Celeris-1 Decision vs Gemini Decision 1

Celeris-1 Decision 44

Read for a model, on the decision-model split used for Jev, OpenAI Decisions, pplx-decider and Liquid d1 (notice 0 to 12 and churn 0 to 8 in place of the 20-point release-count line). The dated 8 October launch is the last dated change (30). Since 9 October the docs name the model celeris-1.1-decision in every example, the models page and the price table, with no dated entry, changelog or notice, and whether the old celeris-1-decision name still answers is not stated. No deprecation policy or notice period (0 of 12). A 27-day record with one undated version change is too short to show churn, read as Liquid d1's undated changes were (4 of 8). A support email is published but public response evidence was not found (0). Documented current client compatibility (Jev SDK, OpenAI Python SDK 3.26.0 or later) earns 10 of 15, not an award for Celeris-owned SDK maintenance. No owned decision package CI found (0). 30 + 0 + 4 + 0 + 10 + 0 = 44.

Gemini Decision 1 79

Model reading for gemini-decision-1 on the Gemini API's Decisions endpoint. Platform facts are the Gemini API listing's (gemini-api, re-read 1 November), carried over as RULES.md allows for a model on an already graded platform. Released on 11 November 2026, the day of this check (30). Deprecations with earliest dates and no stated minimum notice (4 of 12). Shutdowns in the last 90 days kept to their table (4 of 8). Dated changelogs: google-genai 3.2.0's entry adds the Decisions API; the platform changelog wasn't re-read today (11 of 15). SDK replies not sampled (5 of 10). google-genai 3.2.0 tagged the same day with client.decisions.create; the JavaScript SDK is per Google's post (15). Runtimes stated on the platform (10). 30 + 4 + 4 + 11 + 5 + 15 + 10 = 79. The model is hours old, so these lines are the platform's habits more than this model's record.

Celeris-1 Decision 30

Public per-token prices earn 20. No machine-payment protocol found (0). Activation needs a payment method and credit is bought by card from $5, and no free credit at signup is stated (0). Browser signup and activation prevent autonomous onboarding credit (0). 20 + 0 + 0 + 0 = 20. Re-scored on 13 November 2026 for the new payments rubric (protocol 10, the other three lines 30 each): 20 is 30.

Gemini Decision 1 60

Model reading for gemini-decision-1 on the Gemini API's Decisions endpoint. Platform facts are the Gemini API listing's (gemini-api, re-read 1 November), carried over as RULES.md allows for a model on an already graded platform. No machine payment protocol (0). The pricing page lists $0.10 per million input tokens on the paid tier for every modality and no output charge, without a login (20). Free of charge on the free tier (20). A Google account and an AI Studio key come first (0). 0 + 20 + 20 + 0 = 40. Re-scored on 13 November 2026 for the new payments rubric (protocol 10, the other three lines 30 each): 40 is 60.

Celeris-1 Decision 60

No public machine-readable decision contract found (0). Markdown and llms.txt earn 10. Purpose and limitations earn 20, typed question variants and explicit limits 15, and examples and errors 15. Versioned paths alone do not establish a public changelog (0). The docs now give the decision model's context window (131,072 tokens, with a fixed part reserved for answers). 0 + 10 + 20 + 15 + 15 + 0 = 60.

Gemini Decision 1 80

Model reading for gemini-decision-1 on the Gemini API's Decisions endpoint. Platform facts are the Gemini API listing's (gemini-api, re-read 1 November), carried over as RULES.md allows for a model on an already graded platform. No published machine-readable contract for the Decisions endpoint; the request and response types are generated and typed in google-genai 3.2.0, Apache-2.0 (10 of 25). llms.txt with Markdown twins on the platform (10). The guide and model page say what the endpoint is for and list what it doesn't do (no caching, Batch, Flex, Priority, function calling, structured outputs or text generation; no YouTube or gs:// sources; history only as text) (18 of 20). Fields carry stated rules: question keys match [A-Za-z0-9_-]+ up to 64 characters, 1 to 1,000 questions, 2 to 255 options or levels, option keys 1 to 128 characters, P(true) between 0.01 and 0.99, nesting to 100 levels (14 of 15). Python, JavaScript and REST examples, and errors documented as HTTP 400 with codes safety, prohibited_content, blocklist, image_safety and content_blocked (13 of 15). Dated SDK changelog and the platform's dated changelog (15). 10 + 10 + 18 + 14 + 13 + 15 = 80.

