OhMyGPT API Docs
  1. Midjourney Open API
OhMyGPT API Docs
  • About This site
  • About new website
  • Midjourney Open API
    • About Midjourney Service
    • Midjourney Blend Image Generation Task Creation
      POST
    • Midjourney Text-to-Image Task Creation
      POST
    • Midjourney Execute Action Task Creation
      POST
    • Midjourney Query Specific Task ID Execution Status
      POST
    • Midjourney Paginated Bulk Query Tasks
      POST
    • Midjourney Describe Prompt Extraction Task Creation
      POST
    • Retrieve Images Generated by Midjourney from Object Storage
      GET
    • Retrieve Compressed Images Generated by Midjourney from Object Storage + WSRV
      GET
    • Retrieve Images Generated by Midjourney from Object Storage + WSRV
      GET
    • Proxy Discord Images via WSRV
      GET
    • Proxy and Compress Discord Images via WSRV
      GET
  • Management API
    • Create a New API Key
      POST
    • Update API Key Information
      POST
    • Query All of User's API Keys
      POST
    • Delete Specified API Key
      POST
    • Query User Membership Expiration Date
      POST
    • User Balance Query
      POST
    • Query the current model rates
      GET
  • OpenAI
    • About OpenAI Compatible API
    • About Azure OpenAI API
    • Audio
      • Text To Speech API
    • Chat
      • Chat Completion
      • Completion (Legacy)
    • Images
      • Create Image
    • Realtime API
  • Anthropic Claude
    • Deprecated
      • ChatCompletions
      • Claude2 API
    • Anthropic Official Claude API
  • Policies
    • Terms of Service
    • Privacy Policy
  • Other OpenAPIs
    • Search API
      • Google Custom Search API
      • Google Search By Serper
    • Azure API
      • Get Azure TTS voice list
      • Azure TTS
  1. Midjourney Open API

About Midjourney Service

Introduction#

MidJourney is a currently popular and powerful AI image model that can generate high-quality images through extremely simple prompts. It has a very low usage threshold and is therefore very popular.
However, since Midjourney officially does not provide an API interface, it is not convenient for the vast number of developers to integrate it into their own products. Therefore, this site provides a Midjourney API interface through Discord reverse engineering, which can conveniently allow developers/enterprise customers to quickly integrate reliable Midjourney capabilities into their own tools, products, and websites at a low cost, creating value for you or empowering your products.
The Mj function in the AI drawing on this site's webpage is developed based on these interfaces: https://www.ohmygpt.com/draw

Interface Description#

The MidJourney interface capabilities currently implemented by OhMyGPT are as follows:
MidJourney text-to-image capability (imagine)
MidJourney button action execution (action): Can perform functions such as image upscaling (UPSCALE), image variation (VARIATION), image expansion drawing (ZOOM), etc.
MidJourney image-to-text capability (describe): Can extract the prompt from the image
MidJourney multi-image blending generation capability (blend): Can blend 2 or more and less than 5 images through AI to generate new images
Note: If you need to call the MidJourney related interfaces, please ensure that your key has the midJourney permission checked and saved in the key permission control.
Recommended request body sending format: application/json
Supports real-time push of MidJourney task execution results via WebHook (recommended), and also supports actively polling MidJourney task execution results through ID.
WebHook callback notifications are ultimately delivered by Cloudflare Worker.
Recommended WebHook callback interface debugging tool website: https://webhook.site
Regarding how to determine the legitimacy of the WebHook and whether it was sent by this site, you can add some query parameters (such as random strings) to the WebHook URL for easy verification, so that your program can verify whether the WebHook is legitimate after receiving it.
Please refer to the documentation of the corresponding interface for details.

Service Access Flow Chart#

The access process is very simple. The following takes a flow chart of accessing text-to-image + executing various task actions as an example:

Pricing Description#

The MidJourney on this site is divided into two account pools. In FAST account mode, Midjourney accounts with Fast Hour will be used to provide you with services, bringing you high-speed and highly reliable MidJourney capabilities, while the NORMAL mode mostly uses the RELAXED mode to provide services, offering you the ultimate cost performance.
After each task is successfully executed, the fees deducted are as follows:
Action TypeFAST Mode Token CostNORMAL Mode Token Cost
IMAGINE140007000
UPSCALE35001750
VARIATION140007000
ZOOM140007000
PAN140007000
DESCRIBE35001750
BLEND140007000
Note: Since the two resource pools are mutually independent and managed separately, for continuous action execution, it is necessary to ensure that the mode is the same. For example, an IMAGINE task executed in NORMAL mode can only continue to execute actions in NORMAL mode, and cannot execute optional actions in FAST mode for tasks executed in NORMAL mode.

About Rate and Request Limits#

The rate limit for the MidJourney service on this site is mainly based on the user's membership level to limit the length of the task queue being executed.
Regular users are allowed to have up to 3 unfinished tasks in the queue
VIP users are allowed to have up to 20 unfinished tasks in the queue
Premium users are allowed to have up to 50 unfinished tasks in the queue
Modified at 2024-09-04 14:14:17
Previous
About new website
Next
Midjourney Blend Image Generation Task Creation
Built with