GLM-5.2 is now availableLearn more
EvoLink.AIEvoLink.AI

Midjourney V8.1 API

Call the Midjourney V8.1 API directly on EvoLink — per-request pricing from $0.075, a live playground, HD/2K output options through model parameters, image-to-image, Omni Reference, and Style Reference. New accounts get 10 free credits to test V8.1 before any commitment.
Model Type:
✓GenerateRetextureRemove BGMask Edit
VariationRemixCanvas

Price: $0.079 - 0.238(~ 5.4 - 16.2 credits) per request (4 images)

Highest stability with guaranteed 99.9% uptime. Recommended for production environments.

Each variant uses a different model parameter. Edit variants require a completed mj-v8.1 task ID.

0 (suggested: 2,000)

Click Generate to see preview

History

Max 20 items

0 running · 0 completed

Your generation history will appear here

Midjourney V8.1 API Pricing, Playground, and Integration

The fastest way to use the Midjourney V8.1 API in production workflows. Transparent per-request pricing, a browser playground, image-to-image with reference image support via Omni Reference, and complete Midjourney V8.1 API documentation — all behind one EvoLink key. 10 free credits on signup.

Midjourney V8.1 API playground and pricing on EvoLink

Billing Rules

  • •Fast and Turbo return 4 images per request — some may be filtered by content review, so you get 1–4 back.
  • •Credits are charged per request, not per image.
  • •Draft and Fast are billed the same (1×); Turbo is 2×.
  • •HD (2K) adds a further 1.5× multiplier, stacking with the speed tier (e.g. Turbo + HD = 3× the base).
  • •Draft (sketch) returns 24 images at 0.5K instead, and cannot be combined with HD.

Pricing

Midjourney V8.1
Image Generation
Speed:Draft
Quality:Sketch
Price:
$0.079/ image
(5.4 Credits)
Midjourney V8.1
Image Generation
Speed:Fast
Quality:Standard
Price:
$0.079/ image
(5.4 Credits)
Midjourney V8.1
Image Generation
Speed:Turbo
Quality:Standard
Price:
$0.159/ image
(10.8 Credits)
Midjourney V8.1
Image Generation
Speed:Fast
Quality:HD
Price:
$0.119/ image
(8.1 Credits)
Midjourney V8.1
Image Generation
Speed:Turbo
Quality:HD
Price:
$0.238/ image
(16.2 Credits)

If it's down, we automatically use the next cheapest available—ensuring 99.9% uptime at the best possible price.

What Can You Build with Midjourney V8.1?

Product Photography and Commerce Visuals

Build commercial image pipelines with Midjourney V8.1. This is a strong fit for midjourney product photography use cases, including ecommerce packshots, product mockups, ad creatives, and branded concept images.

Explore Creative Use Cases
Creative asset production example

Midjourney Image to Image Workflows

Guide every generation with reference images. The Midjourney V8.1 API supports midjourney image to image through image prompts, Omni Reference (--oref), Style Reference (--sref), and image weight (--iw) for repeatable, style-consistent output.

View Reference Examples
Image-to-image transformation example

Reference Image Workflows with Omni Reference

Use a Midjourney reference image to anchor the subject, object, or scene of every generation. The Midjourney V8.1 API supports Omni Reference (--oref) and Style Reference (--sref) so teams can build repeatable, brand-consistent image pipelines.

See Reference Examples
Midjourney reference image workflow example

Why Choose Midjourney V8.1 API?

Access Midjourney V8.1 through evolink.ai for a developer-friendly API experience with HD/2K output options, transparent pricing, async task handling, and one EvoLink key for production image workflows.

HD/2K Output Options and Speed Tiers

The EvoLink V8.1 route exposes 1080p and 2K quality options through model_params, plus Draft, Fast, and Turbo speed tiers for balancing cost, queue priority, and output quality. Use the pricing table on this page as the billing source of truth for each combination.