Celeris-1 Decision 55

Closed model with service terms earns 15. Privacy and security statements explain processing and 90-day usage records, but not prompt retention or a training exclusion, earning 15 of 30. No dated deprecation policy found, and the move to celeris-1.1-decision carries no dated notice (0). Named subprocessors and regional-routing disclosure earn 15 of 20; a decision-specific residency guarantee was not found. 15 + 15 + 0 + 15 = 45.

Gemini Decision 1 70

Model reading for gemini-decision-1 on the Gemini API's Decisions endpoint. Platform facts are the Gemini API listing's (gemini-api, re-read 1 November), carried over as RULES.md allows for a model on an already graded platform. Closed service with clear terms, SDKs Apache-2.0 (15). The pricing page states that free-tier content is used to improve products and paid-tier content isn't; abuse retention has no number (15 of 30). Deprecations table; the model page names no deprecation for this model (15 of 20). Data may be cached anywhere Google has facilities; no subprocessor list checked (5 of 20). Every benchmark, latency and cost comparison is Google's own, and the post gives charts without scores in its text. 15 + 15 + 15 + 5 = 50.

Celeris-1 Decision 50

Read as a hosted model API. status.celeris.ai has a Celeris-1 Decision component (decision endpoint) with history (20). The model launched on 8 October 2026, so its record is 27 days long on 4 November. The history page, re-read on 4 November, lists one incident, the 19 August Celeris-1 outage, which predates this model, and nothing since. A short clean record reads as 15 of 30 in this run (excaliclaw for 11 clean days, the OpenAI Decisions API for 26 days), up from the 9 October 5 for one day (15). The rate-limits page gives a separate sustained request rate per workspace and model but no number (0). 429 carries Retry-After, the page gives backoff with jitter, and a decision has no side effects (15). Enterprise SLA marketing gives no public commitment, per the 9 October check (0). The terms, updated 15 October 2026, still describe an early access period (0). 20 + 15 + 0 + 15 + 0 + 0 = 50.

Gemini Decision 1 40

Model reading for gemini-decision-1 on the Gemini API's Decisions endpoint. Platform facts are the Gemini API listing's (gemini-api, re-read 1 November), carried over as RULES.md allows for a model on an already graded platform. Status page at aistudio.google.com/status with no readable components or history (10 of 20) and no readable incident record (5 of 30). Rate-limit tiers and spend limits published for the platform, but the public rate-limit page, read on 11 November, has no row for Decision 1 and sends you to AI Studio (5 of 15). Backoff guidance for 429 and 503 and SDK retries (15). No SLA (0). The guide and the model page, read on 11 November, state no launch stage; the endpoint is v1beta and the model has one version, so half, as Gemini 4 Carbon was read (5 of 10). 10 + 5 + 5 + 15 + 0 + 5 = 40.

Celeris-1 Decision 80

Compact probability answers earn 25. Multiple questions, bounded options and image controls earn 15 of 20; the docs now state a 131,072-token window but no output-budget control, so the line stays partly met. Actionable errors earn 20. Retry guidance earns 10 of 20 because duplicate inference can be billed and no idempotency contract was found. Simple required fields and documented compatible Python clients earn 10 of 15; no Celeris-owned decision SDKs in two languages found. 25 + 15 + 20 + 10 + 10 = 80.

Gemini Decision 1 85

Read on the tool lines, as the other decision-model listings are. Model reading for gemini-decision-1 on the Gemini API's Decisions endpoint. Platform facts are the Gemini API listing's (gemini-api, re-read 1 November), carried over as RULES.md allows for a model on an already graded platform. Answers are probabilities only, and the shared input is billed once across up to 1,000 questions (25 of 25). Limits are written down: 262,144 tokens shared by the input and all questions, 1,000 questions, 2 to 255 options, inline data to 100 MB (50 MB for PDFs), 15 MB per external URL (20 of 20). Errors return HTTP 400 with a named code an agent can branch on, plus the platform's backoff advice (15 of 20). SDK retries and backoff guidance, no idempotency key; nothing is written, so a repeat only costs input again (10 of 20). Three required fields, SDK 3.2 or later in Python and JavaScript, and REST (15 of 15). 25 + 20 + 15 + 10 + 15 = 85.