MiniMax Image 01

Text to ImageImage to ImageBatch Generation

MiniMax Image-01 is MiniMax’s first dedicated text-to-image model, available through APIXO for prompt-based generation and single-reference image-to-image creation. It combines detailed scene composition and subject rendering with APIXO controls for prompt optimization, seed-controlled iteration, flexible dimensions, and batch size.

APIXO Modes

Text / One Reference

Price

$0.0035 / Image

Resolution

1K / 2K

Batch Size

1–9 Images

Released

Feb 15, 2025

Loading workspace...

MiniMax Image 01 Model API Rate Structure

MiniMax Image-01 is billed per generated image. A task requesting between one and nine outputs is billed for the corresponding number of images.

1 image

APIXO price

$0.0035

2 images

APIXO price

$0.007

4 images

APIXO price

$0.014

9 images

APIXO price

$0.0315

Images	APIXO price
1 image	$0.0035
2 images	$0.007
4 images	$0.014
9 images	$0.0315

Common Cost Examples

Example: 4 MiniMax Image-01 images = 4 × $0.0035 = $0.014.

Checking API access...

Integrate with AI

Copy a prompt for your AI assistant to install APIXO MCP, read the live schema, and wire this model into your app.

Endpoints

Create task

POSThttps://api.apixo.ai/api/v1/generateTask/minimax-image-01

Poll status

GEThttps://api.apixo.ai/api/v1/statusTask/minimax-image-01?taskId={taskId}

Request body

request_type

async

Use callback with callback_url for webhooks.

input

object

Mode, prompt, references, size, duration, and audio settings.

request_typerequired

Typeselect

Use async to poll statusTask, or callback to receive a webhook when the result is ready.async · callback

callback_urlconditional

Typetext

Public HTTPS URL for callback delivery.Only in request_type=callback

moderequired

Typeselect

Choose the generation workflow supported by this model.text-to-image · image-to-image

promptrequired

Typestring

Describe the subject, composition, style, lighting, and details you want in the final image.

aspect_ratiorequired

Typeselect

Choose the output frame ratio.1:1 · 16:9 · 4:3 · 3:2 · 2:3 · 3:4 · 9:16 · 21:9

resolutionrequired

Typeselect

Choose the output resolution tier. Higher tiers can cost more.1K · 2K

num_imagesoptional

Typeselect

Number of images to request.1 · 2 · 3 · 4 · 5 · 6 · 7 · 8 · 9

sizeoptional

Typetext

Optional WIDTH*HEIGHT size from 512 to 2048 per side. Resolution and aspect ratio take precedence when both are provided.

prompt_optimizeroptional

Typeboolean

Let MiniMax optimize the prompt before generation.

seedoptional

Typetext

Use -1 for random output or provide an integer seed up to 2147483647.

Parameter	Type	Required	Description
`request_type`	select	required	Use async to poll statusTask, or callback to receive a webhook when the result is ready.async · callback
`callback_url`	text	conditional	Public HTTPS URL for callback delivery.Only in request_type=callback
`mode`	select	required	Choose the generation workflow supported by this model.text-to-image · image-to-image
`prompt`	string	required	Describe the subject, composition, style, lighting, and details you want in the final image.
`aspect_ratio`	select	required	Choose the output frame ratio.1:1 · 16:9 · 4:3 · 3:2 · 2:3 · 3:4 · 9:16 · 21:9
`resolution`	select	required	Choose the output resolution tier. Higher tiers can cost more.1K · 2K
`num_images`	select	optional	Number of images to request.1 · 2 · 3 · 4 · 5 · 6 · 7 · 8 · 9
`size`	text	optional	Optional WIDTH*HEIGHT size from 512 to 2048 per side. Resolution and aspect ratio take precedence when both are provided.
`prompt_optimizer`	boolean	optional	Let MiniMax optimize the prompt before generation.
`seed`	text	optional	Use -1 for random output or provide an integer seed up to 2147483647.

File parameters (URL arrays)

image_urls[mode=image-to-image]Upload exactly one reference image for MiniMax Image 01 image-to-image mode.Only in mode=image-to-image

Example (cURL)

curl -X POST "https://api.apixo.ai/api/v1/generateTask/minimax-image-01" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "request_type": "async",
    "input": {
      "mode": "text-to-image",
      "prompt": "Premium editorial product launch image for a compact AI voice recorder on a clean walnut desk, soft morning window light, brushed aluminum body, glass reflections, realistic shadows, modern studio workspace, no text, photorealistic, high detail.",
      "resolution": "2K",
      "aspect_ratio": "16:9",
      "num_images": 1,
      "size": "1024*1024",
      "prompt_optimizer": false,
      "seed": -1
    }
  }'

Full API documentation

Capabilities

Model Strengths for Directed Image Creation

Precise Prompt Control

MiniMax positions Image-01 around close prompt-to-image alignment. Detailed descriptions can coordinate subject, environment, composition, lighting, material, and visual style instead of relying on a short theme alone.

