GPT Image 1.5 Text to Image API

openai/gpt-image-1.5/text-to-image

1024x1024 · 1024x1536 · 1536x1024

GPT Image 1.5 Text to Image transforms text prompts into high-fidelity visuals, featuring precise instruction adherence, accurate in-image typography, and photorealistic material textures. It preserves complex spatial layouts and lighting coherence while rendering vibrant scenes across square, portrait, and landscape dimensions.

Get API Key

Input

PromptRequired0/1000

SizeOptional

NOptional

OutputIdle

Generated images will appear here

Estimated cost: 2 × 1 = 2 credits · $0.010

2 credits ($0.010) per image, multiplied by n.

Continue using

GPT Image 1.5 Edit Kling O3 Image Text to Image Flux Schnell Text to Image

Examples

A four-panel comic page in a clean 2x2 grid with thin white gutters, warm hand-inked storybook style with soft watercolor fills. The same character appears in every panel: a small garden snail mail carrier with a teal spiral shell, a tiny red cap and a brown leather satchel. Panel 1: at a mushroom post office, the snail proudly takes a letter stamped EXPRESS; speech bubble: "Express delivery? Leave it to me!" Panel 2: light rain on clover leaves, the snail sliding on under a leaf umbrella; bubble: "Just a little drizzle..." Panel 3: the snail inching across a garden hose like a bridge at sunset; bubble: "Almost there!" Panel 4: winter snow on the ground at a frog's round wooden door, the frog in a scarf reading the letter; frog's bubble: "My birthday party... was last summer." Crisp, correctly spelled lettering in every bubble, consistent character design across panels, gentle humor, no logos, no watermark.

Photorealistic documentary photograph inside a small-town radio studio at 2 a.m. A middle-aged host with a short gray beard and headphones around his neck leans toward a vintage broadcast microphone, one hand resting on a worn analog mixing console with glowing amber VU meters. Above the studio window a red illuminated sign reads "ON AIR". Taped to the wall beside him is a handwritten index card with four lines: "NIGHT OWL SHOW", "2:00 Call-in: Rosa, Maple St.", "2:15 Fog report", "2:30 Lullaby hour". A shelf of cassette tapes whose spines carry only handwritten dates such as "MAR 94" and "OCT 96", a steaming enamel mug, a desk lamp casting warm tungsten light, cool blue streetlight through the window. Shallow depth of field, realistic skin texture, subtle film grain, every piece of text sharp and correctly spelled, no band or artist names, no brand names, no logos, no watermark.

An educational cross-section illustration of a beaver lodge in a forest pond, drawn like a clean natural-history textbook plate with soft watercolor and fine ink lines on off-white paper. The dome of sticks and mud rises above the water, and a cutaway reveals the inside. One adult beaver rests in a dry chamber above the waterline while a second beaver swims up through a submerged tunnel. Title at the top: "Inside a Beaver Lodge". Exactly five labels in neat black sans-serif text, each with a thin leader line pointing to the correct part: "Living Chamber", "Underwater Entrance", "Air Vent", "Winter Food Cache", "Mud and Stick Walls". Show a clear water surface line and a pile of leafy branches stored on the pond floor as the food cache. Accurate beaver anatomy, balanced layout with generous margins, no other text, no logos, no watermark.

REST API

Quick Start

This flow submits one valid GPT Image 1.5 Text to Image request, captures its task_id, and reads image URLs after the asynchronous task ends.

Connect to the Vidgo API

Create an API key, keep it on the server, and send it as Authorization: Bearer VIDGO_API_KEY.

Endpoint: POSThttps://api.vidgo.ai/api/generate/submit
Authentication: Authorization: Bearer VIDGO_API_KEY

Submit one image task

Send the current model ID, prompt to the unified submit endpoint. The example keeps only first-call fields.

