{ "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": "2026-11-07", "license": "CC-BY-4.0", "method": "https://www.anchorterminal.com/benchmark/", "methodology": "0.7", "openapi": "https://www.anchorterminal.com/openapi.json", "preview": false, "run": "2026-10-01", "runLabel": "October 2026 research run", "terms": "https://www.anchorterminal.com/terms/#data" }, "tool": { "slug": "vertex-ai", "name": "Vertex AI (Gemini Enterprise Agent Platform)", "vendor": "Google Cloud", "vendorUrl": "https://cloud.google.com/products/gemini-enterprise-agent-platform", "kind": "model", "category": "inference", "summary": "Google Cloud's enterprise API for Gemini models and Model Garden partner and open models, including Claude, Llama and Qwen, on the platform formerly called Vertex AI, with regional endpoints, provisioned throughput and IAM access.", "url": "https://www.anchorterminal.com/tools/vertex-ai", "markdownUrl": "https://www.anchorterminal.com/tools/vertex-ai.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/vertex-ai.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/vertex-ai.json", "dns": "vertex-ai.grade.anchorterminal.com", "repo": "https://github.com/googleapis/python-genai", "license": "Proprietary service under the Google Cloud Platform terms. Partner models carry their providers' terms. The Google Gen AI SDKs are Apache-2.0", "transports": [ "http" ], "remoteUrl": "https://aiplatform.googleapis.com/v1", "packages": [ { "registry": "pypi", "name": "google-genai" }, { "registry": "npm", "name": "@google/genai" }, { "registry": "pypi", "name": "google-cloud-aiplatform" } ], "auth": "mixed", "authNotes": "OAuth 2.0 bearer tokens from application default credentials or service accounts, with IAM roles on a Google Cloud project, which the docs recommend for production. Google Cloud API keys, including express mode keys (Preview) that need no project or location in the URL, are recommended for testing. The OpenAI-compatible endpoint accepts only Google Cloud auth.", "pricing": "usage", "pricingNotes": "Per-token prices per model, with global and higher non-global rates and Standard, Priority and Flex/Batch options. Gemini 4 Argon costs $4/$20 per million, with 50% credits back through 2026-11-30. Gemini 3.8 Flash costs $0.75/$3.75 through 2026-12-31, then $1.50/$7.50. Claude Opus 5.5 $4/$20. Batch and Flex half price on Gemini. Only requests that return 200 are charged. Express mode gives new users 90 days free with no billing details (https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing).", "priceSummary": "from $0.30 / 1M in", "where": "hosted", "x402": { "level": "no", "evidence": "No x402, MPP or L402 on the pricing page or in the express mode docs (checked 2026-11-06). Access needs a Google account and, after the express trial, a Cloud billing account.", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": null, "npmWeekly": null, "pypiWeekly": 20917051, "asOf": "2026-11-06" }, "docsUrl": "https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/start", "rateLimitsUrl": "https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/standard-paygo", "openapi": "https://aiplatform.googleapis.com/$discovery/rest?version=v1", "capabilities": [ "inference.llm", "inference.open-weights" ], "tags": [ "official", "hosted", "model", "open-weights", "enterprise", "usage-priced", "free-tier", "no-card", "python", "typescript", "status-page" ], "lastRelease": "2026-11-05", "graded": true, "anchor": { "graded": true, "score": 88.7, "grade": "AA", "agentReady": true, "rank": 2, "ranked": true, "rankOf": 1486, "categoryRank": 1, "methodology": "0.7", "run": "2026-10-01", "scores": { "ergonomics": 97, "maintenance": 91, "payments": 40, "reliability": 99, "schema": 94, "security": 97, "transparency": 90 }, "pending": [ "performance", "tasks" ], "breakdown": [ { "key": "reliability", "name": "Reliability", "weight": 16, "effectiveWeight": 20, "score": 99, "points": 19.8, "reason": "Google Cloud status dashboard with per-product history (20). Its incident feed, read on 6 November, has no incident naming Vertex Gemini API, Gemini or the Agent Platform in the 90 days. The regional incidents of 20 August, 1 September and 20 October (europe-west2) and the Cloud Storage incident of 8 and 9 October didn't list it among affected products (30). Standard PayGo publishes usage tiers by 30-day spend with baseline throughput, 2,000,000 to 50,000,000 tokens a minute for Flash models and 500,000 to 10,000,000 for Pro, plus quota tables for other methods (15). A 429 page says to use the global endpoint and truncated exponential backoff, and a retry-strategy page (15). SLA of 99.5 per cent a month on generateContent and streamGenerateContent, 95 per cent for short-term availability models, and a latency SLO on Provisioned Throughput. The 429 page says pay-as-you-go 429s don't count toward the SLA error rate (10). Gemini 4 Argon reached GA on 13 October and Gemini 3.8 Flash moved to the 12-month tier, and the v1 API, 3.5 Flash-Lite and Claude Opus 5.5 are GA, but express mode was Preview at the 6 October check (9 of 10, up from 8). Up from 98 on 6 October.", "checked": "2026-11-06" }, { "key": "performance", "name": "Performance", "weight": 10, "effectiveWeight": 0, "pending": true, "points": 0, "reason": "Pending. Latency is measured per call by our probes, which haven't run yet, so this run doesn't score it. Its weight is shared across the assessed categories until the first probe window closes." }, { "key": "schema", "name": "Schema \u0026 documentation", "weight": 13, "effectiveWeight": 16.25, "score": 94, "points": 15.28, "reason": "Model reading. Keyless discovery document for the Agent Platform API v1, revision 20260930, with 1,128 methods and 1,493 schemas (25). No llms.txt, but every docs page answers as Markdown at `.md.txt`, counted as for vertex-ai-tuning (10). Model cards give limits, capabilities and retirement dates, and the 3.8 Flash card says when to use 3.7 Flash