Image

DALL-E 3 API

OpenAI's third-generation text-to-image model (Oct 2023 - May 2026), best known for turning plain-English descriptions into images that actually match what you asked for. Now retired; superseded by OpenAI's GPT Image models.

Get API key Read the docs

~29s
Avg. generation: 15 credits
From

DALL-E 3 image of a futuristic cozy living room with a holographic jellyfish tank, a sleeping orange tabby cat, and a rainy cyberpunk skyline

Playground

Try DALL-E 3 right here.

model: dall-e-3

Prompt

Aspect ratio

Style

Estimated cost 15 credits · $0.15 Generate in Studio

Output

Your output lands here. Hit generate to run this request in Studio.

Pricing

Simple per-generation pricing.

15 credits per generation ≈ $0.15

You only pay for successful generations. Failed jobs are refunded automatically.
One credit balance across every model on Apiframe, no per-model plans.
Start with free credits. No subscription required.
Volume discounts on larger plans.

See plans and credit packs

Specs

At a glance.

Provider OpenAI

Model ID dall-e-3

Aspect ratios 1:1, 3:2, 2:3

Avg. time ~29s

Quickstart

How to call the DALL-E 3 API.

Send one POST /v2/images/generate request with your API key. The call returns a jobId you can poll, or pass a webhook_url and the result is pushed to you the moment it's ready.

Swap dall-e-3 for any other model and nothing else changes.

Get API key Read the docs

generate.js

const response = await fetch("https://api.apiframe.ai/v2/images/generate", {
  method: "POST",
  headers: {
    "X-API-Key": "afk_your_api_key_here",
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    "prompt": "a sleek silver sports car on a coastal highway at sunset, hyper-realistic",
    "model": "dall-e-3",
    "dalleParams": {
      "style": "vivid"
    }
  }),
});
const { jobId } = await response.json();
console.log(jobId);

import requests

response = requests.post(
    "https://api.apiframe.ai/v2/images/generate",
    headers={
        "X-API-Key": "afk_your_api_key_here",
        "Content-Type": "application/json",
    },
    json={
        "prompt": "a sleek silver sports car on a coastal highway at sunset, hyper-realistic",
        "model": "dall-e-3",
        "dalleParams": {
            "style": "vivid"
        }
    },
)
print(response.json())  # { "jobId": "...", "status": "QUEUED" }

curl -X POST https://api.apiframe.ai/v2/images/generate \
  -H "X-API-Key: afk_your_api_key_here" \
  -H "Content-Type: application/json" \
  -d '{
        "prompt": "a sleek silver sports car on a coastal highway at sunset, hyper-realistic",
        "model": "dall-e-3",
        "dalleParams": {
            "style": "vivid"
        }
    }'

let job;
do {
  await new Promise((r) => setTimeout(r, 2000));
  job = await fetch("https://api.apiframe.ai/v2/jobs/JOB_ID", {
    headers: { "X-API-Key": "afk_your_api_key_here" },
  }).then((r) => r.json());
} while (job.status !== "COMPLETED" && job.status !== "FAILED");
console.log(job.result);

import requests, time

while True:
    job = requests.get(
        "https://api.apiframe.ai/v2/jobs/JOB_ID",
        headers={"X-API-Key": "afk_your_api_key_here"},
    ).json()
    if job["status"] in ("COMPLETED", "FAILED"):
        break
    time.sleep(2)
print(job["result"])

curl https://api.apiframe.ai/v2/jobs/JOB_ID \
  -H "X-API-Key: afk_your_api_key_here"

Input schema

Every field DALL-E 3 accepts, with types and defaults. The full reference lives in the docs.

Field	Type	Description
prompt required	string	Text description of what to generate.
model required	string	The model identifier for this endpoint. Default:"dall-e-3" · "dall-e-3"
dalleParams.style	string	Style Default:"vivid" · "vivid", "natural"

DALL·E versions

Every DALL·E image model on Apiframe. Switch with one parameter.

DALL-E 3 Flagship This page

DALL-E 3 questions

What teams ask before shipping with DALL-E 3. Everything else lives in the docs.

Is DALL-E 3 free to use?

While it is a heavy premium model, it can be accessed for free via Microsoft Copilot (formerly Bing Image Creator). Direct, unlimited conversational access within ChatGPT requires a ChatGPT Plus, Team, or Enterprise subscription.

Can I use DALL-E 3 images commercially?

Yes. OpenAI's terms specify that you own the images you create using DALL-E 3, giving you the right to reprint, sell, or merchandise them, regardless of whether you generated them via a free tier or paid subscription.

Why does DALL-E 3 refuse some of my prompts?

This is usually due to its safety filters. It will reject prompts that name living artists, feature contemporary political or public figures, or contain keywords flagged for violence, explicit content, or copyright infringement.

How does DALL-E 3 compare to Midjourney?

DALL-E 3 wins heavily on understanding complex prompts and text generation, making it incredibly easy to use. Midjourney is often preferred by digital artists for its raw, ultra-stylized, and cinematic aesthetic output, but it requires learning specific prompt syntax.

Could you use DALL-E 3 without ChatGPT?

Yes, via Apiframe, Bing Image Creator and Microsoft Designer/Copilot.

Could it generate text inside images?

Yes, that was DALL-E 3's strength.