> ## Documentation Index > Fetch the complete documentation index at: https://docs.apiyi.com/llms.txt > Use this file to discover all available pages before exploring further. # GPT Image 2.6 New Capabilities > Model selection for GPT Image 2.6 Flare and Sunburst, plus complexity control, SVG vector output, animated GIFs, markup-guided edits, interactive examples, and real results. > [!NOTE] > > The Playground provides three named examples: **raster PNG with complexity, SVG, and a two-frame GIF**. Enter `Bearer sk-xxx` under **Authorization**, choose an example, edit the prompt, and send the request. > [!WARNING] > > `data[0].b64_json` has no `data:` prefix, and SVG and GIF responses are also base64-encoded. The browser Playground may be unable to display a long base64 response even when the request succeeded. Use the Python example below to decode and save the result locally. ## Model selection GPT Image 2.6 was released on 2026-11-04. It retains `/v1/images/generations` and `/v1/images/edits`, and adds complexity control, SVG output, animated GIF output, and markup-guided editing. | Model | Focus | Best for | | - | - | - | | `gpt-image-2.6-flare` | Fast iteration | Drafts, batch generation, social content, and rapid prompt comparisons | | `gpt-image-2.6-sunburst` | Detailed visual work | Complex layouts, dense text, finished assets, and precise editing | See the [model pricing directory](https://docs.apiyi.com/en/models/index.md) for current token rates. Actual cost depends on size, quality, output format, and token usage. SVG also incurs authoring-model charges, so its cost is not comparable to a standard PNG. ## New capabilities > [card] [Complexity control](#complexity-control-planning) > > Controls planning before rendering, independently of the quality setting. > [card] [SVG vector output](#svg-generate-editable-vector-files) > > Returns editable paths, shapes, and colors for icons, illustrations, and UI assets. > [card] [Animated GIF output](#gif-generate-looping-animations) > > Produces a complete GIF in one request with frame count and frame duration controls. > [card] [Markup-guided edits](#markup-guided-edits) > > Uses a transparent annotation layer to identify the edit region while the prompt describes the change. ## complexity: control planning `complexity` controls how much the model plans before rendering. It is intended for dense text, complex layouts, and relationships between objects. `quality` controls rendering quality instead; the two settings serve different purposes. | Official level | Recommended use | | - | - | | `low` | Focused edits, simple compositions, and quick drafts | | `medium` | A balance for ordinary layouts and multiple constraints | | `high` | Dense text, complex layouts, and object relationships; used by default when complexity is omitted | Complexity has no separate fee. Higher levels can increase latency and introduce unwanted changes. Compare results for your task instead of assuming that a higher level is always better. > [accordion] Upstream test note: additional accepted levels > > The upstream error response in our test also listed `none`, `xhigh`, and `max`, and the current route accepted them. OpenAI's public guide documents `low / medium / high`; production requests should use those official levels rather than relying on additional values as a long-term compatibility guarantee. ## SVG: generate editable vector files Set `output_format: "svg"`. The current upstream also requires the nested `svg.model` field to select the text model that authors the vector code: ```json theme={null} { "model": "gpt-image-2.6-sunburst", "prompt": "A minimal flat vector icon of a rocket, exactly three solid colors, geometric editable shapes, no text, no raster texture, transparent background.", "output_format": "svg", "svg": { "model": "gpt-5.6-terra" }, "quality": "low", "size": "1024x1024", "n": 1 } ``` ![Vector rocket icon with red fins, a blue window, and a white body](https://mintcdn.com/apiyillc/I9X_C01jz8OkWw6c/images/gpt-image-2-6/rocket.svg?fit=max\&auto=format\&n=I9X_C01jz8OkWw6c\&q=85\&s=c2dc54229ae6495d2926adcc44513fa4) A real SVG generated through APIYI's passthrough route: editable path and circle elements ### Cost and limitations * The image model creates a reference image, then a text model authors the SVG. `usage` covers the reference image and `svg_usage` covers the authoring model; both