Submit request

curl --request POST \
  --url "https://api.vidgo.ai/api/generate/submit" \
  --header "Authorization: Bearer $VIDGO_API_KEY" \
  --header "Content-Type: application/json" \
  --data '{
  "model": "openai/gpt-image-1.5/text-to-image",
  "input": {
    "prompt": "A serene mountain landscape at sunset.",
    "size": "1024x1024",
    "n": 1
  }
}'

Wait for the image result

Read data.task_id and poll only while status is not_started or running. Stop on both finished and failed.

Track status

GET https://api.vidgo.ai/api/generate/status/{task_id}

Poll every 2–5 seconds and back off on 429/5xx. Or provide top-level callback_url to receive a terminal-state callback.

not_startedrunningfinishedfailed

Submit response

{
  "code": 200,
  "data": {
    "task_id": "task-example",
    "status": "not_started",
    "created_time": "2026-09-25T08:00:00"
  }
}

Finished response

{
  "code": 200,
  "data": {
    "task_id": "task-example",
    "status": "finished",
    "created_time": "2026-09-25T08:00:00",
    "files": [
      {
        "file_url": "https://example.com/result.png",
        "file_type": "image"
      }
    ]
  }
}

Complete runnable polling example

Expand for the same payload end to end, including business-code, missing-task-ID, failed-state, unexpected-state, and network-error handling.

Complete runnable polling example

set -euo pipefail
: "${VIDGO_API_KEY:?Set VIDGO_API_KEY in your environment}"

REQUEST_BODY=$(cat <<'JSON'
{
  "model": "openai/gpt-image-1.5/text-to-image",
  "input": {
    "prompt": "A serene mountain landscape at sunset.",
    "size": "1024x1024",
    "n": 1
  }
}
JSON
)

SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  --request POST \
  --url "https://api.vidgo.ai/api/generate/submit" \
  --header "Authorization: Bearer $VIDGO_API_KEY" \
  --header "Content-Type: application/json" \
  --data "$REQUEST_BODY")

TASK_ID=$(printf '%s' "$SUBMIT_RESPONSE" | jq -r '.data.task_id // .task_id // empty')
if [ -z "$TASK_ID" ]; then
  printf 'Submit response did not include task_id:
%s
' "$SUBMIT_RESPONSE" >&2
  exit 1
fi

while true; do
  STATUS_RESPONSE=$(curl --silent --show-error --fail-with-body \
    --url "https://api.vidgo.ai/api/generate/status/$TASK_ID" \
    --header "Authorization: Bearer $VIDGO_API_KEY")
  STATUS=$(printf '%s' "$STATUS_RESPONSE" | jq -r '.data.status // .status // empty')

  case "$STATUS" in
    finished)
      printf '%s' "$STATUS_RESPONSE" | jq -r '(.data.files // .files // [])[]?.file_url'
      break
      ;;
    failed)
      printf '%s' "$STATUS_RESPONSE" | jq -r '.data.error_message // .error_message // "Generation failed"' >&2
      exit 1
      ;;
    not_started|running)
      sleep 2
      ;;
    *)
      printf 'Unexpected task status: %s
' "$STATUS" >&2
      exit 1
      ;;
  esac
done

Request Parameters

This table lists only public fields inside input. See Quick Start for top-level model and optional callback_url usage.

Field	Type	Required	Default	Description
input.prompt	string	Yes	–	Describe the image to generate using 1–1,000 characters, including at least one non-whitespace character.
input.size	string	No	1024x1024	Output image dimensions in pixels. Defaults to 1024x1024. 1024x1024, 1024x1536, 1536x1024.
input.n	integer	No	1	Number of output images: integer 1, 2, 3 or 4. Defaults to 1. 1, 2, 3, 4.

Response Fields

The submit response identifies the task. The status response supplies image files or failure details at a terminal state.

