GPT Image 2.6 Sunburst API and MCP for AI agents
TollNode gives Claude, Cursor or any AI agent GPT Image 2.6 Sunburst, OpenAI's newest image model for detailed compositions and precise edits, over API and MCP, from $0.069 per image, with no subscription.
Ask for 'a clean illustrated map of a coastal town labelled HARBOUR, MARKET and LIGHTHOUSE' and get a finished image link back.
No subscription · Sign-up optional · From $0.069 per call · Charged only when it works · No OpenAI account needed
Create a clean illustrated map of a small coastal town from above, labelled HARBOUR, MARKET, LIBRARY, TRAIN STATION and LIGHTHOUSE, soft pastel colors, flat vector style, 4:3, medium quality
TollNode · OpenAI · medium$0.123 · 1 image
| Result | Detail |
|---|---|
| File | 1 image link, does not expire |
| Quality | medium |
| Aspect ratio | 4:3 |
Real result, shown below.
GPT Image 2.6 Sunburst image examples
Made by this node in our own tests, from the request shown under each.

“A clean illustrated map of a small coastal town seen from above, with labelled places: HARBOUR, MARKET, LIBRARY, TRAIN STATION and LIGHTHOUSE, soft pastel colours, flat vector style”
The request that made it
Send the same body to get this kind of result. Change the prompt or the options to get your own.
{
"prompt": "A clean illustrated map of a small coastal town seen from above, with labelled places: HARBOUR, MARKET, LIBRARY, TRAIN STATION and LIGHTHOUSE, soft pastel colours, flat vector style",
"quality": "medium",
"aspect_ratio": "4:3"
}What you control with GPT Image 2.6 Sunburst
Prompt and style
GPT Image 2.6 Sunburst prompt to image
Describe the image in plain words, including any labels.
- Prompt
- A clean illustrated map of a small coastal town, labelled HARBOUR, MARKET, LIBRARY...
- Aspect ratio
- 4:3
- Quality
- medium
You get
- prompt: what to create or change, up to 2,000 characters
- aspect_ratio: 7 fixed shapes from 1:1 to 16:9, default 1:1
- complexity: how much it plans first, helps dense text and layouts
Reference images
Edit or guide from up to 6 photos
Give it up to 6 image URLs to edit or guide results.
- input_images
- optional, up to 6 (none in this example)
- background
- auto (default)
- output_format
- png, jpeg or webp
You get
- input_images: up to 6 reference or source image URLs (https)
- background: auto, transparent or opaque background
- from $0.069
Quality and price
Low, medium, high, xhigh or max quality
Pick the quality; the price follows it.
- Quality
- medium (default)
- Price
- set by quality option
- Complexity
- same price at any level
You get
- quality: sets detail level and price, default medium
- complexity: low, medium or high planning, same price
Failed calls are never charged, and image links returned by TollNode don't expire.
What people ask their AI to do with it
Marketers
Ad images with readable labels and text
“Create a 16:9 ad image for a hiking app with a trail map labeled TRAILHEAD, SUMMIT and CAMPGROUND, flat vector style, medium quality”
medium
Cost today$0.123
Teachers
Diagrams and illustrated maps for lessons
“Make a labeled diagram of a plant cell with parts NUCLEUS, MITOCHONDRIA and CHLOROPLAST, flat illustration, high quality”
high
Cost today$0.174
Game designers
Fantasy maps and labeled game assets
“Generate a fantasy world map with labeled regions IRONHOLD, DARKWOOD and RIVERBEND, parchment style, 3:4, xhigh quality”
xhigh
Cost today$0.339
Founders
Pitch deck diagrams and flowcharts
“Draw a 16:9 flowchart for our onboarding process with steps SIGN UP, VERIFY and LAUNCH, clean corporate style, max quality”
max
Cost today$0.676
Real estate agents
Illustrated neighborhood and property maps
“Create an illustrated map of our new subdivision labeled CLUBHOUSE, POOL and PARK, soft colors, 4:3, medium quality”
medium
Cost today$0.123
Authors and publishers
Book cover art with title text
“Design a book cover illustration of a coastal town at sunset with the title THE LIGHTHOUSE KEEPER in bold text, 2:3, high quality”
high
Cost today$0.174
Use it as a GPT Image 2.6 Sunburst MCP server in Claude, Cursor or Codex
Connect once. Then just ask.
