Veo 3.1 API pricing: what each tier costs and the cheapest way to run it

Veo 3.1 costs $0.075 to $1.20 per 4-, 6-, or 8-second 720p video on UnificAlly, below Google's direct Gemini API rate on every generation tier. Use Lite Relaxed for low-cost drafts and Fast for most finals. Quality costs several times as much as Fast, so save it for the videos where Fast falls short.

TL;DR: Veo 3.1 generates 4-, 6-, or 8-second videos at 24 FPS in 16:9 or 9:16 with synchronized audio. UnificAlly charges a flat $0.075 for Lite Relaxed, $0.15 for Lite, $0.30 for Fast, or $1.20 for Quality per 720p video. Google's direct API bills each output second instead, so a flat per-video rate costs less, and the gap widens with every second up to eight. See the live rate card or open the Veo 3.1 API playground.

Update (May 10, 2026): Google deprecated the Fast Relaxed variant. It is no longer available on UnificAlly. Use Fast for the same output on the standard queue, or Lite Relaxed for the cheapest draft path.

Update (July 18, 2026): Added a section on Veo 3 pricing for teams still on the older model.

Update (October 7, 2026): Every rate in this post now comes from UnificAlly's live price list and refreshes on each deploy, so the numbers below are always current.

Update (October 19, 2026): Added a real logo-animation test on Lite Relaxed, with the prompt, settings and output, plus a cost comparison against Grok Imagine 1.5 Video and Kling 4.0.

What is Veo 3.1?

Veo 3.1 is a text-to-video and image-to-video model from Google that generates MP4 videos with synchronized native audio. It launched on November 17, 2025. Google extended it in the Gemini API and Vertex AI in early 2026 with Lite / Fast / Quality variants, Scene Extension, and 4K upscaling.

Each generation accepts a prompt, optional start and end frames on any variant, and optional reference images on Fast, Lite, and Lite Relaxed. The model returns a 24 FPS MP4 in 16:9 or 9:16 with audio in the same file.

What's new in Veo 3.1

Veo 3.1 is the first widely available video model that produces synchronized audio in the same call as the video. Sound effects, ambience, and dialogue arrive already locked to on-screen action. That removes a separate sound design pass for short videos and makes Veo 3.1 a strong default for ad cutdowns, social verticals, and storyboard-to-pitch workflows where audio is the bottleneck.

The 4K preview variant and the dedicated Upscale endpoints also let teams keep raw generation costs low (generate at the cheapest variant, upscale only the videos that survive review), which matters once you generate at production volumes.

What you can do with Veo 3.1

Three generation variants

• Veo 3.1 Lite. Cheapest variant; supports frame mode, reference mode, and voice presets.
• Veo 3.1 Fast. Faster generation with the same input modes as Lite: frame mode, reference mode (up to three images), and optional voice presets.
• Veo 3.1 Quality. Google's top-end output; frame mode only, with no reference images, and the highest quality per video.

Lite has a Lite Relaxed counterpart that runs at lower priority for a lower listed price.

Inputs

• Text-to-video. A prompt is enough on every variant.
• Image-to-video (frame mode). Supply a start frame and an optional end frame to bracket the motion. Available on every variant.
• Reference images. Fast, Lite, and Lite Relaxed accept up to three reference images to steer subject and style, with optional voice presets. Not available on Quality, and it cannot be combined with frame mode in the same request.

Extend and Upscale

• Veo 3.1 Extend continues a completed video from its task ID using a chosen base model (Lite through Quality). Useful for narrative cuts longer than a single 8-second generation.
• Veo 3.1 Upscale 1080p and Veo 3.1 Upscale 4K take a finished task ID and return an upscaled MP4. Use them as a final pass on videos that survive review.

Output

• Resolutions: 720p, 1080p, and 4K (4K is preview on Google's side).
• Durations: 4, 6, or 8 seconds per video; chain with Extend for longer narratives.
• Aspect ratios: 16:9 and 9:16.
• Frame rate: 24 FPS.
• Format: MP4 with native audio.