instead, but the docs mix the Vertex AI and Agent Platform names, and the OpenAI page tells new users to call the Gemini Developer API instead (16 of 20). Structured output with `response_schema` and `response_mime_type: application/json` always follows the schema per the docs, and complex schemas fail with a 400 (15). Examples on every page and a 429 guide, but we found no full error code list for generateContent (13 of 15). Versioned v1 and v1beta1 APIs and release notes with entries on most working days, newest 5 November 2026 (15).", "checked": "2026-11-06" }, { "key": "ergonomics", "name": "Agent ergonomics", "weight": 13, "effectiveWeight": 16.25, "score": 97, "points": 15.76, "reason": "Model reading of the checklist (tool use, structured output, caching, context, batch, SDKs, errors). Function calling with `FunctionCallingConfig` mode ANY and `allowedFunctionNames` to force a named tool (20). Schema-guaranteed JSON output (15). Implicit and explicit context caching, cached input at 0.1x, $0.075 per million on 3.8 Flash through 31 December (15). 1,048,576-token context on 3.8 Flash, a unified 1,048,576-token input and output limit on Gemini 4 Argon, and 1,000,000 on Claude Opus 5.5 (15). Flex/Batch at half price on Gemini (10). Gen AI SDKs for Python and JavaScript among others, and the OpenAI libraries work with Google Cloud auth (10). 429 handling documented per quota framework, with standard Google status codes elsewhere (12 of 15).", "checked": "2026-11-06" }, { "key": "security", "name": "Security \u0026 auth", "weight": 14, "effectiveWeight": 17.5, "score": 97, "points": 16.98, "reason": "Model reading. OAuth 2.0 with IAM roles and service accounts, which the docs recommend for production, with API keys for testing. No key in a query string found in the docs we read (30). The training restriction in the Service Specific Terms says Google won't use customer data to train or fine-tune any model without permission, GA and pre-GA alike (20). Default in-memory caching for 24 hours that can be disabled, flagged prompts logged up to 90 days unless an abuse-monitoring exception is granted or the customer has a Cloud Master Agreement, the Interactions API storing by default, and Claude Fable 5 and Mythos 5 requiring 30-day retention shared with Anthropic (12 of 15, a judgement call matching the Fable exception on the Anthropic and Bedrock listings). Cloud Audit Logs, with Data Access logs off until enabled, and optional request-response logging to BigQuery (15). google.com security.txt valid to 2030-04-01, the Google VRP, and Generative AI on the platform in ISO 27001, 27017 and 27018 and SOC 1, 2 and 3 scope per the 1 October services-in-scope check for vertex-ai-tuning, not re-read on 6 October (20).", "checked": "2026-11-06" }, { "key": "payments", "name": "Payments \u0026 pricing", "weight": 10, "effectiveWeight": 12.5, "score": 40, "points": 5, "reason": "No x402, MPP or L402 (0). Per-token prices per model and option published without a login (20). Express mode gives new Google Cloud users 90 days free within quotas with no billing details, though it's in Preview and needs a @gmail.com account (20). A person signs up in the console to get the express key (0).", "checked": "2026-11-06" }, { "key": "tasks", "name": "Task success", "weight": 10, "effectiveWeight": 0, "pending": true, "points": 0, "reason": "Pending. Task success needs the category task suites run through each tool, which haven't run yet, so this run doesn't score it. Its weight is shared across the assessed categories until then. A data provider's data-quality score is published on its listing now and becomes half of this category when it's scored." }, { "key": "maintenance", "name": "Maintenance \u0026 community", "weight": 7, "effectiveWeight": 8.75, "score": 91, "points": 7.96, "reason": "Model reading. Gemini Omni 1.2 Flash GA on 5 November, Grok 4.7 GA on 27 October, Gemini 4 Argon GA on 13 October and Claude Haiku 5.5 on 7 October 2026 (30). Stable models stay at least 12 months, and since 6 October Gemini 4 Argon and Gemini 3.8 Flash are in that tier, while 3.7 and 3.6 Flash remain short-term with at least 45 days' notice once a date is set (10 of 12, up from 8). Gemini 2.5 Pro, Flash and Flash-Lite were due to retire on 20 October, three models on one date after more than 12 months, with replacements named. We didn't check partner model retirements (6 of 8, down from 8). Dated release notes on most working days, newest 5 November, and Cloud Customer Care (15). python-genai replies not sampled this run (5 of 10). Current SDKs, google-genai 3.0.0 on 6 November and `@google/genai` 3.0.0, and google-cloud-aiplatform 2.7.0 on 28 October 2026 (15). Supported runtimes stated, Python 3.10 or later and Node 20 or later, per the 6 October check (10). Unchanged at 91.", "checked": "2026-11-06" }, { "key": "transparency", "name": "Transparency \u0026 trust", "weight": 7, "effectiveWeight": 8.75, "score": 90, "points": 7.88, "note": "editorial 83, provenance 97", "reason": "Closed service under the Google Cloud terms, with the Gen AI SDKs under Apache-2.0 and a public discovery document (18, as for Bedrock's open service models). The zero data retention and abuse monitoring pages agree with the Cloud terms and give periods for each case, 24 hours in memory, up to 90 days for flagged prompts, 30 days for Advanced AI models, 3 days for Search grounding logs and 30 days for Maps grounding, and say which can't be switched off (27 of 30). A dated model versions table with release and retirement dates and a stated 12-month or 45-day policy, but on 6 November it still listed Gemini 2.5 Pro, Flash and Flash-Lite as available with a 20 October 2026 retirement date and left them out of the retired table (18 of 20, down from 20). The Cloud subprocessor list with locations, per the 1 October vertex-ai-tuning check, regional and multi-region endpoints, and per-model ML processing locations on the partner model cards (20).", "checked": "2026-11-06" } ], "assessment": { "date": "2026-11-06", "basis": "public evidence", "confidence": "medium", "notes": { "ergonomics": "Model reading of the checklist (tool use, structured output, caching, context, batch, SDKs, errors). Function calling with `FunctionCallingConfig` mode ANY and `allowedFunctionNames` to force a named tool (20). Schema-guaranteed JSON output (15). Implicit and explicit context caching, cached input at 0.1x, $0.075 per million on 3.8 Flash through 31 December (15). 