Start creating

Leap API

Sana 1.5 4.8B APINVIDIA's model, through Leap

NVIDIA's efficient image model, at a cent a megapixel. One Leap key and one balance run it and every other model, priced per call in dollars.

Get an API keyRead the quickstart

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: $LEAP_API_KEY" \  -H "content-type: application/json" \  -H "prefer: wait=60" \  -d '{    "model": "nvidia/sana-1.5-4.8b",    "input": {      "prompt": "A silk scarf in the wind on a ferry deck",      "aspect_ratio": "1:1"    }  }' # Video often outlasts the wait and answers "queued" or "running".# Put its "id" in GENERATION_ID and read it again until it is done:# curl https://api.tryleap.ai/v1/generations/$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
nvidia/sana-1.5-4.8b
Price per call
$0.0135
This call
An image costs $0.0135.
First top-up
A first top-up of $5, with no fee, covers 370 calls like it.

What it makes

Made with Sana 1.5 4.8B

Real Sana 1.5 4.8B runs on Leap. Each one passed Leap's media quality check before it was shown.

More on the Sana 1.5 4.8B page
  • An isometric bedroom studio at night, a real run on Leap

    An isometric bedroom studio at night

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": "nvidia/sana-1.5-4.8b",  "status": "succeeded",  "output": [    {      "type": "image",      "url": "https://api.tryleap.ai/files/..."    }  ],  "error": null,  "usage": {    "cost_usd": "0.0135"  }}

Inputs

What Sana 1.5 4.8B 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/nvidia/sana-1.5-4.8b.

Promptprompt
Text, up to 4,000 characters, required
Aspect ratioaspect_ratio
1:1, 3:4, 9:16, 4:3, 16:9. Default: 1:1
Imagesn
1 to 4. Default: 1
Num Inference Stepssettings.num_inference_steps
1 to 50. Default: 18The number of inference steps to perform.
Guidance scale (CFG)settings.guidance_scale
0 to 20. Default: 5The CFG (Classifier Free Guidance) scale is a measure of how close you want the model to stick to your prompt when looking for a related image to show you.
Style Namesettings.style_name
(no style), Cinematic, Photographic, Anime, Manga, Digital art, Pixel art, Fantasy art, Neonpunk, 3d model. Default: (no style)The style to generate the image in.
Negative promptnegative_prompt
Text, up to 2,000 charactersWhat the image should not contain.
Seedseed
0 to 4294967295The same seed and input give the same image.

Pricing

Price per call

An image costs $0.0135. A first top-up of $5, with no fee, covers 370 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.

A free quote
curl https://api.tryleap.ai/v1/quotes \  -H "x-api-key: $LEAP_API_KEY" \  -H "content-type: application/json" \  -d '{    "model": "nvidia/sana-1.5-4.8b",    "input": {      "prompt": "A silk scarf in the wind on a ferry deck",      "aspect_ratio": "1:1"    }  }'

How it works

How the Sana 1.5 4.8B 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 Sana 1.5 4.8B, read its inputs and fetch the result, on your balance. Signing in happens in the browser, so there is no key to paste.

Connect an agentThe agent guide
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

Sana 1.5 4.8B API questions

How much does the Sana 1.5 4.8B API cost?
An image costs $0.0135. 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 Sana 1.5 4.8B API for free?
No. API keys run on paid credit, so a key's first call needs a top-up, and quotes are free. An image costs $0.0135. A first top-up of $5, with no fee, covers 370 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 NVIDIA's own API?
No. Leap is a separate service: it sends your call to NVIDIA's model and gives you what it makes, so you need no NVIDIA account. One Leap key runs Sana 1.5 4.8B 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 Sana 1.5 4.8B, 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 Sana 1.5 4.8B.

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