How much does Krea (latest) cost on varg?

Krea (latest) costs from $0.01 per run on varg ($0.024/MP on the cheapest route). 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 Krea (latest) 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": "krea". 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 Krea (latest) 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 Krea (latest) with call_tool, passing tool "image" and "model": "krea".

How long does a Krea (latest) 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.

Images · Text to image · Image to image

Krea (latest) API

The latest Krea image model — currently Krea 3. Pin krea_3 to stay on a version.

Price: From $0.01 per run $0.024/MP
Typical time: ~15 s
Model id: krea

Krea (latest) 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.

POST /v2/tools/image/call

curl -X POST https://api.varg.ai/v2/tools/image/call \
  -H "Authorization: Bearer $VARG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "krea",
  "prompt": "A ceramic teapot on a linen tablecloth, soft window light, film grain",
  "aspect_ratio": "4:3"
}'

Try it in the Playground Get an API key

Krea (latest) pricing

From $0.01 per run. Prices are in US dollars and are the provider's own, with no markup. Krea (latest) has 3 routes: "model": "krea" 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.

krea from $0.03/image
krea:image/krea/krea-3
Text to image, Image to image Krea 3 (early access) — Krea's newest image model: text-to-image and edits with up to 8 input images, fast / high / ultra thinking, 1K or 2K.
Resolution 2k
$0.06/image
Other
$0.03/image
Extra per image_urls
+$0.02
Extra when thinking_mode is high
+$0.02
Extra when thinking_mode is ultra
+$0.02
Minimum charge
$0.03
Most one request can cost
$0.24
Typical time
~15 s
fal from $0.125/image
fal:krea/v3/edit
Image to image Krea 3 edit on fal — edits and combines 1-8 reference images from a text instruction; low / medium / high / ultra reasoning.
Reasoning level ultra
$0.35/image
Reasoning level high
$0.25/image
Other
$0.125/image
Minimum charge
$0.125
Most one request can cost
$0.35
Typical time
~30 s
fal $0.024/MP
fal:krea/v3/text-to-image
Text to image Krea 3 text-to-image on fal — Krea's newest image model; berry (quality) or jam (speed).
Per megapixel
$0.024
Minimum charge
$0.01
Most one request can cost
$0.11
Typical time
~30 s

Krea (latest) 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=krea

Krea (latest) request fields
Field	What it does
`model` string required	`krea` 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.krea`

Krea (latest) options for krea
Field	What it does
`prompt` string	Text description of the image to generate, or the edit to apply to the input images.
`negative_prompt` string	What to keep out of the image.
`image_urls` array of URL strings	—
`seed` number	Random seed for reproducible generation.
`width` number	Explicit output width in pixels (with height; instead of resolution). Allowed 0–4096
`height` number	Explicit output height in pixels (with width; instead of resolution). Allowed 0–4096
`resolution` string	Allowed 1k \| 2k
`aspect_ratio` string	Allowed 1:1 \| 4:5 \| 3:4 \| 2:3 \| 9:16 \| 5:4 \| 4:3 \| 3:2 \| 16:9 \| 21:9
`thinking_mode` string	Allowed fast \| high \| ultra

`provider_options.fal`

Krea (latest) options for fal
Field	What it does
`prompt` string	Description of the image to generate.
`negative_prompt` string	What to keep out of the image. Used by berry only.
`image_urls` array of URL strings	—
`sync_mode` boolean	Return images as data URIs instead of saving them in request history.
`output_format` string	Allowed png \| jpeg
`reasoning_level` string	Allowed low \| medium \| high \| ultra
`enable_safety_checker` boolean	Check output images for unsafe content. Disabling requires account authorization.

Call the Krea (latest) 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

curl -X POST https://api.varg.ai/v2/tools/image/call \
  -H "Authorization: Bearer $VARG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "krea",
  "prompt": "A ceramic teapot on a linen tablecloth, soft window light, film grain",
  "aspect_ratio": "4:3"
}'

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": "krea",
    "prompt": "A ceramic teapot on a linen tablecloth, soft window light, film grain",
    "aspect_ratio": "4:3"
  }),
})
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": "krea",
      "prompt": "A ceramic teapot on a linen tablecloth, soft window light, film grain",
      "aspect_ratio": "4:3"
    },
).json()  # {"id": "job_…", "status": "queued"}

2. Get the result

Poll the job until its status is completed, failed or cancelled; Krea (latest) typically takes about 15 s. The result is at output.outputs[0].url.

GET /v2/jobs/{id}

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].url

JavaScript

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.

request body

{
  "model": "krea",
  "prompt": "A ceramic teapot on a linen tablecloth, soft window light, film grain",
  "aspect_ratio": "4:3",
  "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 Krea (latest) with call_tool. Sign in with varg, no API key to paste. How to connect it

call_tool

{
  "tool": "image",
  "input": {
    "model": "krea",
    "prompt": "A ceramic teapot on a linen tablecloth, soft window light, film grain",
    "aspect_ratio": "4:3"
  },
  "wait": true
}

Krea (latest) API: questions

How much does Krea (latest) cost on varg?: Krea (latest) costs from $0.01 per run on varg ($0.024/MP on the cheapest route). 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 Krea (latest) 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": "krea". 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 Krea (latest) 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 Krea (latest) with call_tool, passing tool "image" and "model": "krea".
How long does a Krea (latest) 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/krea.md, and every model is listed in varg.ai/models/llms.txt.