ToAPIs
    homeToAPIs
    Image GenerationQwen Image and other domestic image modelsVideo GenerationSeedance, Kling, Wan…Chat & WritingDeepSeek, Zhipu GLM…Speech & MusicVoiceover, TTS, Podcasts
    New ReleaseSeedance 2.5
    PricingAPI DocsMCP
    Alternatives
    Log InStart Free
    All ModelsPricingAPI DocsMCPAlternatives
    Log InStart Free

    Language

    Esc
    • Seedance 2.5Video Generation
    • Seedance 2.0 MiniVideo Generation
    • Kling 4.0 FlashVideo Generation
    • Kling 3.0 TurboVideo Generation
    • Qwen Image 3.0Image Generation
    • All Image ModelsCategory
    • All Video ModelsCategory
    • DeepSeek V4 ProDeepSeek · Text
    • DeepSeek V4 FlashDeepSeek · Text
    • GLM-5.3 FlashZhipu · Text

    Quick Answer

    • Generate 4–15s video at 720p from text prompts, first and last frames, or up to 5 reference images, with native synchronized audio.

    Key Parameters

    • model | string | required | - | - | Fixed to `gemini-omni-1.2-flash-preview`.
    • prompt | string | required | - | - | Video description.
    • duration | integer | optional | 10 | 4-15 | Output duration in seconds; defaults to 10, supports 4-15.
    • aspect_ratio | string | optional | 16:9 | 16:9 | 9:16 | Aspect ratio, defaults to 16:9.
    • resolution | string | optional | 720p | 720p | Output resolution, currently 720p.
    • image_urls | string[] | optional | - | - | Reference image URLs, up to 5; mutually exclusive with first/last frame fields.
    • first_image_url / last_image_url | string | optional | - | - | First/last frame image URLs; mutually exclusive with image_urls.

    Common Errors

      Gemini Omni 1.2 Flash

      Generate 4–15s video at 720p from text prompts, first and last frames, or up to 5 reference images, with native synchronized audio.

      Model Type:
      Text To VideoImage To VideoMultimodal Reference
      Pricing: 720p · per request · 4–15s $0.2
      Production route
      Live
      PlaygroundExamplesSimilarREADMEAPI

      Input

      FormJSON

      First frame

      Last frame

      Describe subject, camera, scene, and style.122 / 1200

      Advanced options

      Example params

      Output

      PreviewJSON
      View API DocsGet API Key

      Generation takes some time. Please wait.You can leave this page. [ Task Logs ] lets you check the generated content directly.

      Request preview

      {
        "model": "gemini-omni-1.2-flash-preview",
        "prompt": "A cinematic tracking shot through a sunlit futuristic city, natural pedestrian motion, steady camera and soft reflections.",
        "aspect_ratio": "16:9",
        "duration": 10
      }

      3

      Media modes

      4–15s

      Output duration

      720p

      Output quality

      16:9 | 9:16

      Aspect ratios

      Generated examples

      Explore what Gemini Omni 1.2 Flash can create

      Create with this model

      Gemini Omni 1.2 Flash #1

      Gemini Omni 1.2 Flash #2

      Transparent pricing

      Omni 1.2 Flash pricing

      Flat $0.20 per request for any 4–15s duration. Account rates apply.

      Top up credits

      720p · per request · 4–15s

      ToAPIs

      $0.2

      request

      SpecificationToAPIs priceBilling basis
      720p · per request · 4–15s

      ToAPIs

      $0.2

      request

      request

      The displayed price is a planning reference. Final billing follows the current account quote.

      Why ToAPIs

      Three ways to create video

      Start from a prompt, first/last frames or reference images — media modes are mutually exclusive.

      Text to video

      Generate 4–15 seconds at 720p from a prompt, in 16:9 or 9:16.

      First and last frames

      Provide a first frame image and optionally a last frame image to steer the opening and ending.

      Reference images

      Guide the subject and style with up to 5 reference images; cannot be combined with first/last frames.

      Prepare a creative brief

      Outline the story, motion and sound before production.

      1. 1

        Describe the scene

        Write down the subject, setting, camera movement and the sounds that give the scene its atmosphere.

      2. 2

        Choose a workflow to explore

        Decide whether to start from a prompt, images or an existing clip, then identify the details to preserve or change.

      3. 3

        Plan the final presentation

        Match the clip length, pacing and final resolution to your intended presentation.

      Plan your next video

      Short visual stories

      Sketch a short narrative with clear scene progression, camera direction and synchronized sound.

      Reference-led revisions

      Plan consistent visual direction across drafts, edits and extended scenes using your own source material.

      FAQ

      Gemini Omni 1.2 Flash FAQ

      Can I generate with this model now?

      Yes. Gemini Omni 1.2 Flash is live on ToAPIs as an async video task API: submit with POST /v1/videos and poll GET /v1/videos/{task_id} for the result.

      What settings and image inputs are supported?

      4–15 seconds at 720p with 16:9 or 9:16 aspect ratio. Provide a first frame and optional last frame image, or up to 5 reference images; the two media modes are mutually exclusive.

      What inputs are not supported?

      Video inputs, resolutions other than 720p, base64 or local file paths, and editing, extension or upscaling workflows are not available through this endpoint.

      How is it billed?

      Flat $0.20 per request regardless of duration. Final billing follows your current account quote.

      Gemini Omni 1.2 Flash API

      Create with Gemini Omni 1.2 Flash

      The model is live on ToAPIs. Try it in the playground or call POST /v1/videos from your code.

      Start creatingRead video API documentation

      Gemini Omni 1.2 Flash

      Generate 4–15s video at 720p from text prompts, first and last frames, or up to 5 reference images, with native synchronized audio.

      Create an account
      ToAPIs
      homeToAPIs
      Enterprise AI API gateway: text, image, video, and audio models behind one interface.

      Popular Models

      • Seedance 2.5 API
      • Seedance 2.0 API
      • Seedance 2 Mini API
      • Kling 4.0 Flash API
      Show moreShow less
      • Kling 3.0 Turbo API
      • All models

      API Categories

      • AI Image API
      • AI Video API
      • Text-to-Video API
      • Image-to-Video API
      Show moreShow less
      • AI Image Editing API
      • LLM & Reasoning API
      • All API tools →

      Alternatives

      Alternatives
      • Kie.ai alternative
      • Fal.ai alternative
      • OpenRouter alternative
      • Replicate alternative
      • Wavespeed AI alternative
      • All comparisons →

      Model Guides

      Model Guides
      • Seedance 2 integration
      • Seedance 2.5 integration
      • Kling 3.0 integration
      • All model guides →

      Developers & Platform

      Developers & Platform
      • API documentation
      • MCP
      • Pricing
      • Model playground
      • LLMs.txt
      • System status
      • Contact support
      • Model guide directory
      PrivacyTermsAcceptable UseData DeletionData RetentionSubprocessors & RegionsBilling & RefundsCookie PolicySitemapAbout

      开发者:深圳市鲸枢智能科技有限公司联系地址:深圳市宝安区新安街道灵芝园社区创业二路188号勤诚达大厦2603ICP 备案:粤ICP备2026010399号-1|粤B2-20263416© 2026 ToAPIs. All rights reserved.