# FLUX 3 Image MCP and API by Black Forest Labs | FlyMy.AI

> Black Forest Labs FLUX 3 Image draws from a prompt, edits or combines up to ten pictures and checks the web so real products and places come out right.

Page: https://flymy.ai/mcp/models/flux-3-image/

MCP / Models / Image generation

# FLUX 3 Image MCP: images and edits that check the web

Black Forest Labs FLUX 3 Image draws from a prompt, edits or combines up to ten pictures and checks the web so real products and places come out right. Run it from Claude Code, Codex, Cursor or any MCP client through one FlyMy.AI MCP, or call its API.

[Use FLUX 3 Image](https://flymy.ai/mcp/models/flux-3-image/#start) [Inputs and price](https://flymy.ai/mcp/models/flux-3-image/#inputs)

No API key, from $0.041 / run, Text and image to image, Black Forest Labs, Commercial use

$ YOUR NEXT RUN

Claude Code, Codex, Cursor, Any agent

## Use FLUX 3 Image 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/flux-3-image.md. Help me connect the FlyMy.AI MCP to this assistant, then run FLUX 3 Image (flymyai/flux-3-image) for this task: Generate a 9:16 product photo of a red vintage bicycle against a pastel wall with FLUX 3 Image at 4k.
```

[Open FlyMy.AI](https://app.flymy.ai/new-agent) [Download brief](https://flymy.ai/mcp/models/flux-3-image.md)

## What FLUX 3 Image does

Send a prompt for a new image, or add images (up to ten links or uploads; the first is the one that is edited) and write each change as an instruction that names the pictures by number. grounding, on by default, lets the model look up what the prompt names on the web, so real products, places and events come out right; set it to false for a faster result from the prompt alone. resolution is 768sq, 1k (the default), 1.5k, 2k or 4k, or match_input to keep the first picture's size when editing; aspect_ratio is auto or one of 15 shapes, and width and height (256 to 6256, sent together) set an exact size. It makes one image per request, billed by size tier, and an edit costs the same as a new image. It does not make video: FLUX 3 Video does.

## FLUX 3 Image inputs

Every input of `flymyai/flux-3-image` as its live schema lists them. Returns `image` (array).

| Input | Type, values and default |
|---|---|
| [#](https://flymy.ai/mcp/models/flux-3-image/#input-prompt) `prompt` | string required What to create, or how to change the pictures in images: one instruction per change, naming the pictures by number |
| [#](https://flymy.ai/mcp/models/flux-3-image/#input-images) `images` | string optional Pictures to edit or combine: up to 10 links (a JSON array or one link) or uploads; the first is the one that is edited. Leave out to create from the prompt alone |
| [#](https://flymy.ai/mcp/models/flux-3-image/#input-aspect_ratio) `aspect_ratio` | string optional Allowed: auto, 21:9, 2:1, 16:9, 3:2, 7:5, 4:3, 5:4, 1:1, 4:5, 3:4, 5:7, 2:3, 9:16, 1:2, 9:21 Default: `auto` Shape of the image; auto follows the first picture, or the prompt |
| [#](https://flymy.ai/mcp/models/flux-3-image/#input-resolution) `resolution` | string optional Allowed: 768sq, 1k, 1.5k, 2k, 4k, match_input Default: `1k` Billed per image by size: 768sq $0.041, 1k $0.048, 1.5k $0.07, 2k $0.10, 4k $0.607; match_input (editing only) keeps the first picture's size and bills its tier |
| [#](https://flymy.ai/mcp/models/flux-3-image/#input-width) `width` | integer optional Allowed: 256 to 6256 Exact width in pixels, 256-6256, sent together with height; replaces resolution and aspect_ratio. Billed at the smallest size tier that covers width x height (up to 16.8 MP, 4.2 MP with images) |
| [#](https://flymy.ai/mcp/models/flux-3-image/#input-height) `height` | integer optional Allowed: 256 to 6256 Exact height in pixels, 256-6256, sent together with width |
| [#](https://flymy.ai/mcp/models/flux-3-image/#input-grounding) `grounding` | boolean optional Default: `true` Let the model look up what the prompt names on the web, so real products, places and events come out right; false is faster |
| [#](https://flymy.ai/mcp/models/flux-3-image/#input-safety_tolerance) `safety_tolerance` | integer optional Allowed: 0 to 4 Default: `2` Content filter: 0 strictest to 4 most permissive |

## Ask your agent

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

**“Generate a 9:16 product photo of a red vintage bicycle against a pastel wall with FLUX 3 Image at 4k.”** runs `flymyai/flux-3-image`

**“Make three versions of a poster for a yoga class in the park with FLUX 3 Image and send me the links.”** runs `flymyai/flux-3-image`

**“Use FLUX 3 Image to place the product from the photo I attach on a busy cafe table by the window.”** runs `flymyai/flux-3-image`

## FLUX 3 Image price

From $0.041 per run, depending on resolution, width and height; one image, by size tier: a custom width and height bill the smallest tier that covers them. A run at the default settings costs $0.048. A run costs $0.041 to $0.607, depending on resolution and width and height. Billed to your FlyMy.AI balance; no seats, no subscription and no minimum.

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

## Call FLUX 3 Image 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/flux-3-image",
  "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/flux-3-image/predict/async/result/?request_id=<prediction_id>`.