Native MJ Syntax

Use supported Midjourney-style parameters directly in your prompts, including --ar for aspect ratio, --s for stylize, --chaos for variation, --sref for Style Reference, --oref for Omni Reference, --iw for image weight, --seed, --raw, and related reference controls. Speed and resolution are passed via model_params, not in the prompt.

Enterprise-Ready Infrastructure

EvoLink wraps the V8.1 route in an async API workflow with task IDs, status polling, callback support, unified credits, and API-key authentication, so teams can integrate image generation without building separate routing and billing logic.

How to Integrate Midjourney V8.1

Three steps to add professional image generation to your application.

1

Get Your Credentials

Sign up at evolink.ai to receive your secure API key. This single key grants you authenticated access to the Midjourney V8.1 model pipeline.

2

Construct Your Payload

Define your prompt with native MJ syntax, choose a speed tier (draft/fast/turbo), and optionally provide reference images. Our developer-friendly docs make configuration intuitive.

3

Retrieve and Display

Send the request and poll for results. Each completed task returns up to 4 high-quality images. Our optimized delivery network ensures reliable performance.

Key Capabilities of Midjourney V8.1

Explore the technical strengths of MJ V8.1 accessible via our platform.

Quality

HD/2K Output Options

Choose 1080p for everyday work or the 2K quality option when you need a sharper final image. Resolution is controlled through EvoLink model parameters and billed according to the pricing table on this page.

Power

Native Prompt Syntax

Supports the V8.1 prompt controls exposed by this route: --ar (aspect ratio), --s (stylize), --chaos, --exp, --raw, --seed, --sref (Style Reference), --oref (Omni Reference), --iw (image weight), --sw (style weight), and --ow (Omni weight). The version is locked to V8.1, so --v is handled for you.

Flexibility

Three Speed Tiers

Draft (1x), Fast (1x), and Turbo (2x) modes let you balance cost vs. priority for every request, and 1080p (1x) or 2K (1.5x) lets you balance cost vs. quality.

Control

Omni and Style Reference

Use --oref (Omni Reference) to anchor subjects across generations and --sref (Style Reference) for style transfer, with adjustable --sw weight. These controls are especially useful for midjourney personalization, brand-consistent product photography, and reusable style systems.

Architecture

Async Processing

Asynchronous task handling with progress tracking. Poll for status and retrieve results when ready. Typical completion in 1-3 minutes.

Safety

Content Review

Built-in content safety filtering. Each of the 4 images is individually reviewed, and only approved images are returned in the results.

Midjourney V8.1 vs Other Image APIs

ModelBest fitWhere it winsWhen to choose it
Midjourney V8.1Production image generation, product photography, reference-image workflowsMJ-style prompt control, Omni Reference, Style Reference, 4 images per request, and HD/2K quality options on one EvoLink routeChoose it when visual direction, subject anchoring, and Midjourney-style creative control matter more than raw lowest cost.
Midjourney V7Existing Midjourney V7 pipelines and stable legacy workflowsSame Midjourney family with familiar workflow patterns and existing EvoLink route supportChoose it when you already built around V7 behavior or need to keep an older production route unchanged.
Nano Banana ProImage editing, product mockups, text-heavy visuals, and Google Gemini image workflowsStrong instruction following, conversational image iteration, and high-fidelity visual editing through the Gemini image stackChoose it when editable mockups, readable text, or Gemini-native workflows are more important than MJ prompt syntax.
GPT Image 2OpenAI image workflows, world-knowledge-aware generation, and precise instruction followingUses text and image understanding with strong contextual awareness through OpenAI's image generation APIChoose it when your app already uses OpenAI APIs or needs image generation tied closely to broader reasoning workflows.

Frequently Asked Questions

Everything you need to know about the product and billing.

