Skip to content

GPT-Image 2.6 โ€‹

Updated

โ† Back to the GPT-Image overview for a version comparison and selection guide.

Endpoint: POST https://vod.intl.tencentcloudapi.comAction: CreateAigcImageTask

GPT-Image 2.6 is the latest generation of the GPT-Image family on VOD, released on 2026-11-06. It ships two variants:

VariantPositioningBest for
sunburstEditing precisionWorkflows where editing precision comes first: complex compositions, fine-grained revisions, small text
flareFast generationFast, high-quality everyday image generation: batch drafts, prompt iteration

The basic call is the same as 2.5 โ€” just swap ModelVersion for one of the 2.6 values; the request structure stays the same.

On top of that, 2.6 is the only GPT-Image series that supports GIF animation and SVG vector output (since 2026-11-06), enabled through ExtInfo.

This page is one of three GPT-Image API documents. See also GPT-Image 2.0 and GPT-Image 2.5.

Basic information โ€‹

ItemValue
ModelNameOG
ModelVersionimage2.6_sunburst_* / image2.6_flare_* โ€” * is a placeholder, not a value you can pass; see ModelVersion enumeration for all 10 actual values
Result pollingDescribeTaskDetail
Guardrail bypassNot supported

ModelVersion enumeration โ€‹

Five tiers per variant, 10 values in total.

Tiersunburstflare
lowimage2.6_sunburst_lowimage2.6_flare_low
mediumimage2.6_sunburst_mediumimage2.6_flare_medium
highimage2.6_sunburst_highimage2.6_flare_high
xhighimage2.6_sunburst_xhighimage2.6_flare_xhigh
maximage2.6_sunburst_maximage2.6_flare_max

Choosing a quality tier โ€‹

Higher tiers mean higher fidelity, but also longer generation times and higher cost.

TierCharacteristicsRecommended for
lowFastest generation, lowest costQuick drafts, batch testing, prompt iteration
mediumThe sweet spot between speed, cost, and qualityMost day-to-day production and general design work
highRicher detail, texture, lighting and shadowReview-ready output, images that need careful rendering
xhighHigher fidelity than highFinal review, upscaled use
maxHighest fidelity; strong on complex text and small typeFinal deliverables, print material, high-precision product shots

2.6 has no separate measured timing table

The overall trend matches 2.5: at the same tier, flare is clearly faster than sunburst. Use the 2.5 measurements as an order-of-magnitude reference.

Request parameters โ€‹

ParameterRequiredTypeDescription
SubAppIdYesIntegerSubapplication ID
ModelNameYesStringFixed value OG
ModelVersionNoStringModel version, e.g. image2.6_sunburst_medium. Defaults to the engine default image2_medium (the 2.0 series) when omitted
PromptYesStringGeneration prompt, up to 32,000 characters
FileInfos.NNoArrayReference images (image-to-image), up to 16. Acts as a mask when ReferenceType=mask. See Passing reference images
OutputConfig.StorageModeNoStringTemporary (7-day retention) / Permanent (returns a FileId)
OutputConfig.ResolutionNoString1K / 2K / 4K
OutputConfig.AspectRatioNoString1:1 / 3:2 / 2:3 / 3:4 / 4:3 / 16:9 / 9:16 / 21:9 / 9:21
OutputConfig.OutputImageCountNoIntegerNumber of images; 1โ€“8 for OG
OutputConfig.OutputFormatNoStringjpeg / png. Follows the model default when omitted. GIF / SVG do not use this field โ€” see GIF and SVG output
OutputConfig.PersonGenerationNoStringAllowAdult / Disallowed (no people or faces in the image)
OutputConfig.InputComplianceCheckNoStringInput compliance check: Enabled / Disabled
OutputConfig.OutputComplianceCheckNoStringOutput compliance check: Enabled / Disabled
OutputConfig.LogoAddNoStringAdd a logo watermark: Enabled / Disabled
InputRegionNoStringInput region: Mainland (Chinese mainland) / Oversea (outside the Chinese mainland) / OverseaUSWest (US West)
ExtInfoNoStringJSON string carrying model-specific options; see Special settings and GIF and SVG output
SessionContextNoStringSession identifier echoed back in the callback

Request example โ€‹

json
{
  "SubAppId": 123456789,
  "ModelName": "OG",
  "ModelVersion": "image2.6_sunburst_medium",
  "Prompt": "a serene japanese garden, soft morning light",
  "OutputConfig": {
    "StorageMode": "Permanent",
    "Resolution": "1K",
    "AspectRatio": "1:1",
    "OutputImageCount": 1
  },
  "SessionContext": "job-001"
}

Response example โ€‹

json
{
  "AigcImageTask": {
    "Status": "FINISH",
    "ErrCode": 0,
    "Progress": 100,
    "Output": {
      "FileInfos": [
        {
          "FileUrl": "http://<host>.vod2.myqcloud.com/.../aigcImageGenFile.png",
          "ExpireTime": "2026-08-01T10:29:48Z",
          "MetaData": {
            "Width": 1024,
            "Height": 1024,
            "Container": "png"
          }
        }
      ]
    }
  }
}

Special settings โ€‹

Everything below works identically across the 2.0 / 2.5 / 2.6 series. The 2.6-only GIF / SVG output has its own section.