Field	Type	Description
code	integer	Business response code; 0 or 200 indicates success.
message	string	Optional human-readable response message.
data.task_id	string	Unique task ID used for status queries after submission.
data.status	string	not_started, running, finished, or failed.
data.created_time	string	Task creation timestamp.
data.progress	integer	Progress from 0–100 in status responses.
data.files[]	array	Generated files in returned order when finished.
data.files[].file_url	string	Direct generated-image URL.
data.files[].file_type	string	Image results are identified as image.
data.files[].watermark_url	string \| null	Optional watermarked-file URL when present.
data.error_message	string \| null	Readable failure reason for failed tasks.

Task Lifecycle

Only the first two states may be polled again. finished and failed are terminal.

not_started
Accepted and queued; wait before checking again.
running
Image generation is in progress; continue polling.
finished
Successful terminal state; validate files and read image URLs.
failed
Failure terminal state; read error_message and stop.

Polling and Errors

AuthenticationKeep a valid VIDGO_API_KEY on the server and send requests with Bearer authentication.
Validation400 indicates an invalid model ID, field, enum, length, or image count.
Polling intervalStart at 2–5 seconds, use exponential backoff for 429/5xx, and enforce an overall timeout.
Terminal statesRead image URLs from files after finished, or error_message after failed. Both states end polling.
Callback optionProvide a public top-level callback_url to receive a flat task object after finished or failed.
Network errorsDistinguish request timeout, network failure, and task failure. Retry the same query only when safe.

Model Specifications

Specification	Value	Details
Model	openai/gpt-image-1.5/text-to-image	Text-to-image generation.
size	1024x1024 / 1024x1536 / 1536x1024	Default: 1024x1024

GPT Image 1.5 Text to Image API documentation

GPT Image 1.5 Text to Image

GPT Image 1.5 Text to Image is OpenAI's flagship multimodal text-to-image generation model built on advanced transformer diffusion architecture. Featuring superior semantic understanding and multi-step prompt reasoning, it delivers native in-image typography, photorealistic lighting, and fine micro-texture rendering with generation speeds up to 4x faster than prior generations. The model natively outputs 1024x1024 square, 1024x1536 portrait, and 1536x1024 landscape dimensions, and generates up to 4 consistent variations per request for professional design, advertising, and digital production.

Why Choose GPT Image 1.5 Text to Image?

Deep Multimodal Reasoning & Multi-Subject LayoutsPowered by advanced multimodal reasoning, the model parses intricate multi-layered prompts to render complex scenes and multi-subject relationships with exceptional fidelity.
Native In-Image Typography & Clear SignageRenders crisp, legible English text on signage, packaging, labels, and posters without common artifacting or spelling distortions.
Photorealistic Micro-Textures & Ambient LightingFaithfully renders skin details, fabric textures, liquid reflections, and ambient diffuse lighting without plastic artifacts.
Parallel 1–4 Image Variation GenerationGenerates 1 to 4 distinct visual variations in a single request, accelerating creative concepting and design exploration.

Parameters

Parameter	Requirement	Description
prompt	Required	Describe the image to generate using 1–1,000 characters, including at least one non-whitespace character.
size	Optional	Output image dimensions in pixels. Defaults to 1024x1024. Default`1024x10241024x15361536x1024`
n	Optional	Number of output images: integer 1, 2, 3 or 4. Defaults to 1. Default`1234`

How to Use

Draft a Structured PromptDescribe the primary subject, visual style, spatial environment, and lighting (up to 1,000 characters). Enclose target in-image text in quotes.
Select Canvas DimensionsSpecify the size parameter based on your use case: 1024x1024 (square), 1024x1536 (portrait), or 1536x1024 (landscape).
Configure Image CountSet the n parameter from 1 to 4 images per generation (defaults to 1), with billing scaling linearly per image.
Submit and Retrieve VisualsPost the request to receive a unique task_id, then track status via polling or webhook callback to download your generated images.

Pricing

Each image costs 2 credits ($0.010). Total cost is multiplied by n.