1,048,576-token context on 3.8 Flash, a unified 1,048,576-token input and output limit on Gemini 4 Argon, and 1,000,000 on Claude Opus 5.5 (15). Flex/Batch at half price on Gemini (10). Gen AI SDKs for Python and JavaScript among others, and the OpenAI libraries work with Google Cloud auth (10). 429 handling documented per quota framework, with standard Google status codes elsewhere (12 of 15).", "maintenance": "Model reading. Gemini Omni 1.2 Flash GA on 5 November, Grok 4.7 GA on 27 October, Gemini 4 Argon GA on 13 October and Claude Haiku 5.5 on 7 October 2026 (30). Stable models stay at least 12 months, and since 6 October Gemini 4 Argon and Gemini 3.8 Flash are in that tier, while 3.7 and 3.6 Flash remain short-term with at least 45 days' notice once a date is set (10 of 12, up from 8). Gemini 2.5 Pro, Flash and Flash-Lite were due to retire on 20 October, three models on one date after more than 12 months, with replacements named. We didn't check partner model retirements (6 of 8, down from 8). Dated release notes on most working days, newest 5 November, and Cloud Customer Care (15). python-genai replies not sampled this run (5 of 10). Current SDKs, google-genai 3.0.0 on 6 November and `@google/genai` 3.0.0, and google-cloud-aiplatform 2.7.0 on 28 October 2026 (15). Supported runtimes stated, Python 3.10 or later and Node 20 or later, per the 6 October check (10). Unchanged at 91.", "payments": "No x402, MPP or L402 (0). Per-token prices per model and option published without a login (20). Express mode gives new Google Cloud users 90 days free within quotas with no billing details, though it's in Preview and needs a @gmail.com account (20). A person signs up in the console to get the express key (0).", "reliability": "Google Cloud status dashboard with per-product history (20). Its incident feed, read on 6 November, has no incident naming Vertex Gemini API, Gemini or the Agent Platform in the 90 days. The regional incidents of 20 August, 1 September and 20 October (europe-west2) and the Cloud Storage incident of 8 and 9 October didn't list it among affected products (30). Standard PayGo publishes usage tiers by 30-day spend with baseline throughput, 2,000,000 to 50,000,000 tokens a minute for Flash models and 500,000 to 10,000,000 for Pro, plus quota tables for other methods (15). A 429 page says to use the global endpoint and truncated exponential backoff, and a retry-strategy page (15). SLA of 99.5 per cent a month on generateContent and streamGenerateContent, 95 per cent for short-term availability models, and a latency SLO on Provisioned Throughput. The 429 page says pay-as-you-go 429s don't count toward the SLA error rate (10). Gemini 4 Argon reached GA on 13 October and Gemini 3.8 Flash moved to the 12-month tier, and the v1 API, 3.5 Flash-Lite and Claude Opus 5.5 are GA, but express mode was Preview at the 6 October check (9 of 10, up from 8). Up from 98 on 6 October.", "schema": "Model reading. Keyless discovery document for the Agent Platform API v1, revision 20260930, with 1,128 methods and 1,493 schemas (25). No llms.txt, but every docs page answers as Markdown at `.md.txt`, counted as for vertex-ai-tuning (10). Model cards give limits, capabilities and retirement dates, and the 3.8 Flash card says when to use 3.7 Flash instead, but the docs mix the Vertex AI and Agent Platform names, and the OpenAI page tells new users to call the Gemini Developer API instead (16 of 20). Structured output with `response_schema` and `response_mime_type: application/json` always follows the schema per the docs, and complex schemas fail with a 400 (15). Examples on every page and a 429 guide, but we found no full error code list for generateContent (13 of 15). Versioned v1 and v1beta1 APIs and release notes with entries on most working days, newest 5 November 2026 (15).", "security": "Model reading. OAuth 2.0 with IAM roles and service accounts, which the docs recommend for production, with API keys for testing. No key in a query string found in the docs we read (30). The training restriction in the Service Specific Terms says Google won't use customer data to train or fine-tune any model without permission, GA and pre-GA alike (20). Default in-memory caching for 24 hours that can be disabled, flagged prompts logged up to 90 days unless an abuse-monitoring exception is granted or the customer has a Cloud Master Agreement, the Interactions API storing by default, and Claude Fable 5 and Mythos 5 requiring 30-day retention shared with Anthropic (12 of 15, a judgement call matching the Fable exception on the Anthropic and Bedrock listings). Cloud Audit Logs, with Data Access logs off until enabled, and optional request-response logging to BigQuery (15). google.com security.txt valid to 2030-04-01, the Google VRP, and Generative AI on the platform in ISO 27001, 27017 and 27018 and SOC 1, 2 and 3 scope per the 1 October services-in-scope check for vertex-ai-tuning, not re-read on 6 October (20).", "transparency": "Closed service under the Google Cloud terms, with the Gen AI SDKs under Apache-2.0 and a public discovery document (18, as for Bedrock's open service models). The zero data retention and abuse monitoring pages agree with the Cloud terms and give periods for each case, 24 hours in memory, up to 90 days for flagged prompts, 30 days for Advanced AI models, 3 days for Search grounding logs and 30 days for Maps grounding, and say which can't be switched off (27 of 30). A