Image model API

Sana Sprint API

SANA-Sprint 1.6B is best for ultra-fast, high-quality text-to-image generation, producing 1024×1024 images in just 0.1 seconds. The model is a One-Step Diffusion with Continuous-Time Consistency Distillation developed by NVIDIA, designed to handle various natural language processing tasks with high efficiency which also includes multiple specialized endpoints, each optimized for a particular type of task. This allows users to achieve better results by choosing the most suitable endpoint for their needs.

Model id
sana-sprint
Takes
Text (required)
Makes
Image
Endpoint
POST /api/v1/images/generations
Made by
NVIDIA
Mode
Synchronous

Call Sana Sprint

Base URL https://payload.rentprompts.com/api/v1. Replace the placeholder with your key.

Model sana-sprint

POST /api/v1/images/generations

curl https://payload.rentprompts.com/api/v1/images/generations \
  -H "Authorization: Bearer rp_live_YOUR_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "sana-sprint",
  "prompt": "A lighthouse at dusk, watercolor",
  "n": 1
}'

Replace rp_live_YOUR_KEY with your key, ideally via the RENTPROMPTS_API_KEY environment variable. Keys are shown only once, so they are never filled in here. Get your API key →

What a typical call costs

Worked out from Sana Sprint's published price (4.6 J / image). You pay only for successful results, from your Joule balance.
  • 1 image4.6 Joules
  • 4 images18.4 Joules

Send requests to POST /api/v1/images/generations. Sana Sprint answers synchronously: the result comes back in the response to the same request.

Settings

Optional parameters this model accepts (pass them in settings on /v1/run, or as top-level fields where OpenAI defines them).
NameTypeDefaultRange / options
inference_stepsinteger21 – 4
intermediate_timestepsfloat1.30.5 – 1.5
guidance_scalefloat4.51 – 20
output_qualityinteger800 – 100
Sana Sprint API — Pricing & Code Examples | RentPrompts