Google AI models for your agent: Veo, Nano Banana, Lyria and Gemini
Use Google's media models from your AI agent: Veo 3.1 and Gemini Omni Flash for video, Nano Banana for images, Lyria for music and Gemini TTS for voice. You need no Google Cloud project or API key. This page also lists tools that read Google Search, Maps, News and Trends data.
Use any of these from your AI Agent, with no Google account or API key. Your AI Agent works out the exact price, runs the tool from your balance and tells you what it cost. Failed uses are free.
Connect your AI AgentAll Google tools and prices
Google: Veo 3.1
$1.30 per 5-second clip
VideoThe tool you openedProven · 100% successGoogle's state-of-the-art video generation model, built for maximum visual fidelity in final production cuts.
Google: Veo 3.1 Fast
$0.52 per 5-second clip
VideoProven · 100% successGoogle's mid-tier video generation model balancing speed and quality.
Google: Veo 3.1 Lite
$0.195 per 5-second clip
VideoProven · 100% successGoogle's most cost-effective video generation model, designed for high-volume applications and rapid iteration.
Google Gemini Image to Video
$0.26 per 5-second clip
VideoMixed resultsBring a still image to life, or interpolate between a starting and an ending frame. Returns an MP4 video artifact (24 fps, 3-10 s, native audio) with a signed download link. Supports one or two public image URLs (PNG, JPEG, WebP, HEIC, GIF), 360p-4k output, 16:9 or 9:16, motion and camera direction in the prompt. Suited for: product shots, illustrations and photos to motion, first-to-last-frame transitions, loops.
Google Gemini Reference to Video
$0.26 per 5-second clip
VideoMixed resultsGenerate a new video featuring the people, objects, or style shown in reference media instead of animating a frame. Returns an MP4 video artifact (24 fps, 3-10 s, native audio) with a signed download link. Supports up to 6 reference images and 3 reference clips (max 3 s each, audio ignored), <IMAGE_REF_N> / <VIDEO_REF_N> prompt tags, 360p-4k, 16:9 or 9:16. Suited for: consistent characters across shots, product placement, brand-style clips.
Google Gemini Text to Video
$0.26 per 5-second clip
VideoMixed resultsTurn a text prompt into a short video with synchronized audio (speech, music, ambience). Returns an MP4 video artifact (24 fps, 3-10 s) with a signed download link. Supports 360p / 720p / 1080p / 4k output, 16:9 or 9:16, timed events in natural language ("after 3 seconds ..."), multi-shot storyboards, on-screen text, and single-continuous-shot prompting. Suited for: social clips, ads and product b-roll, explainers, concept previews.
Google Gemini Extend Video
$0.26 per 5-second clip
VideoNewContinue an existing video seamlessly: the model uses the last seconds of the source as context and generates what happens next, keeping motion, characters, and audio coherent. Returns an MP4 video artifact (24 fps, source plus 3-10 s, native audio) with a signed download link. Supports one public source clip of at most 10 s, up to 3 reference images for new characters, scene cuts and audio direction in the prompt, 360p-4k output. Suited for: lengthening generated clips, adding a closing beat, chaining scenes.
Google: Gemini 3 Pro Image (Nano Banana Pro)
$0.195 per image
ImageProven · 99% successGenerate or edit one image with Gemini 3 Pro Image at 1K, 2K or 4K on Google's own API, from a prompt and optional reference image URLs; the image returns inline as base64.
Google: Gemini 3.1 Flash Image (Nano Banana 2)
$0.065 per image
ImageNewGenerate or edit one image with Gemini 3.1 Flash Image at 512px, 1K, 2K or 4K on Google's own API, from a prompt and optional reference images; the image returns inline as base64.
Google: Gemini 3.1 Flash Lite Image (Nano Banana 2 Lite)
$0.052 per image
ImageNewGenerate or edit one 1K image with Gemini 3.1 Flash Lite Image on Google's own API, the cheapest Gemini image model; the image returns inline as base64.
Google: Gemini 3.8 Flash TTS
$0.065 per voice clip
VoiceNewSpeak a text in one of 30 prebuilt voices, or a two-speaker dialogue, with Gemini 3.8 Flash TTS on Google's own API; the audio returns inline as base64 WAV (24 kHz mono).
Google: Gemini 3.8 Flash-Lite TTS
$0.0455 per voice clip
VoiceNewSpeak a text in one of 30 prebuilt voices, or a two-speaker dialogue, with Gemini 3.8 Flash-Lite TTS on Google's own API; the audio returns inline as base64 WAV (24 kHz mono).
Google: Lyria 3 Clip
$0.052 per track
MusicProven · 100% successCompose a 30-second music clip from a text prompt with Lyria 3 Clip on Google's own API; the MP3 returns inline as base64.
Google: Lyria 3.5
$0.104 per track
MusicProven · 100% successCompose a full song (about three minutes) from a text prompt with Lyria 3.5 on Google's own API; the MP3 returns inline as base64 with its lyrics or section markers.
Business reviews from Google and other sites (async task)
$0.002 per call
DataProven · 100% successThis endpoint provides results from the “Reviews” element of Google SERPs, including not only Google user reviews but also reviews from other reputable sources (e.g., TripAdvisor, Yelp, Trustpilot).
Domain metric trends for product categories
$0.1607 per call
DataProven · 100% successThis endpoint will provide you with dynamics of change in metrics of domains relevant to the specified product and service categories.
Get Google autocomplete suggestions
$0.0013 per call
DataProven · 100% successExpand a partial Google query into ranked autocomplete suggestions.
Google Ads history by domain — ad copy and keywords
$0.039 per 10 rows
DataProven · 100% successGoogle Ads a domain has run over time, with ad copy and the keywords it ran against
Google Ads keyword ideas for a site, by domain
$0.117 per call
DataProven · 100% successNote that Google Ads Keywords Data API is based on the latest version of the Google Ads API that has replaced legacy Google AdWords API.
Google Ads traffic forecast for keywords and bid
$0.117 per call
DataProven · 100% successGoogleAdsAdTrafficByKeywordsLive
Google Ads Transparency ads by advertiser (async task)
$0.0008 per call
DataProven · 100% successGoogle Ads Search provides information on ads that are run by advertisers on Google Ads.
Google Ads Transparency advertisers by keyword (async task)
$0.0008 per call
DataProven · 100% successGoogle Ads Advertisers provides information on advertisers that run campaigns on Google Ads based on the Ads Transparency platform.
Google advertiser's running ads — Ads Transparency Center
$0.0195 per call
DataProven · 100% successAds a Google advertiser is running now, from the Ads Transparency Center
Google AI Mode answer for a query
$0.0195 per call
DataProven · 100% successGoogle's conversational AI Mode answer for a query
Starting prices. Prices can vary with length and quality. Your AI Agent works out the exact price, runs the tool from your balance and tells you what it cost. Failed uses are free.
What do you want your agent to do?
Make a video clip with sound
Veo 3.1 Fast balances speed and quality for most clips. Veo 3.1 is for final cuts, and Veo 3.1 Lite for drafts and volume.
Keep a character or product across shots
The Google Gemini video tools (Gemini Omni Flash) build a clip around up to 6 reference images, or extend a clip you already have.
Make or edit an image
Nano Banana 2 handles most images, up to 4K. Nano Banana Pro is Gemini 3 Pro Image, and Nano Banana 2 Lite is the cheapest, at 1K.
Compose a song or jingle
Lyria 3.5 composes a full song of about three minutes from a prompt. Lyria 3 Clip makes a 30-second clip.
Read a script aloud
Gemini 3.8 Flash TTS reads text in one of 30 voices, or as a dialogue between two speakers.
Read Google search results
Organic results, Maps places, News, Trends and Scholar are on this page too. Our SERP API page compares them.
How to choose the best Google AI tool or MCP for you
Veo tier
Veo 3.1 for final cuts, Veo 3.1 Fast for most clips, Veo 3.1 Lite for drafts and high volume. All three make clips from a text prompt, with sound unless you switch it off.
Veo or Gemini Omni Flash
Pick the Google Gemini video tools to animate a photo, build a clip around reference images or clips, or extend a video. They make clips of 3 to 10 seconds.
Nano Banana tier
Nano Banana 2 for most images, Nano Banana Pro when quality matters most, and Nano Banana 2 Lite at 1K for cheap drafts.
Search data: routed or single source
Tools marked Best of N providers try several sources in turn, which helps when one is down. Single-source tools return that source's own fields.
| If you need | Choose | Today's price |
|---|---|---|
| A final ad clip with sound | Veo 3.1 | |
| Many short drafts | Veo 3.1 Lite | |
| A clip that matches your reference photos | Google Gemini Reference to Video | |
| A product photo that moves | Google Gemini Image to Video | |
| A 4K image at the best quality | Nano Banana Pro | |
| A short jingle for an ad | Lyria 3 Clip | |
| Google Trends interest for your keywords | Google Trends interest over time |
Quick picks: Veo 3.1 Fast for clips, Nano Banana 2 for images, Lyria 3.5 for songs, Gemini 3.8 Flash TTS for voice-overs.
Why use Google's models through Agensi?
