Skip to main content
​

​
Organization and Enterprise Discounts

Modellix now offers discounts on Media Models and LLM for organization and enterprise customers.To request a discount, email support@modellix.ai.
​

​
Postpaid Billing

Modellix now supports postpaid billing: use the service first and pay afterward.Postpaid usage is calculated by calendar month. On the 1st of each month, Modellix issues a bill for the previous month. Pay that bill within the stated payment period to keep the service running. If the bill is not paid within that period, the service is stopped.To switch to postpaid billing, contact support@modellix.ai.
​

​
Comfy Registry and Manager Installation

Modellix for ComfyUI 0.1.0 is published on Comfy Registry. Search for Modellix in ComfyUI-Manager, check publisher modellix, select 0.1.0, install, and restart ComfyUI. The package ID for CLI installs is modellix-comfyui. ComfyUI 0.40.0+ and Python 3.10+ are required.The release includes Generate, Get Task, Upload Media, and URL List, with live model schemas, native image/video/audio connections, local API key settings, and recovery of existing tasks. Git installation remains available. Future package changes reach Registry installations through a new version release.Registry security scanning is separate from publication. If Manager reports pending security validation or no active release versions, use Git installation while the Registry review completes.
​

​
Plugin Media MCP Routing

Plugin 4.7.0 submits image, video, and audio tasks through Media Generation MCP when those tools are available and the input is not a local file. It uses the CLI for local files, batch, and downloads, and the REST API when both Media Generation and the CLI are unavailable.
  • Name a provider/model slug in your prompt. When you leave the model unnamed, the agent asks which slug to run and waits.
  • An unknown paid submission stays on that attempt. Recover with the returned task ID, or check task history when no ID came back.
GitHub marketplace installs, git checkouts, and npx skills add from the plugin repository install 4.7.0. The published npm package @modellix/modellix-plugin is still 4.2.2.The Skill guide matches this execution policy. modellix-design is the execution skill.

​
Prompt Planning and Local Edit Skills

The same release adds four skills beside modellix-design and modellix-image-prompt-engineering.
  • modellix-social-card and modellix-infographic write prompts and hand generation to modellix-design.
  • modellix-ffmpeg and modellix-moviepy edit files already on disk. Their check scripts print an install command. You install FFmpeg, moviepy, and Pillow yourself, and the scripts do not call Modellix.
Those four skills ship with the plugin and with a checkout of the repository. A skill-only install of modellix-design includes execution only.
​

​
ComfyUI Schema Review and Recovery Errors

Modellix for ComfyUI now blocks Queue after a saved schema changes until you check the affected fields and select Accept Reviewed Schema. Refreshing or reopening a workflow cannot silently approve changed parameters.
  • Credential changes clear the previous account’s model catalog, pricing, and fields, including late responses.
  • Get Task errors and local deadlines keep the current task ID for copying and recovery.
  • Parameter errors retain cleaned upstream field guidance. A 404 identifies the requested task or model, and generation POST requests remain protected against automatic replay.
​

​
ComfyUI Startup Compatibility Check

Modellix for ComfyUI now checks the host version before loading its four nodes or registering local routes. Hosts below ComfyUI 0.40.0, including pre-releases of that version, receive an explicit compatibility message. Unreadable version metadata also blocks registration with update or repair guidance.Update ComfyUI to 0.40.0 or later and restart before using the package.
​

​
ComfyUI Recovery and Workflow Examples

Modellix for ComfyUI now includes screenshots of real image, frame-to-video, speech, task-recovery, and local key-setup workflows.
  • Reviewing an updated model schema keeps the existing paid attempt. Unknown submissions and damaged protection records cannot silently create another task.
  • Switching models while their fields load cannot submit the previous model. New Attempt clears an entered recovery ID and the old task display.
  • Local deadlines include preparation and shared waits. Recovering an undecodable download fetches a fresh copy from the original task, and result links support a custom local result directory.
The package remains available through GitHub installation; Registry and Manager publication are separate.
​

​
Modellix for ComfyUI

Modellix for ComfyUI is available through GitHub installation. Choose a live media model in one Generate node, edit its schema-driven fields, and connect native IMAGE, VIDEO, and AUDIO inputs and outputs.
  • Generate uploads connected inputs and submits once. Use Wait for downloaded native results or Submit only to return the task ID immediately.
  • Get Task retrieves or waits for existing tasks. Upload Media and URL List support reusable uploads and ordered reference arrays.
  • Configure keys in Settings for the current session or OS secure storage, or use MODELLIX_API_KEY. Saved attempt identities and task records support recovery across host restarts without automatic paid-request replay.
The tutorial covers installation, all four nodes, importable workflows, cancellation, recovery, and common errors. The initial compatibility baseline is ComfyUI 0.40.0 with frontend 1.55.17 and Python 3.10 or later. Registry and Manager publication are separate from the available Git clone installation channel.
​

​
Canvas Task Waits

Agent Canvas 0.1.18 adds wait_modellix_image_task, with a 30-second default and a 45-second maximum per call. Canceling a wait stops the local read while preserving the paid task for recovery. Completed tasks can be finalized repeatedly without inserting duplicate images.