Can Veo 3.1 animate a logo? A real test

"Veo 3.1 logo" is one of the most common ways people reach this post, so we ran the use case instead of describing it. On October 19, 2026 we sent our own logo (a 1024x1024 PNG with a transparent background) to Veo 3.1 Lite Relaxed as the start frame, through the UnificAlly MCP, at the cheapest settings. This is the unedited output:

• Model: google/veo-3.1-lite-relaxed, start_image_url set to the logo PNG, aspect_ratio 16:9, duration 4, resolution 720p, seed 9626.
• Prompt: "Logo reveal animation: the logo sits centered on a clean dark background. Thin lines of emerald light trace its outline, the shape assembles from scattered glowing particles, settles into place with a soft bounce, then a subtle lens flare sweeps across. Smooth motion graphics style, camera fixed. AUDIO: a short rising synth swell and a soft whoosh on the settle."
• Cost: $0.075, flat for the 4 second clip, audio included.

What worked: the mark stayed crisp and correctly proportioned for all four seconds, the green outline trace arrived as prompted, and the particle burst reads as a motion-graphics reveal rather than a photoreal scene. What to plan for: the transparent background rendered as black (fine here, since the prompt asked for dark), the clip opens on the still logo for roughly the first second before anything moves, and the model ran the prompt in reverse order, tracing first and dissolving into particles at the end instead of assembling from them. For a reveal that ends on a clean logo, describe the final frame last and keep the particle language out of the closing beat.

Practical settings for logo work: a flat PNG on a solid background, 16:9 or 9:16 to match the placement, 4 seconds (longer only pads the hold), Lite Relaxed to iterate on the prompt, then Fast at $0.30 for the final. Upscale the keeper to 1080p for $0.025 or 4K for $0.60 rather than generating every draft at full resolution.

Veo 3.1 vs Grok Imagine 1.5 Video vs Kling 4.0 for a logo clip

The two image-to-video models most often searched alongside Veo for this job, priced on UnificAlly for a short logo animation. Veo bills per video; the other two bill per second, so a 5 second clip is shown.

Veo 3.1 is the cheapest of the three for a 4 to 8 second logo clip and the only one that reaches 4K; pick Grok Imagine when you want 1080p native with an end frame, and Kling 4.0 when the logo has to hold inside a longer single shot.

How much does the Veo 3.1 API cost?

UnificAlly bills the selected Veo tier once per generated video: 4-, 6-, and 8-second requests cost the same, and the price changes only with resolution. Google's direct Gemini API bills each output second, so our flat rate is below Google's direct price on every generation tier, and the saving grows with duration. These are our current rates for every tier and resolution:

Two add-on endpoints sit alongside generation. Extend follows the base model you pick, and Upscale is a flat rate per video:

Generate an eight-second Veo 3.1 video from $0.075.

How much does Veo 3 cost?

Searching for "Veo 3 pricing" (or "veo3 api pricing", the same question without the space) usually lands you on Veo 3.1 numbers, so here is the older model on its own. Google bills Veo 3 per output second on the Gemini API, at the same per-second rates it charges for Veo 3.1, so there is no price reason to stay on Veo 3.

Veo 3.1 replaced it as the current generation and adds the Lite variant, reference images on Fast, Lite, and Lite Relaxed, Scene Extension, and 4K upscaling. If you are budgeting a new project, price it on Veo 3.1: from $0.075 per video on UnificAlly, flat for up to eight seconds.

How to use Veo 3.1 on UnificAlly

The API is async: POST a generation, then poll a task endpoint until the MP4 is ready.

const API = 'https://api.unifically.com';
const headers = {
  Authorization: `Bearer ${process.env.UNIFICALLY_API_KEY}`,
  'Content-Type': 'application/json',
};

const start = await fetch(`${API}/v1/tasks`, {
  method: 'POST',
  headers,
  body: JSON.stringify({
    model: 'google/veo-3.1-fast',
    input: {
      prompt: 'Aerial shot of a coastal cliff at golden hour, gulls circling overhead, waves crashing below',
      aspect_ratio: '16:9',
      duration: 8,
    },
  }),
}).then((r) => r.json());

while (true) {
  await new Promise((r) => setTimeout(r, 3000));
  const task = await fetch(`${API}/v1/tasks/${start.data.task_id}`, { headers }).then((r) => r.json());
  if (task.data.status === 'completed') {
    console.log(task.data.output.video_url);
    break;
  }
  if (task.data.status === 'failed') throw new Error(task.data.error_message);
}

Change model for the variant you want: google/veo-3.1-lite, google/veo-3.1-quality or google/veo-3.1-lite-relaxed. Extending a clip is google/veo-3.1-extend with the source task_id, and upscaling is google/veo-3.1-upscale with a resolution of 1080p or 4k (or pass that resolution on the generation request and the upscale runs inside the same task). The polling endpoint is the same for every Veo task.

