }