GPT Image 2.6 Sunburst API Docs
Precision studio variant of GPT Image 2.6 for commercial product rendering, fine typography, and up to 10-image reference editing across 1K, 2K, and 4K.
POST /v1/images/generations · gpt-image-2.6-sunburst
Request schema
gpt-image-2.6-sunburst shares the exact same parameter schema and token rates as Flare while tuned for precision studio lighting, fine typography, and up to 10-image reference composition across 1K, 2K, and 4K.
| Field | Type & Default | Constraints & Description |
|---|---|---|
AuthorizationRequiredHeader | string | Bearer cm_live_... server-side API key from your account. |
Idempotency-KeyOptionalHeader | stringDefault: recommended | 1 to 255 ASCII chars. Prevents duplicate submissions and charges for 24h. |
modelRequired | "gpt-image-2.6-sunburst" | Stable public model ID for GPT Image 2.6 Flare. |
promptRequired | string | Non-empty UTF-8 prompt describing the desired image. |
sizeOptional | 15 aspect ratiosDefault: "1:1" | "1:1", "16:9", "9:16", "4:3", "3:4", "3:2", "2:3", "5:4", "4:5", "21:9", "9:21", "2:1", "1:2", "3:1", "1:3". |
resolutionOptional | "1K" | "2K" | "4K"Default: "1K" | Output resolution tier across all 15 ratios. |
qualityOptional | "low" | "medium" | "high" | "xhigh" | "max"Default: "low" | 5 rendering quality tiers; higher quality emits more output tokens. |
output_formatOptional | "png" | "jpeg" | "webp"Default: "png" | Output image format (use png or webp when background is transparent). |
backgroundOptional | "auto" | "transparent" | "opaque"Default: "auto" | Background alpha mode. |
image_urlsOptional | string[] (1..10)Default: omitted | Optional 1 to 10 HTTPS reference image URLs for image editing. |
Studio generation & multi-image edit examples
Switch between Flare and Sunburst at any time by changing only "model": "gpt-image-2.6-sunburst".
curl -sS -X POST "https://api.callmodels.dev/v1/images/generations" \
-H "Authorization: Bearer $CALLMODELS_API_KEY" \
-H "Idempotency-Key: img_req_20261115_01" \
-H "Content-Type: application/json" \
-d '{
"model": "gpt-image-2.6-sunburst",
"prompt": "Macro studio product shot of a brushed titanium mechanical chronograph on black slate, crisp dial typography",
"size": "16:9",
"resolution": "2K",
"quality": "high",
"output_format": "png"
}'Task response payloads
Returns a 30-day signed files.callmodels.dev image URL and token-metered cost_credits upon completion.
{
"id": "task_01e561ba-859e-47fe-be79-60bc6f1d6499",
"model": "gpt-image-2.6-sunburst",
"object": "image.generation.task",
"status": "pending",
"created_at": "2026-11-15T09:49:18.000Z"
}Reference specification quotes & token rates
Token rates match Flare (image_output 3.525 Credits / 1K tok, image_input 0.94 Credits / 1K tok, text_input 0.5875 Credits / 1K tok).
| Specification | Callmodels Credits | USD Equiv. | Official Ref. |
|---|---|---|---|
| 16:9 or 9:16 · 1K · low (462 out tok est.) | 1.628550 Credits | $0.0163 | $0.040 |
| 1:1 · 1K · low (824 out tok est.) | 2.904600 Credits | $0.0290 | $0.040 |
| 16:9 or 9:16 · 1K · high (965 out tok est.) | 3.401625 Credits | $0.0340 | $0.190 |
| 1:1 · 1K · high (1,756 out tok est.) | 6.189900 Credits | $0.0619 | $0.190 |
| 1:1 · 2K · high (3,568 out tok est.) | 12.577200 Credits | $0.1258 | — |
| 1:1 · 4K · max (23,719 out tok est.) | 83.609475 Credits | $0.8361 | — |