Openai · Image model

GPT Image 1 / 2

GPT Image is OpenAI's natively multimodal image generation family

Generate on Coinis Read the docs

One API key. Every model.

per image
Example
AI image
Commercial use included Verified May 26, 2026 Outputs are yours No training on your data
Endpoints

Start building with GPT Image 1 / 2.

One model. Three ways to call it. Same key, same bill.

MIN

Image generation

One call. Same key. Same bill.

$0.35 / image

MAX

Image generation

One call. Same key. Same bill.

$0.35 / image

GPT Image 2 (Cloudflare AI)

Image generation

One call. Same key. Same bill.

$0.09 / image

Capabilities

What it does best.

GPT Image capabilities

  • Precise in-image text rendering. blends readable symbols, typography, and labels directly into generated imagery, making it practical for logos, posters, and infographics[^1]
  • Strong instruction following. handles up to 10–20 distinct objects in a single scene with accurate trait and spatial binding, well beyond what most image models manage[^2]
  • Image API: Generations endpoint. creates images from a text prompt with no reference required[^3]
  • Image API: Edits endpoint. modifies existing images partially or entirely using a new prompt, replacing or extending specific regions[^3]
  • Responses API: multi-turn editing. supports iterative high-fidelity edits via conversation context. accepts image File IDs as input. action mode can be set to auto, generate, or edit[^3]
  • In-context learning from reference images. analyzes uploaded images and integrates their details into generation, enabling style transfer and scene continuation[^2]
  • Output controls. adjust quality, size, format, compression, and transparent background support. generate multiple images in one request via the n parameter[^3]
  • Wide style range. photorealism, vintage film photography, Polaroid, 3D rendering, concept art, product mockups, infographics, and diagrams[^1]
  • C2PA provenance metadata. every output is tagged as AI-generated by GPT-4o, giving buyers and publishers a verifiable content credential[^2]
API

Call GPT Image 1 / 2 in three lines.

One key. One base URL. Same SDK shape you already use. 

# 1. set your key
export COINIS_API_KEY="sk_live_..."

# 2. call the model
curl https://api.app.coinis.com/v1/image/generate \
  -H "Authorization: Bearer $COINIS_API_KEY" \
  -d '{"prompt":"neon city, rain, tracking shot"}'
import { Coinis } from "@coinis/sdk";
const coinis = new Coinis(process.env.COINIS_API_KEY);

const job = await coinis.image.generate({
  model: "models/openai/gpt-image",
  prompt: "neon city, rain, tracking shot",
});
from coinis import Coinis
coinis = Coinis(os.environ["COINIS_API_KEY"])

job = coinis.image.generate(
    model="models/openai/gpt-image",
    prompt="neon city, rain, tracking shot",
)
Response 
{
  "id": "gen_8fa2c1",
  "status": "succeeded",
  "model": "models/openai/gpt-image",
  "output": {
    "image_url": 
                "https://cdn.coinis.com/gen_8fa2c1.mp4"
              
              ,
    "format": "mp4"
  },
  "tokens_used": 10
}

Already on another provider's SDK? Change the host. Keep the call.

Pricing

Token pricing. No surprises.

One wallet across every model. No API accounts to juggle.

GPT Image 1 / 2 · MIN
3.5 tokens
per image · $0.35
Photoreal
$0.35 / image
One key. Every model. One invoice. 1 token = $0.10
1 image ≈ 3 tokens ($0.35)
Budget variant: GPT Image 2 (Cloudflare AI) · $0.09 / image
Start free. 15 tokens a week.

No credit card.

Why pay through Coinis
  • One wallet for every model. No API keys. No separate bills.
  • Generate ads. Launch to Meta. Track in one place.
  • On-brand output from your Brand Profile.

1 token = $0.10 pay-as-you-go. Less on a plan.

Standard vs Fast

Pick the run for the job.

MIN

Final renders, studios
Resolution —
Price $0.35 / image

MAX

Rapid tests, high volume
Resolution —
Price $0.35 / image
Use cases

Two buyers. One model.

For builders

Resell every model. One key. One bill.

Unified API across video, image, audio, and LLM.

Generate 500 variants overnight.

Async queue plus webhooks. Batch at scale.

White-label the output.

Ship it under your brand. Outputs are yours.

For creatives

Ship a Reel before lunch.

Prompt to platform-native clip in minutes.

