OpenAI GPT Image-1 generates images from text prompts from OpenAI's latest text-to-image model, ideal for creating visual assets. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
Idle
$0.042per run·~23 / $1
ExamplesView all
Create a professional and visually engaging magazine cover for a lifestyle magazine called "Urban Pulse." Include these featured article headlines clearly: "10 Hidden Cafés You'll Love in NYC" "Minimalist Apartments: Small Spaces, Big Ideas" "Exclusive Interview: Behind the Scenes with Indie Band Echo District" Use contemporary typography, vibrant colors, and include an eye-catching main photograph with a person standing in front of a city scene
Photorealistic vintage-style photo from the 1960s. A smiling family is proudly posing in their suburban driveway next to their brand-new, bubble-canopy, atomic-powered car. The car has sleek, chrome fins and emits a soft blue glow from its rear reactor. In the background is their mid-century modern home and a monorail gliding silently in the distance.
A female cyborg agent with silver hair and glowing cybernetic eyes, crouching on a rooftop overlooking a futuristic, neon-lit cityscape at night. Rain is falling, creating reflections on her metallic limbs. Dynamic, gritty anime style.
Photorealistic, cinematic shot. A lone bio-engineer in a clean, minimalist orbital laboratory is carefully examining a glowing plant specimen inside a hexagonal terrarium. The Earth is visible through the large viewport behind her, casting a soft blue light across the sterile white interior of the station. Her expression is a mix of fatigue and wonder.
Cinematic portrait of a handsome man in his early 30s with sharp features and well-groomed stubble, wearing a tailored navy blue suit. He's standing on a high-rise balcony at night, with the blurred city lights of Tokyo in the background. Moody, dramatic lighting.
A beautiful woman with a healthy, athletic build, wearing an earth-toned bikini, standing under a gentle waterfall in a lush, vibrant tropical rainforest. Sunbeams cut through the canopy, creating a magical, misty atmosphere.
Make an image of a birthday card for my mom's 50th birthday, include all the gifts that I got her illustrated as a single black ink drawing. add a headline drawn in an elegant black script: Happy 50th Birthday, Mom!
A small robot exploring an abandoned city, stylized cartoon look, bright and soft color palette, charming illustration
A high school girl in a sailor uniform standing at a train crossing in a quiet suburban town, looking up at the sky filled with beautiful, dramatic clouds and lens flare. Sakura petals are gently falling around her. Nostalgic and emotional atmosphere, in the style of Japanese manga
A cute cartoon fox wearing a tiny wizard hat, sitting on a giant mushroom, colorful whimsical forest background, hand-drawn style, playful illustration
Professional fashion photography of a graceful woman in a stylish, elegant white bikini, lounging on the deck of a luxury yacht sailing in the Mediterranean. The sun is bright, the water is a deep turquoise, and she is holding a tropical drink.
Generate an image of a sleek, red sports car with a polished chrome grille and alloy wheels. The car is parked on a sunlit beach with waves gently lapping at the shore and palm trees swaying in the background. The scene has a bright and cheerful tone with warm sunlight casting soft shadows on the car. The image is taken from a slightly elevated angle to capture the car's sleek design and the beach in the background. The image should be in a photorealistic style with high-resolution details.
A highly detailed portrait of an elderly man with deep wrinkles, wearing a dark blue coat, sitting in a sunlit library, realistic lighting and textures, photograph style
A young woman with curly hair sitting at a café table, wearing a beige trench coat, soft morning light on her face, shallow depth of field, realistic skin texture, candid photography style
Related Models
README
OpenAI GPT Image 1
GPT Image 1 is OpenAI’s latest multimodal image generation model, built to understand both text and image inputs and produce visually coherent, high-quality image outputs. It combines the reasoning power of GPT-4-Turbo with DALL·E-class visual synthesis—allowing for creative, controllable, and context-aware generation across illustration, photography, design, and visualization tasks.
🧠 Key Features
-
Multimodal Understanding Accepts both text and image inputs, enabling style transfer, editing, or contextual composition.
-
Flexible Styles Produces photorealistic renders, stylized artwork, concept art, infographics, and 3D-style illustrations.
-
High Visual Fidelity Maintains object relationships, lighting consistency, and color balance with strong adherence to prompts.
-
Accurate Text Rendering Capable of generating clean typography—ideal for posters, memes, comics, and branding visuals.
-
Knowledge-Grounded Creativity Uses GPT-4’s world knowledge to generate factual, contextually appropriate visuals.
⚙️ Parameters
- Prompt: Required text description of the desired image.
- Size: Supports
1024×1024,1024×1536, and1536×1024. - Quality: Choose between
low,medium, andhigh.
