framefields vs Gemini Omni 1.2 Flash

framefields 46

Apache-2.0, an OSI licence, in LICENCE and the npm metadata (30). A privacy policy and terms of service for the hosted parts, effective 26 October 2026, say what the dashboard and gateway collect, that request bodies aren't kept, that output files are kept while the account is open and deleted on request, that content isn't used to train models, and that sharing goes to Cloudflare, fal, Dodo Payments, GitHub and Google. Retention has no periods in days and there is no DPA. NOTICE.md now states that vision models download on first use (18). No deprecation policy; the changelog names removed styles and exports without notice periods (3). The privacy policy names sub-processors and says data may be processed in the United States and Asia, and states no analytics trackers on the site; no telemetry was found in the library's source, which has no statement either way (15). 30 + 18 + 3 + 15 = 66.

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.

framefields 74

A library with no tool definitions to load. The four skills are 88 KB of Markdown and load only when a task matches (16). Output can be sized to the check, by one frame, a contact-sheet grid with a step, a frame range, a quality level, and on the worker an LFS include list (16). comp.lint() returns { severity, code, message, layerId }, renderVideo({ qa }) returns measured issues with times, and worker jobs fail with { code, message, phase, retryable, hint } (18). Frames are a function of the frame number; worker jobs take an idempotencyKey and a source.commit pin, and renders accept an AbortSignal (16). Setup needs Node.js 22, an ES module project and an approved skia-canvas install script; TypeScript only (8).

Gemini Omni 1.2 Flash 54

Read on the lines the Veo listing used for video models. 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. Per the Omni guide (written for 1.1 on the same API), the video comes back in the response, inline as base64 or as a Google-hosted file to poll until ACTIVE with delivery uri for outputs over 4 MB (12 of 15). No callback (0 of 10). Resolution, aspect ratio and delivery control output size, and edits run turn by turn through previous_interaction_id without regenerating from scratch (10). No list of past jobs found (0 of 10). Standard Google error statuses on the platform, with FAILED as the only Omni-specific state (12 of 14). No idempotency key, and whether failed generations are billed isn't stated (5 of 20). Only model and input are required, with 720p and 16:9 as defaults, and SDKs in five languages plus the CLI (15). 12 + 0 + 10 + 0 + 12 + 5 + 15 = 54.

framefields 61

Read with the local-software lines, because the library and the renderer worker run on the owner's machines. Official npm package framefields with Node.js 22 or later stated in the README and getting-started page, though not in engines (20). The one public CI workflow still builds, typechecks and tests only the renderer worker on pushes to main, with GPU tests skipped, and the library's own Vitest suite isn't run in CI. Its pass state on 2 November couldn't be read (GitHub's pages and API refused); the last ten runs passed per the 20 October check (10). Seven bug issues filed on 13 October 2026 by an outside reporter were closed with fixes within a day, per the 20 October check. 2.9.3 (31 October) fixed prompted tracking that failed for every npm user since 2.9.0 the same day, because a peer package was never published (18). Changesets changelog with major, minor and patch entries, but 2.7.0, a minor release, removed TextReveal's track style, and 2.2.0 removed exports from @framefields/client-utils, a companion package (8). Version 2.12.0, but the README badge still says beta, so 5 of 15 (5). 20 + 10 + 18 + 8 + 5 = 61.

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.

framefields 77

Read as a library. No OpenAPI or other formal contract; the package ships TypeScript declarations for every export and validates with zod, counted as 15 of 25 as for other SDKs (15). llms.txt at framefields.dev and a docs index at /docs/llms.txt with a Markdown version of every page and full and compact text files (10). Authoring rules, a workflow page and four skills say what to do and in what order, cheapest check first (15). Options are typed with enums, such as quality (very_low, low, high, very_high) and codec (h264, vp9, vp8), and job fields have defaults (12). Examples on every guide page; lint and QA codes, troubleshooting and worker error codes are each catalogued with a fix (14). Semantic versions with a changesets CHANGELOG.md in the repository, 2.4.0 to 2.12.0 added since 20 October; no GitHub releases and no changelog page on the site (11).

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.

framefields 89

Version 2.12.0 on 2 November 2026, the day of the check, per the repository's version bumps; npm wasn't readable (30). 19 version bumps from 2.4.0 to 2.12.0 in the 14 days since 20 October, 42 since 5 October, five of them betas (20). Outside bug reports of 13 October 2026 were fixed and closed within a day, per the 20 October check; issue and pull request reply times weren't re-read, and pull requests #39 to #52 and #64 to #77, all from the vendor's own branches, were merged between 21 October and 2 November (18). It is Gatewai's own package, current with the skills, which follow its version (15). Dependencies are current (zod 4, mediabunny 1.61.6 as a stated minimum), but CI covers only the worker and the GPU backend depends on webgpu 0.4, a pre-1.0 package (6). 30 + 20 + 18 + 15 + 6 = 89.

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.

framefields 45

Read with the framework lines. The library takes no credentials for local rendering. The optional AI gateway and cloud renders take a FRAMEFIELDS_API_KEY from the dashboard, stored hashed with a per-key monthly spending limit, and the self-hosted worker uses one bearer key for all jobs plus a git token (15). The worker refuses repositories outside a required FF_REPO_ALLOWLIST, removes secrets from the environment before project code runs, shares node_modules read-only, and its README warns that allowed repositories' code runs in the worker's process. The getting-started page has the owner deny five of six dependency install scripts (12). It renders the owner's assets and returns no third-party text, apart from preview notes a person writes for the agent (10). Worker results report the rendered commit SHA, timings and GPU; no audit log (5). No SECURITY.md in the repository and no security.txt on 2 November (403 at /.well-known/, 404 at the root); OSV holds no advisory for framefields. npm provenance per the 20 October check (none on 2.3.2), not re-read. Vision models are fetched from pinned Hugging Face revisions with a SHA-256 check (3).

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.