Clueso vs Gemini Omni 1.2 Flash

Clueso 30

Read as a closed hosted service. The public changelog at www.clueso.io/changelog dates the MCP launch to 16 June 2026 and a new release of the Clueso MCP to 26 September 2026, 46 days ago (20). Other entries since 13 August (Clueso Agents, plans, transitions, AI chat, the simplified editor on 1 November) describe the web app, not what the server serves, so only one dated MCP entry falls in the last 90 days (0). A dated public changelog and a help centre with a support contact; support not tested (10 of 15). The repository's server.json and README name the registry entry io.clueso/video, but the earlier registry reading isn't on a readable registry page, and a vendor's own server.json is a claim (0). No package health to read for a hosted server (0). 20 + 0 + 10 + 0 + 0 = 30.

Gemini Omni 1.2 Flash 83

Model reading for gemini-omni-1.2-flash on the Gemini API. 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 and generally available on 5 November 2026; the SDKs added it to the Interactions model list on 10 November (30). Deprecations with earliest dates and no stated minimum notice (4 of 12). Churn in Google's video line: every Veo model on the Gemini API shut down by 22 October, and from 3 December 2026 requests to Omni 1.1 Flash are routed to 1.2 Flash and billed at its rates, four weeks after this release (4 of 8). Dated SDK and platform changelogs (15). SDK replies not sampled (5 of 10). Current SDKs in five languages (15). Runtimes stated (10). 30 + 4 + 4 + 15 + 5 + 15 + 10 = 83.

Clueso 15

No public status page found, so no readable incident history (0 + 5). No numeric rate limits for the MCP server or general retry guidance found in the setup guide or help centre (0, 0). The pricing page lists SLAs only on the Enterprise plan with no published SLA document, and the terms say availability is governed by an SLA only where one has been signed (0). The hosted server has been generally available on every plan since the 16 June 2026 launch (10). 0 + 5 + 0 + 0 + 0 + 10 = 15.

Gemini Omni 1.2 Flash 45

Model reading for gemini-omni-1.2-flash on the Gemini API. 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). Platform rate-limit tiers; the public rate-limit page has no Omni 1.2 row (5 of 15). Backoff guidance for 429 and 503 and SDK retries (15). No SLA read for the Gemini API route, and the Omni guide says provisioned throughput isn't supported there; Google's post puts it on Google Cloud (0). Google's post of 5 November says generally available, and the SDK commit marks the model GA (10). 10 + 5 + 5 + 15 + 0 + 10 = 45.

Clueso 40

The setup guide (last modified 25 September 2026) lists 40 tools with names and descriptions and a few parameter values, but no input schemas, and the 18 October tool inventory came from a call to the MCP endpoint, which this run strikes, so no machine-readable contract was read (0 of 25). The help centre publishes llms.txt with Markdown copies of each page, the setup guide included (10). Tool descriptions say what each does and how tools combine in worked workflows (15 of 20). Parameters and allowed values are named for a few tools only (find type, source org, stock or all, provider), with no types or required fields for the rest (5 of 15). Example prompts, worked multi-tool workflows and a troubleshooting section (10 of 15). A dated public changelog names the MCP launch on 16 June and a new MCP release on 26 September, but the hosted server carries no version of its own, so the line is only partly met, and with no earlier partial value to keep it stays at 0 (as crustdata and pdf-co were held). 0 + 10 + 15 + 5 + 10 + 0 = 40.

Gemini Omni 1.2 Flash 69

Model reading for gemini-omni-1.2-flash on the Gemini API. 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. Called through the Interactions API, which the platform's Discovery document doesn't type; the SDK's generated Interactions types list the model (10 of 25). llms.txt with Markdown twins (10). The Omni guide, read on 11 November, covers Omni 1.1 Flash on the same API and lists what isn't supported (system instructions, temperature, negative prompts, audio references, YouTube sources) and the regional limits; it doesn't name 1.2 (16 of 20). Aspect ratio (16:9 or 9:16), resolution (360p, 720p, 1080p, 4k) and delivery are enumerated; length is set in the prompt, not a field (10 of 15). REST and SDK examples; a failed generation sets the file state to FAILED, and other error codes aren't documented beyond the platform's page (8 of 15). Dated SDK and platform changelogs (15). 10 + 10 + 16 + 10 + 8 + 15 = 69.

