FLORA vs Replicate image models

FLORA 68

OAuth with the authorisation code grant, PKCE (the metadata lists plain and S256, the docs S256), dynamic client registration, refresh tokens and revocation at the token endpoint, with no named scopes, no documented token lifetimes and no list of OAuth connections in FLORA's settings; API keys ak_ scoped to chosen workspaces with Read, Write and Billing permissions, shown once, five at a time and revoked at once, with no expiry or rotation feature. Only the header form is documented (24 of 30). Read-only keys and per-workspace scoping, roles that cap what an agent can do, guests who cannot generate, spending caps per member, workspace, organisation and overage, and a quote-first rule; flora_run_canvas_nodes spends with no confirmation step (16 of 20). Agents read canvas prompts, comments, Techniques and files written by others; the security page says to treat them as data, to review the quote after reading shared content and to use least-privilege keys for unattended accounts, with no technical filtering described (11 of 15). Operators see spend by member in the app and through flora_get_usage, organisation usage exports through the API, charged_cost per run and failed webhook deliveries; FLORA's own MCP logs are not exposed to the operator (9 of 15). The trust centre lists SOC 2 Type 2, GDPR and CCPA (published 26 October 2026) with no report shown; no security.txt was found on flora.ai, and no disclosure policy or bug bounty for the service. The SDK's SECURITY.md points SDK reports at Stainless while its README says the SDK is generated by Fern (8 of 20). 24+16+11+9+8 = 68.

Replicate image models 35

Plain bearer API tokens with no scopes (20). No read-only or least-privilege mode, and monthly spend limits were removed in July 2025 (0). The MCP server returns community model descriptions and READMEs with no injection guidance (5). Each prediction is listed with inputs, outputs and logs (10). No security.txt, disclosure policy or certification found, as on Replicate's music listing; osv.dev lists no advisory for Replicate's replicate and replicate-mcp packages on 4 November, its one hit being the unrelated replicate-js (0). 20 + 0 + 5 + 10 + 0 = 35.

FLORA 46

Hosted reading, for the MCP server and the REST API. A status page at status.flora.ai is linked from the home page and the MCP page, but its robots.txt answered a client error twice on 2 November 2026, so under our rules nothing on that host was fetched and its components are unread (10 of 20, for a linked page whose content we could not check). No readable incident history, so the floor, and this is our fetch rule rather than a finding about FLORA (5). No requests-per-minute figure is published, as the cost and limits page says in so many words; batch sizes (1 to 20 generations, 20 run ids, 50 canvas nodes, 25 files), the polling cooldown (15 seconds, or 2 seconds a run) and one-at-a-time generation for new unpaid accounts are given with numbers (8 of 15). 429 rate_limited is documented with Retry-After on the API and retry_after_seconds on MCP, a 60-second fallback, exponential backoff and a retryability table, and the SDK retries 408, 429 and 5xx twice. Idempotency-Key covers every mutating REST request for two hours, but flora_create_generations over MCP has none and the docs say to read history before retrying (13 of 15). No SLA; the terms provide the service as is (0). No beta or preview label on either surface; the old beta endpoint was removed on 30 June 2026, though the registry version is 0.11.5 (10). 10+5+8+13+0+10 = 46.

Replicate image models 75

replicatestatus.com answers 301 to Cloudflare's status page filtered to Replicate, which has a Replicate component with its own history (20). Its 90-day history shows five days with incidents, 14, 15, 17, 24 and 28 September 2026, among them some models failing to start, a Pruna issue and intermittent 500 errors for backend services, read as partial as on Replicate's other listings, and none in the last 30 days (20). Limits of 600 create-prediction requests a minute, 3,000 for other endpoints and 6 for accounts with granted credit and no payment method (15). A 429 body gives the reset time, about 30 seconds, with no Retry-After header or idempotency keys, read at 10 as on Replicate's other listings (10). No SLA (0). GA (10). 20 + 20 + 15 + 10 + 0 + 10 = 75.

