Images · Text to image · Image to image

Iris-Z Small API

Iris-Z Small (FLUX.2-based joint RGB + depth model, lighter tier): text-to-image up to 1.31 MP, images painted from a depth map at the 512 or 1024 tier, or an image plus aligned depth from text.

Price
From $0.03 per run from $0.03/image
Typical time
~15 s
Model id
iris_z_small

Iris-Z Small 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": "iris_z_small",
  "prompt": "a lighthouse on a rocky cliff at dusk, waves crashing below"
}'

Iris-Z Small pricing

From $0.03 per run. Prices are in US dollars and are the provider's own, with no markup. Iris-Z Small has 3 routes: "model": "iris_z_small" 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 $0.03/image
    fal:speridlabs/iris-z/small/text-to-image

    Text to image Iris-Z Small text-to-image: preset sizes or custom sizes up to 1280x1024 (multiples of 16), up to 50 steps, PNG or JPEG. $0.03 up to 1 MP, $0.06 above.

    Image size square_hd
    $0.03/image
    Image size square
    $0.03/image
    Image size portrait_4_3
    $0.03/image
    Image size portrait_16_9
    $0.03/image
    Image size landscape_4_3
    $0.03/image
    Image size landscape_16_9
    $0.03/image
    Other
    $0.06/image
    Minimum charge
    $0.03
    Most one request can cost
    $0.06
    Typical time
    ~15 s
  • fal from $0.05/image
    fal:speridlabs/iris-z/small/depth-to-image

    Image to image Iris-Z Small depth-to-image: paints an image that follows a depth, disparity or colorized depth map, with an optional prompt. Keeps the map's aspect ratio; 512 or 1024 tier. $0.05 up to 1 MP, $0.10 above.

    Resolution 512
    $0.05/image
    Resolution 1024
    $0.10/image
    Other
    $0.10/image
    Minimum charge
    $0.05
    Most one request can cost
    $0.10
    Typical time
    ~15 s
  • fal from $0.05/image
    fal:speridlabs/iris-z/small/text-to-rgbd

    Text to image Iris-Z Small text-to-RGB-D: an image plus an aligned colorized depth map and float32 log-depth array from a prompt, up to 1280x1024. Only the RGB image is the job output. $0.05 up to 1 MP, $0.10 above. Address it by model_key.

    Image size square_hd
    $0.05/image
    Image size square
    $0.05/image
    Image size portrait_4_3
    $0.05/image
    Image size portrait_16_9
    $0.05/image
    Image size landscape_4_3
    $0.05/image
    Image size landscape_16_9
    $0.05/image
    Other
    $0.10/image
    Minimum charge
    $0.05
    Most one request can cost
    $0.10
    Typical time
    ~15 s

Iris-Z Small 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=iris_z_small

Iris-Z Small request fields
FieldWhat it does
model string requirediris_z_small 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

Iris-Z Small options for fal
FieldWhat it does
prompt string The prompt to generate an image from. Prompts are truncated to 512 text-encoder tokens.
output_format string Allowed png | jpeg
num_inference_steps integer The number of inference steps to perform. Allowed 1–50
enable_safety_checker boolean If set to true, the safety checker will be enabled. Disabling it requires account authorization; unauthorized requests are always checked, and images flagged as unsafe are returned as black images.
resolution string Allowed 512 | 1024
depth_format string Allowed depth | disparity | colorized
depth_image_url string (URL) URL of the depth map to paint an image from.

Call the Iris-Z Small 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": "iris_z_small",
  "prompt": "a lighthouse on a rocky cliff at dusk, waves crashing below"
}'
JavaScript
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": "iris_z_small",
    "prompt": "a lighthouse on a rocky cliff at dusk, waves crashing below"
  }),
})
const job = await res.json() // { id: "job_…", status: "queued" }
Python
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": "iris_z_small",
      "prompt": "a lighthouse on a rocky cliff at dusk, waves crashing below"
    },
).json()  # {"id": "job_…", "status": "queued"}

2. Get the result

Poll the job until its status is completed, failed or cancelled; Iris-Z Small 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
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
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": "iris_z_small",
  "prompt": "a lighthouse on a rocky cliff at dusk, waves crashing below",
  "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 Iris-Z Small with call_tool. Sign in with varg, no API key to paste. How to connect it

call_tool
{
  "tool": "image",
  "input": {
    "model": "iris_z_small",
    "prompt": "a lighthouse on a rocky cliff at dusk, waves crashing below"
  },
  "wait": true
}

Iris-Z Small API: questions

How much does Iris-Z Small cost on varg?
Iris-Z Small costs from $0.03 per run on varg (from $0.03/image 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 Iris-Z Small 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": "iris_z_small". 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 Iris-Z Small 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 Iris-Z Small with call_tool, passing tool "image" and "model": "iris_z_small".
How long does a Iris-Z Small 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/iris_z_small.md, and every model is listed in varg.ai/models/llms.txt.