# GPT Image 2.5 MCP and API - Text to image by OpenAI | FlyMy.AI

> OpenAI GPT Image 2.5 (Flare) is the everyday image tier: sharper detail and more natural light than 2.0, with transparent backgrounds.

Page: https://flymy.ai/mcp/models/gpt-image-2-5/

MCP / Models / Image generation

# GPT Image 2.5 MCP: everyday images with no API key

OpenAI GPT Image 2.5 (Flare) is the everyday image tier: sharper detail and more natural light than 2.0, with transparent backgrounds. Run it from Claude Code, Codex, Cursor or any MCP client through one FlyMy.AI MCP, or call its API.

[Use GPT Image 2.5](https://flymy.ai/mcp/models/gpt-image-2-5/#start) [Inputs and price](https://flymy.ai/mcp/models/gpt-image-2-5/#inputs)

No API key, from $0.009 / run, Text to image, OpenAI, Commercial use

$ YOUR NEXT RUN

Claude Code, Codex, Cursor, Any agent

## Use GPT Image 2.5 in your assistant

Paste this prompt into Claude Code, Codex, Cursor or any agent. It reads the guide and helps you connect.

```
Read https://flymy.ai/skill.md and https://flymy.ai/mcp/models/gpt-image-2-5.md. Help me connect the FlyMy.AI MCP to this assistant, then run GPT Image 2.5 (flymyai/gpt-image-2-5) for this task: Generate an product photo of a red vintage bicycle against a pastel wall with GPT Image 2.5.
```

[Open FlyMy.AI](https://app.flymy.ai/new-agent) [Download brief](https://flymy.ai/mcp/models/gpt-image-2-5.md)

## What GPT Image 2.5 does

GPT Image 2.5, called Flare, is the previous generation of OpenAI's everyday image model, superseded by GPT Image 2.6. It generates from a prompt with quality low, medium or high, size 1024x1024, 1536x1024, 1024x1536 or auto, and a transparent, opaque or auto background. It does not edit a supplied picture; GPT Image 2.5 Edit does.

## GPT Image 2.5 inputs

Every input of `flymyai/gpt-image-2-5` as its live schema lists them. Returns `image` (array).

| Input | Type, values and default |
|---|---|
| [#](https://flymy.ai/mcp/models/gpt-image-2-5/#input-prompt) `prompt` | string required |
| [#](https://flymy.ai/mcp/models/gpt-image-2-5/#input-background) `background` | string optional Allowed: transparent, opaque, auto |
| [#](https://flymy.ai/mcp/models/gpt-image-2-5/#input-moderation) `moderation` | string optional Allowed: low, auto |
| [#](https://flymy.ai/mcp/models/gpt-image-2-5/#input-quality) `quality` | string optional Allowed: high, medium, low Default: `medium` |
| [#](https://flymy.ai/mcp/models/gpt-image-2-5/#input-size) `size` | string optional Allowed: 1024x1024, 1536x1024, 1024x1536, auto Default: `1024x1024` |

## Ask your agent

Requests to paste as they are, once the FlyMy.AI MCP is connected.

**“Generate an product photo of a red vintage bicycle against a pastel wall with GPT Image 2.5.”** runs `flymyai/gpt-image-2-5`

**“Make three versions of a poster for a tech meetup about AI agents with GPT Image 2.5 and send me the links.”** runs `flymyai/gpt-image-2-5`

**“Create an isometric 3D illustration of a chef plating a dessert in slow motion with GPT Image 2.5.”** runs `flymyai/gpt-image-2-5`

## GPT Image 2.5 price

From $0.009 per run, depending on quality and size. A run at the default settings costs $0.032. A run costs $0.009 to $0.188, depending on quality and size. Billed to your FlyMy.AI balance; no seats, no subscription and no minimum.

[See usage pricing →](https://flymy.ai/pricing/)

## Call GPT Image 2.5 from code

The same model, from an agent or from your own code. Keys stay in your FlyMy.AI account.