dated model versions table with release and retirement dates and a stated 12-month or 45-day policy, but on 6 November it still listed Gemini 2.5 Pro, Flash and Flash-Lite as available with a 20 October 2026 retirement date and left them out of the retired table (18 of 20, down from 20). The Cloud subprocessor list with locations, per the 1 October vertex-ai-tuning check, regional and multi-region endpoints, and per-model ML processing locations on the partner model cards (20)." }, "sources": [ { "what": "status incident feed", "url": "https://status.cloud.google.com/incidents.json", "seen": "2026-11-06" }, { "what": "generative AI SLA", "url": "https://cloud.google.com/vertex-ai/generative-ai/sla", "seen": "2026-10-06" }, { "what": "platform SLA", "url": "https://cloud.google.com/vertex-ai/sla", "seen": "2026-10-06" }, { "what": "SLA index", "url": "https://cloud.google.com/terms/sla", "seen": "2026-10-06" }, { "what": "pricing", "url": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "seen": "2026-11-06" }, { "what": "quotas", "url": "https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/quotas", "seen": "2026-10-06" }, { "what": "Standard PayGo tiers", "url": "https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/standard-paygo", "seen": "2026-10-06" }, { "what": "429 errors", "url": "https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/deploy/error-code-429", "seen": "2026-10-06" }, { "what": "model versions and retirement", "url": "https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/model-versions", "seen": "2026-11-06" }, { "what": "zero data retention", "url": "https://docs.cloud.google.com/gemini-enterprise-agent-platform/resources/zero-data-retention", "seen": "2026-10-06" }, { "what": "abuse monitoring", "url": "https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/abuse-monitoring", "seen": "2026-10-06" }, { "what": "express mode", "url": "https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/start/express-mode/overview", "seen": "2026-10-06" }, { "what": "API keys", "url": "https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/start/api-keys", "seen": "2026-10-06" }, { "what": "quickstart", "url": "https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/start", "seen": "2026-10-06" }, { "what": "OpenAI compatibility", "url": "https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/start/openai", "seen": "2026-10-06" }, { "what": "structured output", "url": "https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/capabilities/control-generated-output", "seen": "2026-10-06" }, { "what": "Gemini 3.8 Flash card", "url": "https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/gemini/3-8-flash", "seen": "2026-11-06" }, { "what": "Claude Opus 5.5 card", "url": "https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/partner-models/claude/opus-5-5", "seen": "2026-10-06" }, { "what": "release notes", "url": "https://docs.cloud.google.com/gemini-enterprise-agent-platform/release-notes", "seen": "2026-11-06" }, { "what": "discovery document", "url": "https://aiplatform.googleapis.com/$discovery/rest?version=v1", "seen": "2026-10-06" }, { "what": "google-genai on PyPI", "url": "https://pypi.org/pypi/google-genai/json", "seen": "2026-11-06" }, { "what": "google-cloud-aiplatform downloads", "url": "https://pypistats.org/api/packages/google-cloud-aiplatform/recent", "seen": "2026-11-06" }, { "what": "security.txt", "url": "https://www.google.com/.well-known/security.txt", "seen": "2026-11-06" }, { "what": "Gemini 4 Argon card", "url": "https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/gemini/4-argon", "seen": "2026-11-06" }, { "what": "google-cloud-aiplatform on PyPI", "url": "https://pypi.org/pypi/google-cloud-aiplatform/json", "seen": "2026-11-06" } ], "openQuestions": [ "Changed since 6 October 2026 (rechecked 6 November). Gemini 4 Argon GA on 13 October and Gemini 3.8 Flash moved from short-term to the 12-month tier (reliability 98 to 99; maintenance notice up, churn down, still 91); Gemini 2.5 Pro, Flash and Flash-Lite due to retire on 20 October but still shown as available (transparency 85 to 83); Claude Haiku 5.5, Grok 4.7 GA and google-genai 3.0.0 added; no Vertex incident on the status feed", "unchecked: partner model retirements (Claude, Llama, Mistral and others) in the last 90 days, which sit outside the Gemini model versions table", "unchecked: services-in-scope and subprocessor list were not re-read on 6 October and rely on the 1 October vertex-ai-tuning check", "The Claude Opus 5.5 batch prices on the pricing page ($2.50/$12.50) are more than half the $4/$20 list price, unlike other models; we couldn't tell whether this is a page error", "Whether Gemini 2.5 Pro, Flash and Flash-Lite were retired on 20 October 2026 or extended, since the model versions table read on 6 November still lists them as available with that date", "unchecked on 6 November: express mode's Preview status, the SLA pages and the zero data retention and abuse monitoring pages, which rest on the 6 October reading" ] }, "negative": 0, "verdict": "Gemini, Claude and open models through one Google Cloud API with IAM, regional endpoints, schema-guaranteed JSON and a 99.5 per cent SLA, and no Vertex incident on the Cloud status page in the 90 days to 6 November 2026. Gemini 4 Argon and 3.8 Flash have 12-month availability, but short-term Flash models get a 95 per cent SLA.", "bestFor": "Google Cloud customers who need Gemini with residency, VPC-SC, provisioned throughput and an SLA, or Claude under a Google bill.", "strengths": [ "No incident naming Vertex or Gemini on status.cloud.google.com between 8 July and 6 October 2026", "Public discovery document for the v1 API (revision 20260930) with 1,128 methods and 1,493 schemas", "JSON output follows a supplied `response_schema` when `response_mime_type` is `application/json`", "Express mode gives new users 90 days free with an API key and no billing details", "Only requests that