Glimpse vs Vertex AI (Gemini Enterprise Agent Platform)

Glimpse 20

Model reading of the checklist (tool use, structured output, caching, context, batch, SDKs, errors). On 17 October the tool, tool_choice, response_format, structured_outputs, cached-price, context, output-limit and batch readings for this model all came from OpenRouter's endpoints API, which this run doesn't use, so they are struck. No readable first-hand page states them today. Elorian's docs sit on a host that refuses our crawler, and Together's model page says only text, image and video in and text out on a dedicated deployment. Tool use (0 of 20), structured output (0 of 15), prompt caching (0 of 15), context length (0 of 15), batch (0 of 10). OpenRouter's SDKs in TypeScript, Python and Go, and any OpenAI client works (10 of 10, per the 17 October check, not re-read on 4 November 2026). OpenRouter's documented error codes with limit_source and remedy hints, nothing specific to video or image limits (10 of 15, per the 17 October check, not re-read on 4 November 2026). 0 + 0 + 0 + 0 + 0 + 10 + 10 = 20.

Vertex AI (Gemini Enterprise Agent Platform) 97

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).

Glimpse 23

Hosted lines, read on the OpenRouter route. OpenRouter's status host refuses our crawler in robots.txt, so the 17 October reading of it is struck, and Elorian has no status page found (0 of 20). No 90-day incident record could be read. The 17 October uptime figures came from OpenRouter's endpoints API, a JSON data API this run doesn't use, and are struck (5). OpenRouter's limits page documents credit, budget and rate limits and a key endpoint that reports what's left, but sets no request cap on paid models, and no limit for Glimpse was found (8 of 15, per the 17 October check, not re-read on 4 November 2026, openrouter.ai paused on its terms). The errors page documents Retry-After on 429 and 503 and on 402 in-flight budget errors, and says the official SDKs honour it, with no safe-retry guidance or idempotency keys recorded (10, Retry-After alone, the value this run gives backoff or Retry-After guidance by itself; per the 17 October check, not re-read on 4 November 2026). No SLA from Elorian or for this endpoint (0). Elorian and Together label Glimpse a research preview (0). 0 + 5 + 8 + 10 + 0 + 0 = 23.

Vertex AI (Gemini Enterprise Agent Platform) 99

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.

Glimpse 40

Model reading. Elorian publishes no API reference, model card or llms.txt in public. Its docs sit at platform.elorian.ai/docs, a host whose robots.txt answers access denied. The 17 October contract reading rested on OpenRouter's OpenAPI-documented chat endpoint, with no recorded visible download link on a host now paused, and on the parameter list from OpenRouter's endpoints API, both struck (0 of 25). OpenRouter's llms.txt and Markdown docs, including video input (10, per the 17 October check, not re-read on 4 November 2026). The launch post and Together's model page name the jobs (visual search, video captioning, dense counting, robotics planning) and the post states limits (token cost, no action outputs yet), but nothing says when not to use it or how video is sampled (6 of 20). Typed parameters for OpenRouter's chat endpoint in its API reference, with no reasoning effort levels documented for this model (10 of 15, per the 17 October check, not re-read on 4 November 2026; the 17 October tool_choice reading came from the struck endpoints API). OpenRouter's examples and error reference, with no Glimpse-specific examples or limits on video length or image count (7 of 15). OpenRouter's dated changelog, with no changelog from Elorian (7 of 15, held as partly met; the dated canonical slug came from the struck endpoints API). 0 + 10 + 6 + 10 + 7 + 7 = 40.

Vertex AI (Gemini Enterprise Agent Platform) 94

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).

Glimpse 38

Closed model with weights not released and the open-weight base model unnamed. Elorian's terms sit on platform.elorian.ai, whose robots.txt answers access denied, so they were not read; published terms on a refusing host keep the closed-service value, held at 13 of 30. The privacy policy says Elorian trains on submitted content from free use and gives no retention periods, and the acceptable use policy, updated 19 October 2026, is still titled Privacy Policy and still carries a drafting comment from a terms outline in its markup (10 of 30, held as partly met; the 17 October comparison with the terms rested on the struck script reading). No deprecation policy or dated notices (0 of 20). Services hosted in the United States and subprocessors named by category only, and OpenRouter shows Together as the provider with its data policy (8 of 20). 13 + 10 + 0 + 8 = 31.

Vertex AI (Gemini Enterprise Agent Platform) 90

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).

Glimpse 56

Model reading. OpenRouter bearer keys with per-key credit limits, management keys and OAuth PKCE, no permission scopes (25 of 30, per the 17 October check, not re-read on 4 November 2026). Training on API data on this route is off according to OpenRouter's policy display for Together (no training, no prompt retention). Elorian's privacy policy trains on Inputs and Outputs from free access by default and says different terms may apply to paid and API use. The 17 October reading of Elorian's terms came from a script on a host that now refuses our crawler and is struck. Whether Elorian receives prompts from the Together deployment was not established (8 of 20, held as partly met). OpenRouter's zero-retention filter and Together's no-retention flag, against Elorian's retention 'for as long as reasonably necessary' with no period (8 of 15). OpenRouter's per-generation activity records for the operator (10 of 15). OpenRouter's security.txt was valid at its last check. Elorian has no security.txt, disclosure policy, bug bounty or certification found (5 of 20, held as partly met). 25 + 8 + 8 + 10 + 5 = 56. Readings of OpenRouter and Elorian pages per the 17 October check, not re-read on 4 November 2026.

Vertex AI (Gemini Enterprise Agent Platform) 97

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).

Glimpse 51

Model reading. Announced on 16 October 2026, 19 days before 4 November, and still labelled a research preview on Together's model page that day (30). One release, no history of versions or retirements and no deprecation notice period (3 of 20). Elorian's support page says there is no support queue, and channels are email and a Discord server, not tested (6 of 25, per the 17 October check, not re-read on 4 November 2026; the terms' no-support clause came from the struck script reading). No official SDK from Elorian. OpenRouter's SDKs are current (8 of 15). No package or CI of Elorian's to read. OpenRouter's SDK repositories run CI (4 of 10). 30 + 3 + 6 + 8 + 4 = 51.

Vertex AI (Gemini Enterprise Agent Platform) 91

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.