GPT-image 2.6 โ
โ Back to the GPT-image overview for a version comparison and selection guide.
GPT-image 2.6 is the latest generation of the GPT-image family and ships two variants on TokenHub:
| Model ID | Positioning | Best for |
|---|---|---|
custom-model-og-v2.6-f | Flare โ faster | Fast iteration, batch drafts, interactive previews. As fast as roughly 6 seconds per image at the low tier |
custom-model-og-v2.6-s | Sunburst โ more detail | Complex compositions, fine-grained editing, keeping characters and products consistent across multiple rounds of revision |
The two share identical request fields and the same token unit price. Compared with 2.5, overall generation is about 50% faster.
This page is one of three GPT-image API documents. See also GPT-image 2.0 and GPT-image 2.5.
Prerequisites โ
- You have registered a Tencent Cloud account and activated the TokenHub service.
- Your account has been allowlisted for this model.
- You have obtained an API Key. How to do it: go to Online Inference โ Vision Models, search for
custom-model-og-v2.6-fandcustom-model-og-v2.6-s, enable pay-as-you-go, then create a Key for the model under API-Key management.
Important
- This model is a test model and requires an allowlist entry granted by the backend team before it can be used. Contact the product team and submit your UIN and AppId.
- Allowlisting takes effect per model ID โ
-fand-smust be requested separately. - GIF output requires an additional GIF preview entitlement for the model.
- TokenHub settles on an hourly cycle. Sales should apply for customer discounts in good time.
Replace YOUR_API_KEY in every example below with your own API Key. Authentication uses the request header Authorization: Bearer YOUR_API_KEY.
Basic Information โ
| Item | Value |
|---|---|
| model | custom-model-og-v2.6-f / custom-model-og-v2.6-s |
| Supported tasks | Text-to-image, image editing, markup-based editing, animated GIF, SVG vector |
| Request domain (international site) | tokenhub-intl.tencentcloudmaas.com (Singapore) |
| Authentication | Authorization: Bearer <API_KEY> |
| Result return | Synchronous; the result is contained in the response body |
Quality tier quality | auto / low / medium / high / xhigh / max |
Planning tier complexity | low / medium / high, default high |
| Output formats | png / jpeg / webp / gif / svg |
| Guardrail removal supported | Not supported |
What Changed Versus 2.5 โ
| Change | Description |
|---|---|
| Generation speed | About 50% faster overall. Flare reaches roughly 6 seconds per image at the low tier |
| complexity decoupled from quality | A new complexity parameter independently controls "planning effort before rendering", separate from quality, which governs pixel detail |
| Animated GIF output | output_format=gif, supporting 2~16 frames with adjustable per-frame duration |
| SVG vector output | output_format=svg, producing infinitely scalable vector graphics directly |
| Markup-based editing | Carries over the annotation-layer capability from 2.5 |
Choosing Between complexity and quality
complexitygoverns how much compute the model spends planning the scene before it starts drawing;qualitygoverns pixel rendering precision.- Local tweaks (swapping a background, changing a signboard) โ
complexity=lowplus whateverqualityyou need, which skips re-laying-out the scene. - Many elements in one frame, dense text, complex layouts โ raise
complexity. - Changing
complexityis not billed separately, but higher tiers add latency and may introduce unintended changes. Benchmark it on your own workloads.
Submit a Text-to-Image Task โ
1. Endpoint Description โ
- Request domain (international site):
tokenhub-intl.tencentcloudmaas.com(Singapore) - Endpoint:
POST /v1/wand/og-image/generation
Generates an image synchronously from the input text and returns the result directly.