return 200 are charged", "Gemini 4 Argon, GA since 13 October 2026, has a 1,048,576-token unified limit at $4/$20 per million tokens" ], "weaknesses": [ "The SLA drops from 99.5 to 95 per cent for short-term availability models, Gemini 3.7 and 3.6 Flash among them", "Gemini 3.6 Flash, released 21 July 2026, retires on 19 November 2026, and 3.7 Flash on 28 January 2027", "Zero retention needs an exception request, and flagged prompts may be kept up to 90 days", "The Interactions API stores prompts and responses unless `store` is set to false", "No llms.txt on the docs site, and the docs mix the Vertex AI and Agent Platform names", "The model versions table still listed Gemini 2.5 Pro, Flash and Flash-Lite as available after their 20 October 2026 retirement date" ], "agentNotes": [ "Call the `global` location on aiplatform.googleapis.com unless data residency requires a Region. The 429 guide says it spreads load and reduces errors", "Back off exponentially on 429 `Resource exhausted`. On Standard PayGo it means shared capacity is busy, not a fixed quota", "Send `response_schema` with `response_mime_type: application/json`. JSON mode alone doesn't guarantee valid output", "Set `store` to false on Interactions API calls. It defaults to true and keeps prompts and responses", "Pin `gemini-4-argon` or `gemini-3.8-flash`, both in the 12-month tier, rather than 3.7 or 3.6 Flash, which retire on 28 January 2027 and 19 November 2026" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "AA", "methodology": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 88.7 } ], "editorialScores": { "ergonomics": 97, "maintenance": 91, "payments": 40, "reliability": 99, "schema": 94, "security": 97, "transparency": 83 }, "provenanceScore": 97, "checked": { "categories": { "ergonomics": "2026-11-06", "maintenance": "2026-11-06", "payments": "2026-11-06", "reliability": "2026-11-06", "schema": "2026-11-06", "security": "2026-11-06", "transparency": "2026-11-06" }, "last": "2026-11-06", "oldest": "2026-11-06", "stale": false, "staleAfterDays": 90 }, "scoreHistory": [ { "date": "2026-11-06", "grade": "AA", "kind": "listed", "method": "0.7", "score": 88.7 } ] }, "connect": { "install": "pip install google-genai # or: npm i @google/genai", "http": "curl -X POST \\\n -H \"Content-Type: application/json\" \\\n -H \"Authorization: Bearer $(gcloud auth print-access-token)\" \\\n \"https://aiplatform.googleapis.com/v1/projects/${GOOGLE_CLOUD_PROJECT}/locations/global/publishers/google/models/gemini-3.8-flash:generateContent\" \\\n -d '{\"contents\":{\"role\":\"user\",\"parts\":{\"text\":\"Explain how AI works in a few words\"}}}'" }, "letme": { "capability": "https://letme.dev/inference.llm", "tool": "https://letme.dev/vertex-ai" }, "sameCompany": [ "gemini-api", "gemini-embedding", "vertex-ai-tuning", "cloud-run-gpus", "google-model-armor", "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", "google-maps-platform", "google-cloud-translation", "google-calendar-api", "firebase-cloud-messaging", "google-cloud-storage", "google-drive-api", "gemini-enterprise", "gemini-cli", "google-search-console", "google-ads-api", "google-forms", "google-sheets-api", "gmail-api", "google-people-api" ], "notable": [ "Google Cloud renamed Vertex AI to Gemini Enterprise Agent Platform, and the docs, pricing and SLA now use that name while the API host stays aiplatform.googleapis.com (https://cloud.google.com/vertex-ai/generative-ai/sla)", "SLA of 99.5 per cent a month on generateContent and streamGenerateContent, falling to 95 per cent for short-term availability models, Gemini 3.7 and 3.6 Flash among them on 6 November 2026 (https://cloud.google.com/vertex-ai/generative-ai/sla)", "Gemini 4 Argon (GA on 13 October 2026) and Gemini 3.8 Flash sit in the 12-month tier on 6 November 2026, while Gemini 3.7 and 3.6 Flash are short-term models with at least 45 days' notice (https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/model-versions)", "Model Garden partner models include Claude Opus 5.5, Sonnet 5.5, Haiku 5.5 (added 7 October 2026) and Fable 5.1, xAI Grok 4.7 (GA on 27 October 2026) and DeepSeek-V4.1-Flash in Public Preview (https://docs.cloud.google.com/gemini-enterprise-agent-platform/release-notes)", "Google won't train on customer data without permission, flagged prompts may be logged up to 90 days for abuse monitoring, and zero retention needs an exception request (https://docs.cloud.google.com/gemini-enterprise-agent-platform/resources/zero-data-retention)", "Claude Fable 5 and Mythos 5 retain prompts and responses up to 30 days and require sharing that data with Anthropic for abuse monitoring (https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/abuse-monitoring)", "Gemini 4 Argon has a unified 1,048,576-token limit for input and output, implicit caching only, and ignores custom temperature, top_p and top_k (https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/gemini/4-argon)" ], "area": "models", "details": [ { "label": "Surface listed", "value": "Generative inference on aiplatform.googleapis.com (generateContent, the Interactions API, the OpenAI-compatible path and Model Garden partner models). Tuning is the vertex-ai-tuning listing, the Gemini Developer API is gemini-api and Gemini Enterprise is gemini-enterprise. Read from Google Cloud docs, pricing, release notes and status feed on 6 November 2026; no project was made" }, { "label": "Free tier", "value": "Express mode (Preview), 90 days for new Google Cloud users within quotas, no billing details, @gmail.com accounts" }, { "label": "Trains on API data", "value": "No, without prior permission, per the training restriction in the Service Specific Terms" }, { "label": "Data retention", "value": "In-memory cache 24 hours (can be disabled). Flagged prompts up to 90 days. Advanced AI models, Claude Fable 5 and Mythos 5 included, 30 days" }, { "label": "Zero data retention", "value": "By exception request for abuse monitoring, plus turning off