Things to know about Veo 3.1

• Generating at Quality before iterating. Lock the prompt and framing on Lite Relaxed first. Failed tasks are not billed, but a video that completes and misses the brief is. That miss costs $1.20 on Quality and $0.075 on Lite Relaxed.
• Using reference-image mode on the wrong variant. Reference images work on Fast, Lite, and Lite Relaxed. Quality does not accept them. Use start / end frame mode there instead.
• Forgetting Extend needs a finished task ID. Extend is a separate endpoint that takes the prior task ID plus the base model. You cannot extend a video that has not finished generating.
• Upscaling everything by default. Upscale 4K is $0.60 per video. Use it as a finishing pass on the videos that survived review, not on every generation.
• Treating 4K as production-locked. Google still labels 4K as preview on Vertex. Expect occasional capacity or quality variance vs 1080p output.

Veo 3.1 FAQ

What is Veo 3.1?

Veo 3.1 is Google's text-to-video and image-to-video model. It generates 4 to 8 second 24 FPS MP4 videos at 720p, 1080p, or 4K with synchronized native audio, in 16:9 or 9:16 aspect ratios.

How much does Veo 3.1 cost on UnificAlly?

Generation runs from $0.075 per 720p video for Lite Relaxed up to $1.20 for Quality, with Lite at $0.15 and Fast at $0.30. Extend follows the base model's rate. Upscale 1080p is $0.025 and Upscale 4K is $0.60. The pricing page lists every resolution.

How much does Veo 3 cost?

Google bills Veo 3 per output second on the Gemini API, at the same per-second rates as Veo 3.1, so new projects should price on Veo 3.1 instead: it starts at $0.075 per video on UnificAlly, flat for up to eight seconds.

Does Veo 3.1 generate audio?

Yes. All three Veo 3.1 variants generate synchronized audio (speech, sound effects, and ambience) inside the same MP4 as the video. There is no separate audio call.

What is the longest Veo 3.1 video I can generate?

A single Veo 3.1 generation returns 4, 6, or 8 seconds. To go longer, use Veo 3.1 Extend with the prior task ID and a chosen base model to continue the video.

Can Veo 3.1 animate a logo from a PNG?

Yes. Pass the PNG as start_image_url on any variant and describe the motion in the prompt; the test above used Lite Relaxed at $0.075 and kept the mark crisp for the whole clip. Use a solid background in the file, since transparency renders as black, and treat the first second as a hold on the still logo.

What prompt works for a Veo 3.1 logo animation?

Name the background, the single effect you want (an outline trace, a particle assemble, a light sweep), the camera ("camera fixed") and the audio, and state the final frame last. The exact prompt from our test is above; the one change we would make is dropping the particle language from the ending so the reveal lands on a clean logo.

Is Veo 3.1 free or unlimited anywhere?

No. Google bills Veo 3.1 per output second on the Gemini API, and UnificAlly bills a flat rate per video. What you can do is try it free: every new UnificAlly account starts with a $0.50 signup balance, enough for 6 Lite Relaxed videos at 720p.

Which variant should I start with?

Start on Lite Relaxed at $0.075 to lock the prompt and framing. Reference images and voice presets already work there. Move to Fast at $0.30 for quicker turnaround and for most final videos. Pay $1.20 for Quality only when Fast falls short on a shot: it costs several times as much and drops reference-image support.

Related reading on Veo 3.1

• Veo 3.1 model page: live playground and full parameter reference.
• Gemini Omni 1.1 Flash vs Veo 3.1: how Veo compares against Google's newer video model on pricing, references, and Arena rank.
• Veo 3.1 vs SeeDance 2.0: head-to-head comparison and pricing.
• Kling 2.6 and MiniMax Hailuo: other video APIs on UnificAlly.
• Nano Banana 2: pair with Veo 3.1 for image-to-video pipelines.