Azurade AI

npx add-mcp 'https://azurade.com/mcp'

Image and video generation for AI agents

One MCP server and one REST API in front of 37 image and video models. Both bill the credit balance you use in the web app, at the same prices.

MCP server

https://azurade.com/mcp

REST API

/api/v2, keys as Bearer tokens. Reference

Billing

A credit costs $0.02 to $0.04. Credits never expire; 4 free on signup.

Connect an MCP client

Claude (web and desktop)

1. Open Customize > Connectors.
2. Click +, then Add custom connector.
3. Paste the URL.

On Team and Enterprise an owner adds it first under Organization settings > Connectors. The free plan allows one custom connector.

https://azurade.com/mcp

ChatGPT

1. Turn on Developer mode in Settings > Security and login.
2. Press + on the Plugins page and create an app with the URL.
3. Pick it from the Developer mode tool in a chat.

Developer mode is on Plus, Pro, Business, Enterprise and Edu, on the web.

https://azurade.com/mcp

Claude Code

1. Add the server.
2. Run /mcp in a session and pick azurade to sign in.

claude mcp add --transport http azurade https://azurade.com/mcp

Codex

1. Add the server.
2. Sign in with codex mcp login azurade.

codex mcp add azurade --url https://azurade.com/mcp

Gemini CLI

1. Add the server.
2. Run /mcp auth azurade in a session.

gemini mcp add --transport http azurade https://azurade.com/mcp

Cursor

1. Use Add to Cursor, or put this in ~/.cursor/mcp.json.

{"mcpServers": {"azurade": {"url": "https://azurade.com/mcp"}}}

Add to Cursor

VS Code

1. Run MCP: Open User Configuration, or edit .vscode/mcp.json.
2. Add this server entry.

{"servers": {"azurade": {"type": "http", "url": "https://azurade.com/mcp"}}}

On first use the client opens an Azurade page where you sign in and click Allow, and it's connected without you copying a key.

A client that cannot sign in sends a key from your profile page instead:

claude mcp add --transport http azurade https://azurade.com/mcp --header "Authorization: Bearer sk-..."

Then ask for a picture in Claude:

A teal dragon breathing a stream of photos into the night sky, painterly

estimate_generation

model: "nano-banana-pro", resolution: "2K", aspect_ratio: "4:5"

← cost: 9, balance: 240, affordable: true

create_generation

same arguments

← status: "completed", cost: 9

outputs[0].url: https://azurade.com/api/files/output\_result\_files/r8f2k1x0q9m4b7d/dragon.png

Here it is. That took 9 credits; 231 left.Made with Nano Banana Pro on Azurade

REST API

1. Create a key on your profile page. GET /api/v2/models is public; everything else takes the key.
2. POST /api/v2/generations/estimate takes the same body and returns the cost and whether your balance covers it. It starts nothing.
3. The create call answers 202 with an id. Poll GET /api/v2/generations/<id> until the status is failed, or completed with files in outputs.

The MCP tools call the same code, so prices, refunds, content screening and error codes match. Download links need no authentication: anyone you share one with can open the file.

Full contract: the OpenAPI document, generated from the running code and browsable at /swagger/. Agents that read skills can start from SKILL.md.

Request

curl -X POST https://azurade.com/api/v2/generations \
  -H "Authorization: Bearer $AZURADE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "nano-banana", "prompt": "a lighthouse at dusk"}'

Response, then the poll

202 Accepted
{"id": "r8f2k1x0q9m4b7d", "model": "nano-banana", "type": "image",
 "status": "pending", "cost": 2}

GET /api/v2/generations/r8f2k1x0q9m4b7d
{
  "id": "r8f2k1x0q9m4b7d",
  "status": "completed",
  "cost": 2,
  "outputs": [{
    "url": "https://azurade.com/api/files/output_result_files/.../lighthouse.png",
    "content_type": "image/png"
  }]
}

What the agent can do

Eleven tools. A finished image comes back with its download link and a small inline preview, so the agent can look at what it made before deciding to try again.

Choose a model

list_models

Every model with its type and the credit price of a default request.

get_model

One model's parameters: names, defaults, allowed values.

estimate_generation

The exact credit cost of a request. Free, starts nothing.

Generate

create_generation

Starts an image or video and waits up to about 50 seconds for it.

get_generation

Status and file links; waits again while the job runs.

list_generations

Your history, newest first.

create_upload_url

A one-off link the agent's shell uploads a local file to with curl.

Prompts

enhance_prompt

Rewrites a short prompt using the target model's prompting guide.

moderate_prompt

Runs the content-policy screen on a prompt without generating.

Account

get_account

Your credit balance.

buy_credits

A card checkout link for a credit pack, for you to pay when the balance runs out.

Models and prices

Credits for a request that sends only a prompt, the figure estimate_generation returns for it. † marks a model whose price changes with resolution, duration or inputs; estimate those before you submit. A credit costs $0.02 to $0.04 depending on the pack or plan.