caching, logging and Interactions storage. Not possible with Search or Maps grounding" }, { "label": "Rate limits", "value": "Standard PayGo tiers by 30-day spend, for example 2,000,000 to 50,000,000 TPM for Flash models and 500,000 to 10,000,000 for Pro, plus Provisioned Throughput" }, { "label": "Batch", "value": "50% off on Gemini through Flex/Batch. Claude batch prices listed per model" }, { "label": "SLA", "value": "99.5% monthly uptime, 95% for short-term availability models (Gemini 3.7 and 3.6 Flash on 6 November 2026), latency SLO on Provisioned Throughput" }, { "label": "Endpoints", "value": "Global `aiplatform.googleapis.com` and regional `{location}-aiplatform.googleapis.com`, plus an OpenAI-compatible `endpoints/openapi` path" }, { "label": "Status", "value": "status.cloud.google.com, product 'Vertex Gemini API'" } ], "models": [ { "id": "gemini-3.1-pro-preview", "name": "Gemini 3.1 Pro (preview)", "inputPer1M": 2, "outputPer1M": 12, "contextTokens": 1048576, "maxOutput": 65536, "role": "flagship", "note": "$4/$18 over 200K tokens", "taskCosts": { "bugfix": 1.09, "research": 22.03, "website": 5.09 } }, { "id": "gemini-3.8-flash", "name": "Gemini 3.8 Flash", "inputPer1M": 0.75, "outputPer1M": 3.75, "contextTokens": 1048576, "maxOutput": 65536, "released": "2026-09", "role": "default", "note": "global price; $1.50/$7.50 from 2027-01-01; short-term availability", "taskCosts": { "bugfix": 0.41, "research": 8.23, "website": 1.88 } }, { "id": "gemini-3.5-flash-lite", "name": "Gemini 3.5 Flash-Lite", "inputPer1M": 0.3, "outputPer1M": 2.5, "contextTokens": 1048576, "maxOutput": 65536, "released": "2026-07", "role": "fast", "note": "available until 2027-07-21 or later", "taskCosts": { "bugfix": 0.16, "research": 3.34, "website": 0.79 } }, { "id": "claude-opus-5-5", "name": "Claude Opus 5.5", "inputPer1M": 4, "outputPer1M": 20, "contextTokens": 1000000, "maxOutput": 128000, "released": "2026-09", "role": "flagship", "note": "partner model, global price", "taskCosts": { "bugfix": 2.16, "research": 43.88, "website": 10.03 } } ], "unitPrices": [ { "item": "Grounding with Google Search over 5,000 a month (Gemini 3)", "unit": "1k-requests", "usd": 14 } ], "deprecations": [ { "what": "`gemini-2.5-pro`, `gemini-2.5-flash` and `gemini-2.5-flash-lite` retire", "date": "2026-10-20", "source": "https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/model-versions", "kind": "shutdown" }, { "what": "`gemini-3.6-flash` retires", "date": "2026-11-19", "source": "https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/model-versions", "kind": "shutdown" }, { "what": "`gemini-live-2.5-flash-native-audio` retires", "date": "2026-12-13", "source": "https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/model-versions", "kind": "shutdown" }, { "what": "Gemini 3.6, 3.7 and 3.8 Flash prices double to $1.50/$7.50", "date": "2027-01-01", "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "kind": "price" }, { "what": "`gemini-3.7-flash` retires", "date": "2027-01-28", "source": "https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/model-versions", "kind": "shutdown" } ], "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://cloud.google.com/terms", "privacy": "https://policies.google.com/privacy", "statusPage": "https://status.cloud.google.com", "changelog": "https://docs.cloud.google.com/gemini-enterprise-agent-platform/release-notes", "securityTxt": "valid", "checked": "2026-11-06", "notes": [ "The product runs under the Google Cloud Platform terms, whose contracting Google entity depends on the billing country, as for vertex-ai-tuning.", "www.google.com/.well-known/security.txt expires on 2030-04-01 (read 2026-11-06).", "docs.cloud.google.com has no llms.txt (404 on 6 October 2026), but each docs page answers as Markdown when `.md.txt` is added to its URL." ], "score": 97, "checks": [ { "check": "Legal entity named", "value": "Google LLC", "points": 20, "max": 20, "state": "ok" }, { "check": "Domain age", "value": "google.com, registered 1997-09-15 (29 years)", "points": 15, "max": 15, "state": "ok" }, { "check": "Endpoint on the vendor's domain", "value": "aiplatform.googleapis.com", "points": 15, "max": 15, "state": "ok" }, { "check": "Terms of service", "value": "read, states 7 of the 7 things a reader expects", "points": 10, "max": 10, "state": "ok" }, { "check": "Privacy policy", "value": "read, states 7 of the 8 things a reader expects, and has 1 clause that costs points", "points": 7.3, "max": 10, "state": "part" }, { "check": "Status page", "value": "status.cloud.google.com", "points": 10, "max": 10, "state": "ok" }, { "check": "Changelog", "value": "published", "points": 10, "max": 10, "state": "ok" }, { "check": "security.txt", "value": "valid", "points": 10, "max": 10, "state": "ok" }, { "check": "People named", "value": "5 named with their role, none with a public profile", "points": 7, "max": 10, "state": "part" }, { "check": "Support route", "value": "help pages", "points": 5, "max": 5, "state": "ok" } ], "policies": [ { "kind": "terms", "url": "https://cloud.google.com/terms", "state": "read", "readAt": "2026-10-08", "statedDate": "2026-09-02", "words": 13806, "points": 10, "max": 10, "expected": [ { "key": "terms.date", "label": "Gives the date it was last updated", "found": true, "quote": "(Last modified September 2, 2026)", "says": "Last updated 2026-09-02" }, { "key": "terms.law", "label": "Names the governing law or courts", "found": true, "quote": "federal government entity, then the following applies: ALL CLAIMS ARISING OUT OF OR RELATING TO THIS AGREEMENT OR THE SERVICES WILL BE GOVERNED BY THE LAWS OF THE UNITED STATES OF AMERICA, EXCLUDING ITS CONFLICT OF LAWS RULES.", "says": "The law of the United States of America" }, { "key": "terms.liability", "label": "States a limit on its liability", "found": true, "quote": "…GWS Services, SecOps Services, Looker (original) Services, or Cloud Identity Services, as applicable, is limited to the Fees Customer