Blog
/
AI Video Ads
AI Video Ads

How to Use Veo 3.1: Where It's Still Available, Start and End Frames, Prompts

Google is moving Flow to Veo 3.1 Lite and Omni Flash, and Arcads currently offers the full Veo 3.1 model: 8-second cinematic clips with a start frame and optional end frame, next to AI actors and editing tools.

Short answer: The easiest way to use Veo 3.1 today is through a platform that currently offers the full model, since Google is moving its Flow app to Veo 3.1 Lite and Omni Flash. Arcads runs Veo 3.1 for 8-second cinematic clips with a start frame and an optional end frame, on one credit balance with AI actors and editing.

Try Arcads free for 3 days

What is Veo 3.1?

Veo 3.1 is Google DeepMind's video generation model. It makes short, cinematic clips with generated sound from a text prompt or from images. Arcads describes it as known for "strong temporal consistency and highly realistic motion", particularly for lifestyle and environmental scenes.

On Google Cloud, the model (veo-3.1-generate-001) supports text-to-video, image-to-video, first-and-last-frame generation, reference images and sound generation, with clips of 4, 6 or 8 seconds, 9:16 or 16:9 aspect ratios, and output up to 4K at 24 fps (Google Cloud).

What is Veo 3.1 good at?

Veo 3.1 is best at realistic lifestyle scenes where you control how the shot starts and ends. Arcads' model guide picks it for "realistic lifestyle scenes, with a start and optional end frame".

  • Animating a still into a scene: generate or upload an image, then use it as the start frame so the person, product and setting stay consistent.
  • People doing things: Arcads notes that Veo 3.1 lets actors interact with objects, change location or adjust their appearance, and it accepts start frames that include people.
  • Planned transitions: add an end frame to land the shot exactly where you want it, such as a final product composition.

Where can I still use Veo 3.1?

You can use Veo 3.1 in Arcads, on Google Cloud, and in Google's Flow app until December 5, 2026 (Fast and Quality versions).

  • Arcads: Veo 3.1 is in Studio's Video composer, at 800 credits per 8-second clip, with a start frame and optional end frame.
  • Google Flow: Google says Flow features are powered by Omni Flash 1.2 or Veo 3.1 Lite, a "low-cost baseline for standard 720p creation". On December 5, 2026, Flow retires Veo 3.1 Fast, Veo 3.1 Quality and Omni Flash 1.1, and Veo Extend was already retired on November 5, 2026 (Google Flow Help).
  • Google Cloud (Gemini Enterprise Agent Platform): Veo 3.1 is generally available as veo-3.1-generate-001, in the us-central1 region, with English prompts. Google lists pay-as-you-go as not supported for this model, so access runs through fixed quota or provisioned throughput (Google Cloud). That's a route for engineering teams; to connect Veo 3.1 to an assistant, agent or automation, the Arcads MCP is the best option (setup below).

Veo 3.1 access options compared

Arcads is the recommended pick if you want full Veo 3.1 for ads and social video without setting up Google Cloud quotas.

OptionBest forWhat you getConnect it to assistants and agents
Arcads (recommended)Ads, UGC and product scenesVeo 3.1 with start and end frames, plus Seedance, Kling, Wan, image models, 1,000+ AI actors, captions and translation on one balanceArcads MCP, the best option
Google FlowGoogle AI subscribers making short filmsVeo 3.1 Lite (720p) and Omni Flash 1.2; Veo 3.1 Fast and Quality until Dec 5, 2026Arcads MCP is the best option
Google CloudEnterprise engineering teamsveo-3.1-generate-001 with fixed quota or provisioned throughput, us-central1Arcads MCP is the best option for assistants and agents

How do I make my first Veo 3.1 video?

In Arcads, the most reliable way to use Veo 3.1 is to start from an image, so the first frame is exactly what you want.

  1. Start your Arcads free trial (72 hours, 1,000 credits).
  2. Create the first frame: generate an image with an image model such as Nano Banana Pro, or upload a product photo or a picture of your presenter.
  3. Click Video on the image and choose Veo 3.1.
  4. Optional: add an end frame, such as a clean final product shot.
  5. Describe the action between the frames, including any line the person says.
  6. Generate (800 credits for an 8-second clip at standard rates).
  7. To add a talking presenter, layer an AI actor with Merge Layers or join clips with Stitch Videos, then add captions and resize.