### From an agent, through the MCP

The agent calls `get_model_schema`, then `run_model` with:

```
{
  "endpoint_id": "flymyai/gpt-image-2-5",
  "input": {
    "prompt": "A ceramic mug on a sunlit kitchen counter, product photo"
  }
}
```

### From your code, over HTTP

Form fields, not JSON; files go as uploads or public URLs. The answer is a `prediction_id`; read the result at `https://api.flymy.ai/api/v1/flymyai/gpt-image-2-5/predict/async/result/?request_id=<prediction_id>`.

```
curl -X POST https://api.flymy.ai/api/v1/flymyai/gpt-image-2-5/predict/async/ \
  -H "X-API-KEY: $FLYMYAI_API_KEY" \
  -F 'prompt=A ceramic mug on a sunlit kitchen counter, product photo'
```

## Questions about GPT Image 2.5

**Do I need a OpenAI API key for GPT Image 2.5?**

No. GPT Image 2.5 runs on FlyMy.AI's account, so you need no OpenAI key or plan: sign in to FlyMy.AI once and each run is billed to your FlyMy.AI balance.

**How much does GPT Image 2.5 cost?**

From $0.009 per run, depending on quality and size. There is no subscription or minimum; the price comes from FlyMy.AI billing and was checked on 2026-11-09.

**How do I use GPT Image 2.5 in Claude Code, Codex or Cursor?**

Add the FlyMy.AI MCP with one command and sign in, then ask in plain words, for example: "Generate an product photo of a red vintage bicycle against a pastel wall with GPT Image 2.5." Your agent reads the inputs with get_model_schema and runs flymyai/gpt-image-2-5 with run_model.

**What does GPT Image 2.5 need as input?**

GPT Image 2.5 requires prompt; it also takes 4 optional inputs, each listed on this page with its allowed values and default.

**Can I call GPT Image 2.5 from my own code?**

Yes. Send form fields to https://api.flymy.ai/api/v1/flymyai/gpt-image-2-5/predict/async/ with your FlyMy.AI API key in the X-API-KEY header.

## More image generation models

Text to image: product shots, ads, posters and illustrations from a prompt, many with reference images.

### GPT Image 2.6

OpenAI's current default image model: faster than 2.5, with text that stays readable.

Text to image / from $0.009 / run

Link: https://flymy.ai/mcp/models/gpt-image-2-6/

### GPT Image 2.6 Sunburst

The precision tier of 2.6 for packaging, campaigns and detailed illustration.

Text to image / from $0.009 / run

Link: https://flymy.ai/mcp/models/gpt-image-2-6-sunburst/

### GPT Image 2.5 Sunburst

The slower, more exact 2.5 tier for campaign and product imagery where detail matters.

Text to image / from $0.009 / run

Link: https://flymy.ai/mcp/models/gpt-image-2-5-sunburst/

### GPT Image 2.0

OpenAI's 2.0 generator for pipelines tuned to it, with three sizes and transparent output.

Text to image / from $0.009 / run

Link: https://flymy.ai/mcp/models/gpt-image-2-0/

### GPT Image 1.5

An earlier OpenAI image model, kept for pipelines built on it; transparent backgrounds supported.

Text to image / from $0.009 / run

Link: https://flymy.ai/mcp/models/gpt-image-1-5/

### Nano Banana 2.1

Gemini's newest image model: 14 references, up to 4K, with adjustable thinking.

Text and image to image / from $0.0336 / image

Link: https://flymy.ai/mcp/models/nano-banana-2-1/

## Go to the source

[GPT Image 2.5 in the playground →](https://app.flymy.ai/models/flymyai/gpt-image-2-5), [Model endpoints in the docs →](https://docs.flymy.ai/api/models-endpoints), [Image generation guide →](https://docs.flymy.ai/guides/generate-images), [Every model on FlyMy.AI →](https://flymy.ai/mcp/models/), [Every MCP in the catalog →](https://flymy.ai/mcp/#catalog), [Usage pricing →](https://flymy.ai/pricing/)

From the FlyMy.AI model catalog of 2026-11-09: inputs from the model's live schema, prices from FlyMy.AI billing. Requests are examples to paste, not recorded runs.

---

For agents: the FlyMyAI operating guide (sign up, connect, run models, tools and agents) is https://flymy.ai/skill.md, and https://flymy.ai/llms.txt lists the other pages and the documentation.