Image models 22

Model id	Best for	Takes	Credits
nano-banana	Quick image edits and blending several reference images	text, image	2
qwen-image-2.1	Generating and editing in one model, with transparent backgrounds	text, image	2†, price varies
recraft-crisp-upscale	Upscaling an image with crisp edges and text	image	2
remove-background	Cutting the subject out onto a transparent background	image	2
flux-dev	General-purpose images with control over steps, guidance and seed	text, image	3†, price varies
gpt-image-2.5	Photorealistic images with precise text up to 4K, and tighter edits	text, image	3†, price varies
qwen-image	Images and edits with clean in-image text in Chinese or English	text, image	3†, price varies
qwen-image-edit	Editing one image with a text instruction	text, image	3
qwen-image-edit-plus	Edits that combine several input images, such as swapping outfits	text, image	3
qwen-image-edit-plus-lora	Image edits in the style of a custom LoRA	text, image	3
seedream-3	Photoreal images at up to 2048 px	text	3
seedream-4	Up to 6 images per request, and edits with up to 10 references	text, image	3†, price varies
seedream-4.5	Detailed images up to 4K, and edits with up to 14 references	text, image	3
wan-2.7-image	Images and sets of up to 12 related images, up to 4K on Pro	text, image	3†, price varies
flux-kontext-pro	Editing an image with a text instruction while the rest stays put	text, image	4
nano-banana-2	Images up to 4K with legible text, many references and web search	text, image	4†, price varies
nano-banana-2-lite	Fast, cheap drafts and quick edits at 1K	text, image	4
restore-image	Repairing old, scratched or faded photos	image	4
gpt-image-2	Photorealism and exact text in images, such as posters and UI mockups	text, image	6
imagen-4-ultra	Detailed photorealistic images from a text prompt	text	6
nano-banana-pro	High-fidelity images up to 4K with accurate text and compositing	text, image	9†, price varies
qwen-image-layered	Splitting an image into separate transparent layers for editing	text, image	11†, price varies

Video models 15

Model id	Best for	Takes	Credits
wan-2.2	Low-cost short clips, with LoRA support	text, image	1†, price varies
seedance-2-mini	Lower-cost video with a soundtrack from text or images, up to 15 s	text, image, video, audio	20.5†, price varies4.1 per second
motion-control	Making a character from a photo copy the moves in a reference video	text, image, video	27.5†, price varies5.5 per second
veo3.1	8 s video with native sound from text, first and last frames, or references	text, image	30†, price varies
wan-3.0	Clips up to 30 s at 1080p with sound, from text, frames or image, video and audio references	text, image, video, audio	40†, price varies8 per second
wan-2.6	Multi-shot video from text or an image, 5 to 15 s at up to 1080p	text, image, video	53†, price varies
wan-2.7	Video from text or images, continuing a clip, or editing a video	text, image, video, audio	60†, price varies
wan-3.0-prime	Faster clips up to 30 s at 1080p with sound, from text, frames or image, video and audio references	text, image, video, audio	63†, price varies12.6 per second
seedance-pro	1080p video from a prompt, 2 to 12 s	text	75†, price varies15 per second
seedance-2	Video with a soundtrack from text or images, up to 15 s, with a fast tier	text, image, video, audio	102.5†, price varies20.5 per second
veo3-fast	Faster, cheaper 8 s video with native sound	text	120
seedance-2.5	Clips up to 30 s at 1080p, steered by image, video or audio references	text, image, video, audio	160†, price varies32 per second
hunyuan	Text-to-video with control over frame count, size and steps	text	250
veo2	Short clips from a prompt or a first-frame image	text, image	250†, price varies50 per second
veo3	8 s video with native sound and dialogue at up to 1080p	text	320

Questions

Do I need an API key to use the MCP server?

Not with a client that supports MCP authorization, which covers Claude, ChatGPT, Claude Code, Codex, Gemini CLI, Cursor and VS Code. The client opens an Azurade page, you sign in and click Allow, and it's connected. A client without OAuth support sends a key from your profile page as Authorization: Bearer sk-...

How do I disconnect a client?

Each connection is a key named after the client, for example "Claude (connected app)", on your profile page. Delete it and the client loses access at once.

What does a generation cost through the API?

The same credits as in the web app. There's no separate developer plan or per-seat fee. A failed generation is refunded to your balance automatically.

Why does create_generation sometimes answer pending?

Most MCP clients give up on a tool call after 60 seconds, so the server returns after about 50 with the job's id. The agent calls get_generation, which waits another 50 seconds. Images usually finish inside the first call; a video can take a few.

Can the agent use an image from my computer?

Yes. create_upload_url gives the agent a link and a curl command; it uploads the file from your machine and passes the returned URL to the model. The link works for 15 minutes and needs no key. A file that is already online needs no upload.

What happens when the agent runs out of credits?

It calls buy_credits and hands you a checkout link for a credit pack. You pay by card on the checkout page, which shows the price, and the credits land on your balance at once. The agent cannot pay by itself.

Can an agent without a key sign itself up?

It can ask for a key, but you approve it. The agent gives you a link and a six-digit code; you sign in, type the code, and the agent receives a key named "Agent" on your account. Delete that key on your profile page to cut it off.