Usage	Rate	Details
Standard generation	2 credits/image · $0.010/image	2 × n credits · $0.010 × n
n = 1 / 2 / 3 / 4	2 / 4 / 6 / 8 credits	$0.010 / $0.020 / $0.030 / $0.040

Best Use Cases

Brand Advertising & Social Media VisualsCreate striking promotional banners and social media campaign visuals with custom signage text and vivid lighting.
E-Commerce Product ShowcasesRender realistic commercial product staging with accurate depth of field and ambient lighting for merchandise.
Poster Headlines & Package DesignDesign creative event posters, typographic flyers, and packaging mockups with clear embedded textual labels.
Concept Art & Storybook IllustrationsTranslate creative story ideas into expressive digital art with cinematic mood, rich textures, and stylistic consistency.

Pro Tips

Structure prompts logically: define subject characteristics, composition, lighting ambiance, material textures, and any target text in order.
When rendering in-image text, enclose the desired English phrase in quotes (e.g., a coffee cup with the text "Morning Brew") and keep phrases concise.
Choose 1536x1024 for landscape banners and desktop wallpapers, 1024x1536 for mobile feeds and stories, and 1024x1024 for square avatars or merchandise.
Set n to 4 during early concept exploration to evaluate four distinct variations in a single generation round.

Notes

prompt is required and accepts 1 to 1,000 characters to guide composition, lighting, and style.
size supports 1024x1024 (square), 1024x1536 (portrait), and 1536x1024 (landscape), defaulting to 1024x1024.
n sets the number of parallel output variations from 1 to 4 (defaults to 1), with billing calculated as 2 credits ($0.010) multiplied by n.
This endpoint generates brand-new visuals directly from text prompts; for image editing, inpainting, or reference-based variations, select the GPT Image 1.5 Edit endpoint.

Related Models

Grok Imagine Image 2.0 Text to Image preview

Grok Imagine Image 2.0 Text to ImageGenerate crisp, high-fidelity images up to 2K from text prompts with Grok Imagine Image 2.0. Features designer-grade typography, precise prompt adherence, and versatile aspect ratios.

Grok Imagine Image 2.0 EditGenerate crisp, high-fidelity images up to 2K from text prompts with Grok Imagine Image 2.0. Features designer-grade typography, precise prompt adherence, and versatile aspect ratios.

Qwen Image 3.0 Text-to-ImageAlibaba Qwen Image 3.0 Standard and Pro generation and editing with eight aspect ratios, 1K or 2K output, and ordered one-to-three-image editing.

Qwen Image 3.0 Image EditAlibaba Qwen Image 3.0 Standard and Pro generation and editing with eight aspect ratios, 1K or 2K output, and ordered one-to-three-image editing.

Qwen Image 3.0 Pro Text-to-Image preview

Qwen Image 3.0 Pro Text-to-ImageAlibaba Qwen Image 3.0 Standard and Pro generation and editing with eight aspect ratios, 1K or 2K output, and ordered one-to-three-image editing.

Qwen Image 3.0 Pro Image EditAlibaba Qwen Image 3.0 Standard and Pro generation and editing with eight aspect ratios, 1K or 2K output, and ordered one-to-three-image editing.

Seedream 5.0 Pro Text-to-ImageThe ByteDance Seedream 5.0 Pro API generates 1K or 2K JPEG/PNG images from prompts and edits one to ten ordered HTTP(S) image inputs.

Seedream 5.0 Pro Image EditThe ByteDance Seedream 5.0 Pro API generates 1K or 2K JPEG/PNG images from prompts and edits one to ten ordered HTTP(S) image inputs.

Nano Banana 2 Lite Text to Image preview

Nano Banana 2 Lite Text to ImageGenerate crisp 1K images in ~4 seconds from text prompts with Nano Banana 2 Lite. Optimized for high-volume rapid iteration, in-image text in 25+ languages, and 10 aspect ratios at $0.025 per generation.