2. Input Parameters โ
| Parameter | Required | Type | Description |
|---|---|---|---|
model | Yes | String | Model selection: custom-model-og-v2.6-f or custom-model-og-v2.6-s |
prompt | No | String | Text description. Up to 32,000 characters |
size | No | String | Output image size. Custom sizes are supported (each side โค 3840px, width and height multiples of 16, long-to-short side ratio โค 3:1, total pixels 655,360~8,294,400) |
quality | No | String | Quality tier. auto, low, medium, high, xhigh, max |
complexity | No | String | Planning effort before rendering, independent of quality. low / medium / high, defaults to high when omitted. Not billed separately |
n | No | Integer | Number of images to generate, 1~10. Default: 1. Must be 1 for SVG output |
background | No | String | Background transparency. opaque, transparent, auto. When transparent is chosen, the output format must be png or webp |
output_format | No | String | Output format. png (default), jpeg, webp, gif, svg |
output_compression | No | Integer | Compression level (0-100). Supported only for webp / jpeg output, default 100 |
frame_count | No | Integer | GIF frame count. 2~16, defaults to 9 when omitted. Supported only when output_format=gif |
frame_duration_ms | No | Integer | GIF per-frame duration (milliseconds). Minimum 20, defaults to 200 when omitted. Rounded to the nearest 10ms during encoding; the per-frame cap is 655,350ms. Supported only when output_format=gif |
svg | No | Object | SVG author-model settings. Requires output_format=svg. See "SVG Vector Output" below |
response_format | No | String | Return format of the generated image. Options: url or b64_json |
3. Output Parameters โ
| Parameter | Type | Description |
|---|---|---|
output_format | String | Return format of the generated image. Example: png |
quality | String | Quality actually applied. Example: medium |
size | String | Size of the generated image. Example: 1024x1024 |
background | String | Background setting actually applied. Example: auto |
created | Integer | Unix timestamp (in seconds) of image creation. Example: 1776946569 |
data | Array of ResultImage | List of generated result images |
usage | Usage | Token statistics |
request_id | String | Unique request ID generated by the server and returned with every request. Provide this RequestId when troubleshooting |
4. Examples โ
Request Example
curl --location 'https://tokenhub-intl.tencentcloudmaas.com/v1/wand/og-image/generation' \
--header 'Authorization: Bearer YOUR_API_KEY' \
--header 'Content-Type: application/json' \
-d '{
"model": "custom-model-og-v2.6-f",
"quality": "medium",
"complexity": "low",
"prompt": "a dancing kitten",
"size": "1024x1024",
"n": 1
}'Response Example
{
"background": "opaque",
"created": 1786095835,
"data": [
{
"url": "https://xxxxxxxxxxxx.png"
}
],
"output_format": "png",
"quality": "medium",
"size": "1024x1024",
"usage": {
"total_tokens": 27180
},
"request_id": "eaa4b07b-ccde-40a4-b184-822e3c5a4e60"
}Animated GIF Output โ
Set output_format to gif to produce an animation directly โ no separate video model and no manual frame stitching required.
Parameters โ
| Parameter | Values | Default | Description |
|---|---|---|---|
output_format | gif | โ | Required; enables GIF output |
frame_count | 2~16 | 9 | Number of frames |
frame_duration_ms | โฅ 20 | 200 | Per-frame duration (milliseconds), rounded to the nearest 10ms |
At the defaults, 9 frames ร 200ms โ a 1.8-second loop.
Limitations โ
| Limitation | Description |
|---|---|
| Supported endpoints | Text-to-image endpoint only; not supported on image editing endpoints |
| Unsupported capabilities | Streaming responses, partial_images, mask, custom output_compression |
| Size constraints | The requested size must satisfy the selected model's GIF size limits |
| Entitlement | Requires the model's GIF preview entitlement |
Example โ
curl --location 'https://tokenhub-intl.tencentcloudmaas.com/v1/wand/og-image/generation' \
--header 'Authorization: Bearer YOUR_API_KEY' \
--header 'Content-Type: application/json' \
-d '{
"model": "custom-model-og-v2.6-f",
"prompt": "an owl blinking, seamless loop",
"output_format": "gif",
"frame_count": 12,
"frame_duration_ms": 120,
"size": "1024x1024"
}'SVG Vector Output โ
Set output_format to svg to obtain infinitely scalable vector graphics directly โ ideal for icons, illustrations, and diagrams, and it removes the raster-to-vector conversion step.
How It Works โ
The server first generates a reference image with the image model, then an SVG author model produces the vector content from it. Consequently:
- The top-level
modeldetermines which image model generates the reference image; - In the SVG case,
complexitycontrols the planning effort for the reference image, independent of the SVG author model's reasoning effort; svg.modelspecifies the SVG author model, andsvg.reasoningcontrols its reasoning effort.