Midjourney does not currently publish a public developer API in its public docs. EvoLink provides a managed Midjourney V8.1 API route: one API key, supported MJ-style prompt syntax, async task IDs, and per-request billing. If you were searching for "does midjourney have an api", this page is the fastest way to call V8.1 from code through EvoLink.
Midjourney V8.1 API pricing on EvoLink is per request, not per image. Standard generation (text-to-image and image-to-image) starts at $0.075 per request at Fast + 1080p and goes up to $0.225 at Turbo + 2K. Variant operations — variation, remix, canvas edit, advanced edit, and retexture — start at $0.1125 (Fast) and reach $0.225 at Turbo. Remove-background is a flat $0.075. Speed tiers are Draft (1x), Fast (1x), and Turbo (2x); resolution is 1080p (1x) or 2K quality option (1.5x). Draft and Fast cost the same — there is no half-price draft.
New EvoLink accounts receive 10 free credits on signup, which you can spend on the Midjourney V8.1 API directly from the playground on this page. It is the simplest way to test image-to-image, Omni Reference, and product photography workflows before any paid commitment.
Full Midjourney V8.1 API documentation — endpoint, parameters, async task lifecycle, callback URL, and error codes — lives in the EvoLink API manual. You can also try every parameter live in the playground above before integrating.
For midjourney image to image, pass reference image URLs at the start of your prompt (or via the image_urls parameter). The API supports three shapes: one image URL plus text, two or more image URLs with or without text, and reference URLs combined with --iw (image weight) to tune influence. A single image URL with no text is rejected by Midjourney.
Yes. The Midjourney V8.1 route supports Omni Reference via --oref to anchor subjects, objects, or scenes across generations, and Style Reference via --sref with adjustable --sw style weight. These are the right controls for repeatable brand visuals, midjourney product photography, and consistent creative direction.
Inside the prompt, the V8.1 API accepts the supported route parameters shown in the API reference and Prompt Builder, including --ar, --s, --chaos, --exp, --raw, --seed, --iw, --sref, --sw, --oref, and --ow. Speed and quality are passed via model_params, not in the prompt. The version is locked to V8.1, so --v is handled for you. Character Reference (--cref), --cw, --tile, --weird, --niji, --q, and --no are not exposed on this route; use --oref in place of --cref.
Yes. Midjourney V8.1 is a strong fit for midjourney product photography: hero shots, ecommerce packshots, launch visuals, mockups, and ad creatives. Pair a clean prompt with Omni Reference (--oref) for subject anchoring and Style Reference (--sref) for brand-consistent lighting and material direction.
A strong midjourney image prompt covers subject, composition, environment, lighting, camera or rendering cues, and style goal. Then add parameters: --ar for ratio, --s for stylize, --iw for reference weight, and --sref or --oref when you need repeatability. The Prompt Builder on this page assembles valid V8.1 prompts for you.
Yes. Every mj-v8.1 generation request produces 4 image variations. Each image is individually reviewed by Midjourney's content safety filter, so you may receive 1-4 approved images. Billing is per request, not per image, regardless of how many pass review.
Draft and Fast cost the same (1x); Draft is useful for exploration and batch ideation, while Fast is the default for production workflows. Turbo (2x) gives higher queue priority for urgent requests. To get a sharper final, re-run a winning prompt at Turbo and/or with the 2K quality option rather than expecting a half-price draft tier — V8.1 has no discounted draft.
When you submit a request, the API immediately returns a task ID. Poll /v1/tasks/{task_id} to check progress, or provide a callback_url to receive a webhook when the task finishes. Typical completion is 1-3 minutes; the task timeout is 10 minutes.

Prompt

Image Prompt

Up to 20 images
Drop files here or click to upload

JPG, JPEG, PNG, WEBP, GIF · Max 10MB · Up to 20 files

Composition

--ar

Style & Creativity

--s
100
--chaos
0
--exp
0
--raw

Control

--seed

Style Reference

--srefUp to 20 images
Drop files here or click to upload

JPG, JPEG, PNG, WEBP, GIF · Max 10MB · Up to 20 files

Object Reference

--oref1 image only
Drop files here or click to upload

JPG, JPEG, PNG, WEBP, GIF · Max 10MB · Up to 1 file

Assembled Prompt0 chars

Enter a prompt to begin...