Nano Banana 2 Lite EditGenerate crisp 1K images in ~4 seconds from text prompts with Nano Banana 2 Lite. Optimized for high-volume rapid iteration, in-image text in 25+ languages, and 10 aspect ratios at $0.025 per generation.

Grok Imagine Image Quality Text to Image preview

Grok Imagine Image Quality Text to ImageGenerate high-fidelity images up to 2K resolution from text prompts with Grok Imagine Image Quality. Features photorealistic detail, sharp text rendering, and 5 aspect ratios.

Grok Imagine Image Quality EditGenerate high-fidelity images up to 2K resolution from text prompts with Grok Imagine Image Quality. Features photorealistic detail, sharp text rendering, and 5 aspect ratios.

GPT Image 2 Text-to-ImageOpenAI image generation and editing with quality tiers, flexible size controls, and single-image outputs up to 4K.

GPT Image 2 Image EditOpenAI image generation and editing with quality tiers, flexible size controls, and single-image outputs up to 4K.

Wan 2.7 Image Standard Text to Image preview

Wan 2.7 Image Standard Text to ImageCreate and edit images from prompts or reference photos with Wan 2.7 Image Standard and Pro models.

Wan 2.7 Image Standard EditCreate and edit images from prompts or reference photos with Wan 2.7 Image Standard and Pro models.

GPT Image 1.5 Text to Image API Frequently Asked Questions

What is the GPT Image 1.5 Text to Image API?

GPT Image 1.5 Text to Image is an OpenAI model for image generation from text prompts. It creates high-fidelity visuals across 1024x1024, 1024x1536, or 1536x1024 dimensions with precise instruction following, photorealistic material textures, and clear in-image typography. Built on OpenAI's advanced multimodal diffusion architecture, it preserves spatial perspective and lighting coherence while rendering complex scenes and text. You can call it programmatically or try it from the playground above.

Does GPT Image 1.5 Text to Image support rendering in-image text?

Yes. The model features enhanced typography capabilities, allowing it to render legible English words on signage, posters, and product labels. Enclosing your target text in double quotes within the prompt (such as a storefront with "Coffee Lab") ensures clear font presentation and accurate spelling.

Which image dimensions does GPT Image 1.5 Text to Image support?

The model supports three standard dimensions: 1024x1024 (1:1 square, default), 1024x1536 (2:3 portrait), and 1536x1024 (3:2 landscape). Generations are composed natively at the chosen aspect ratio without cropping.

How many image variations can GPT Image 1.5 Text to Image generate in one request?

You can generate 1 to 4 images per request using the n parameter (defaults to 1). All variations are processed in parallel based on the same prompt, allowing fast comparison of different compositions and color palettes.

How does GPT Image 1.5 Text to Image calculate credits per generation?

Billing is strictly per generated image at 2 credits ($0.010) per image. Total cost equals 2 × n credits ($0.010 × n), with identical rates across all supported dimensions. If a task fails due to a system error, all deducted credits are refunded automatically.

How should prompts be structured for GPT Image 1.5 Text to Image?

Organize prompts hierarchically: detail the core subject, camera framing (e.g., close-up, wide-angle), ambient lighting (e.g., golden hour side lighting), and surface textures. Concrete physical descriptors yield superior results compared to generic quality buzzwords.

Can images generated by GPT Image 1.5 Text to Image be used commercially?

Yes. Subject to OpenAI's standard content policies, users retain full commercial rights to images generated through the API, allowing deployment in digital marketing, commercial packaging, website UI design, and published merchandise.

When should I choose GPT Image 1.5 Text to Image over GPT Image 1.5 Edit?

Use GPT Image 1.5 Text to Image when generating brand-new visuals entirely from written concepts. If you already have an existing image and wish to perform inpainting, background modification, or subject edits, use the GPT Image 1.5 Edit endpoint instead.