💰 Pricing
| Resolution | Low ($) | Medium ($) | High ($) |
|---|---|---|---|
| 1024 × 1024 | 0.011 | 0.042 | 0.167 |
| 1024 × 1536 / 1536 × 1024 | 0.016 | 0.063 | 0.250 |
💡 Tips for Best Results
- Write prompts that specify style, subject, composition, and lighting.
Example: “A small robot exploring an abandoned city, cartoon style, bright colors.”
- Use high quality for detailed or large-format outputs.
- Prefer landscape (1536×1024) for cinematic or wide compositions, and portrait (1024×1536) for characters or vertical art.
📝 Notes
- All generated content follows OpenAI’s safety and content policies.
- If a prompt triggers moderation, rephrase or simplify it.
- This model supports multi-image input via API, enabling creative editing and composition workflows.
- For performance and latency-sensitive cases, use medium quality as the balanced default.
Gpt Image 1 Text To Image API — Quick start
Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/openai/gpt-image-1/text-to-image with your input as JSON. The endpoint returns a prediction id; poll the prediction endpoint until status flips to completed, then read the output URL from data.outputs[0]. Examples for Gpt Image 1 Text To Image below.
HTTP example
# Submit the prediction
curl -X POST "https://api.wavespeed.ai/api/v3/openai/gpt-image-1/text-to-image" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $WAVESPEED_API_KEY" \
-d '{
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"size": "1024*1024",
"quality": "medium",
"enable_sync_mode": false,
"enable_base64_output": false
}'
# Response includes a prediction id. Poll for the result:
curl -X GET "https://api.wavespeed.ai/api/v3/predictions/{request_id}/result" \
-H "Authorization: Bearer $WAVESPEED_API_KEY"
# When status is "completed", read the output from data.outputs[0].Node.js example
// npm install wavespeed
const WaveSpeed = require('wavespeed');
const client = new WaveSpeed(); // reads WAVESPEED_API_KEY from env
const result = await client.run("openai/gpt-image-1/text-to-image", {
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"size": "1024*1024",
"quality": "medium",
"enable_sync_mode": false,
"enable_base64_output": false
});
console.log(result.outputs[0]); // → URL of the generated outputPython example
# pip install wavespeed
import wavespeed
output = wavespeed.run(
"openai/gpt-image-1/text-to-image",
{
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"size": "1024*1024",
"quality": "medium",
"enable_sync_mode": false,
"enable_base64_output": false
}
)
print(output["outputs"][0]) # → URL of the generated outputGpt Image 1 Text To Image API — Frequently asked questions
What is the Gpt Image 1 Text To Image API?
Gpt Image 1 Text To Image is a OpenAI model for image generation, exposed as a REST API on WaveSpeedAI. OpenAI GPT Image-1 generates images from text prompts from OpenAI's latest text-to-image model, ideal for creating visual assets. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing. You can call it programmatically or try it from the playground above.
How do I call the Gpt Image 1 Text To Image API?
POST your input parameters to the model's REST endpoint (shown in the API tab of this playground) with your WaveSpeedAI API key in the Authorization header. Submission returns a prediction ID; poll the prediction endpoint until status flips to "completed", then read the output URL from the result. The playground generates a ready-to-paste code sample in Python, JavaScript, or cURL for whatever inputs you've set. Full request/response shape is documented at https://wavespeed.ai/docs/docs-api/openai/openai-gpt-image-1-text-to-image.
How much does Gpt Image 1 Text To Image cost per run?
Gpt Image 1 Text To Image starts at $0.042 per run. That figure is the base price — the final charge scales with the parameters you set in the form (output size, length, count, references, or whatever knobs this model exposes), so a higher-quality or larger output costs more than a minimal one. The exact cost for your current input is shown live next to the Generate button before you submit, and the actual per-call charge is recorded on the prediction afterwards.
What inputs does Gpt Image 1 Text To Image accept?
Key inputs: `prompt`, `size`, `enable_base64_output`, `enable_sync_mode`, `quality`. The full JSON schema (types, defaults, allowed values) is rendered above the Generate button and mirrored in the API reference at https://wavespeed.ai/docs/docs-api/openai/openai-gpt-image-1-text-to-image.
How long does Gpt Image 1 Text To Image take to generate?
Average end-to-end generation time on WaveSpeedAI is around 28 seconds per request — measured across recent runs. Queue time scales with global demand; live status is visible in the prediction record.
Can I use Gpt Image 1 Text To Image outputs commercially?
Commercial usage rights depend on the model's license, set by its provider (OpenAI). The license summary appears on the model card above; see WaveSpeedAI's Terms of Service for platform-level conditions.