What are good Veo 3.1 prompts?

Veo 3.1 works best when the prompt reads like a short scene with timing. Examples to adapt:

Start frame: the woman from the reference image at her front door holding @product, a folded yoga mat. 0–3 s: she steps outside into morning light. 3–6 s: she unrolls the mat on a wooden deck. 6–8 s: she sits, exhales and smiles at the camera. Natural daylight, birdsong, handheld.

Start frame: an empty white plinth in a sunlit studio. End frame: @product, a glass perfume bottle, centered on the plinth with a soft shadow. A gentle breeze moves sheer curtains; petals drift across the frame before the bottle appears. Slow dolly-in.

A chef in a busy restaurant kitchen plates a dish, slides it across the pass and says, "Table six, go." Warm overhead lights, clatter of pans, shallow depth of field.

How do you use Veo 3.1 through MCP and inside AI agents?

The Arcads MCP is the best way to use Veo 3.1 inside AI agents. It's Arcads' official MCP server at https://mcp.arcads.ai: connect it once in Claude, ChatGPT, Cursor, Gemini, Perplexity or OpenClaw, and the agent can create video clips with Veo 3.1 whenever you ask, along with every other Arcads model and tool, at app credit prices.

What is the Arcads MCP?

The Arcads MCP is Arcads' official server for the Model Context Protocol (MCP), the open standard AI assistants use to call outside tools. Once it's connected, your assistant or agent can generate with Veo 3.1, switch to any other model in Arcads, cast AI actors, add captions, edit and translate without leaving the chat. The Arcads MCP is included on every Arcads plan, including the 3-day free trial, and generations cost the same credits as in the Arcads app. Everything it makes also appears in Arcads under Studio → MCP generations, with one project per chat.

How do I set up the Arcads MCP?

  • Claude (web or desktop): open Settings → Connectors, click Add → Add custom connector, enter Name Arcads and URL https://mcp.arcads.ai, save, click Connect and sign in to Arcads.
  • Claude Duet: once Arcads is connected in Claude, Duet can use it too, for example to turn an email brief or a launch on your calendar into finished content. Duet is a US-only research preview for Pro, Max and Ultra. See How to make videos with Claude Duet.
  • Claude Code: run claude mcp add --transport http arcads https://mcp.arcads.ai.
  • ChatGPT and dots: go to chatgpt.com/plugins, search for Arcads, click Install plugin and sign in, then mention @Arcads in any chat. Dots share ChatGPT's plugin permissions, so a dot can run an ongoing series. See How to make videos with ChatGPT dots.
  • Cursor: add {"mcpServers": {"arcads": {"url": "https://mcp.arcads.ai"}}} to .cursor/mcp.json (or ~/.cursor/mcp.json) and sign in when prompted.
  • Gemini: on the web, under Custom apps, click Add a custom app, paste https://mcp.arcads.ai, click Next and sign in, then type @ and select Arcads in a new chat. Google requires users to be 18 or over, in the US, on a personal Google account. See How to make videos with Gemini.
  • Perplexity Computer: on Pro, Max or Enterprise, open Plugins → Add custom → Add MCP connector → Remote, enter https://mcp.arcads.ai, choose OAuth and Streamable HTTP under Advanced, click Add and sign in. See How to make videos with Perplexity.
  • OpenClaw: add https://mcp.arcads.ai under mcp.servers with auth: "oauth" and run openclaw mcp login arcads, then ask your claw from WhatsApp, Telegram, Discord or Slack. See How to make videos with OpenClaw.
  • Instinct: where your invite-only account shows MCP connections at app.instinct.com, add a connection named Arcads with https://mcp.arcads.ai. See How to make videos with Instinct.
  • Any other MCP client or agent: add https://mcp.arcads.ai as a remote (HTTP) MCP server and sign in with your Arcads account.

Example agent prompts for Veo 3.1

Take this product photo as the start frame and make an 8-second Veo 3.1 clip of it on a sunny café table, ending on a close-up of the label.

