Start creating

Leap API

Veo 3.1 Lite APIGoogle's model, through Leap

The lowest-cost Veo, for drafts and volume. One Leap key and one balance run it and every other model, priced per call in dollars.

First $5 top-up, no card fee.

  • One key for every model
  • Every call quoted first
  • A failed call costs nothing
curl https://api.tryleap.ai/v1/generations \  -H "x-api-key: $LEAP_API_KEY" \  -H "content-type: application/json" \  -H "prefer: wait=60" \  -d '{    "model": "google/veo-3.1-lite",    "input": {      "prompt": "Steam rises gently from the spaghetti, warm sunlight drifts across the wooden table, slow push-in",      "aspect_ratio": "16:9",      "duration": 4,      "resolution": "720p",      "audio": true    }  }' # Video often outlasts the wait and answers "queued" or "running".# Put its "id" in GENERATION_ID and read it again until it is done:# curl https://api.tryleap.ai/v1/generations/$GENERATION_ID -H "x-api-key: $LEAP_API_KEY"

Set LEAP_API_KEY and send it. With prefer: wait=60 the answer holds the result when the call finishes within a minute; a longer one is read again by its ID.

Model ID
google/veo-3.1-lite
Price per call
$0.164 to $0.88
This call
A 4-second 720p clip with sound costs $0.272.
First top-up
A first top-up of $5, with no fee, covers 18 calls like it.

What it makes

Made with Veo 3.1 Lite

Real Veo 3.1 Lite runs on Leap. Each one passed Leap's media quality check before it was shown.

  • Desert jellyfish, generated on Leap

    “The colossal jellyfish pulses and drifts slowly across the dusk sky above the desert town, its glowing tendrils sway and trail over the rooftops, the tiny people on the street look up, the camera tilts up slowly. Dreamlike, cinematic.”

  • Forest library, generated on Leap

    “Smooth cinematic drone approach: the camera glides forward and slowly descends toward the circular timber-and-glass library in the misty pine forest, morning fog drifts between the trees, tiny people walk along the rooftop garden ring, warm windows glow, sunrise light. Stable aerial shot.”

  • Observation deck, generated on Leap

    “Science fiction: a slow cinematic dolly forward through the quiet white observation deck toward the crew member standing at the panoramic window, the giant ringed planet drifts slowly outside, soft light shifts across the floor. Smooth, majestic.”

  • Chrome ribbon, generated on Leap

    “Abstract motion design: the liquid chrome ribbon slowly folds, ripples and twists through the dark room while the camera orbits gently around it, crisp mirror reflections of the strip lights slide across its surface, small caustic sparks on the floor. Smooth, premium, seamless motion.”

  • Forest living room, generated on Leap

    “Interior film: the sheer linen curtains billow gently in a soft breeze, sunlight and window shadows shift slowly across the oak floor, mist drifts among the pines outside, the camera dollies slowly sideways through the living room. Calm, architectural, no people.”

  • The spaghetti food photo, animated: steam and drifting sunlight

    “Steam rises gently from the spaghetti, warm sunlight drifts across the wooden table, slow push-in”

The answer

What comes back

A generation. Check status first: succeeded has the file in output, a signed link that works for 24 hours, so download what you keep. failed has error and failure_cause, and costs nothing. usage.cost_usd is what the call was charged.

200 OK, trimmed
{  "id": "gen_...",  "object": "generation",  "model": "google/veo-3.1-lite",  "status": "succeeded",  "output": [    {      "type": "video",      "url": "https://api.tryleap.ai/files/..."    }  ],  "error": null,  "usage": {    "cost_usd": "0.272"  }}

Your own photo

Start from an image

Upload the image to POST /v1/files and pass the ID it returns in first_frame. Inputs take file IDs, not URLs. Files and uploads covers video and sound.

curl, with jq
# Upload the photo (PNG, JPEG or WebP, up to 4 MB) and keep its ID.FILE_ID=$(curl -s "https://api.tryleap.ai/v1/files?filename=photo.jpg" \  -H "x-api-key: $LEAP_API_KEY" \  -H "content-type: image/jpeg" \  --data-binary @photo.jpg | jq -r .id) # Then run the model with it.jq -n --arg file "$FILE_ID" '{  "model": "google/veo-3.1-lite",  "input": {    "prompt": "Steam rises gently from the spaghetti, warm sunlight drifts across the wooden table, slow push-in",    "aspect_ratio": "16:9",    "duration": 4,    "resolution": "720p",    "audio": true,    "first_frame": $file  }}' \  | curl https://api.tryleap.ai/v1/generations \    -H "x-api-key: $LEAP_API_KEY" \    -H "content-type: application/json" \    -H "prefer: wait=60" \    -d @- # Still "queued" or "running" after the wait? Read it again by its "id".