contribute to cost. * `svg_usage.reasoning_tokens` is already included in `svg_usage.output_tokens`. Do not add it again. * SVG is available only through `/v1/images/generations` with `n=1`. The edit endpoint does not support SVG output or SVG as a raster input. * Streaming, partial images, `output_compression`, and `prompt_rewriter` are unsupported. * The result is static vector XML without scripts, external resources, or embedded raster images. Decode and save it as `.svg`, not as a PNG. ## GIF: generate looping animations Set `output_format: "gif"` and describe the subject, motion, and loop in the prompt. This low-cost example should produce **2 frames at 100ms each, for a total duration of 0.2 seconds**: ```json theme={null} { "model": "gpt-image-2.6-sunburst", "prompt": "A minimal two-frame looping animation of a yellow circle moving slightly right and returning to its starting position on a plain white background, no text, seamless loop.", "output_format": "gif", "quality": "low", "size": "512x512", "frame_count": 2, "frame_duration_ms": 100, "n": 1 } ``` ![Two-frame looping animation of a yellow circle moving right and returning to its starting position](https://mintcdn.com/apiyillc/I9X_C01jz8OkWw6c/images/gpt-image-2-6/two-frame-loop.gif?s=d010bf9dbb9b5c3a3e9b915bb2164a3d) A real GIF generated through APIYI's passthrough route: 2 frames and 0.2 seconds | Parameter | Official range and default | Notes | | - | - | - | | `frame_count` | 2–64, default 9 | More frames generally increase latency and cost | | `frame_duration_ms` | 20–2000ms, default 200ms, rounded to 10ms | Total duration is approximately frame count multiplied by frame duration | | `size` | `auto` or a valid WIDTHxHEIGHT | Size of each finished frame; frame count, frame size, and the total pixel budget must all fit | GIF is generation-only and does not support streaming, partial images, custom `output_compression`, or `prompt_rewriter`. Do not use `frame_count` or `frame_duration_ms` with PNG, JPEG, WebP, or SVG. ### Verify the actual frame count Do not rely only on HTTP 200 or the response's `output_format`. If a route drops the frame fields, it can still return a default 9-frame, 1.8-second GIF. Inspect the actual file with `ffprobe`: ```bash theme={null} ffprobe -v error -select_streams v:0 -count_frames \ -show_entries stream=codec_name,width,height,nb_read_frames,duration \ -of json result.gif ``` For this example, expect `nb_read_frames=2` and `duration=0.200000`. ## Markup-guided edits GPT Image 2.6 also supports markup-guided edits through the `markup` field on `/v1/images/edits`: 1. Keep the original image as the first input. 2. Create a transparent PNG at the same dimensions and add circles, arrows, or sketches around the region to change. 3. Upload that annotation layer as `markup`, then describe the change and the details to preserve in `prompt`. 4. Markup applies to the first input image and cannot be combined with `mask` or `prompt_rewriter`. For ordinary editing, multi-image fusion, and masks, see the [Image Edit API](https://docs.apiyi.com/en/api-capabilities/gpt-image-2/image-edit.md). Markup forwarding must be verified separately on the target route; this page does not present it as a tested interactive example. ## Client-side decoding All output formats use `data[0].b64_json`; only the file extension changes: ```python theme={null} import base64 from pathlib import Path payload = response.json() fmt = payload["output_format"] raw = base64.b64decode(payload["data"][0]["b64_json"]) Path(f"result.{fmt}").write_bytes(raw) ``` SVG decodes to UTF-8 XML, while GIF and raster formats decode to binary files. Production code should also check the HTTP status, `error` field, and actual file signature rather than trusting the extension alone. ## Route compatibility and troubleshooting > [!WARNING] > > New 2.6 fields require native JSON passthrough. Compatibility can vary across upstream routes, and these public examples do not guarantee identical behavior in every group. Verify them in the group your account actually uses. | Symptom | What to check first | | - | - | | `SVG generation requires 'svg.model'` even though it was provided | Whether the route filtered or rewrote the nested `svg` object | | A request for 2 frames at 100ms returns 9 frames and 1.8 seconds | Whether `frame_count` and `frame_duration_ms` were dropped in favor of defaults | | An invalid complexity