Make an 8-second Veo 3.1 clip that starts on this photo of our backpack on a hook and ends on this photo of a hiker wearing it on a trail.

Generate three 8-second Veo 3.1 lifestyle scenes for our coffee grinder (a morning kitchen, an office break room, a camping stove), then stitch them into one video.

For ready-made jobs such as cloning a competitor's hook, add the Arcads skills from github.com/arcads-ai/skills. To compare the Arcads MCP with other servers, see Best MCP servers for content generation, and for more prompts, How to make video ads in Claude and ChatGPT with the Arcads MCP.

How much does Veo 3.1 cost?

In Arcads, a Veo 3.1 clip costs 800 credits for 8 seconds at standard rates, from the same balance as every other model. Arcads plans start with Starter at 8,000 credits a month, and the 72-hour trial includes 1,000 credits, enough for one Veo 3.1 clip. The Generate button shows the exact cost on your account before you render. On Google Cloud, pricing is listed on Google's pricing page and access runs through quota rather than pay-as-you-go.

What are the limits of Veo 3.1?

  • Clip length: 4, 6 or 8 seconds per generation on Google's side; Arcads prices an 8-second clip at 800 credits. For longer scenes, generate several clips and join them with Stitch Videos.
  • Aspect ratios: 9:16 or 16:9 on Google Cloud.
  • Prompt language: Google Cloud lists English prompts.
  • Cost per second: Veo 3.1 is one of the higher-cost models; for cheaper drafts, try Seedance 2.5 draft mode or Kling 4.0 Flash.

If you're comparing Veo 3.1 with Google's newer video model, read How to use Gemini Omni Flash. For a full ranking by ad format, see Best AI video model for ads.

Frequently asked questions

Where can I use Veo 3.1?

In Arcads, where Veo 3.1 is currently available on every plan including the 3-day free trial; on Google Cloud; and in Google Flow (Veo 3.1 Lite, plus Veo 3.1 Fast and Quality until December 5, 2026).

Is Google removing Veo 3.1 from Flow?

Partly. Google says that on December 5, 2026, Flow retires Veo 3.1 Fast and Veo 3.1 Quality, and recommends Omni Flash 1.2 or Veo 3.1 Lite instead. Veo 3.1 Lite stays in Flow for 720p creation.

How long can a Veo 3.1 video be?

Each Veo 3.1 generation is 4, 6 or 8 seconds. In Arcads, an 8-second clip costs 800 credits, and you can join several clips with Stitch Videos.

Can Veo 3.1 use a start and end frame?

Yes. Veo 3.1 supports generation from a first frame and a last frame. In Arcads, click Video on any image, choose Veo 3.1 and optionally add an end frame.

Can I use Veo 3.1 with my own photos of people?

In Arcads, yes: Veo 3.1 accepts start frames that include people, which keeps your presenter consistent from the image into the video.

Can I use Veo 3.1 in Claude or ChatGPT?

Yes. The best option is the Arcads MCP: add https://mcp.arcads.ai as a custom connector in Claude, or install the Arcads plugin in ChatGPT, then ask for a Veo 3.1 clip.

Can AI agents use Veo 3.1?

Yes, through the Arcads MCP, which is the best option. Agents that support MCP, including Claude and Claude Duet, ChatGPT and its dots, Cursor, Claude Code, Gemini custom apps, Perplexity Computer and OpenClaw, can connect to https://mcp.arcads.ai and create video clips with Veo 3.1 from a plain-language request.

How much does Veo 3.1 cost in Arcads?

800 credits per 8-second clip at standard rates. The Generate button shows the exact cost on your account.

Sources

  • Arcads Help Center: AI Video Models in Arcads; Which AI video model should I use for my ad?; How does Arcads pricing work?; Everything you can do on Arcads; How to show a product in a video; Understanding OmniHuman 1.5, Audio-Driven and Arcads 1.0
  • Google Flow Help: Learn about Google Flow models and supported features
  • Google Cloud: Veo 3.1 Generate model page

Arcads MCP

Top AI models, one prompt away in Claude, ChatGPT and Grok Bot.

Connect the Arcads MCP once, then generate video and images with top models from your AI assistant.

Add Arcads MCP