Images · Text to image · Image to image
MAI-Image-2.7 Flash API
Microsoft MAI-Image-2.7 Flash, the lower-cost tier: text-to-image and instruction edits with up to 5 input images, 1K (~1 MP) or 2K (~4 MP), 7 aspect presets or custom sizes up to 4,194,304 px, PNG/JPEG/WebP, optional transparent background.
- Price
- From $0.011/image
- Typical time
- ~15 s
- Model id
mai_image_2_7_flash
MAI-Image-2.7 Flash runs on one varg API key and one credit balance, the same as every other model here. You pay the provider's price, with no markup.
curl -X POST https://api.varg.ai/v2/tools/image/call \
-H "Authorization: Bearer $VARG_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "mai_image_2_7_flash",
"prompt": "A ceramic teapot beside a sunlit window, realistic photography."
}'MAI-Image-2.7 Flash pricing
From $0.011/image. Prices are in US dollars and are the provider's own, with no markup. MAI-Image-2.7 Flash has 2 routes: "model": "mai_image_2_7_flash" picks one automatically, or pass a route key as "model" to pin it. For the exact price of a request, send the same body to POST https://api.varg.ai/v2/estimate.
- fal from $0.011/image
fal:microsoft/mai-image-2.7/flash/text-to-imageText to image MAI-Image-2.7 Flash text-to-image: 1K (~1 MP) or 2K (~4 MP) presets in 7 aspect ratios, or a custom size (each side ≥768, up to 4,194,304 px total; priced at the 4 MP rate). PNG/JPEG/WebP, optional transparent background.
- Resolution 2K
- $0.041/image
- Image size square_hd
- $0.011/image
- Image size portrait_4_3
- $0.011/image
- Image size landscape_4_3
- $0.011/image
- Image size portrait_3_2
- $0.011/image
- Image size landscape_3_2
- $0.011/image
- Image size portrait_16_9
- $0.011/image
- Image size landscape_16_9
- $0.011/image
- Other
- $0.041/image
- Most one request can cost
- $0.05
- Typical time
- ~15 s
- fal from $0.011/image
fal:microsoft/mai-image-2.7/flash/editImage to image MAI-Image-2.7 Flash edit: text-instruction edits from 1-5 input images at 1K or 2K, PNG/JPEG/WebP, optional transparent background. Without aspect_ratio the output follows the input size and is priced at the 4 MP worst case (6¢ for one input); pass aspect_ratio for the 1K price (3¢ for one input).
- Resolution 2K
- $0.041/image
- Image size square_hd
- $0.011/image
- Image size portrait_4_3
- $0.011/image
- Image size landscape_4_3
- $0.011/image
- Image size portrait_3_2
- $0.011/image
- Image size landscape_3_2
- $0.011/image
- Image size portrait_16_9
- $0.011/image
- Image size landscape_16_9
- $0.011/image
- Other
- $0.041/image
- Extra per image_urls
- +$0.0103
- Most one request can cost
- $0.10
- Typical time
- ~20 s
MAI-Image-2.7 Flash inputs
The JSON body of the request. Media inputs are URLs: upload a local file with POST /v2/files and pass the URL it returns. Full JSON Schema, no key needed: api.varg.ai/v2/tools/image?model=mai_image_2_7_flash
| Field | What it does |
|---|---|
model string required | mai_image_2_7_flash picks a route automatically. To pin one, pass a route key from Pricing above. |
prompt string | — |
files array of { url } | — |
aspect_ratio string | Allowed e.g. 16:9 | 9:16 | 1:1 | 4:3 | 3:4 | 21:9 | auto |
Provider options
Optional, under provider_options.<provider>. Only the options of the provider that runs the job apply; pin a route to choose it.
provider_options.fal
| Field | What it does |
|---|---|
prompt string | The text prompt to generate an image from. |
image_urls array of URL strings | — |
sync_mode boolean | If `True`, the media will be returned as a data URI and the output data won't be available in the request history. |
background string | Allowed opaque | transparent |
resolution string | Allowed 1K | 2K |
output_format string | Allowed jpeg | png | webp |
Call the MAI-Image-2.7 Flash API
POST https://api.varg.ai/v2/tools/image/call with Authorization: Bearer $VARG_API_KEY. It answers 202 with a job right away.