string still returns 200 | Validation behavior can differ across upstreams; this alone does not prove the field was dropped. Compare valid-level behavior and inspect upstream logs | | Playground shows `unable to complete request` | Check whether the response was actually 200; long base64 may exceed the browser's display capacity, so decode locally | | SVG cost is higher than expected | Inspect both `usage` and `svg_usage`, not only reference-image tokens | ## Related documentation * [GPT-Image-2.5 / 2 overview](https://docs.apiyi.com/en/api-capabilities/gpt-image-2/overview.md) * [Standard text-to-image Playground](https://docs.apiyi.com/en/api-capabilities/gpt-image-2/text-to-image.md) * [Image Edit Playground](https://docs.apiyi.com/en/api-capabilities/gpt-image-2/image-edit.md) * [Image API essentials and best practices](https://docs.apiyi.com/en/api-capabilities/image-api-best-practices.md) * [Model pricing directory](https://docs.apiyi.com/en/models/index.md) ## OpenAPI ````yaml api-reference/gpt-image-2-6-generate-openapi-en.yaml POST /v1/images/generations openapi: 3.1.0 info: title: GPT Image 2.6 Text-to-Image and New Capabilities API description: > Text-to-image with OpenAI `gpt-image-2.6-flare` / `gpt-image-2.6-sunburst`, including raster images, complexity control, SVG vector output, and animated GIF output. - Complexity: official low / medium / high levels, default high, with no separate fee - SVG: set output_format=svg and provide svg.model; generations only, n=1 - GIF: set output_format=gif and optionally frame_count and frame_duration_ms - Responses contain data[0].b64_json for client-side base64 decoding **Authentication**: Add `Authorization: Bearer YOUR_API_KEY` to request headers **Get an API Key**: Visit the [APIYI Console](https://api.apiyi.com/token) version: 1.0.0 servers: - url: https://api.apiyi.com description: Primary endpoint security: - bearerAuth: [] paths: /v1/images/generations: post: tags: - GPT Image 2.6 summary: 'GPT Image 2.6: generate PNG, SVG, or GIF' description: > Generate images from text prompts with GPT Image 2.6. The three named request examples demonstrate complexity, SVG, and GIF. Complexity controls planning before rendering and is independent of rendering quality. SVG requires the nested svg.model field. GIF frame controls apply only when output_format=gif. SVG and GIF do not support streaming, partial images, or output_compression. operationId: generateGptImage26 requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/Image26Request' examples: complexityPng: summary: Raster PNG + low complexity description: >- Use a four-panel infographic to inspect complexity; quality=low controls cost value: model: gpt-image-2.6-sunburst prompt: >- A clean 2x2 technical infographic on a white background. Top-left: a red circle labeled 'A'. Top-right: a blue square labeled 'B'. Bottom-left: a green triangle labeled 'C'. Bottom-right: a yellow hexagon labeled 'D'. A black arrow connects A to B to C to D in that order. Exactly four labels, balanced grid, no other text. output_format: png complexity: low quality: low size: 1024x1024 'n': 1 svgVector: summary: SVG vector icon description: >- Keep the nested svg.model object; the response also contains svg_usage value: model: gpt-image-2.6-sunburst prompt: >- A minimal flat vector icon of a rocket, exactly three solid colors, geometric editable shapes, no text, no raster texture, transparent background. output_format: svg svg: model: gpt-5.6-terra quality: low size: 1024x1024 'n': 1 gifAnimation: summary: Two-frame looping GIF description: >- The finished file should contain 2 frames and last 0.2 seconds, not the default 9 frames value: model: gpt-image-2.6-sunburst prompt: >- A minimal two-frame looping animation of a yellow circle moving slightly right and returning to its starting position on a plain white background, no text, seamless loop. output_format: gif quality: low size: 512x512 frame_count: 2 frame_duration_ms: 100 'n': 1 responses: '200': description: >- Generation succeeded; returns base64-encoded PNG, JPEG, WebP, SVG, or GIF content: application/json: schema: $ref: '#/components/schemas/Image26Response' '400': description: >- Invalid parameters, or the active route did not forward new fields such as svg.model '401': description: Unauthorized - invalid API Key '403': description: Content moderation block '429': description: Rate limit or