​
Plugin REST Recovery

Plugin 4.2.2 rejects redirects on authenticated REST calls and enforces the remaining request budget across connection, headers, and response reads. Known task IDs remain available after a timeout; ambiguous paid submissions are never automatically retried.The Skill and setup guides now use the current execution skill name, modellix-design, alongside the optional image prompt skill.
​

​
Media Generation MCP

The Media Generation MCP is available at https://tool.modellix.ai/mcp/media. Its eight tools cover model discovery, executable schemas, paid submissions, immediate task reads, bounded waits, and file upload, listing, and deletion. Connect with a Modellix API key and an MCP 2026-07-28 client.

​
Wait for Existing Tasks

Query Task Result accepts wait=true with a bounded timeout. A normal deadline returns HTTP 200 and the current task snapshot. Continue waiting with the same task ID; do not submit another generation request.Modellix CLI 0.0.11 uses server-side waits, preserves unfinished snapshots on overall timeout, and adds file list. CLI and MCP media uploads support image, video, and audio inputs up to 16 MiB, with explicit deletion when file quota is exhausted. Plugin 4.2.0 applies the same wait and recovery policy to its REST fallback.
​

​
Register Provider Asset

Register Provider Asset (POST /api/v1/media/providers/{provider}/assets) registers one public HTTPS URL in the ByteDance asset library for the authenticated team. Only bytedance is supported. The call is not billed.The response returns asset_id and status without waiting for moderation. When status is active, pass asset://<asset_id> in Seedance and Seedream image and video fields. url may be a URL returned by the Media Files API.

​
Model Price Discounts

Model cards on Modellix Explore now show price discounts. Each card lists the original price with a strikethrough and the discounted price beside it.
​

​
Modellix CLI Get Schema

modellix-cli now includes model get-schema.Use the exact provider/model slug from model list. The command calls the public Get Schema endpoint and does not require an API key. JSON is the default; --output human summarizes the contract; --quiet prints the inference URL.
For full usage details, see the CLI documentation.

​
Skill and Plugin Schema Lookup

The Modellix Skill and Plugin now read request-body schemas with model get-schema instead of guessing fields from documentation pages.The agent fetches the schema when you name a non-default model, when the body needs extra fields, or after HTTP 400. It skips the call for documented default examples or a complete body you already supplied. If the CLI is unavailable, it falls back to Docs MCP, docs_url from model describe, or llms.txt.
​

​
DeepSeek Harness Plugin

dsh-modellix is now available for DeepSeek Harness.Install the plugin in the Harness Web profile, then connect one Modellix API key. The plugin loads the live LLM catalog into the model selector, runs chat-first media generation with a session result panel, and lets the Agent call Web Search and Web Fetch when a question needs the public web.Source: github.com/Modellix/dsh-modellix
​

​
Signup Credit Ended

New registrations no longer receive a complimentary $1 credit.To request trial credit, contact the Modellix team at support@modellix.ai.
​

​
Web Search and Web Fetch

Modellix now provides Web Search and Web Fetch at https://tool.modellix.ai. Authenticate with your Modellix API Key.Web Search (POST /v1/web-search) searches the public web and returns ranked results. Choose depth (lite, standard, or rich) and optionally filter by domain, time range, topic, or country.

​
Web Fetch

Web Fetch (POST /v1/web-fetch) extracts readable content from public HTTP or HTTPS URLs (up to 20 per request). Failed URLs are returned separately.Query Web Search and Web Fetch history with Get Tool Logs (GET /v1/logs).
​

​
Modellix Agent Canvas Plugin

We launched Modellix Agent Canvas, a local workspace-bound stdio MCP plugin for visual AI work.Use an Excalidraw infinite canvas with Modellix image generation and editing, paid-operation confirmation, durable task recovery, HTML drafts, and presentations—without a deployed Canvas service. Install from the host plugin marketplace or MCP config for Codex, Cursor, Claude Code, OpenCode, and other local MCP hosts.Source: github.com/Modellix/modellix-agent-canvas

​
Japanese UI Language Support

The Modellix website and console UI now support Japanese.Open the Japanese locale at modellix.ai/ja_JP to browse product pages and the console in Japanese.ようこそ、日本のユーザーの皆さま。Modellix を日本語でお使いいただけます。ぜひご利用ください。
​

​
Online Invoice Export

You can now export invoices online from the console.On the Orders page, open any order and download its invoice directly—no manual request required.
​

​
Modellix CLI Upgrade

modellix-cli has been upgraded with a fuller command set for terminal, scripting, and agent workflows.