FLORA 83

Closed service with a dated changelog. The newest MCP changelog entry is 23 October 2026, and flora.ai/updates has product entries to 28 October (30). 31 dated MCP changelog entries between 4 August and 23 October 2026 (20). Support at support@florafauna.ai, bug and feature forms, a Discord linked from the home page, weekly training sessions, and GitHub issues on the skills repository as its support URL (2 open); no response times stated (10 of 15). ai.flora/flora 0.11.5 is in the official MCP registry under a DNS-verified namespace since 16 October 2026 (15). The TypeScript SDK @flora-ai/flora 0.21.1 (14 October 2026, 157 downloads in the week to 1 November) has CI, release-please and an npm publish workflow; the skills repository was last pushed on 18 October 2026 (8 of 10). 30+20+10+15+8 = 83.

Replicate image models 70

Every dated source of the vendor's own counts. The changelog's newest entry is still 21 April 2026, but Cog, Replicate's own CLI and model server, tagged v0.23.1 on 19 October 2026, counted in full as on Replicate's deployments, video and music listings (30). Cog tagged v0.22.0 on 13 August, v0.23.0 on 22 September and v0.23.1 on 19 October, three releases in the 90 days from 6 August (20). Issue reply times couldn't be read because GitHub's pages answer 403 (5, kept as the earlier partial). Stable clients are JavaScript 1.4.0 (17 November 2025) and Python 1.0.7 (27 May 2025), the same evidence as on 1 October (12). Client repositories carry CI workflows but have had no commit since August and November 2025 (3). 30 + 20 + 5 + 12 + 3 = 70.

FLORA 53

No x402, MPP or L402 (0). Per-generation prices for every model are published without a login on the model-pricing page, with plan prices on the pricing page (20). Free gives each new workspace $2.50 of usage, which the docs and the MCP changelog (1 September 2026) say an agent can spend through MCP; the REST API answers paid_plan_required on Free, the pricing page marks MCP 'Not included' there, and no page says whether Free needs a card, so this is a one-off trial on one surface (15 of 20). A person signs up in a browser and approves OAuth, or makes a key in Settings (0). 0+20+15+0 = 35. Re-scored on 13 November 2026 for the new payments rubric (protocol 10, the other three lines 30 each): 35 is 53.

Replicate image models 45

No x402, MPP or L402 (0). Per-image prices for official models (FLUX.1 schnell $3 per 1,000, FLUX.1 dev $0.025, FLUX 1.1 pro $0.04, Ideogram v3 Quality $0.09, Recraft V3 $0.04, re-read on the pricing page) and per-second GPU prices, all without a login (20). No standing free tier, but an account granted credit can run predictions without a payment method at up to 6 a minute, read as on Replicate's other listings (10 of 20). Browser sign-up (0). 0 + 20 + 10 + 0 = 30. Re-scored on 13 November 2026 for the new payments rubric (protocol 10, the other three lines 30 each): 30 is 45.

FLORA 68

Closed service under terms of service (17 November 2025) that name FLORA AND FAUNA FLOWERSHOP, INC., give the user all rights in output and limit FLORA's licence in user data to running the service; the SDK is Apache-2.0 and the skills MIT (15 of 30). The terms, the data, security and IP page and the MCP security page agree that FLORA does not train on user data or let model providers train on it. The privacy notice (1 June 2026) is silent on training, names only Google Analytics and an unnamed session replay tool, and gives no retention period beyond the life of the account; a DPA is for Enterprise and paid workspaces with client data (18 of 30). The MCP changelog dates deprecations with replacements (a beta endpoint deprecated 28 May and removed 30 June 2026, execute deprecated 11 September and retired 8 October 2026) and a retired-tools page lists five, but there is no written notice period, and flora_comments forwards with no end date (12 of 20). The sub-processors page (2 June 2026) names 23 services with their locations, including India, the UK, China and Singapore, with no commitment to notice of changes (16 of 20). 15+18+12+16 = 61.

Replicate image models 75

Closed platform under terms updated 1 April 2026 naming Replicate, LLC; the clients are Apache-2.0 and each image model keeps its own licence (15). API prediction inputs, outputs, files and logs are deleted after an hour by default and web predictions are kept indefinitely, re-read on 4 November; the privacy policy gives no retention period and nothing says what the providers behind official models keep (18, as on Replicate's video listing). No written deprecation policy, but the changelog dates platform deprecations such as the monthly spend limit on 1 July 2025 (12, aligned with the other Replicate listings). A subprocessor page lists 17 companies with their purpose, each in the United States; model providers aren't on it (15). 15 + 18 + 12 + 15 = 60.