paid for such Services during the 12 month period before the event giving rise to Liability, except Google’s total aggregate Liability for damages arising out of or related to Services…", "says": "Capped at the fees paid in the 12 months before the claim or $5,000" }, { "key": "terms.termination", "label": "Says how the agreement or account can be ended", "found": true, "quote": "Customer may also terminate this Agreement for convenience under Section 8.5 (Termination for Convenience)." }, { "key": "terms.changes", "label": "Says how changes to the terms are announced", "found": true, "quote": "(i) With respect to GCP Services and their corresponding TSS, unless otherwise noted by Google, material updates to this Agreement will become effective 30 days after they are posted.", "says": "Gives 30 days of notice before a change" }, { "key": "terms.use", "label": "Lists what users may not do", "found": true, "quote": "For clarity, Customer may not integrate the Google Workspace Services, SecOps Services, or Cloud Identity Services into Customer Applications or create or host Customer Applications using the Google Workspace Services, SecOps Services, or Cloud Identity Services under this Agreement, and Customer may only integrate Lo…" }, { "key": "terms.sla", "label": "Refers to a service level or uptime commitment", "found": true, "quote": "Cloud-native relational database with unlimited scale and 99.999% availability.", "says": "Names 99.999% availability" } ], "toKnow": [ { "key": "terms.cutoff", "label": "Says access can be ended without notice or for any reason", "found": true, "quote": "For purposes of GCP Services and TSS only, Google may terminate this Agreement or any applicable Order Form for its convenience at any time with 30 days' prior written notice to Customer." } ], "notes": [ { "date": "2026-10-08", "text": "Google may change its fees at any time unless an addendum or order form expressly says otherwise.", "quote": "Google may change the Fees at any time unless otherwise expressly agreed in an addendum or Order Form." }, { "date": "2026-10-08", "text": "Google's total liability for services or software supplied free of charge is limited to 5,000 US dollars.", "quote": "except Google’s total aggregate Liability for damages arising out of or related to Services or Software provided free of charge is limited to $5,000." }, { "date": "2026-10-08", "text": "When automated safety tools detect potential abuse of Generative AI Services, Google may log customer prompts to review whether a violation occurred.", "quote": "Google may log Customer prompts solely for the purpose of reviewing and determining whether a violation has occurred." } ] }, { "kind": "privacy", "url": "https://policies.google.com/privacy", "state": "read", "readAt": "2026-10-08", "statedDate": "2026-10-01", "words": 14332, "points": 7.3, "max": 10, "expected": [ { "key": "privacy.date", "label": "Gives the date it was last updated", "found": true, "quote": "Effective October 1, 2026 | Archived versions | Download PDF", "says": "Last updated 2026-10-01" }, { "key": "privacy.collected", "label": "Says what personal data is collected", "found": true, "quote": "This Privacy Policy is meant to help you understand what information we collect, why we collect it, and how you can update, manage, export, and delete your information." }, { "key": "privacy.retention", "label": "Says how long data is kept", "found": true, "quote": "The types of location data we collect and how long we store it depend in part on your device and account settings." }, { "key": "privacy.processors", "label": "Says who else receives the data", "found": true, "quote": "For example, we use service providers to help operate our data centers, deliver our products and services, improve our internal business processes, and offer additional support to customers and users." }, { "key": "privacy.sale", "label": "Says whether personal data is sold or shared for advertising", "found": true, "quote": "If Google is involved in a merger, acquisition, or sale of assets, we’ll continue to ensure the confidentiality of your personal information and give affected users notice before personal information is transferred or becomes subject to a different privacy policy." }, { "key": "privacy.rights", "label": "Says what rights people have over their data", "found": true, "quote": "If European Union or United Kingdom data protection law applies to the processing of your information, you can review the European requirements section below to learn more about your rights and Google’s compliance with these laws." }, { "key": "privacy.contact", "label": "Gives a privacy contact", "found": true, "quote": "And if you have any questions about this Privacy Policy, you can contact us." }, { "key": "privacy.transfers", "label": "Says where data is transferred or stored", "found": false } ], "toKnow": [ { "key": "training", "label": "Says it may use customer content to train or improve models, and no opt-out was found", "found": true, "quote": "We use your interactions with AI models and technologies like Gemini Apps to develop, train, fine-tune, and improve these models to better handle your requests, and update their classifiers and filters including for safety, language understanding, and factuality.", "costsPoints": true } ], "notes": [ { "date": "2026-10-08", "text": "Members of organisations using Google Workspace or Google Cloud Platform are referred to the separate Google Cloud Privacy Notice for how those services collect and use personal information.", "quote": "If you’re a member of an organization that uses Google Workspace or Google Cloud Platform, learn how these services collect and use your personal information in the Google Cloud Privacy Notice." }, { "date": "2026-10-08", "text": "Google says it uses publicly available information from the web and other public sources to help train machine learning models behind products such as Google Translate, Gemini