Structured Composition

The model is designed to organize complex scenes with layered environments, foreground and background relationships, and deliberate light and shadow. This makes it useful for art-directed concepts rather than isolated subject generation alone.

Human Subject Rendering

Image-01 focuses on lifelike skin texture, facial expression, lighting, and other fine human details. Its official image-to-image workflow supports a person reference, although resemblance should be reviewed rather than treated as exact identity preservation.

Material and Object Detail

MiniMax highlights the model’s ability to render objects with differentiated surfaces, reflections, and material characteristics. Product concepts can therefore communicate finish and atmosphere, while exact dimensions and branding still require validation.

High-Batch Efficiency

Generate up to nine images in one APIXO task to compare compositions, lighting treatments, character interpretations, or campaign directions. Each successful image is billed separately, allowing teams to scale exploration without creating individual requests.

Seeded Iteration

APIXO accepts a fixed integer seed or a random setting. Reusing a seed helps compare controlled prompt and layout changes, but it does not guarantee identical output when other request settings change.

Workflows

Start from a Description or One Subject Reference

Text-to-Image Generation

Describe the desired subject, composition, lighting, materials, environment, and style without uploading an image. APIXO lets each request target a preset ratio or supported custom dimensions and return between one and nine generated results.

Prompt-Led

Single-Reference Image-to-Image

Supply exactly one public image URL with a required prompt. The reference guides a newly generated result—officially including subject-reference use for people—rather than providing mask-based editing, inpainting, or guaranteed pixel-level preservation.

Reference-Guided

Specifications

MiniMax Image-01 Options on APIXO

Verified output and generation controls for the current public route.

1K / 2K

Resolution

512–2048 PX

Custom Sides

8 Presets

Aspect Ratios

1–9

Images per Task

One URL

Reference Input

1–1500 Characters

Prompt Length

Use Cases

Production Uses for MiniMax Image-01

Ecommerce

Product Scene Concepts

Place a product concept within styled interiors, editorial sets, or contextual environments while directing lighting and material treatment. Use batches to compare visual approaches, then verify packaging, dimensions, logos, and factual product details against approved assets.

Campaign Design

Multi-Format Creative Sets

Develop coordinated landscape, portrait, square, and ultrawide concepts for advertising or social campaigns. Eight APIXO aspect-ratio presets allow the composition to be planned for its intended placement instead of cropped from one universal canvas.

Character Concepts

Reference-Guided Portraits

Use one person reference to guide a newly generated portrait or character scene with different lighting, wardrobe, environment, or visual treatment. Human review remains necessary where exact identity or biometric resemblance matters.

Content Operations

Batch Visual Production

Request up to nine candidates for article art, thumbnails, moodboards, campaign exploration, or application-generated media. Seed and prompt-optimizer controls help teams compare deliberate iterations without adding a separate batch endpoint.

Notes & FAQ

MiniMax Image-01 Requirements and Limits

Important Notes

APIXO requires a non-empty prompt between 1 and 1,500 characters for both workflows.

Image-to-image accepts exactly one publicly reachable reference-image URL.

When custom size and resolution-plus-ratio are both supplied, APIXO gives resolution and aspect ratio precedence.

APIXO documents typical processing of 15–40 seconds, but actual completion time can vary.

The public route does not expose masks, inpainting, outpainting, negative prompts, transparency, or watermark controls.

Hands, anatomy, embedded text, logos, exact identity, and precise product geometry should be reviewed before publication.

Frequently Asked Questions

Yes. APIXO maps the route specifically to MiniMax Image-01 and exposes only text-to-image and single-reference image-to-image workflows. It does not group later MiniMax image models, Hailuo video generation, or MiniMax speech, music, and language products.

The image guides a newly generated result rather than acting as a fixed canvas. MiniMax officially describes image-to-image support with subject reference for people; APIXO does not expose separate composition-reference, Style Reference, mask-editing, or multi-reference modes.

APIXO accepts a batch count from one through nine. Each successful image is billed separately at the same rate, regardless of whether the task uses text-to-image or image-to-image.

APIXO charges $0.0035 per successfully generated image. The route uses the same flat per-image rate for text-to-image and image-to-image and adjusts final billing to the number of successful outputs.

No. A fixed seed provides a controlled starting condition for iteration, but changes to the prompt, reference image, dimensions, ratio, resolution, prompt optimization, or provider behavior can change the result. Preserve approved source assets outside the generation workflow.