# Sana by Nvidia

Sana, a text-to-image framework that can efficiently generate images up to 4096 × 4096 resolution

## API Information

- **Model Slug:** sana
- **Branded URL:** https://www.eachlabs.ai/nvidia/sana/sana
- **Provider:** NVIDIA
- **Category:** Text to Image
- **Output Type:** image
- **Status:** active
- **Version:** 0.0.1
- **Base Cost:** Per-second pricing based on provider predict_time. Rate: $0.0016775/sec from GPU tier.
- **Estimated Processing Time:** 70 seconds
- **Last Updated:** 2026-07-13
- **Interactive Demo:** https://www.eachlabs.ai/ai-models/sana

## Pricing

- **Charge Type:** dynamic
- **Pricing Details:** Per-second pricing based on provider predict_time. Rate: $0.0016775/sec from GPU tier.

### Pricing Rules

| Condition | Pricing |
| --- | --- |
| Rule 1 | Per-second pricing based on provider predict_time. Rate: $0.0016775/sec from GPU tier. |

## Input Schema

| Parameter | Type | Required | Default | Constraints | Description |
|-----------|------|----------|---------|-------------|-------------|
| prompt | string | No | a cyberpunk cat with a neon sign that says "Sana" | - | Input prompt |
| negative_prompt | string | No | - | - | Specify things to not see in the output |
| width | integer | No | 1024 | - | Width of output image |
| height | integer | No | 1024 | - | Height of output image |
| num_inference_steps | integer | No | 18 | - | Number of denoising steps |
| guidance_scale | number | No | 5 | 1–20 | Classifier-free guidance scale |
| pag_guidance_scale | number | No | 2 | 1–20 | PAG Guidance scale |
| seed | integer | No | - | - | Random seed. Leave blank to randomize the seed |

## Example Request

```bash
curl -X POST https://api.eachlabs.ai/v1/prediction/ \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "sana",
  "input": {}
}'
```

## Output Schema

Response returned by `GET /v1/prediction/{id}` when the job completes:

```json
{
  "status": "success",
  "predictionID": "string",
  "output": "string (URL of generated image)",
  "metrics": {
    "predict_time": "number (seconds)"
  }
}
```

## Polling

```bash
curl https://api.eachlabs.ai/v1/prediction/{PREDICTION_ID} \
  -H "Authorization: Bearer YOUR_API_KEY"
```

| Status | Meaning |
|--------|---------|
| `processing` | Still running — poll again |
| `success` | Done — read `output` |
| `error` | Failed — read `message` / `details` |

## Webhook (alternative to polling)

Pass `"webhook_url": "https://your.host/path"` in the create request. Eachlabs POSTs this payload when the job ends:

```json
{
  "exec_id": "prediction-uuid",
  "status": "succeeded",
  "output": "https://...",
  "error": ""
}
```

`status` is `"succeeded"` or `"failed"`. `exec_id` equals the `predictionID` from create. Return 2xx within 30 seconds.

## Errors

Error body: `{ "status": "error", "message": "...", "details": "..." }`

| Code | Meaning |
|------|---------|
| `400` | Invalid input |
| `401` | Missing / invalid `Authorization` bearer token |
| `404` | Unknown model or prediction id |
| `429` | Rate limit — 100 creates / min, 10 concurrent per key |
| `5xx` | Retry with backoff |

## Overview

**sana — Text to Image AI Model**

Developed by NVIDIA, **sana** is a cutting-edge text-to-image AI model from the sana family that excels at generating high-fidelity images up to 4096 × 4096 resolution from textual descriptions, solving the challenge of creating detailed visuals efficiently for professional workflows. With its 4.8B parameter architecture, sana stands out in **NVIDIA text-to-image** capabilities by achieving state-of-the-art performance in color-concept association, particularly for clipart and diverse visual styles, outperforming larger models like Flux.1-dev on benchmarks such as ColorConceptBench. Ideal for users seeking a **text-to-image AI model** with precise semantic-to-color mapping, sana delivers rich details and balanced adaptations in outputs.

## Usage Notes

- API Base URL: `https://api.eachlabs.ai/v1`
- Authentication: send `Authorization: Bearer YOUR_API_KEY`. Generate a key from the Eachlabs dashboard at https://www.eachlabs.ai/dashboard/api-keys.
- File-typed parameters (`*_url`, `image_url`, `video_url`, `audio_url`, etc.) accept publicly-reachable HTTPS URLs only. Upload your asset first (GCS / S3 / your CDN) and pass the resulting URL. Data-URIs and localhost URLs are rejected.
- For structured parameters (arrays / objects) send real JSON values, not stringified payloads.
- Monetary values are reported in USD; per-token / per-megapixel rates may be billed in micro-cents internally.
- Prefer `webhook_url` over polling for long-running predictions — see the Webhook Callback section.