V8.1 Quick Reference

--ar W:H — Aspect ratio (integers only)

--s 0-1000 — Stylize (default 100)

--chaos 0-100 — Variation between 4 images

--exp 0-100 — Experimental aesthetics

--raw — Disable beautification

--sref URL — Style reference

--oref URL — Object reference (generation takes longer)

--v 8.1, speed tier, and resolution are handled by the API automatically.

POST
/v1/images/generations

Generate Image

Midjourney V8.1 (mj-v8.1) generates 4 high-quality images per request. Supports text-to-image and image-to-image with native Midjourney prompt syntax.

Asynchronous processing mode, use the returned task ID to .

Generated image links are valid for 24 hours, please save them promptly.

💡Each request produces 4 images. Some may be filtered by Midjourney's content review, so you'll get 1–4 back.Credits are charged per request, not per image.

Request Parameters

modelstringRequiredDefault: mj-v8.1

Image generation model name.

ValueDescription
mj-v8.1Midjourney V8.1 model
Examplemj-v8.1
promptstringRequired

Prompt describing the image to generate. Supports the V8.1 route parameters exposed in the Prompt Guide, including --ar, --s, --chaos, --exp, --raw, --seed, --sref, --oref, and image-reference controls. For image-to-image, place image URLs at the beginning of the prompt (native MJ syntax).

Notes
  • This model uses Midjourney V8.1 — no need to specify --v 8.1
  • --v / --version parameters are not supported and will be ignored
  • Speed flags (--fast, --turbo, --draft) are not supported in prompt — use the speed parameter instead
  • Use the top-level quality parameter (standard / hd) for output quality; do not pass resolution as a prompt flag
  • Image-to-image: place image URLs before the text prompt (e.g. https://example.com/ref.jpg a cat --ar 16:9)
  • Route-exposed MJ-style parameters include --ar, --s, --chaos, --exp, --raw, --seed, --sref, --oref, --iw, --sw, and --ow
Examplehttps://example.com/reference.jpg a serene Japanese garden with cherry blossoms --ar 16:9 --s 500
model_params.speedstringOptionalDefault: fast

Generation speed tier. Affects pricing and queue priority.

ValueDescription
draftEconomy sketch mode (1× price): returns 24 images at 0.5K. Incompatible with hd quality.
fastDefault mode (1× price)
turboFastest queue priority (2× price)
Examplefast
qualitystringOptionalDefault: standard

Output quality tier (top-level parameter, OpenAI-compatible). Affects pricing.

ValueDescription
standardStandard output (1× price)
hdHD output (1.5× price). Incompatible with draft speed.
Examplestandard
callback_urlstringOptional

HTTPS callback address after task completion.

Notes
  • Triggered on completion, failure, or cancellation
  • HTTPS only, no internal IPs
  • Max length: 2048 chars
  • Timeout: 10s, Max 3 retries
Examplehttps://your-domain.com/webhooks/mj-task-completed

Request Example

{
  "model": "mj-v8.1",
  "prompt": "a serene Japanese garden with cherry blossoms --ar 16:9 --s 500",
  "quality": "standard",
  "model_params": {
    "speed": "fast"
  },
  "callback_url": "https://your-domain.com/webhooks/callback"
}

Response Example

{
  "created": 1757156493,
  "id": "task-unified-1757156493-xkd8mv2r",
  "model": "mj-v8.1",
  "object": "image.generation.task",
  "progress": 0,
  "status": "pending",
  "task_info": {
    "can_cancel": true,
    "estimated_time": 120
  },
  "type": "image",
  "usage": {
    "billing_rule": "per_call",
    "credits_reserved": 6.0,
    "user_group": "default"
  }
}