Going to Google directly means a Google Cloud project or Gemini API key, with billing and quotas you set up yourself. Through Agensi your agent runs Veo, Gemini Omni Flash, Nano Banana, Lyria and Gemini TTS with no key, from the same balance as Kling, ElevenLabs and our data tools. It runs each job from your balance, tells you what it cost, and keeps the files in your Dashboard for 30 days.
| What you get | Official MCP per brand | Own API key or community server | Agensi |
|---|---|---|---|
| Accounts | One per brand | One per brand | One |
| API keys | Per brand, or a sign-in | Per brand, kept by you | None |
| Payment | A plan or credits per brand | Per brand | One balance, per use |
| Spending control | Varies | Up to you | Limits per use, day and month, or ask first |
| Several sources in one answer | Connect several servers | Several servers and keys | One connection |
| Skills for the whole job | No | No | Yes, from the marketplace |
When another way is the better choice. Use Google directly if you already build on Google Cloud or the Gemini API, need settings our tools don't expose, or want Google's own quotas and data terms. Google Cloud also publishes open-source MCP servers for its media models, which you run with your own Google Cloud project; Google says they are not an officially supported product.
Set up in your AI agent
Connect your AI agent to Agensi once, sign in and click Allow. After that it can use every tool: it runs one from your balance and tells you what it cost. No API keys or provider accounts.
- Open Settings, then Connectors, then Browse connectors and add Agensi (or Add custom connector and paste https://mcp.agensi.io/mcp/auth).
- Sign in to Agensi and click Allow. One agent per account: connecting a new one disconnects the old one.
- Ask for what you want, for example: "Use Agensi to make a launch kit for our coffee app: a hero image with Nano Banana 2, a short clip of the app on a phone with Veo 3.1 Fast, and a 30-second jingle with Lyria." Top up from $5 if your balance is low; failed uses are free.
- Run: claude mcp add agensi --transport http --url https://mcp.agensi.io/mcp/auth
- Sign in to Agensi and click Allow. One agent per account: connecting a new one disconnects the old one.
- Ask for what you want, for example: "Use Agensi to make a launch kit for our coffee app: a hero image with Nano Banana 2, a short clip of the app on a phone with Veo 3.1 Fast, and a 30-second jingle with Lyria." Top up from $5 if your balance is low; failed uses are free.
- Open chatgpt.com/plugins, click Add, then Add custom MCP server. Paste https://mcp.agensi.io/mcp/auth and choose OAuth. Create it, click Connect, then sign in to Agensi and click Allow.
- Sign in to Agensi and click Allow. One agent per account: connecting a new one disconnects the old one.
- Ask for what you want, for example: "Use Agensi to make a launch kit for our coffee app: a hero image with Nano Banana 2, a short clip of the app on a phone with Veo 3.1 Fast, and a 30-second jingle with Lyria." Top up from $5 if your balance is low; failed uses are free.
- Add an HTTP MCP server named "agensi" with url https://mcp.agensi.io/mcp/auth to .cursor/mcp.json.
- Sign in to Agensi and click Allow. One agent per account: connecting a new one disconnects the old one.
- Ask for what you want, for example: "Use Agensi to make a launch kit for our coffee app: a hero image with Nano Banana 2, a short clip of the app on a phone with Veo 3.1 Fast, and a 30-second jingle with Lyria." Top up from $5 if your balance is low; failed uses are free.
- Add to ~/.codex/config.toml: [[mcp]] name = "agensi", type = "url", url = "https://mcp.agensi.io/mcp/auth"
- Sign in to Agensi and click Allow. One agent per account: connecting a new one disconnects the old one.
- Ask for what you want, for example: "Use Agensi to make a launch kit for our coffee app: a hero image with Nano Banana 2, a short clip of the app on a phone with Veo 3.1 Fast, and a 30-second jingle with Lyria." Top up from $5 if your balance is low; failed uses are free.
Grok, VS Code, GitHub Copilot, Cline, Kiro and other agents with remote MCP and sign-in work too: see the setup guide.
What it costs: a worked example
"Use Agensi to make a launch kit for our coffee app: a hero image with Nano Banana 2, a short clip of the app on a phone with Veo 3.1 Fast, and a 30-second jingle with Lyria."
1 × Hero image
1 × Short clip with sound
1 × 30-second jingle
Your agent works out the exact price for your request and tells you what it cost.
Combine Google AI tools with skills
- Veo3 Cinematic Video Prompt GeneratorWrites cinematic Veo prompts with shot lists, camera direction and sound design.
- AI Image Generator: On-Brand Images, No API KeysMakes product shots, ads, thumbnails and icons in one consistent style, with drafts before finals.
- Local Biz Outreach FinderFinds local businesses with outdated websites through Google Maps and drafts outreach that names the problems.