GPT Image 1.5

GPT Image 1.5 generates high-fidelity images with strong prompt adherence, preserving composition, lighting, and fine-grained detail.

By OpenAI

Pricing: $0.133 per image

Overview

GPT-Image 1.5 by OpenAI, high-fidelity images with strong prompt adherence. Three quality tiers, three sizes, transparent background support. From $0.009/image.

Key capabilities

• **Quality × size pricing matrix**, Choose low, medium, or high quality at three size options, 9 price points from $0.009 to $0.200 per image, letting you optimise cost for every use case.
• **Transparent background support**, Native transparent background output, no post-processing removal needed for product photography on white or overlay use cases.
• **OpenAI's strongest image model**, GPT-Image 1.5 is OpenAI's highest-quality image generation model, built on the same foundation as their multimodal research.

GPT-Image model family by OpenAI

| Model | Details |

|---|---|

| **GPT-Image 1.5 (Generation)** (this model) | Text-to-image with quality × size pricing tiers |

| **GPT-Image 1.5 (Edit)** | Image editing and inpainting variant |

Technical specifications

| Spec | Details |

|---|---|

| Architecture | Autoregressive Vision Model |

| Sizes | 1024×1024 · 1536×1024 · 1024×1536 |

| Quality Tiers | Low · Medium · High |

| Background | Auto · Transparent · Opaque |

| Output Formats | JPEG · PNG · WebP |

| License | Commercial |

Examples

• An underwater coral reef tea house at the bottom of a crystal-clear tropical ocean. Bamboo replaced by swaying kelp and sea fans, fish swim where birds would fly, jellyfish provide the lantern light, a sea turtle approaches the entrance. Warm bioluminescent glow, caustic light patterns on the sandy floor.

Frequently asked questions

What is GPT-Image 1.5?

GPT-Image 1.5 is OpenAI's text-to-image model built on their autoregressive vision architecture. It generates high-fidelity images with strong prompt adherence, preserving composition, lighting, and fine-grained detail. It supports three quality tiers (low, medium, high) across three image sizes.

How much does GPT-Image 1.5 cost on Runflow?

Pricing depends on quality and size. Low quality starts at $0.009/image (1024×1024). Medium quality starts at $0.034/image. High quality starts at $0.133/image. Larger sizes (1536×1024 or 1024×1536) cost slightly more. There are also small token charges for input/output text processing.

What's the difference between low, medium, and high quality?

Quality controls the detail and fidelity of the generated image. Low is fast and cheap, useful for prototyping. Medium is a balanced option. High produces the sharpest, most photorealistic outputs and is recommended for production. You can set quality per request.

Does GPT-Image 1.5 support transparent backgrounds?

Yes. Set background to 'transparent' and GPT-Image 1.5 will output the image with a transparent background, useful for product photography, overlays, and composite workflows. No background removal post-processing needed.

What image sizes does GPT-Image 1.5 support?

GPT-Image 1.5 supports three sizes: 1024×1024 (square), 1024×1536 (portrait), and 1536×1024 (landscape). Choose via the image_size parameter.

What are the token charges?

In addition to the per-image fee, GPT-Image 1.5 charges $0.005 per 1K input text tokens and $0.010 per 1K output text tokens. For most prompts (under 200 words) this adds less than $0.002 total.

Can I use GPT-Image 1.5 commercially?

Yes. GPT-Image 1.5 is available under a commercial license. You can use it in production SaaS products, client deliverables, and high-volume generation pipelines.

Related models

• GPT Image 2 Edit, GPT Image 2.0, OpenAI's latest image model, is capable of making fine-grained, detailed edits to images.
• GPT Image 2, GPT Image 2.0, OpenAI's latest image model, is capable of creating extremely detailed images with fine typography.
• FLUX.1 [dev] Edit, Image-to-image edits with FLUX.1 [dev]. Pass a source image plus a prompt and a transformation strength to redirect the composition while preserving subject identity.
• Multi Angles, Re-render the same subject from a different camera angle. Pick a horizontal view, a vertical angle, and a shot distance: the model rotates the camera around the subject and re-renders the scene from that pose.

Discoverable surfaces

• Dispatch endpoint: POST https://api.runflow.io/v1/models/gpt-image-1.5/runs
• Per-model spec (markdown): https://app.runflow.io/models/gpt-image-1.5/llms.txt
• Docs page: https://docs.runflow.io/models/gpt-image-1.5
• Public OpenAPI spec: https://docs.runflow.io/api/openapi.public.json
• Agent skill (start here): https://www.runflow.io/.well-known/agent-skills/runflow/SKILL.md