Name: SANA-Sprint 1.6B API: One-Step Text to Image by NVIDIA
Brand: magicapi
SKU: api-magicapi-one-step-diffusion-api-nvidia-sana-sprint-1-6b
Availability: InStock
Author: API Market

Shashank Agarwal

# ⚡ Text-to-Image Generator API (NVIDIA SANA-Sprint 1.6B)

## Overview
SANA-Sprint 1.6B is a text-to-image model from NVIDIA. Its developer describes it as one-step diffusion with continuous-time consistency distillation: it produces an image in 1 to 4 sampling steps.

Send a text `prompt`. Each request returns the URL of one image, from 256 to 4096 pixels on each side.

## Features
- **Few sampling steps**: `inference_steps` from 1 to 4 (default 2).
- **Image size**: `width` and `height` from 256 to 4096 pixels (default 1024 x 1024).
- **Timestep tuning**: `intermediate_timesteps` (1 to 1.5, default 1.3) applies when `inference_steps` is 2.
- **Guidance**: `guidance_scale` from 1 to 20 (default 4.5).
- **Output format**: `jpg` (default), `webp` or `png`, with `output_quality` for jpg and webp.
- **Seed**: set `seed` to 0 or above to repeat a result; the default `-1` randomizes it.

## Use Cases
1. **Fast drafts**: quick image drafts while iterating on a prompt.
2. **Interactive apps**: image generation inside apps where users wait for the result.
3. **High-volume generation**: many images for catalogs, tests or datasets at a low price per request.
4. **Concept art and illustrations**: scenes and characters from a text description.

## Visual Examples
### Example Input
Prompt: "a tiny astronaut hatching from an egg on the moon", 1024 x 1024 pixels, 2 inference steps, `jpg` output.

```json
{
  "seed": -1,
  "width": 1024,
  "height": 1024,
  "prompt": "a tiny astronaut hatching from an egg on the moon",
  "output_format": "jpg",
  "guidance_scale": 4.5,
  "output_quality": 80,
  "inference_steps": 2,
  "intermediate_timesteps": 1.3
}
```

### Example Output
![SANA-Sprint 1.6B output: a tiny astronaut hatching from an egg on the moon](https://blog.api.market/wp-content/uploads/2026/10/sana-sprint-1-6b-output-2595hmby-api-market.jpg)

## Input Parameters
| Field | Type | Required | Default | Allowed values | Description |
| --- | --- | --- | --- | --- | --- |
| `prompt` | string | No | `a tiny astronaut hatching from an egg on the moon` |  | Input prompt |
| `width` | integer | No | `1024` | `256` to `4096` | Width of the output image in pixels |
| `height` | integer | No | `1024` | `256` to `4096` | Height of the output image in pixels |
| `inference_steps` | integer | No | `2` | `1` to `4` | Number of sampling steps |
| `intermediate_timesteps` | number | No | `1.3` | `1` to `1.5` | Intermediate timestep value. Only used when inference_steps is 2; recommended values are 1.0 to 1.4 |
| `guidance_scale` | number | No | `4.5` | `1` to `20` | CFG guidance scale |
| `seed` | integer | No | `-1` |  | Seed value. Set a value below 0 to randomize the seed |
| `output_format` | string | No | `jpg` | `webp`, `jpg`, `png` | Format of the output image |
| `output_quality` | integer | No | `80` | `0` to `100` | Quality when saving the output image, from 0 to 100. 100 is best quality, 0 is lowest quality. Not used for png outputs |

No field is required. If you send no `prompt`, the model uses its default prompt `a tiny astronaut hatching from an egg on the moon`.

## Pricing
- **Pay As You Go (PAYG) pricing**: you only pay for what you use.
- **Price**: $0.014 per API unit.
- **1 API unit = 1 request with up to 8 seconds of processing.** A request that takes longer uses one unit per started block of 8 seconds (for example, 10 seconds of processing uses 2 units, $0.028).
- **Example cost**: the example took 0.6 seconds of processing, which is 1 unit, $0.014.
- **Failed or cancelled predictions are not billed.**
- **GET requests to check prediction status** are free and don't count toward API unit usage.
- **No monthly subscription fee.**

## API Documentation

### Base URL
All API requests go to: `https://prod.api.market/api/v1/magicapi/one-step-diffusion-api-nvidia-sana-sprint-1-6b`

### Authentication
Send your api.market API key in the `x-api-market-key` header:
```
x-api-market-key: YOUR_API_MARKET_KEY
```

### Asynchronous Processing
**IMPORTANT**: This API is asynchronous. The flow is:
1. Send a POST request to `/predictions`. A successful request returns **201 Created** with a prediction `id` and a `status` of `starting` or `processing`.
2. Poll GET `/predictions/{id}` with that ID.
3. Keep polling while `status` is `starting` or `processing`.
4. Stop when `status` is `succeeded` (read `output`), `failed` or `canceled` (read `error`).