​
What’s New

  • Authentication profiles: init, auth login/status/whoami/logout, and named profiles with config inspection and cleanup.
  • Environment checks: doctor verifies Node.js, API key resolution, connectivity, and balance.
  • Model discovery: model list and model describe to find and inspect model slugs.
  • Model execution: model run (with model invoke as a compatible alias), --wait, stdin bodies, and model batch for JSONL submissions.
  • Task tooling: task get, task wait, task download, and local task history.
  • Automation-ready output: --json, --quiet, stable exit codes, and CI-friendly flags.
For full usage details, see the CLI documentation.
​

​
File API

We are excited to launch the File API, a free, API-Key-authenticated way to upload media assets and feed them directly into Modellix prediction APIs — no need to host the files yourself.

​
What’s New

  • Upload Media File (POST /api/v1/media/files): Upload a single image, video, or audio file via multipart/form-data. The response returns a file_id, media type, and a download_url you can pass into prediction API input fields such as image_url.
  • List Media Files (GET /api/v1/media/files): List the non-expired files belonging to your team with limit / offset pagination (max page size 100).
  • Delete Media File (DELETE /api/v1/media/files/{file_id}): Delete a file owned by your team to free upload quota immediately.

​
Highlights

  • Free of charge: Uploads are not billed and are not subject to balance freeze (admission).
  • Secure: Files are scoped to your team — there is no cross-team leakage.
  • Time-boxed retention: Uploaded files are retained for about 7 days by default.
  • Flexible formats: Supports common image, video, and audio extensions (e.g., png, mp4, mp3), with a default max file size of 16 MB.
To get started, see Upload media files for the full workflow, limits, and supported formats.
​

​
One-Click Media Export from Playground

We are excited to launch a powerful export feature in the Modellix Playground, allowing you to integrate generated media directly into your external storage or automated workflows.

​
Supported Export Destinations

Instead of downloading files locally and manually uploading them elsewhere, you can now transfer your generated images, videos, and audio directly to third-party platforms:
  • Webhook URL: Deliver the media payload directly to your custom Webhook endpoint to instantly trigger automated backend pipelines.
  • Google Drive: Save assets straight to your Google Drive folders for seamless cloud storage and sharing.
  • Dropbox: Send media assets directly to your Dropbox workspace with a single click.
To get started, generate any media in the Playground and click the Export button in the result panel to select your preferred destination.
​

​
Webhooks and Notification Settings

We are excited to announce two major updates that improve integration automation and account monitoring:

​
API Webhook Support

You can now configure a Webhook URL to receive task results asynchronously once your media generation tasks reach a terminal state.
  • Asynchronous Delivery: No more polling! Include the X-Webhook-URL header in your prediction creation requests, and Modellix will automatically deliver the payload to your endpoint.
  • Detailed Configuration: For full setup instructions, URL requirements, retry rules, and event payload schemas, please check the REST API Webhooks documentation.

​
Console Notification Settings

You can now configure notification alerts directly in the console to stay on top of your workspace events:
  • Low Balance Alerts: Set up email alerts to notify you when your team balance drops below your specified threshold, helping you prevent service interruptions.
  • Configure Now: Set up your notification preferences on the Team Notification Settings page.
​

​
Common API Updates

We have expanded our suite of utility endpoints under the Common API to improve key management, billing transparency, and model discovery:

​
New Utility Endpoints

  • Validate API Key (GET /api/v1/apikey/validate): A lightweight endpoint to programmatically verify whether an API Key is currently valid and active on the Modellix platform.
  • Get Team Balance (GET /api/v1/team/balance): Retrieve the current available balance (in USD with 4 decimal places) for the team workspace associated with the API Key.

​
List Active Models Upgrade

  • Model Descriptions: The List Active Models endpoint (GET /api/v1/models) now returns a description field for each model dynamically, providing a quick summary of the model’s capabilities and use cases directly in the JSON response.
​

​
First Top-Up Discount, Concurrency Entitlements, and Account Deletion

​
First Top-Up: 10% Off Every Tier

Each top-up option now includes a 10% discount on your first purchase of that tier. Visit the Top Up page in the console to see available amounts and apply the discount at checkout.

​
Concurrency Entitlements

When a single top-up reaches a qualifying amount, your workspace unlocks higher concurrent task and RPM limits. Thresholds and current entitlements are listed on the Team Entitlements page.