Same product. Ten formats.

One generation, every aspect ratio.

Commercial UGC without a creator.

Authentic selfie-style ads, on brand.

Marketing assets with embedded text Generate logos, infographics, posters, and UI mockups where the words inside the image are readable and correctly spelled. GPT Image renders text accurately within imagery[^1], which most competing models fail to do reliably.

Iterative brand and character design Refine a character, environment, or brand visual across multiple turns of conversation using the Responses API. Each round of edits preserves context, so you converge on the final look without starting over[^3].

Photorealistic scene generation Produce candid-style, documentary, or cinematic photographs with accurate lighting, reflections, and depth-of-field. The model handles physical simulation well enough for editorial and campaign imagery[^2].

Product and e-commerce imagery Generate product shots, packaging mockups, and lifestyle images with accurate detail and prompt adherence. Swap backgrounds, apply new lighting, or add context without a photo studio[^3].

In-context image transformation Upload a reference image and instruct the model to place it in a new setting, apply a new style, or add UI overlays. Turn a pet photo into an RPG scene or a product render into a seasonal campaign visual[^2].

Renders in seconds. Set a seed. Get the same frame back.

Outputs are yours. Sell them.

Safe for paid ads.

Your prompts are never used for training.

FAQ

GPT Image 1 / 2 FAQs

How much does GPT Image cost per image on Coinis vs OpenAI direct?

On Coinis, GPT Image 2 is available at $0.085 per image via the gpt-image-2-cloudflare variant. GPT Image 1 is priced at $0.354 per image for both the 1024² (gpt-image-1-min) and 1024×1536 (gpt-image-1-max) tiers. OpenAI direct uses token-based pricing for GPT Image 2, meaning cost per image varies with resolution and input tokens. Coinis gives you a flat, predictable per-image rate with no token math required.

What is the difference between GPT Image 1, GPT Image 1.5, GPT Image 2, and GPT Image 1-mini?

GPT Image 2 is OpenAI's current state-of-the-art image generation model. GPT Image 1 is the prior generation, now deprecated by OpenAI, but still supported on Coinis for existing workflows. GPT Image 1.5 and GPT Image 1-mini are intermediate variants in the lineage. On Coinis, the available variants are gpt-image-1-min, gpt-image-1-max, and gpt-image-2-cloudflare.

Is there a GPT Image API I can call without OpenAI Organization Verification?

Yes. OpenAI requires API Organization Verification before granting direct access to GPT Image models. Coinis routes requests through its own infrastructure, so you can call POST /v1/image/generate on Coinis without completing that verification step. You only need a Coinis account.

Can GPT Image render readable text inside images for logos, posters, and infographics?

Yes. Accurate in-image text rendering is one of the model's core strengths. It blends precise symbols and typography into imagery in a way that most other image generation models struggle with. This makes it well-suited for marketing assets, signage, UI mockups, and any creative work where words inside the image must be correct and legible.

Does GPT Image support multi-turn editing and reference images?

Yes, through two paths. The Image API Edits endpoint lets you modify an existing image using a new prompt. The Responses API adds full multi-turn editing: you provide image File IDs, set the action mode to auto, generate, or edit, and refine the output across multiple conversation turns. The model can also learn from uploaded reference images and incorporate their details into new generations.

How long does a GPT Image generation take, and what resolutions are supported?

Because the model produces detailed, high-fidelity outputs, generation can take up to approximately one minute per image. Supported resolutions on Coinis include 1024×1024 (the gpt-image-1-min tier) and 1024×1536 (the gpt-image-1-max tier). Resolution and quality settings can also affect final cost per image within those tiers.

Are GPT Image outputs watermarked or tagged as AI-generated?

GPT Image outputs are not visually watermarked. However, every image is embedded with C2PA metadata that identifies it as AI-generated by GPT-4o. This gives publishers, platforms, and buyers a verifiable content credential without altering the visible image. The tag travels with the file and can be read by any C2PA-compatible viewer.

Related

Pair it with.

FLUX (1.1 / 2)

Model

Ideogram 3.0

Model

Imagen 4 (Fast / Standard / Ultra)

Model

All image models

Catalog
Upscale this Edit a frame Add a voiceover

Start free

Your wallet. Every model. One call away.

Start free. 15 tokens a week. No card.

Generate on Coinis

No credit card.

Pricing and capabilities verified 2026-05-26. Read the docs .