ToAPIs

Gemini Omni Full Guide (Markdown)

Back to model guide

Gemini Omni API Model Guide

TL;DR

  • Flash-oriented positioning optimized for quick generation, low latency, and high iteration speed.
  • Well suited to prototyping, social short-form content, and batch output without a heavyweight production setup.
  • Uses async video task workflows: submit first, then poll task status for results.

Core Capabilities

  • Low-latency output：Built for workflows that need fast feedback and frequent prompt changes.
  • Short-form batch generation：Fits short videos, multi-variant testing, and social creative production.
  • Unified video task contract：Reuses the shared ToAPIs video task interface for easier production handoff.

When to Use

  • When validating concepts, scripts, or motion directions quickly.
  • When producing social short-form video or multiple creative variants at scale.
  • When low-latency feedback is important for rapid prompt iteration.

When Not to Use

  • When polished showcase quality and maximum visual stability matter more than speed.
  • When you require synchronous immediate responses instead of async task workflows.

Runtime Behavior

  • Runs as an async video task flow, returning task state first rather than the final video file.
  • Best suited to short durations, quick feedback cycles, and repeated parameter tuning.
  • Fits server-side queues and production workflows via shared video-task polling patterns.

Minimal Request

{
  "model": "gemini_omni",
  "prompt": "A cinematic shot of a cat running through neon rain",
  "aspect_ratio": "16:9",
  "duration": 6,
  "resolution": "720P"
}

Minimal Response

{
  "id": "video_01JZEXAMPLE",
  "object": "generation.task",
  "model": "gemini_omni",
  "status": "queued",
  "created_at": 1779247407
}

Key Parameters

ParameterTypeRequiredDefaultRangeDescription
modelstringYesgemini_omni-Model identifier. Use the fixed value gemini_omni.
promptstringYes--Main instruction describing the subject, action, scene, and visual style.
aspect_ratiostringNo16:916:99:16
durationintegerNo6610
resolutionstringNo720P720POutput resolution. Currently only 720P is supported; if omitted, the default value is used.

Common Errors

HTTPCodeTriggerFix ActionRetry Policy
400invalid_request_errorRequest payload misses required fields or has invalid field types.Validate model, mode, and input schema before request.Retry only after fixing payload; avoid blind retries.
401authentication_errorMissing Authorization header or invalid API key.Verify Bearer token format and API key scope.Retry after auth fix; rotate key if repeated failures continue.
429rate_limit_exceededRequest rate, concurrency, or current quota hits upstream rate limiting.Apply exponential backoff first, then review request rate, concurrency, and quota usage.Use exponential backoff (e.g., 1s/2s/4s) with jitter; if it persists, reduce submission pressure.
500internal_errorTransient upstream error or internal processing failure.Capture request id and trigger retry workflow.Retry 2-3 times with short delays; escalate if persistent.

FAQ

  1. What is Gemini Omni best for?
    It is best suited to prototyping, social short-form video, batch generation, and fast creative iteration where low latency matters.
  2. Image or video model error: invalid apitype: -1
    This usually means the request was sent to the wrong endpoint. Image and video models typically do not use the chat endpoint. Instead, submit the documented HTTP task request and poll the task status endpoint for results. Check the actual request code, URL, and payload first.
  3. An image or video task failed, but the user was still charged
    Ask the user for the task log or screenshot first and check whether input or output token usage appears. If token accounting shows up, the request was likely sent through a chat endpoint instead of the proper media workflow. Image and video models usually run as async HTTP task APIs: submit the task first, then poll by task id according to the relevant docs.

Related APIs