```
curl -X POST https://api.flymy.ai/api/v1/flymyai/flux-3-image/predict/async/ \
  -H "X-API-KEY: $FLYMYAI_API_KEY" \
  -F 'prompt=A ceramic mug on a sunlit kitchen counter, product photo'
```

## Questions about FLUX 3 Image

**Do I need a Black Forest Labs API key for FLUX 3 Image?**

No. FLUX 3 Image runs on FlyMy.AI's account, so you need no Black Forest Labs key or plan: sign in to FlyMy.AI once and each run is billed to your FlyMy.AI balance.

**How much does FLUX 3 Image cost?**

From $0.041 per run, depending on resolution, width and height; one image, by size tier: a custom width and height bill the smallest tier that covers them. There is no subscription or minimum; the price comes from FlyMy.AI billing and was checked on 2026-11-18.

**How do I use FLUX 3 Image 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 a 9:16 product photo of a red vintage bicycle against a pastel wall with FLUX 3 Image at 4k." Your agent reads the inputs with get_model_schema and runs flymyai/flux-3-image with run_model.

**What does FLUX 3 Image need as input?**

FLUX 3 Image requires prompt; it also takes 7 optional inputs, each listed on this page with its allowed values and default.

**Can I call FLUX 3 Image from my own code?**

Yes. Send form fields to https://api.flymy.ai/api/v1/flymyai/flux-3-image/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, illustrations and editable vector graphics from a prompt, many with reference images.

### FLUX 3 Image Klein

The compact FLUX 3 for quick edits, variations and high-volume work where cost matters.

Text and image to image / from $0.008 / run

Link: https://flymy.ai/mcp/models/flux-3-image-klein/

### Grok Imagine Image 2.0

xAI's image model: prompts and edits of up to five pictures at 1k to 2k, with a medium quality setting.

Text and image to image / from $0.04 / image

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

### Ideogram 4.5

Ideogram's image model for posters, logos and packaging, with text that reads right.

Text to image / from $0.03 / image

Link: https://flymy.ai/mcp/models/ideogram-4-5-text-to-image/

### Ideogram Vector

Logos, icons and illustrations as real SVG paths that scale to any size and open in a vector editor.

Text to vector / from $0.13 / image

Link: https://flymy.ai/mcp/models/ideogram-vector-text-to-vector/

### Kling Image V4

Kuaishou's fourth-generation image model: 2K pictures or a matching series of up to ten.

Text to image / from $0.063 / run

Link: https://flymy.ai/mcp/models/kling-image-v4-text-to-image/

### Krea 3

Krea's image model with prompt expansion: pictures of up to 4 megapixels, billed per megapixel.

Text to image / from $0.0063 / run

Link: https://flymy.ai/mcp/models/krea-3-text-to-image/

## Go to the source

[FLUX 3 Image in the playground →](https://app.flymy.ai/models/flymyai/flux-3-image), [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 2026-11-18: 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.