A polling interval of 1 second and an overall timeout of 600 seconds (10 minutes) work well.

### Endpoints

#### Create a Prediction
```bash
curl -X POST "https://prod.api.market/api/v1/magicapi/one-step-diffusion-api-nvidia-sana-sprint-1-6b/predictions" \
  -H "Content-Type: application/json" \
  -H "x-api-market-key: YOUR_API_MARKET_KEY" \
  -d '{
    "version": "038aee6907b53a5c148780983e39a50ce7cd0747b4e2642e78387f48cf36039a",
    "input": {
      "seed": -1,
      "width": 1024,
      "height": 1024,
      "prompt": "a tiny astronaut hatching from an egg on the moon",
      "output_format": "jpg",
      "guidance_scale": 4.5,
      "output_quality": 80,
      "inference_steps": 2,
      "intermediate_timesteps": 1.3
    }
  }'
```

Response (201 Created):
```json
{
  "id": "2595hmby7xrne0d1ccvry4pe68",
  "version": "038aee6907b53a5c148780983e39a50ce7cd0747b4e2642e78387f48cf36039a",
  "status": "starting",
  "created_at": "2026-10-22T10:45:43.784Z"
}
```

#### Check Prediction Status
```bash
curl -X GET "https://prod.api.market/api/v1/magicapi/one-step-diffusion-api-nvidia-sana-sprint-1-6b/predictions/{id}" \
  -H "x-api-market-key: YOUR_API_MARKET_KEY"
```

Response when the prediction has finished (200 OK):
```json
{
  "id": "2595hmby7xrne0d1ccvry4pe68",
  "status": "succeeded",
  "output": "https://blog.api.market/wp-content/uploads/2026/10/sana-sprint-1-6b-output-2595hmby-api-market.jpg",
  "error": null,
  "created_at": "2026-10-22T10:45:43.784Z",
  "started_at": "2026-10-22T10:47:04.144Z",
  "completed_at": "2026-10-22T10:47:04.735Z"
}
```

`output` is a single URL string pointing to the generated image.

### Status Codes
- **201 Created**: prediction created (POST `/predictions`). This is the normal success response.
- **200 OK**: prediction details returned (GET `/predictions/{id}`).
- **400 Bad Request**: invalid input, for example a `width` below 256 or an `inference_steps` above 4.
- **401 Unauthorized**: missing or invalid API key.
- **404 Not Found**: no prediction with that ID.
- **429 Too Many Requests**: rate limit exceeded.
- **500 Internal Server Error** or **503 Service Unavailable**: temporary server problem; retry later.

## Rate Limits
All plans allow 10 requests per second. Requests above that return `429 Too Many Requests`; back off before retrying and honour any `Retry-After` header. Polling a prediction with GET is free but still counts toward the per-second limit, so poll every 1 to 5 seconds rather than in a tight loop.

## Error Handling
- Check the HTTP status code of every request and read the response body for the error message.
- A prediction can also end with `status` set to `failed`; the `error` field then explains why. Failed predictions are not billed.
- Retry 429, 500 and 503 responses with exponential backoff. Fix the input before retrying a 400.