Passing reference images โ€‹

Each FileInfos entry declares its source with Type:

TypeCompanion fieldDescription
FileFileIdVOD media file ID
UrlUrlPublicly accessible image URL
Base64Base64Base64-encoded image

Base64 limits

  • The total size of all files must not exceed 7 MB, so the Base64-encoded request stays under the 10 MB Cloud API body limit;
  • Images must be jpeg / jpg / png / webp;
  • Do not include a prefix such as data:image/jpeg;base64,.

Multiple reference images โ€‹

A single request accepts multiple reference images, up to 16. Use it for image editing, style transfer, and multi-image fusion (background swaps, element composition, and so on).

json
{
  "SubAppId": 123456789,
  "ModelName": "OG",
  "ModelVersion": "image2.6_sunburst_medium",
  "FileInfos": [
    { "Type": "Url", "Url": "https://<cos>/room.png" },
    { "Type": "Url", "Url": "https://<cos>/fabric.jpg" }
  ],
  "Prompt": "redesign this room with the material palette of the second image, keep the layout unchanged",
  "OutputConfig": {
    "StorageMode": "Permanent",
    "Resolution": "1K",
    "AspectRatio": "9:16"
  },
  "SessionContext": "job-001"
}

Multi-image output (OutputImageCount) โ€‹

OutputConfig.OutputImageCount sets how many images one request generates. OG accepts 1โ€“8 (limits differ per engine; Kling accepts 1โ€“9).

json
{
  "OutputConfig": {
    "StorageMode": "Permanent",
    "Resolution": "1K",
    "AspectRatio": "9:16",
    "OutputImageCount": 3
  }
}

Custom resolution (size) โ€‹

Set the output resolution directly through size inside ExtInfo.

ConstraintValue
Width and heightBoth multiples of 16
Longest edgeAt most 3840px (that is, no larger than 4K)
Total pixels655,360 โ€“ 8,294,400
json
{
  "SubAppId": 123456789,
  "ModelName": "OG",
  "ModelVersion": "image2.6_flare_high",
  "Prompt": "a serene japanese garden, soft morning light",
  "OutputConfig": {
    "StorageMode": "Permanent",
    "Resolution": "1K",
    "AspectRatio": "9:16"
  },
  "ExtInfo": "{\"AdditionalParameters\": \"{\\\"size\\\": \\\"2000x1104\\\"}\"}",
  "SessionContext": "job-001"
}

Common presets are 1024x1024 (square), 1536x1024 (landscape), and 1024x1536 (portrait). 2K (2560x1440) and 4K (3840x2160) output is also available, though anything above 2560px is experimental.

auto mode โ€‹

Set size to auto and the model decides the resolution from the input.

json
{
  "ExtInfo": "{\"AdditionalParameters\": \"{\\\"size\\\": \\\"auto\\\"}\"}"
}

Do not pass auto for AspectRatio

When size is auto, AspectRatio still needs a concrete ratio โ€” it must not be auto as well.

Mask-based image editing โ€‹

Include an image with ReferenceType=mask in FileInfos to mask the region you want edited. The mask and the source image each take one entry.

json
{
  "SubAppId": 123456789,
  "ModelName": "OG",
  "ModelVersion": "image2.6_sunburst_medium",
  "FileInfos": [
    {
      "Type": "Url",
      "Url": "https://<cos>/room-mask.png",
      "ReferenceType": "mask"
    },
    {
      "Type": "Url",
      "Url": "https://<cos>/room.png"
    }
  ],
  "Prompt": "the same sunny indoor lounge with a pool, but with a flamingo standing in the pool",
  "OutputConfig": {
    "StorageMode": "Permanent",
    "Resolution": "1K",
    "AspectRatio": "9:16"
  },
  "SessionContext": "job-001"
}

Transparent background โ€‹

Set background to transparent inside ExtInfo to generate an image with a transparent background.

json
"ExtInfo": "{\"AdditionalParameters\": \"{\\\"background\\\":\\\"transparent\\\"}\"}"

VOD and MPS place this option differently

The same OG engine takes the transparent-background option in different places: VOD nests it in AdditionalParameters inside ExtInfo (the JSON string is double-encoded), whereas MPS takes AdditionalParameters at the top level.

Output format (OutputFormat) โ€‹

OutputConfig.OutputFormat sets the output format. The model default applies when omitted.

json
{
  "OutputConfig": {
    "StorageMode": "Permanent",
    "Resolution": "1K",
    "OutputFormat": "png"
  }
}
ValueDescription
jpegJPEG output
pngPNG output

Choose png when you need lossless output, or when post-processing touches the alpha channel or fine gradients; jpeg is better when file size matters more than fidelity. Transparent backgrounds require png.