Paste this into Claude Code, Cursor or Codex. It connects TollNode and gives your agent a small wallet. Add a few dollars of USDC and you're done.
npx agentcash add https://tollnode.comCopy for your AI agent
Paste this into your agent so it knows what this node does and how to call it.
You can use TollNode's GPT Image 2.6 Sunburst node to create and edit images. Call POST https://tollnode.com/api/v1/nodes/gpt-image-2-6-sunburst with prompt (required, up to 2,000 characters), quality (low, medium, high, xhigh or max, default medium), aspect_ratio (1:1, 3:2, 2:3, 4:3, 3:4, 16:9 or 9:16, default 1:1), complexity (low, medium or high, same price at any level), background (auto, transparent or opaque), output_format (png, jpeg or webp) and input_images (up to 6 https image URLs, optional). The price depends on quality and is charged only when an image is returned. Over MCP, call the 'gpt-image-2-6-sunburst' tool; use list_models to see prices. Give me the image link when it is done.Price
from $0.069
per image
The price depends on the quality you choose. If you don't choose, you get medium.
| low | $0.069 per image |
| mediumdefault | $0.123 per image |
| high | $0.174 per image |
| xhigh | $0.339 per image |
| max | $0.676 per image |
Charged only when a call returns a result. Failed or empty calls cost $0.
GPT Image 2.6 Sunburst without an OpenAI account
No subscription, no credit packs
Pay per image: $0.069 at low quality, up to $0.676 at max quality.
No OpenAI account, no API keys to manage
Your agent calls TollNode directly. You never set up billing with OpenAI.
Only charged when it works
If generation fails or returns nothing, the call costs nothing.
One connection, many image models
The same setup also gives your agent Nano Banana Pro, FLUX and Seedream, so it can compare results.
FAQ
- Is this the official OpenAI API?
- No. TollNode is an independent service. It gives your agent access to GPT Image 2.6 Sunburst through its own API and MCP server, priced per image, with no OpenAI account needed.
- Can I use it as a GPT Image 2.6 Sunburst MCP server in Claude?
- Yes. Add https://tollnode.com/mcp in Claude Code, Claude Desktop or Cursor, and the 'gpt-image-2-6-sunburst' tool appears with its options and prices.
- What does the quality option change?
- Quality sets the detail level and the price: low, medium, high, xhigh or max. Medium is the default. Complexity, which affects how much the model plans first, costs the same at any level.
- Can it edit or combine my own photos?
- Yes. Send up to 6 image URLs in input_images and describe the change. Use background to request a transparent or opaque result.
- Does it handle text and labels inside the image well?
- The summary describes it as built for detailed compositions and precise edits. Set complexity to high for dense text and layouts like maps or diagrams.
- What if no image comes back?
- You're not charged. TollNode only collects payment when a usable image is returned.
- How long are the image links valid?
- They don't expire. Download the file or keep the link.
Works well with
- GPT Image 2 generation and editingRun the same prompt on an earlier GPT Image model to comparefrom $0.018
- Nano Banana Pro image generationCompare the same prompt on Google's image modelfrom $0.204
- Crisp image upscalerEnlarge a finished map or illustration for print$0.010
- Veo 3.1 Fast video with soundTurn a finished illustration into a short video with soundfrom $0.811
Ready in a minute
Connect your AIFor developers: endpoint, inputs and an example response
POST https://tollnode.com/api/v1/nodes/gpt-image-2-6-sunburst
Input
| Field | Type | Notes |
|---|---|---|
| size | enum | Output size, same price: 1K (about 1 megapixel, default, every aspect ratio), 2K (2048 px on the long side; 1:1, 16:9 or 9:16) or 4K (3840x2160 or 2160x3840; 16:9 or 9:16) (1K, 2K, 4K) |
| prompt* | string | What to create or change |
| quality | enum | Sets the price. Default medium (low, medium, high, xhigh, max) |
| background | enum | (auto, transparent, opaque) |
| complexity | enum | How much the model plans first; higher helps dense text and layouts. Same price (low, medium, high) |
| aspect_ratio | enum | Aspect ratio, default 1:1 (1:1, 3:2, 2:3, 4:3, 3:4, 16:9, 9:16) |
| input_images | array | Reference or source image URLs (https), optional. Or send the file inline as a base64 data: URI (up to 4.5 MB) |
| output_format | enum | (png, jpeg, webp) |
Example response
{
"images": [
"https://tollnode.com/api/v1/files/00000000-0000-0000-0000-000000000000/0"
]
}Also described in the OpenAPI file and llms.txt. Setup for every app: Agents & MCP.