insufficient quota '500': description: Internal server error security: - bearerAuth: [] components: schemas: Image26Request: type: object required: - model - prompt properties: model: type: string description: >- Flare is optimized for fast iteration; Sunburst is intended for detailed visual work enum: - gpt-image-2.6-flare - gpt-image-2.6-sunburst default: gpt-image-2.6-sunburst prompt: type: string maxLength: 32000 description: >- Prompt text in English or Chinese. For GIF, describe the subject, motion, and loop example: A minimal flat vector icon of a rocket, three solid colors, no text complexity: type: string description: >- Planning complexity before rendering, independent of quality. Official levels are low / medium / high, with high as the default when omitted. No separate fee enum: - low - medium - high default: high size: type: string description: >- Output size as a preset or a valid WIDTHxHEIGHT string. The GIF example uses 512x512; frame count, frame size, and the total pixel budget must all fit example: 1024x1024 default: auto quality: type: string description: >- Rendering quality, independent of complexity. For SVG, controls the reference image quality enum: - auto - low - medium - high - xhigh - max default: auto output_format: type: string description: >- Output format. SVG and GIF are generation-only and do not support edits, streaming, partial images, or output_compression enum: - png - jpeg - webp - svg - gif default: png output_compression: type: integer description: Compression level for jpeg / webp only; do not use with SVG or GIF minimum: 0 maximum: 100 example: 85 background: type: string description: >- Background mode. transparent requires a compatible output format; JPEG does not support transparency enum: - auto - opaque - transparent default: auto moderation: type: string description: Moderation strength enum: - auto - low default: auto 'n': type: integer description: Number of results. The examples and SVG output use 1 enum: - 1 default: 1 svg: type: object description: >- SVG-specific configuration. The current upstream requires svg.model when output_format=svg properties: model: type: string description: >- Text model that authors the SVG vector code; the example uses gpt-5.6-terra from the model catalog example: gpt-5.6-terra default: gpt-5.6-terra required: - model frame_count: type: integer description: >- GIF frame count. Official documented range: 2–64; default: 9. Only valid when output_format=gif minimum: 2 maximum: 64 default: 9 example: 2 frame_duration_ms: type: integer description: >- Duration of each GIF frame in milliseconds, 20–2000, rounded to 10ms; default 200. Only valid when output_format=gif minimum: 20 maximum: 2000 default: 200 example: 100 Image26Response: type: object properties: created: type: integer description: Unix timestamp background: type: string description: Effective background mode example: opaque data: type: array description: Generated results items: type: object properties: b64_json: type: string description: >- Raw base64 without a data: prefix. Save using output_format; SVG decodes to UTF-8 XML generation_id: type: string description: Generation ID, when provided output_format: type: string example: gif quality: type: string example: low size: type: string example: 512x512 usage: $ref: '#/components/schemas/ImageUsage' svg_usage: $ref: '#/components/schemas/SvgUsage' ImageUsage: type: object description: Token usage for the image model properties: input_tokens: type: integer example: 59 output_tokens: type: integer example: 555 total_tokens: type: integer example: 614 input_tokens_details: type: object properties: text_tokens: type: integer example: 59 image_tokens: type: integer example: 0 output_tokens_details: type: object properties: text_tokens: type: integer example: 0 image_tokens: type: integer example: 555 SvgUsage: type: object description: >- Authoring-model usage returned for SVG output. reasoning_tokens is already included in output_tokens and must not be added again properties: model: type: string example: gpt-5.6-sol input_tokens: type: integer example: 1572 output_tokens: type: integer example: 1437 reasoning_tokens: type: integer example: 994 total_tokens: type: integer example: 3009 securitySchemes: bearerAuth: type: http scheme: bearer description: API Key obtained from the APIYI Console ```` This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.