Apps and Cloud AI.", "quote": "We use publicly available information online or from other public sources to help train new machine learning models and build foundational technologies that power various Google products such as Google Translate, Gemini Apps, and Cloud AI capabilities." } ] } ] }, "humans": { "slug": "vertex-ai", "checked": "2026-11-06", "company": "Google Cloud", "people": [ { "name": "Larry Page", "role": "Co-founder, Google, left executive roles in December 2019 and sits on Alphabet's board", "founder": true, "bio": "Larry Page co-founded Google with Sergey Brin, whom he met at Stanford University in 1995, and co-created the PageRank search ranking algorithm. He was Google's chief executive from 1997 to 2001 and from 2011 to 2015, then led its parent Alphabet until December 2019. He remains on Alphabet's board.", "bioSources": [ "https://about.google/intl/ALL_en/our-story/", "https://en.wikipedia.org/wiki/Larry_Page" ], "page": "/people/larry-page/" }, { "name": "Sergey Brin", "role": "Co-founder, Google, left executive roles in 2019 and sits on Alphabet's board", "founder": true, "bio": "Sergey Brin co-founded Google with Larry Page, whom he met at Stanford University in 1995, and together they built the search engine that became Google. He was president of Alphabet, Google's parent company, until stepping down in 2019, and remains an Alphabet co-founder and board member.", "bioSources": [ "https://about.google/intl/ALL_en/our-story/", "https://en.wikipedia.org/wiki/Sergey_Brin" ], "page": "/people/sergey-brin/" }, { "name": "Sundar Pichai", "role": "CEO, Google and Alphabet", "bio": "Sundar Pichai has been chief executive of Google since 2015 and of its parent Alphabet since 2019. He joined Google in 2004 and led product management for its client software, including Chrome and ChromeOS, then took on Drive, Gmail, Maps and Android before being named product chief.", "bioSources": [ "https://en.wikipedia.org/wiki/Sundar_Pichai", "https://about.google/company-info/" ], "page": "/people/sundar-pichai/" }, { "name": "Thomas Kurian", "role": "CEO, Google Cloud", "bio": "Thomas Kurian has led Google Cloud as chief executive since 2019, after joining Google's cloud organisation in November 2018. Before that he spent more than twenty years at Oracle, rising to president of product development, in charge of Oracle Database, Fusion Middleware and its business applications.", "bioSources": [ "https://en.wikipedia.org/wiki/Thomas_Kurian", "https://en.wikipedia.org/wiki/Google_Cloud" ], "page": "/people/thomas-kurian/" }, { "name": "Demis Hassabis", "role": "Co-founder and CEO, Google DeepMind", "bio": "Demis Hassabis co-founded DeepMind, which started in 2010, and leads Google DeepMind, formed by bringing Google Brain and DeepMind together. He is also chief executive and co-founder of Isomorphic Labs, and shared the 2024 Nobel Prize in Chemistry with John Jumper for AI research on protein structure prediction.", "bioSources": [ "https://deepmind.google/about/", "https://en.wikipedia.org/wiki/Demis_Hassabis" ], "page": "/people/demis-hassabis/" } ], "peopleNote": "Google Cloud is Google's cloud business, so the company-level people are the same as for Google (out/top/antigravity-cli.json), with Thomas Kurian added as CEO of Google Cloud from Wikipedia's Google Cloud article (infobox owner Google, CEO Thomas Kurian) and his own article, read 28 October 2026. Product people named on single listings (Sarah Weldon, Rohit Kumbhalwar, Brad Meador, Haris Ioannou) are left as they are. Copied from data/humans/vertex-ai-tuning.json on 6 November 2026 for the same company, not researched again.", "companySocial": { "linkedin": "https://www.linkedin.com/company/google", "x": "https://x.com/Google" }, "support": { "urls": [ "https://cloud.google.com/support-hub", "https://support.google.com/" ], "contactUrls": [ "https://cloud.google.com/contact" ] }, "sources": [ "https://about.google/intl/ALL_en/our-story/", "https://www.linkedin.com/company/google", "https://x.com/Google", "https://cloud.google.com/contact", "https://cloud.google.com/support-hub" ], "ownership": { "status": "subsidiary", "parent": "Alphabet Inc.", "checked": "2026-10-28", "sources": [ "https://en.wikipedia.org/wiki/Google", "https://about.google/company-info/", "https://en.wikipedia.org/wiki/Google_Cloud" ] } }, "pageJsonUrl": "https://www.anchorterminal.com/tools/vertex-ai.json", "live": { "slug": "vertex-ai", "probe": { "target": "https://aiplatform.googleapis.com/v1", "method": "get", "lastAt": "2026-11-07T18:21:03.779025658Z", "lastOk": true, "lastStatus": 404, "lastMs": 763, "authRequired": false, "uptime24h": 100, "uptime30d": 100, "p50ms24h": 118, "p95ms24h": 752, "samples24h": 200, "samples30d": 200, "days": [ { "date": "2026-11-06", "probes": 13, "ok": 13 }, { "date": "2026-11-07", "probes": 187, "ok": 187 } ] }, "versions": [ { "registry": "github", "name": "googleapis/python-genai", "version": "v3.0.0", "released": "2026-11-06", "seenAt": "2026-11-07T00:15:33.519504561Z" }, { "registry": "npm", "name": "@google/genai", "version": "3.0.0", "seenAt": "2026-11-07T00:15:31.639429892Z" }, { "registry": "pypi", "name": "google-cloud-aiplatform", "version": "2.7.0", "released": "2026-10-28", "seenAt": "2026-11-07T00:15:32.521225598Z" }, { "registry": "pypi", "name": "google-genai", "version": "3.0.0", "released": "2026-11-06", "seenAt": "2026-11-07T00:15:31.485691571Z" } ], "githubStars": 4057, "npmWeekly": 31989360, "pypiWeekly": 38431674, "securityTxt": { "url": "https://google.com/.well-known/security.txt", "state": "valid", "expires": "2030-04-01T00:00:00z", "checkedAt": "2026-11-07T16:01:22.068349931Z" }, "pages": [ { "url": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "kind": "deprecations", "status": 200, "checkedAt": "2026-11-07T14:01:16.257808105Z", "changedAt": "2026-11-07T14:01:16.257808105Z", "fingerprint": "a4fe253bd23f" } ], "updatedAt": "2026-11-07T18:21:03.779025658Z" } } }