​
Self-Service Account Deletion

You can now delete your account from the console without contacting support. Open your account settings and follow the deletion flow when you are ready to close your Modellix account.
We hope you stick around — but if you ever need to leave, you are in full control.
​

​
Explore Filtering and Playground Shortcuts

​
Model Explore: Series and Collections Filtering

The Model Explore page now supports filtering models by series and collections, making it easier to browse related models and discover what you need faster.

​
Playground Shortcuts

The Model Playground now includes a set of quick actions to streamline your workflow:
  • Copy model details: Copy the model’s Markdown documentation content or direct URL with one click.
  • Copy Modellix Skill install command: Instantly copy the npx skills add command for the current model.
  • One-click Skill installation: Install the Modellix Skill directly into Manus, Codex, Claude Cowork, or Cursor.
  • One-click AI chat: Open a conversation about the current model in ChatGPT, Claude, Grok, and other supported assistants.
  • One-click MCP installation: Install the Modellix MCP server into Cursor, Devin, or Windsurf.
​

​
Pricing Page, Model Search, Dashboard, and Request Logs

​
Public Pricing Page

We have launched a dedicated pricing page where pricing for every model supported on Modellix is publicly available. You can search and look up the price of any model directly on the page.Model search has been upgraded to deliver faster, more accurate results when you browse and discover models on Modellix.

​
Dashboard Improvements

The Dashboard now presents clearer, more detailed information and guidance. We have also added a convenient top-up entry so you can add funds without leaving your workflow.

​
Request Log Input Parameters

Request logs now record input parameters for each API call. You can view these parameters directly in the log details to help with debugging and auditing.
​

​
Simplified API Endpoints

We have updated all model API endpoints to provide a cleaner and more intuitive developer experience. The /async suffix has been removed from all model invocation paths.For example, POST /alibaba/qwen-image-edit-plus/async is now simply POST /alibaba/qwen-image-edit-plus.Backwards Compatibility: If you are currently using the /async endpoints, your integrations will not be affected. We have implemented full backwards compatibility, so existing applications will continue to function normally without requiring immediate updates.
​

​
Models API

We have introduced a new utility endpoint to help developers programmatically discover model availability on Modellix:
  • List Active Models: A new GET /api/v1/models endpoint that retrieves a rich JSON array of all currently active (published) models.

​
Key Fields Explained

Each model entry in the returned payload contains:
  • slug: The unique model identifier in provider/model_id format (e.g., google/nano-banana-2-edit).
  • type: The functional category of the model, supporting text-to-image, image-to-image, text-to-video, image-to-video, and video-to-video.
  • docs_url: Direct fully qualified URI to the model’s detailed developer integration documentation page.
For integration examples and the full OpenAPI schema spec, please head over to the List Active Models API reference.
​
  • Banner Notifications: You can now receive important updates and notifications via a banner displayed at the top of the page.
  • Team Settings: You can now configure basic information (like Team Name) and tax details for your workspace team, ensuring compliance and proper invoicing.
​

​
Explore and Playground Features Added

Modellix now supports Model Explore and Playground:
  • Explore: Users can search and query all models supported by Modellix.
  • Playground: Users can directly experience all models supported by Modellix.
Additionally, in this update, the pricing for all models has been explicitly published.
​

​
Modellix CLI

modellix-cli is now available — the official command-line tool for Modellix.

​
What You Can Do

  • List model types: modellix-cli model types to see all supported model types.
  • Create tasks: modellix-cli model invoke to submit async generation tasks with inline JSON or a file body.
  • Query results: modellix-cli task get <task_id> to poll task status and retrieve generation output.

​
Designed for Automation

The CLI is built for scripting and AI agent workflows. All commands support --json output, and authentication works via the MODELLIX_API_KEY environment variable or the --api-key flag.For full usage details, see the CLI documentation.
​

​
Modellix Is Now Live!

Modellix is officially launched! 🎉

​
Console

  • Usage: Rich visualizations with charts and lists to monitor your model API consumption on Modellix.
  • Top Up: Securely add funds via Stripe, with support for auto-recharge.
  • Order: A complete and clear view of every order you have placed.
  • Transaction: A complete and clear record of every transaction, including top-ups and consumption.
Fill out this form to receive $10 – 30 in bonus credits and become one of our first users!
Join our Discord community to connect with us.
​

​
Agent Skill

  • Updated SKILL.md to improve Skill accuracy.
  • Published the Skill to ClawHub.
​

​
Console

  • Registration and login, supporting Email OTP, Google and Github.
  • API Key management: supports creating, deleting, and viewing API Keys, which can be used to access the Model API.