Parameters โ
| Parameter | Type | Description |
|---|---|---|
output_format | String | Set to svg |
svg.model | String | The SVG author model. Required when author-model selection is enabled; otherwise the entire svg object should be omitted |
svg.reasoning | Object | Reasoning settings for the SVG author, independent of the image complexity. When omitted or null, the author model's default is used |
Limitations โ
| Limitation | Description |
|---|---|
| Supported endpoints | Text-to-image endpoint only; not supported on image editing endpoints, and SVG cannot be used as an input image |
n | Must be 1 โ one file per request |
| Unsupported capabilities | Streaming responses, partial_images, prompt_rewriter, output_compression |
| Output | Static vector graphics |
Example โ
curl --location 'https://tokenhub-intl.tencentcloudmaas.com/v1/wand/og-image/generation' \
--header 'Authorization: Bearer YOUR_API_KEY' \
--header 'Content-Type: application/json' \
-d '{
"model": "custom-model-og-v2.6-s",
"prompt": "a minimalist weather icon set with linear strokes",
"output_format": "svg",
"n": 1
}'SVG Is Billed Differently
SVG output incurs two charges at once: the image model bills the reference image's tokens at its own rate, and the SVG author model bills the tokens used to produce the vector content at its rate. The total cost is the sum of the two.
Submit an Image Editing Task โ
1. Endpoint Description โ
- Request domain:
tokenhub-intl.tencentcloudmaas.com(Singapore) - Endpoint:
POST /v1/wand/og-image/edits(json) - Or:
POST /v1/wand/og-image/multipart-edits(multipart) - Or:
POST /v1/wand/og-image/images/edits(json / multipart)
Generates an image synchronously from the input image and returns the result directly.
2. Input Parameters โ
| Parameter | Required | Type | Description |
|---|---|---|---|
model | No | String | Model selection: custom-model-og-v2.6-f or custom-model-og-v2.6-s |
prompt | Yes | String | Text description. Up to 32,000 characters |
images | Yes | Array of ImageRef | Input images. Supported count: 1~16 |
mask | No | ImageRef | Used for partial regeneration (inpainting); must match the input image size |
markup | No | ImageRef | Annotation layer. A transparent PNG that circles the region to change. Cannot be used together with mask |
size | No | String | Output image size. Custom sizes are supported (each side โค 3840px, width and height multiples of 16, long-to-short side ratio โค 3:1, total pixels 655,360~8,294,400) |
n | No | Integer | Number of images to generate, 1~10. Default: 1 |
quality | No | String | Quality tier. auto, low, medium, high, xhigh, max |
complexity | No | String | Planning effort. low / medium / high, default high. Use low for local edits |
background | No | String | Background transparency. transparent, opaque, or auto (default). Example: auto |
output_format | No | String | Output format. Supports png, jpeg, webp. The editing endpoints do not support gif or svg |
output_compression | No | Integer | Compression level (0-100). Supported only for webp / jpeg output |
response_format | No | String | Return format of the generated image. Options: url or b64_json |
transparent Is Available Only in PNG / WebP
For a transparent background, use background=transparent together with output_format=png or webp.
3. Markup-Based Editing โ
Use an annotation layer to tell the model where to edit โ far more precise than describing the location in words ("move the logo a little to the left").
| Constraint | Description |
|---|---|
| Target | The markup applies to the first input image only; the remaining inputs act as reference images |
| File format | Must be a standalone transparent PNG containing transparent pixels; do not flatten the annotation into the source image |
| Size requirement | The markup layer must match the first input image in width and height exactly |
| Pixel cap | The first input image and the markup layer must each stay under 16,777,216 pixels |
| File size | The markup file must not exceed 50 MB |
| Mutually exclusive | Cannot be used together with mask |
| Supported endpoints | Image editing endpoints only; not supported on the text-to-image endpoint |
Request Example (multipart)
curl --location 'https://tokenhub-intl.tencentcloudmaas.com/v1/wand/og-image/multipart-edits' \
--header 'Authorization: Bearer YOUR_API_KEY' \
--form 'model=custom-model-og-v2.6-f' \
--form 'quality=medium' \
--form 'complexity=low' \
--form 'image[]=@kitchen.png' \
--form 'markup=@markup-overlay.png' \
--form 'prompt=change the striped vase inside the red circle to solid cobalt blue ceramic'4. Output Parameters โ
Identical to the text-to-image endpoint; see above.
