promptstringrequired
The prompt for image generation
GPT Image 1.5 Text to Image
openai/gpt-image-1.5Gpt Image 1.5 is OpenAI's advanced text-to-image AI model. Create photorealistic images, illustrations, and concept art from natural language descriptions with exceptional detail and prompt adherence.
Try the model
Playground
Input
The prompt for image generation
Additional Settings More
Customize your input with more control.
Output aspect ratio: 1:1 (1024x1024), 3:2 (1536x1024) or 2:3 (1024x1536). Allowed values: 1:1, 3:2, 2:3.
Output format for the images Allowed values: jpeg, png.
Background for the generated image Allowed values: auto, transparent, opaque.
Quality for the generated image Allowed values: low, medium, high.
ResultExample
What would you like to do next?
Examples
Select an example to load its inputs and result into the playground.
- Open result ↗
Input
{ "aspect_ratio": "1:1", "prompt": "a red apple on a white table, studio light", "quality": "low" } - Open result ↗
Input
{ "prompt": "create a realistic image taken with iphone at these coordinates 41°43′32″N 49°56′49″W 15 April 1912" }
Human preference
Arena
Elo ratings from blind side-by-side votes, compared with other image and video models.
Rankings sourced from Artificial Analysis Arena
- Leaderboard
- Text to Image
- Rank
- #9 of 106
- Elo
- 1123 ±11
- Gap to #1
- −99
Text-to-image arena: people pick the better of two images generated from the same prompt, without seeing the model names.
- #4Nano Banana 2.11176±12
- #5Grok Imagine Image 2.01166±12
- #6MAI-Image-2.61166±12
- #7Nano Banana 2 (Gemini 3.1 Flash Image)1140±10
- #8Muse Image1127±11
- #9GPT Image 1.5 (high)1123±11
- #10MAI-Image-2.6-Flash1119±12
- #11Nano Banana Pro (Gemini 3 Pro Image)1118±10
- #12MAI-Image-2.51118±11
- #13FLUX 3 Image1117±12
GPT Image 1.5 Text to Image
GPT Image 1.5 text-to-image, with transparent-background output for logos and stickers.
Fields
| Field | Type | Default | Notes |
|---|---|---|---|
prompt | string, required | — | Up to 32,000 characters. |
aspect_ratio | 1:1 / 3:2 / 2:3 | 1:1 | 1:1, 3:2, or 2:3; non-square sizes cost more. |
output_format | jpeg / png | png | Output file format. |
background | auto / transparent / opaque | auto | transparent returns a PNG with alpha. |
quality | low / medium / high | high | Higher quality costs more; high is the default. |
Billing
Price depends on quality and shape, plus $0.005 per started 1,000 prompt characters:
| Quality, short prompt | 1:1 | 3:2 or 2:3 |
|---|---|---|
| low | $0.014 | $0.018 |
| medium | $0.039 | $0.056 |
| high | $0.138 | $0.205 |
Failed runs are not charged.
Prompting
- Use
background: transparentwith PNG output for cut-out assets.
Limits
- Three shapes only: 1:1, 3:2, 2:3.
Also on SandBase
Related: openai/gpt-image-1.5/edit, openai/gpt-image-2 (newer).
Start building
Send your first request
Submit this model through the SandBase Unified Run API.
# The quoted heredoc keeps Unicode and shell metacharacters unchanged.
result=$(curl --fail-with-body --silent \
-X POST "https://api.sandbase.ai/v1/run" \
-H "Authorization: Bearer $SANDBASE_API_KEY" \
-H "Content-Type: application/json" \
--data-binary @- <<'SANDBASE_JSON'
{
"model": "openai/gpt-image-1.5",
"prompt": "create a realistic image taken with iphone at these coordinates 41°43′32″N 49°56′49″W 15 April 1912",
"quality": "high",
"background": "auto",
"aspect_ratio": "1:1",
"output_format": "png"
}
SANDBASE_JSON
)
run_id=$(printf '%s' "$result" | jq -r .id)
for attempt in $(seq 1 120); do
status=$(printf '%s' "$result" | jq -r .status)
case "$status" in completed|failed|timeout) break ;; esac
sleep 2
result=$(curl --fail-with-body --silent \
-H "Authorization: Bearer $SANDBASE_API_KEY" \
"https://api.sandbase.ai/v1/run/$run_id")
done
status=$(printf '%s' "$result" | jq -r .status)
[ "$status" = completed ] || { echo "Generation ended: $status" >&2; exit 1; }
printf '%s\n' "$result"2. Authentication
Create a SandBase API key and set it in your server environment. All requests use Bearer authentication.
export SANDBASE_API_KEY="YOUR_API_KEY"Keep the key on your server. Do not expose it in browser code or commit it to a repository.
3. Queue
Submit a request
POST to /v1/run with this model ID and its inputs. The request example above includes submission and polling.
Fetch request status and result
Use the returned run ID to poll until the status is completed, failed or timeout. Read output only after completed.
curl "https://api.sandbase.ai/v1/run/$RUN_ID" \
-H "Authorization: Bearer $SANDBASE_API_KEY"4. Files
Hosted files
Pass a publicly accessible file URL in the model’s image, video or audio field. Supported formats and limits are shown beside each Playground input.
Uploading images
Use the upload or replace control on supported image fields in the Playground. Video URL fields accept a hosted driving video; they do not imply video-upload support.
5. Schema
Input
qualitystring
Quality for the generated image
Default: "high"
Possible values: "low", "medium", "high"
backgroundstring
Background for the generated image
Default: "auto"
Possible values: "auto", "transparent", "opaque"
aspect_ratiostring
Output aspect ratio: 1:1 (1024x1024), 3:2 (1536x1024) or 2:3 (1024x1536).
Default: "1:1"
Possible values: "1:1", "3:2", "2:3"
output_formatstring
Output format for the images
Default: "png"
Possible values: "jpeg", "png"
{
"model": "openai/gpt-image-1.5",
"prompt": "create a realistic image taken with iphone at these coordinates 41°43′32″N 49°56′49″W 15 April 1912",
"quality": "high",
"background": "auto",
"aspect_ratio": "1:1",
"output_format": "png"
}Output
A completed run exposes its result in output. The following is the model’s saved example, not a new generation.
[
{
"source": "Self organization completed prediction",
"source_url": "https://www.sandbase.ai",
"url": "https://static.sandbase.ai/examples/091b2882-b0ce-44ed-bc7e-dc011d9ef03c/output/fcd85d3c-165b-4f66-9a8e-e5a593837462.png"
}
]