Clueso 30

OAuth sign-in to a Clueso workspace, revocable from the account or the assistant per the privacy policy; scopes aren't published (20 of 30). No read-only mode or confirmation step for the server's delete tools (remove_clip, remove_from_project) was found; Reviewer seats are read-only but are an Enterprise option not documented for the connector (0 of 20). The server returns stock-library results, uploaded media and community templates, with no prompt-injection guidance (0 of 15). Exports appear in the editor's Exports tab and projects keep version history (5 of 15). The 19 October security page now answers "Page not found" and www.clueso.io has no security.txt; the privacy policy (6 November 2026) and pricing page claim a SOC 2 Type II report and ISO/IEC 27001 certification, with no report, trust portal or vulnerability disclosure route found, a bare claim (5 of 20). 20 + 0 + 0 + 5 + 5 = 30.

Gemini Omni 1.2 Flash 50

Model reading for gemini-omni-1.2-flash on the Gemini API. 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. Keys bound to a service account and restricted to the Gemini API, with no scopes and a token accepted in the URL (15 of 30, the platform's deduction). The pricing page, read on 11 November, lists no free tier for Omni 1.2 Flash, and paid-tier content isn't used to improve Google's products (15 of 20). Retention of generated videos isn't stated in the guide (5 of 15). Request logs described for Generate Content, not confirmed for Interactions video calls (10 of 15). security.txt and a reward programme, no certification naming the API (5 of 20). Outputs carry a SynthID watermark, and uploads of minors and some recognisable people are refused in the EEA, Switzerland and the UK. 15 + 15 + 5 + 10 + 5 = 50.

Clueso 45

No x402, MPP or L402 route (0). Public plan pricing, Free $0, Solo $40 and Business $120 a month billed yearly, Enterprise on request, with no per-call price (10). The pricing FAQ says the free plan needs no credit card and allows 10 minutes of video export a month (20). A person signs in through a browser to authorise the connector (0). 0 + 10 + 20 + 0 = 30. Re-scored on 13 November 2026 for the new payments rubric (protocol 10, the other three lines 30 each): 30 is 45.

Gemini Omni 1.2 Flash 30

Model reading for gemini-omni-1.2-flash on the Gemini API. 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 $1.50 per million input tokens, $12 per million video output tokens and effective rates of $0.023 a second at 360p, about $0.07 at 720p, $0.104 at 1080p and $0.209 at 4K, without a login (20). No free tier (0). A Google account and AI Studio key, or a Cloud project, come first (0). 0 + 20 + 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.

Clueso 65

Closed service with clear terms of service, last updated 8 October 2026 (15). The privacy policy, last updated 6 November 2026, covers data sent through the connector, keeps recordings for the subscription and up to 30 days after deletion, and says content isn't used to train models; the sub-processor list (21 October 2026) agrees on 30-day deletion and no training, but puts generated media assets in Google Cloud Storage in the United States while both documents say customer content stays in the region the customer picks (25 of 30). No deprecation policy or dated notices; the terms promise only "reasonable notice" of material changes to paid functionality (0). The sub-processor list names every provider with purpose and location, the customer's choice of Mumbai, Frankfurt or California storage, and ten business days' notice of changes (20). 15 + 25 + 0 + 20 = 60.

Gemini Omni 1.2 Flash 72

Model reading for gemini-omni-1.2-flash on the Gemini API. 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). Paid only, so content isn't used to improve products; video retention isn't stated (20 of 30). Deprecations table and a dated routing notice for Omni 1.1 Flash (15 of 20). Data may be processed anywhere Google has facilities on the Gemini API route; no subprocessor list checked (5 of 20). SynthID watermarking is disclosed, and Google names the cases it still handles poorly. 15 + 20 + 15 + 5 = 55.