Inputs

What Veo 3.1 Lite takes

Only prompt is needed; everything else has a default. The same schema is public, with no key, at api.tryleap.ai/v1/public/models/google/veo-3.1-lite.

Promptprompt
Text, up to 4,000 characters, required
First framefirst_frame
An imageAn image the video starts from. It is cropped to the video's shape.
Aspect ratioaspect_ratio
16:9, 9:16. Default: 16:9
Durationduration
4, 6, 8 s. Default: 4 s
Resolutionresolution
720p, 1080p. Default: 720p
Soundaudio
On or off. Default: onGenerate dialogue, effects and music with the video.

Pricing

Price per call

A 4-second 720p clip with sound costs $0.272. A first top-up of $5, with no fee, covers 18 default calls. Prices are the provider's list price plus our margin (35% on most models, less on the dearest video), read from the catalog, and a quote gives the exact price of any input for free.

Veo 3.1 Lite and its family

A free quote
curl https://api.tryleap.ai/v1/quotes \  -H "x-api-key: $LEAP_API_KEY" \  -H "content-type: application/json" \  -d '{    "model": "google/veo-3.1-lite",    "input": {      "prompt": "Steam rises gently from the spaghetti, warm sunlight drifts across the wooden table, slow push-in",      "aspect_ratio": "16:9",      "duration": 4,      "resolution": "720p",      "audio": true    }  }'

How it works

How the Veo 3.1 Lite API works

Every model takes the same request, a model ID and its input, and results, prices, failures and limits work the same way for all of them.

  • Wait for it, or hear when it ends

    prefer: wait=60 holds the request until the result is ready, for up to a minute. A longer run is read again by its ID, or a signed webhook tells your server when it ends.

    prefer: wait=60 / "webhook": "https://..."

    In the docs
  • Failed calls cost nothing

    The price is held when a call starts and charged only if it succeeds. A failed or refused call comes back with its failure_cause, and the hold is released.

    "status": "failed" / "failure_cause": "provider_refused"

    In the docs
  • The price before the call

    POST /v1/quotes takes the same body as a generation and returns its exact price, with the input checked, for free. Every result carries what it was charged.

    POST https://api.tryleap.ai/v1/quotes / "cost_usd"

    In the docs
  • Rate limits

    600 requests a minute per API key and 300 per IP address. A 429 carries Retry-After with the seconds to wait.

    RateLimit-Remaining / Retry-After

    In the docs
  • Safe retries

    Send an idempotency key and a retry after a dropped connection returns the same generation instead of starting a second one.

    idempotency-key: <uuid>

    In the docs
  • Batches

    POST /v1/batches starts up to 50 calls in one request, priced and held together, so either all start or none do.

    POST https://api.tryleap.ai/v1/batches

    In the docs

MCP

Or let your agent call it.

Leap's MCP server lets Claude Code, Claude, VS Code and other MCP clients run Veo 3.1 Lite, read its inputs and fetch the result, on your balance. Signing in happens in the browser, so there is no key to paste.

Add Leap to Claude Code
claude mcp add --transport http leap https://app.tryleap.ai/api/mcp

Claude Code signs you in through the browser the first time it calls Leap.

Teach your coding agent the Leap API
curl -fsSL https://www.tryleap.ai/install.sh | sh

Installs the Leap skill for every coding agent it finds: which endpoint to call, how to read a model's inputs, when to wait and when to poll.

Questions

Veo 3.1 Lite API questions

How much does the Veo 3.1 Lite API cost?
A 4-second 720p clip with sound costs $0.272. By length, resolution and sound, a call costs $0.164 to $0.88. That is the provider's list price plus our margin, the same as in the studio. POST /v1/quotes prices any input for free before you run it.
Can I try the Veo 3.1 Lite API for free?
No. API keys run on paid credit, so a key's first call needs a top-up, and quotes are free. A 4-second 720p clip with sound costs $0.272. A first top-up of $5, with no fee, covers 18 default calls.
Do I pay for calls that fail?
No. The price is held when a call starts and charged only if it succeeds. A call that fails, or that the model's safety filter refuses, comes back with status "failed" and a failure_cause, and the hold is released.
Is this Google's own API?
No. Leap is a separate service: it sends your call to Google's model and gives you what it makes, so you need no Google account. One Leap key runs Veo 3.1 Lite and every other model in the catalog, from one balance.
What are the rate limits?
600 requests a minute per API key and 300 a minute per IP address. A batch starts up to 50 calls in one request. A 429 says how long to wait in its Retry-After header.
Can an AI agent call it?
Yes. Leap's MCP server lets Claude Code, Claude, VS Code and other MCP clients find Veo 3.1 Lite, read its inputs, run it and fetch the result on your balance. The client signs you in through the browser, so there is no key to paste.

Build with Veo 3.1 Lite.

Keys run on paid credit, and the first top-up has no fee. The same key runs every model on Leap.

Get an API key