Text rendering โ€‹

Multilingual text rendering covers Chinese, English, Japanese, Korean, Arabic, and more. The max tier handles complex text and small type best.

GIF and SVG output (2.6 only) โ€‹

Since 2026-11-06 the 2.6 series (all 10 image2.6_sunburst_* / image2.6_flare_* values) can output animated GIFs and SVG vector images directly. The 2.0 / 2.5 series do not support this.

Both are enabled with output_format inside ExtInfo โ†’ AdditionalParameters, not with OutputConfig.OutputFormat (which still accepts only jpeg / png).

output_formatOutputCompanion parametersBilling
gifAnimated GIF (multi-frame)frame_count / frame_duration_msNumber of input images + output image tokens (per million)
svgSVG vector imagesvg.model / svg.reasoning.effortInput and output image fees + an SVG conversion fee

Animated GIF โ€‹

Parameter (inside AdditionalParameters)TypeDescription
output_formatStringFixed value gif
frame_countIntegerNumber of frames, 2โ€“16, default 9
frame_duration_msIntegerDuration of each frame in milliseconds, 20 ~ 2000, default 200, rounded to 10 ms
sizeStringPer-frame size, auto or WIDTHxHEIGHT (e.g. 752x1024). Width and height must be multiples of 16, longest side โ‰ค 3840, long-to-short side ratio โ‰ค 3:1
json
{
  "SubAppId": 123456789,
  "ModelName": "OG",
  "ModelVersion": "image2.6_sunburst_low",
  "Prompt": "the same sunny indoor lounge with a pool, but with a flamingo standing in the pool",
  "ExtInfo": "{\"AdditionalParameters\": \"{\\\"output_format\\\": \\\"gif\\\",\\\"frame_count\\\":10,\\\"frame_duration_ms\\\":200}\"}",
  "OutputConfig": {
    "StorageMode": "Temporary"
  },
  "SessionContext": "job-001"
}

Decoded AdditionalParameters:

json
{ "output_format": "gif", "frame_count": 10, "frame_duration_ms": 200 }

How long is one loop

Total duration โ‰ˆ frame_count ร— frame_duration_ms. The example above runs 10 ร— 200 ms = 2 s per loop; the defaults (9 frames ร— 200 ms) give about 1.8 s.

Frame count ร— frame size share one budget

Internally all frames are first tiled into a single sheet, so a GIF is limited by the total budget of frame_count ร— per-frame size. Exceeding it returns an error such as No supported sheet fits 10 GIF frames at size '752x1024' โ€” the frame count and frame size combination is over the limit. The more frames, the smaller size should be; the exact budget is not published, so reduce the frame count or size when you hit it.

SVG vector image โ€‹

SVG output requires an additional OG multimodal model โ€” the "SVG author model" (svg.model) โ€” which is why it carries a separate conversion fee.

Parameter (inside AdditionalParameters)TypeDescription
output_formatStringFixed value svg
svg.modelStringSVG author model, e.g. og-5.6-sol. See the list of supported values below
svg.reasoning.effortStringReasoning budget of the author model, e.g. medium
json
{
  "SubAppId": 123456789,
  "ModelName": "OG",
  "ModelVersion": "image2.6_sunburst_low",
  "Prompt": "the same sunny indoor lounge with a pool, but with a flamingo standing in the pool",
  "ExtInfo": "{\"AdditionalParameters\":\"{\\\"output_format\\\": \\\"svg\\\",\\\"svg\\\":{\\\"model\\\":\\\"og-5.6-sol\\\",\\\"reasoning\\\":{\\\"effort\\\":\\\"medium\\\"}}}\"}",
  "OutputConfig": {
    "StorageMode": "Temporary"
  },
  "SessionContext": "job-001"
}

svg.model accepts the following 20 values:

og-4.1 / og-4o / og-5 / og-5-chat / og-5-mini / og-5-nano / og-5.1 / og-5.1-chat / og-5.2 / og-5.2-chat / og-5.3-chat / og-5.3-codex / og-5.4 / og-5.4-mini / og-5.4-nano / og-5.4-pro / og-5.5 / og-5.5-pro / og-5.6-luna / og-5.6-sol

Decoded AdditionalParameters:

json
{
  "output_format": "svg",
  "svg": {
    "model": "og-5.6-sol",
    "reasoning": { "effort": "medium" }
  }
}

SVG carries an extra conversion fee

On top of the input and output image fees, SVG output is charged an SVG conversion fee, billed at the per-million-token input / cached-input / output rates of the OG multimodal model named in svg.model. See the AIGC pricing guide for the exact rates.

DocumentDescription
GPT-Image overviewVersion comparison and shared specifications
GPT-Image 2.5Two variants, xhigh / max tiers, measured generation times
GPT-Image 2.0Base series, quality tiers up to high
VOD quick startAuthentication, task submission, and result polling for the VOD API

Built with VitePress ยท Deployed on Tencent EdgeOne Pages