Text to Image

gpt-image-2-official

Official-channel image generation with text, reference-image, and mask workflows.

Commercial useAsync APIfrom 28 Credits

API reference

Submit this model to the capability endpoint, then poll the returned job until it is terminal. Only the parameters below are accepted.

POST /v1/images/generations

Required headers

Authorization: Bearer $ARTANY_API_KEY
Content-Type: application/json
Idempotency-Key: unique-request-id

Use a new 8–128 character Idempotency-Key for each logical generation. Retrying the same request with the same key will not double-charge.

Request body

{
  "model": "gpt-image-2-official",
  "prompt": "A detailed poster of a night market in the rain",
  "n": 1,
  "size": "16:9",
  "resolution": "2k",
  "quality": "high",
  "background": "auto",
  "moderation": "auto",
  "output_format": "png"
}

Parameters

FieldTypeRequiredDescriptionDefaultConstraints
modelstringYesStable Artany public model ID.gpt-image-2-officialThis exact public model ID.
nintegerNoModel-specific image generation option. See its allowed values and constraints in this row.1Range: 1–4
sizestringNoRequested output image aspect ratio or canvas size. Available values are model-specific."1:1"Allowed: auto, 1:1, 3:2, 2:3, 4:3, 3:4, 5:4, 4:5, 16:9, 9:16, 2:1, 1:2, 3:1, 1:3, 21:9, 9:21
promptstringYesNatural-language instruction describing the desired image or video. Include subject, setting, composition, motion, lighting, and style as needed.Length: 1–12000
qualitystringNoRequested quality tier for a supported image model. It may affect latency and price."auto"Allowed: auto, low, medium, high
mask_urlstringNoPublic URL of a mask image that identifies the editable area in a supported image-editing request.Format: uri
backgroundstringNoBackground handling option for image output when transparency or a solid background is supported."auto"Allowed: auto, opaque
image_urlsarray (string items)NoPublic image URLs or supported image data used as source or reference images.Items: 1–16
moderationstringNoProvider moderation setting used when the selected image workflow supports it."auto"Allowed: auto, low
resolutionstringNoRequested output quality tier. Available values are model-specific and can affect price."1k"Allowed: 1k, 2k, 4k
output_formatstringNoRequested file format for the generated image when the selected model supports format selection."png"Allowed: png, jpeg, webp
output_compressionintegerNoCompression level for a supported output format. Higher compression may reduce file size and fidelity.Range: 0–100

Accepted response

The submit endpoint returns HTTP 202 with a normalized job. Poll GET /v1/jobs/{jobId} until the status is terminal.

{
  "id": "job_…",
  "object": "generation.job",
  "model": "gpt-image-2-official",
  "status": "queued",
  "progress": 0,
  "output": null,
  "error": null,
  "billing": {
    "estimated_credits": "28",
    "frozen_credits": "…",
    "charged_credits": "0",
    "state": "frozen",
    "price_version": "2026-07-18.picverse-parity"
  },
  "created_at": "2026-07-21T00:00:00.000Z",
  "completed_at": null
}

Lifecycle and failures

  • queued / running — wait and poll again.
  • succeeded — read output URLs from output; the actual charge is settled.
  • failed / canceled — inspect error; frozen Credits are released.
  • For a schema error, the API returns an error object and identifies the invalid field in param when applicable.

Input

Runs are billed to your Credits at the listed price — same engine as the public API.

Output

Run the model to see results here

Pricing details

Fixed catalog pricing — the listed price is exactly what a run settles for. Version 2026-07-18.picverse-parity.

ModelnsizequalityresolutionPrice
gpt-image-2-official11:2low2k1Credits · ~$0.0100
gpt-image-2-official11:2auto2k1Credits · ~$0.0100
gpt-image-2-official11:3low1k1Credits · ~$0.0100
gpt-image-2-official11:3auto1k1Credits · ~$0.0100
gpt-image-2-official11:3low2k1Credits · ~$0.0100
gpt-image-2-official11:3auto2k1Credits · ~$0.0100
gpt-image-2-official11:3low4k1Credits · ~$0.0100
gpt-image-2-official11:3auto4k1Credits · ~$0.0100

Integrate in minutes

curl -X POST "https://api.artany.ai/v1/images/generations" \
  -H "Authorization: Bearer $ARTANY_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: unique-request-id" \
  -d '{"model":"gpt-image-2-official","prompt":"A detailed poster of a night market in the rain","n":1,"size":"16:9","resolution":"2k","quality":"high","background":"auto","moderation":"auto","output_format":"png"}'

# poll until terminal
curl "https://api.artany.ai/v1/jobs/{job_id}" \
  -H "Authorization: Bearer $ARTANY_API_KEY"