1. Send the request
curl -X POST https://api.varg.ai/v2/tools/image/call \
-H "Authorization: Bearer $VARG_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "mai_image_2_7_flash",
"prompt": "A ceramic teapot beside a sunlit window, realistic photography."
}'JavaScript
const headers = {
Authorization: `Bearer ${process.env.VARG_API_KEY}`,
'Content-Type': 'application/json',
}
const res = await fetch('https://api.varg.ai/v2/tools/image/call', {
method: 'POST',
headers,
body: JSON.stringify({
"model": "mai_image_2_7_flash",
"prompt": "A ceramic teapot beside a sunlit window, realistic photography."
}),
})
const job = await res.json() // { id: "job_…", status: "queued" }Python
import os
import requests
headers = {"Authorization": f"Bearer {os.environ['VARG_API_KEY']}"}
job = requests.post(
"https://api.varg.ai/v2/tools/image/call",
headers=headers,
json={
"model": "mai_image_2_7_flash",
"prompt": "A ceramic teapot beside a sunlit window, realistic photography."
},
).json() # {"id": "job_…", "status": "queued"}2. Get the result
Poll the job until its status is completed, failed or cancelled; MAI-Image-2.7 Flash typically takes about 15 s. The result is at output.outputs[0].url.
curl https://api.varg.ai/v2/jobs/$JOB_ID \
-H "Authorization: Bearer $VARG_API_KEY"
# Poll until "status" is completed, failed or cancelled.
# The result is in output.outputs[0].urlJavaScript
let current = job
while (!['completed', 'failed', 'cancelled'].includes(current.status)) {
await new Promise((resolve) => setTimeout(resolve, 3000))
current = await (await fetch(`https://api.varg.ai/v2/jobs/${current.id}`, { headers })).json()
}
console.log(current.output?.outputs?.[0]?.url)Python
import time
while job["status"] not in ("completed", "failed", "cancelled"):
time.sleep(3)
job = requests.get(f"https://api.varg.ai/v2/jobs/{job['id']}", headers=headers).json()
print(job["output"]["outputs"][0]["url"])Or take a webhook instead of polling
Add options.webhook_url and varg POSTs the finished job to it.
{
"model": "mai_image_2_7_flash",
"prompt": "A ceramic teapot beside a sunlit window, realistic photography.",
"options": {
"webhook_url": "https://your-app.com/varg-webhook"
}
}From Claude, ChatGPT or Cursor (MCP)
The varg MCP server, https://mcp.varg.ai/mcp, runs MAI-Image-2.7 Flash with call_tool. Sign in with varg, no API key to paste. How to connect it
{
"tool": "image",
"input": {
"model": "mai_image_2_7_flash",
"prompt": "A ceramic teapot beside a sunlit window, realistic photography."
},
"wait": true
}MAI-Image-2.7 Flash API: questions
- How much does MAI-Image-2.7 Flash cost on varg?
- MAI-Image-2.7 Flash costs from $0.011/image on varg, on its cheapest route. The total depends on the request. varg charges the provider's price with no markup, from one credit balance. For the exact price of a request before you run it, send the same body to POST https://api.varg.ai/v2/estimate.
- How do I call the MAI-Image-2.7 Flash API?
- Send POST https://api.varg.ai/v2/tools/image/call with the header "Authorization: Bearer $VARG_API_KEY" and a JSON body that includes "model": "mai_image_2_7_flash". The call answers 202 with a job right away. Poll GET https://api.varg.ai/v2/jobs/{id} until "status" is "completed", then read output.outputs[0].url, or pass options.webhook_url to be called back.
- Can I use MAI-Image-2.7 Flash from Claude, ChatGPT or Cursor?
- Yes. Add the varg MCP server (https://mcp.varg.ai/mcp) to Claude, ChatGPT, Cursor or any other MCP client and sign in with varg, with no API key to paste. The agent runs MAI-Image-2.7 Flash with call_tool, passing tool "image" and "model": "mai_image_2_7_flash".
- How long does a MAI-Image-2.7 Flash request take?
- Typically about 15 s on the fastest route, by the catalog's estimate. The API answers at once with a job id, so nothing waits on an open connection while it runs.
For AI agents: this page as Markdown is varg.ai/models/mai_image_2_7_flash.md, and every model is listed in varg.ai/models/llms.txt.