## Implementation Guide
### Example Code

#### JavaScript
```javascript
const apiKey = "YOUR_API_MARKET_KEY";
const baseUrl = "https://prod.api.market/api/v1/magicapi/one-step-diffusion-api-nvidia-sana-sprint-1-6b";

async function createAndWaitForPrediction(input) {
  const response = await fetch(`${baseUrl}/predictions`, {
    method: "POST",
    headers: {
      "Content-Type": "application/json",
      "x-api-market-key": apiKey
    },
    body: JSON.stringify({ version: "038aee6907b53a5c148780983e39a50ce7cd0747b4e2642e78387f48cf36039a", input })
  });

  if (response.status !== 201) {
    throw new Error(`API error: ${response.status} ${await response.text()}`);
  }

  const prediction = await response.json();
  return pollForResults(prediction.id);
}

const delay = (ms) => new Promise((resolve) => setTimeout(resolve, ms));

async function pollForResults(predictionId) {
  const maxTimeout = 600000;
  const pollInterval = 1000;
  const startTime = Date.now();

  while (Date.now() - startTime < maxTimeout) {
    const response = await fetch(`${baseUrl}/predictions/${predictionId}`, {
      headers: { "x-api-market-key": apiKey }
    });

    if (!response.ok) {
      throw new Error(`API error: ${response.status} ${await response.text()}`);
    }

    const prediction = await response.json();

    if (prediction.status === "succeeded") {
      return prediction.output;
    }

    if (prediction.status === "failed" || prediction.status === "canceled") {
      throw new Error(`Prediction ${prediction.status}: ${prediction.error || "Unknown error"}`);
    }

    await delay(pollInterval);
  }

  throw new Error("Prediction timed out after 10 minutes");
}

createAndWaitForPrediction({
  "seed": -1,
  "width": 1024,
  "height": 1024,
  "prompt": "a tiny astronaut hatching from an egg on the moon",
  "output_format": "jpg",
  "guidance_scale": 4.5,
  "output_quality": 80,
  "inference_steps": 2,
  "intermediate_timesteps": 1.3
}).then((output) => console.log(output));
```

#### Python
```python
import time
import requests

API_KEY = "YOUR_API_MARKET_KEY"
BASE_URL = "https://prod.api.market/api/v1/magicapi/one-step-diffusion-api-nvidia-sana-sprint-1-6b"


def create_and_wait_for_prediction(input_data):
    headers = {"Content-Type": "application/json", "x-api-market-key": API_KEY}
    response = requests.post(
        f"{BASE_URL}/predictions",
        headers=headers,
        json={"version": "038aee6907b53a5c148780983e39a50ce7cd0747b4e2642e78387f48cf36039a", "input": input_data},
    )

    if response.status_code != 201:
        raise Exception(f"API error: {response.status_code} {response.text}")

    return poll_for_results(response.json()["id"])


def poll_for_results(prediction_id):
    max_timeout = 600
    poll_interval = 1
    headers = {"x-api-market-key": API_KEY}
    start_time = time.time()

    while time.time() - start_time < max_timeout:
        response = requests.get(f"{BASE_URL}/predictions/{prediction_id}", headers=headers)

        if response.status_code != 200:
            raise Exception(f"API error: {response.status_code} {response.text}")

        prediction = response.json()

        if prediction["status"] == "succeeded":
            return prediction["output"]

        if prediction["status"] in ("failed", "canceled"):
            raise Exception(f"Prediction {prediction['status']}: {prediction.get('error') or 'Unknown error'}")

        time.sleep(poll_interval)

    raise Exception("Prediction timed out after 10 minutes")


print(create_and_wait_for_prediction({
    "seed": -1,
    "width": 1024,
    "height": 1024,
    "prompt": "a tiny astronaut hatching from an egg on the moon",
    "output_format": "jpg",
    "guidance_scale": 4.5,
    "output_quality": 80,
    "inference_steps": 2,
    "intermediate_timesteps": 1.3
}))
```

## FAQ
- **How many steps should I use?**
  - 1 to 4. The default is 2. When you use 2 steps, `intermediate_timesteps` (recommended 1.0 to 1.4) also applies.
- **What sizes can I generate?**
  - Any `width` and `height` from 256 to 4096 pixels. The default is 1024 x 1024.
- **How do I get the same image again?**
  - Send the same input with `seed` set to 0 or above. The default `-1` picks a random seed.
- **How much does one image cost?**
  - $0.014 for a request with up to 8 seconds of processing. The example took 0.6 seconds.
- **What if my prediction fails?**
  - Failed predictions are not billed. Read the `error` field, adjust the input and try again.

## Contact Us
If you have any questions, reach out to us through the chat on the bottom right of the page. You can also email our support team at hello@magicapi.com.


Generate images from text with NVIDIA SANA-Sprint 1.6B, a one-step diffusion model that samples in 1 to 4 steps. Pay as you go, no monthly fee.