5. Examples โ
Request Example (json)
curl --location 'https://tokenhub-intl.tencentcloudmaas.com/v1/wand/og-image/edits' \
--header 'Authorization: Bearer YOUR_API_KEY' \
--header 'Content-Type: application/json' \
-d '{
"model": "custom-model-og-v2.6-s",
"quality": "high",
"complexity": "low",
"prompt": "dancing",
"images": [{ "image_url": "https://xxxxxxxxxxxx.png"}],
"size": "1024x1024",
"n": 2
}'Response Example
{
"background": "opaque",
"created": 1786096322,
"data": [
{
"url": "https://xxxxxxxxxxxx.png"
},
{
"url": "https://xxxxxxxxxxxx.png"
}
],
"output_format": "png",
"quality": "high",
"size": "1024x1024",
"usage": {
"total_tokens": 65920
},
"request_id": "705d12d2-9f68-4cfa-859a-733e449ea675"
}Capability Support Matrix โ
| Capability | Text-to-image endpoint | Image editing endpoints |
|---|---|---|
complexity | โ | โ |
markup annotation editing | โ | โ |
mask partial regeneration | โ | โ |
| Animated GIF output | โ | โ |
| SVG vector output | โ | โ |
Data Structures โ
ResultImage โ
| Parameter | Type | Description |
|---|---|---|
url | String | URL of the returned image |
Usage โ
| Parameter | Type | Description |
|---|---|---|
total_tokens | Integer | Token statistics |
ImageRef โ
| Name | Type | Required | Description |
|---|---|---|---|
image_url | String | No | Images support png and jpg. Pass either the image URL or base64-encoded data. Example: https://xxxxxxxxxxx.png |
Billing and Pricing โ
- Billing mode: Pay-as-you-go (by token), postpaid.
- Settlement cycle: The system aggregates and settles your resource consumption hourly.
- Pricing logic: Cost is determined by token usage and the corresponding unit price:
total cost = token usage ร token unit price. - Usage notes: A unified unit price of
1.6 USD per million tokensapplies. The conversion against upstream vendor tokens is shown below.
| Token type | Vendor USD unit price | TokenHub price | Conversion factor |
|---|---|---|---|
| text input | $5.00 / million | $1.60 / million | 3.125 |
| text cached | $1.25 / million | $1.60 / million | 0.78125 |
| image input | $8.00 / million | $1.60 / million | 5.0 |
| image cached | $2.00 / million | $1.60 / million | 1.25 |
| image output | $30.00 / million | $1.60 / million | 18.75 |
USD Settlement Logic (International Site)
text input tokens ร 3.125
+ text cached input tokens ร 0.78125
+ image input tokens ร 5
+ image cached input tokens ร 1.25
+ output image tokens ร 18.75
= token consumption of a single taskThe Real Cost of 2.6 Differs From 2.5
The token unit price is identical to 2.5, but the output image token count rises significantly at the low and medium tiers, so the per-image cost at those two tiers goes up. Token consumption at high and above is unchanged from 2.5.
Taking 1024x1024 as an example, output image token counts compare as follows:
| quality | 2.5 | 2.6 | Change |
|---|---|---|---|
low | 196 | 823 | about 4.2ร |
medium | 439 | 1,449 | about 3.3ร |
high | 1,756 | 1,756 | Unchanged |
xhigh | 3,122 | 3,122 | Unchanged |
max | 7,024 | 7,024 | Unchanged |
The token counts above are reference values, derived from OpenAI's official token calculator at
1024x1024. Actual consumption is whatever the endpoint returns inusage.total_tokens.
Selection advice: If your workload is dominated by low-quality batch generation (icons, thumbnails, bulk drafts), per-image cost on 2.6 will be noticeably higher than on 2.5 and your budget needs recalculating. At high and above, 2.6 is "same price, faster" and can be adopted directly.
Related Documents โ
| Document | Description |
|---|---|
| GPT-image 2.0 | The base version, with quality tiers up to high |
| GPT-image 2.5 | Adds the xhigh / max quality tiers and markup-based editing |
| Get an API Key | Applying for and managing TokenHub API Keys |