GPT-Image 2.6 โ
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:
| Variant | Positioning | Best for |
|---|---|---|
sunburst | Editing precision | Workflows where editing precision comes first: complex compositions, fine-grained revisions, small text |
flare | Fast generation | Fast, 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
| Item | Value |
|---|---|
| ModelName | OG |
| ModelVersion | image2.6_sunburst_* / image2.6_flare_* โ * is a placeholder, not a value you can pass; see ModelVersion enumeration for all 10 actual values |
| Result polling | DescribeTaskDetail |
| Guardrail bypass | Not supported |
ModelVersion enumeration โ
Five tiers per variant, 10 values in total.
| Tier | sunburst | flare |
|---|---|---|
low | image2.6_sunburst_low | image2.6_flare_low |
medium | image2.6_sunburst_medium | image2.6_flare_medium |
high | image2.6_sunburst_high | image2.6_flare_high |
xhigh | image2.6_sunburst_xhigh | image2.6_flare_xhigh |
max | image2.6_sunburst_max | image2.6_flare_max |
Choosing a quality tier โ
Higher tiers mean higher fidelity, but also longer generation times and higher cost.
| Tier | Characteristics | Recommended for |
|---|---|---|
low | Fastest generation, lowest cost | Quick drafts, batch testing, prompt iteration |
medium | The sweet spot between speed, cost, and quality | Most day-to-day production and general design work |
high | Richer detail, texture, lighting and shadow | Review-ready output, images that need careful rendering |
xhigh | Higher fidelity than high | Final review, upscaled use |
max | Highest fidelity; strong on complex text and small type | Final 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
| Parameter | Required | Type | Description |
|---|---|---|---|
SubAppId | Yes | Integer | Subapplication ID |
ModelName | Yes | String | Fixed value OG |
ModelVersion | No | String | Model version, e.g. image2.6_sunburst_medium. Defaults to the engine default image2_medium (the 2.0 series) when omitted |
Prompt | Yes | String | Generation prompt, up to 32,000 characters |
FileInfos.N | No | Array | Reference images (image-to-image), up to 16. Acts as a mask when ReferenceType=mask. See Passing reference images |
OutputConfig.StorageMode | No | String | Temporary (7-day retention) / Permanent (returns a FileId) |
OutputConfig.Resolution | No | String | 1K / 2K / 4K |
OutputConfig.AspectRatio | No | String | 1:1 / 3:2 / 2:3 / 3:4 / 4:3 / 16:9 / 9:16 / 21:9 / 9:21 |
OutputConfig.OutputImageCount | No | Integer | Number of images; 1โ8 for OG |
OutputConfig.OutputFormat | No | String | jpeg / png. Follows the model default when omitted. GIF / SVG do not use this field โ see GIF and SVG output |
OutputConfig.PersonGeneration | No | String | AllowAdult / Disallowed (no people or faces in the image) |
OutputConfig.InputComplianceCheck | No | String | Input compliance check: Enabled / Disabled |
OutputConfig.OutputComplianceCheck | No | String | Output compliance check: Enabled / Disabled |
OutputConfig.LogoAdd | No | String | Add a logo watermark: Enabled / Disabled |
InputRegion | No | String | Input region: Mainland (Chinese mainland) / Oversea (outside the Chinese mainland) / OverseaUSWest (US West) |
ExtInfo | No | String | JSON string carrying model-specific options; see Special settings and GIF and SVG output |
SessionContext | No | String | Session identifier echoed back in the callback |
Request example โ
{
"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
{
"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:
Type | Companion field | Description |
|---|---|---|
File | FileId | VOD media file ID |
Url | Url | Publicly accessible image URL |
Base64 | Base64 | Base64-encoded image |
Base64 limits
- The total size of all files must not exceed
7 MB, so the Base64-encoded request stays under the10 MBCloud 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).
{
"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 1โ8 (limits differ per engine; Kling accepts 1โ9).
{
"OutputConfig": {
"StorageMode": "Permanent",
"Resolution": "1K",
"AspectRatio": "9:16",
"OutputImageCount": 3
}
}Custom resolution (size) โ
Set the output resolution directly through size inside ExtInfo.
| Constraint | Value |
|---|---|
| Width and height | Both multiples of 16 |
| Longest edge | At most 3840px (that is, no larger than 4K) |
| Total pixels | 655,360 โ 8,294,400 |
{
"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.
{
"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.
{
"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.
"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.
{
"OutputConfig": {
"StorageMode": "Permanent",
"Resolution": "1K",
"OutputFormat": "png"
}
}| Value | Description |
|---|---|
jpeg | JPEG output |
png | PNG 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_format | Output | Companion parameters | Billing |
|---|---|---|---|
gif | Animated GIF (multi-frame) | frame_count / frame_duration_ms | Number of input images + output image tokens (per million) |
svg | SVG vector image | svg.model / svg.reasoning.effort | Input and output image fees + an SVG conversion fee |
Animated GIF โ
Parameter (inside AdditionalParameters) | Type | Description |
|---|---|---|
output_format | String | Fixed value gif |
frame_count | Integer | Number of frames, 2โ16, default 9 |
frame_duration_ms | Integer | Duration of each frame in milliseconds, 20 ~ 2000, default 200, rounded to 10 ms |
size | String | Per-frame size, auto or WIDTHxHEIGHT (e.g. 752x1024). Width and height must be multiples of 16, longest side โค 3840, long-to-short side ratio โค 3:1 |
{
"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:
{ "output_format": "gif", "frame_count": 10, "frame_duration_ms": 200 }How long is one loop
Total duration โ 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) | Type | Description |
|---|---|---|
output_format | String | Fixed value svg |
svg.model | String | SVG author model, e.g. og-5.6-sol. See the list of supported values below |
svg.reasoning.effort | String | Reasoning budget of the author model, e.g. medium |
{
"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:
{
"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.
Related documents โ
| Document | Description |
|---|---|
| GPT-Image overview | Version comparison and shared specifications |
| GPT-Image 2.5 | Two variants, xhigh / max tiers, measured generation times |
| GPT-Image 2.0 | Base series, quality tiers up to high |
| VOD quick start | Authentication, task submission, and result polling for the VOD API |