Gemini Omni 1.2 Flash vs Luma AI API

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.

Luma AI API 47

Model reading. The latest dated API change found is SDK v0.5.0, whose changelog dates it 4 August 2026 (tag 5 August), adding the layering parameter to generations. That is more than 90 days before 4 November, so 10 (within 180 days). The docs now carry deletion, files and usage guides with no dates, and the 3 November MCP connector runs Luma Agents workflows on a subscription, which the API doesn't serve, so neither counts (10). Ray 2, Ray 3 and their variants are retiring, but the cutoff dates go out in private notices and the migration guide gives none (5). No API changelog. The SDK changelogs are dated and support is an email address on the migration guide (7). Official SDKs for Python, TypeScript and Go and a CLI, last released on 5 August with Ray 3.2 and files support, though the new deletion routes aren't in them yet (15). Each SDK repository has a CI workflow (10). 10+5+7+15+10 = 47.

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.

Luma AI API 53

No public OpenAPI document is linked from the docs. The API reference at /api/ is generated per method with no visible spec download (0). docs.agents.lumalabs.ai/llms.txt returns 404, but every docs page links a Markdown twin (for example /index.md and /guides/pricing/index.md) (10). Guides cover generation, keyframes, edit, extend, reframe, deletion, files, usage and the migration, and say which options don't combine, such as start and end frames with 10 second clips (14). Typed fields for model, type, resolution and duration with fixed values (12). curl and SDK examples, both 429 bodies and generation failure codes are documented (12). Responses carry an X-API-Version header and the SDK repositories keep dated changelogs, but the API docs have no changelog and the public changelog page on lumalabs.ai was last updated in June 2025 (5). 0+10+14+12+12+5 = 53.

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.

Luma AI API 57

Better Stack status page at status.lumalabs.ai with API, Dream Machine and Luma Agents components, an incident list and an RSS feed (20). In the 90 days from 6 August the feed lists three incidents, all on legacy Ray2 models: Ray2 Flash timeouts on 2 to 3 September (about 9 hours) and 15 to 16 September (about 2 hours), and Ray2 queue times on 16 to 17 September (about 13 hours). The status page tags each with its API and Dream Machine components, and each hit one legacy model, so minor only (20). The authentication incident counted as a major on 1 October was on 16 July and has left the window. Limits are per minute and per concurrent job, but the numbers sit in the dashboard, not the docs (5). Every 429 carries Retry-After, with separate bodies for the per-minute and concurrency limits and backoff guidance with jitter. Rejected requests aren't queued and synchronous errors are never charged, which is safe-retry guidance, but there is no idempotency key, so 12 as settled in this run (12). No SLA document. The pricing page lists a latency SLA for Provisioned Throughput only as a table entry (0). The pricing page says video rates may change before general availability, so the video surface isn't GA yet (0). 20+20+5+12+0+0 = 57.

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.

Luma AI API 66

Generations come back as small JSON objects with a presigned URL for the output (15). We found no callback for the Agents API, so jobs are polled (0 of 10). Resolution and duration set output size (10). The API reference lists create, get and delete for generations and a list call only for files, so there is no list of past generations (0 of 10). The 429 detail string tells an agent whether to wait for Retry-After or for a job to finish, and failures carry codes (16). No idempotency key. Moderated and failed generations are refunded and synchronous errors aren't charged, so a retry after a failure is safe (10). One generation endpoint with few required fields, and official SDKs for Python, TypeScript and Go plus a CLI (15). 15+0+10+0+16+10+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.

Luma AI API 67

Closed models. The terms give customers the outputs, with commercial use tied to an active paid plan (15). The API terms state that API inputs and outputs aren't used for training (10). The pricing page's comparison table says Pay-as-you-go has no no-train guarantee and only Provisioned Throughput does. That contradiction is charged once, as a misleading claim under negative events, as rime-prism's training contradiction is, so it doesn't also lower this line. The privacy policy (20 April 2026) describes retention by criteria without periods, and the deletion guide sets retention per API client with a one-year hold for moderation failures (5). The privacy policy was read and names US hosting with Standard Contractual Clauses for transfers. No DPA was read (5). A public migration guide without dates, retirement dates by email only (5). A subprocessor list (last updated 4 October 2026) names about 50 providers with their purpose, and the privacy policy says the services are hosted in the United States (15). 15+10+5+5+5+15 = 55.