GPT-Image โ
Endpoint: POST https://vod.intl.tencentcloudapi.comAction: CreateAigcImageTask
GPT-Image is a family of image generation models. It supports text-to-image and multi-reference image generation, plus mask-based local editing, transparent backgrounds, multi-image output, and custom sizes; the 2.6 series can also output animated GIFs and SVG vector images directly. Multilingual text rendering is strong, which makes it a good fit for posters and type-heavy design work.
Three series are available today: image2, image2.5, and image2.6. All three share the same ModelName=OG and the same request fields โ for basic usage only the ModelVersion value differs.
Choose a version โ
The API reference is split per series. Open a card to see that series' ModelVersion enumeration, quality tiers, generation times, and special settings.
image2.6_sunburst_* ยท image2.6_flare_*- Sunburst for editing precision / Flare for speed
- Five tiers each, 10 ModelVersion values in total
- Adds animated GIF / SVG vector output
- Basic call same as 2.5, released 2026-11-06
image2.5_sunburst_* ยท image2.5_flare_*- Sunburst for precision / Flare for speed
- Adds the xhigh and max tiers
- Measured generation time per tier
- Lower tiers are cheaper for batch output
image2_low ยท image2_medium ยท image2_high- Single series, simplest parameters
- Quality tiers up to high
- The default ModelVersion
- Supports mask-based inpainting
Version comparison โ
| Item | 2.0 | 2.5 | 2.6 |
|---|---|---|---|
ModelName | OG | OG | OG |
ModelVersion | image2_lowimage2_mediumimage2_high | 10 values five tiers each for sunburst / flare | 10 values five tiers each for sunburst / flare |
| Variants | 1 | 2 (sunburst / flare) | 2 (sunburst / flare) |
| Quality tiers | low / medium / high | plus xhigh / max | plus xhigh / max |
| ModelVersion values | 3 | 10 | 10 |
| Multi-reference (up to 16) | โ | โ | โ |
mask inpainting | โ | โ | โ |
| Transparent background | โ | โ | โ |
Custom size and auto | โ | โ | โ |
Multi-image output (1โ8) | โ | โ | โ |
Output format OutputFormat | jpeg / png | jpeg / png | jpeg / png |
Animated GIF (2โ16 frames) | โ | โ | โ |
| SVG vector image | โ | โ | โ (extra SVG conversion fee) |
All three series share one set of request fields
FileInfos, OutputConfig, and ExtInfo are written identically across the three series. Switching series means changing ModelVersion only โ the request structure stays the same. The one exception is GIF / SVG output: it is enabled with output_format in ExtInfo and only 2.6 supports it.
Choosing a version โ
- Prefer 2.6 for new integrations: it is the latest generation and its basic parameters match 2.5, so switching costs nothing.
- Animated GIF or SVG output requires 2.6: set
output_format=gif/svginExtInfo; see GIF and SVG output. Note that SVG carries an extra conversion fee. - Pick
flarewhen latency matters: at the same tier, flare is clearly faster than sunburst (measured on 2.5:61 svs169 sat themaxtier). - Pick
sunburstfor editing precision, complex compositions, and small text, and raise the tier toxhighormax. - Use
low/mediumfor quick drafts and prompt iteration; the2.0series is sufficient here and has the simplest parameters. - If three tiers are enough, the
2.0series is still available โ it is the default series whenModelVersionis omitted (image2_medium).
Shared specifications โ
The following applies to all three series. Details and examples live in the per-version documents.
| Item | Value |
|---|---|
| Defaults | ModelVersion=image2_medium / AspectRatio=1:1 |
Resolution Resolution | 1K / 2K (2560x1440) / 4K (3840x2160); anything above 2560px is experimental |
Aspect ratio AspectRatio | 1:1 / 3:2 / 2:3 / 3:4 / 4:3 / 16:9 / 9:16 / 21:9 / 9:21 |
| Reference images | Up to 16 |
| Prompt length | Up to 32,000 characters |
| Text rendering | Chinese, English, Japanese, Korean, Arabic, and more |
| Multi-image output | 1โ8 for OG (1โ9 for Kling) |
| Reference image input | File (FileId) / Url / Base64; Base64 total โค 7 MB, formats jpeg / jpg / png / webp, no data: prefix |
| Custom size | Width and height both multiples of 16; longest edge โค 3840px; total pixels 655,360 โ 8,294,400 |
| Guardrail bypass | Not supported |
Related documents โ
| Document | Description |
|---|---|
| GPT-Image 2.6 | Latest series: five tiers each for sunburst / flare, GIF / SVG output |
| 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 |