Compare model

Image

OpenAI logoGPT Image 2.6 Sunburst

Quality-first images, precise edits and animated GIFs with independent complexity controls.

gpt-image-2.6-sunburst

Best for: Generating and editing images from text prompts

Share

Catalog status

Enabled

Research checked

2026-11-07

Benchmark results

No recorded results

Results are source-attributed, not TokenRex measurements. Different tests and thinking variants are not interchangeable.

Published benchmark coverage

Reviewed sources do not include results for this exact version. Provider specifications and API capabilities remain listed separately.

Model specifications

Positioning

Quality-first

Documented capability

Rendering quality

Auto, Low, Medium, High, XHigh, Max

Documented capability

Input and output modalities

Provider-reported formats; API compatibility is detailed below.

Input

Text
Image

Output

Image
Exact model ID
gpt-image-2.6-sunburst
Model type
Image
Positioning
Quality-first
Rendering quality
Auto, Low, Medium, High, XHigh, Max
Planning complexity
Low, Medium, High (provider default High)
Animation
2–16 GIF frames; 20–2,000 ms per frame
Transparency
PNG, WebP and GIF; not JPEG
Editing
Ordered references, mask or markup; not mask and markup together

Exact token limits are not published in the reviewed sources, so no estimated limits are shown.

Versions and image configurations

One enabled version is currently listed for this model.

GPT Image 2.6 SunburstSelected$3.50 text in / $21.00 image out / $5.60 image in per 1M tokens

Image quality, resolution, pricing and editing

Prices below use the live catalog and current offer. Billing uses ₹96 per US dollar and rounds each charge up to whole paise. OpenAI image models are billed by the tokens the request actually uses, so Low quality costs far less than Max. Gemini image models are billed per image, and each resolution has its own model ID.

ModelQualitySize / resolutionAspect ratioFormatsTransparentEditingPrice
gpt-image-2.6-sunburst
Auto / Low / Medium / High / XHigh / MaxAuto or custom WIDTHxHEIGHTRaster 1:3 to 3:1PNG / JPEG / WebP / animated GIFYesYes (references, mask or markup)
$3.50 text in / $21.00 image out / $5.60 image in per 1M tokens · $5.60 image input / 1M
Quality-first. Complexity Low / Medium / High. GIF: 2–16 frames, 20–2,000 ms each. SVG unavailable. Provider cache rates are $1.25 text / $2 image per 1M; TokenRex does not currently apply a separate cached-input discount for these models.

How to use each control

  • Quality (OpenAI): send quality as low, medium or high. GPT Image 2.5 and 2.6 Flare and Sunburst also accept xhigh and max. If you leave it out, high is used.
  • Size (OpenAI): send size such as 1024x1024, 1536x1024 or 1024x1536. Custom sizes must be multiples of 16, between 1:3 and 3:1, up to 3840 px per side. Bigger images use more tokens and cost more.
  • File format: output_format = png, jpeg or webp, with optional output_compression 0–100.
  • Transparent background: GPT Image 2.5 and 2.6 Flare and Sunburst accept background: "transparent" with PNG or WebP. Tested: Sunburst Max returned a real transparent PNG.
  • Editing: POST /v1/images/edits with one image or several image[] files, in order. OpenAI models also accept a PNG mask. Gemini makes one image per request (n=1).
  • Charges: you only pay for images actually returned. A failed request is refunded. The exact charge is in the x-tokenrex-cost-paise response header.

GPT Image 2.6: animation and precise edits

complexity accepts low, medium or high (default high), independently of quality. It has no separate fee; actual tokens determine the bill.

output_format: gif produces a complete animation. Set frame_count to 2–16 (default 9) and frame_duration_ms to 20–2,000 (default 200, rounded by the provider to 10 ms). Prefer size auto: frames must fit an unpublished pixel budget. In our live tests auto (512×512 frames) and 768×768 worked, while 1024×1024 frames were refused even at 2 frames. Transparent GIF is supported; GIF has binary transparency rather than PNG’s full alpha.

GIF does not accept streaming, partial_images, mask or output_compression. The Playground creates a saved, private job through POST /v1/images/jobs; GET /v1/images/jobs?id=JOB_ID&model=MODEL_ID checks it. Reopening never regenerates it. Direct API generation and edits return completed base64 JSON.

For edits, upload ordered image or image[] files and an optional transparent PNG markup overlay matching the original dimensions. Markup supplies visible instructions; a PNG mask identifies editable regions. Never combine both. Reuse the previous output for iterative edits and restate what must remain unchanged; perfect consistency is not guaranteed.

Official upstream cache rates are $1.25 text input and $2 image input per 1M tokens. TokenRex does not currently offer verified cache discounts for this model, so TokenRex uses normal input rates. Cached output is not offered.

OpenAI describes SVG output, but our current image service does not expose SVG. PNG, JPEG, WebP and GIF are the supported output choices. No exact 2.6 benchmark ranking was independently verified; functional tests are not benchmark scores.

OpenAI pricing · Gemini pricing · OpenAI image controls · Gemini image controls

curl https://tokenrex.ai/api/public/v1/images/generations -H "Authorization: Bearer $TOKENREX_API_KEY" -H "Content-Type: application/json" -d '{"model":"gpt-image-2.6-flare","prompt":"A blue bird waving in a seamless loop","quality":"medium","complexity":"low","output_format":"gif","background":"transparent","frame_count":9,"frame_duration_ms":200,"size":"auto"}'

Features and tool support

TokenRex’s exposed interface, not every feature advertised by the provider. “Available” describes the implemented interface, not a successful test of every input or tool.

Input through TokenRex

Available

Text prompt on POST /v1/images/generations; reference images on edit-capable models. Settings are checked and unsupported ones are rejected.

Output through TokenRex

Available

Generated image (base64) in the chosen size, quality and format supported by this model.

Function tools

Not exposed

Image endpoint only — it creates images and does not run tools.

Positioning

Limited

Quality-first

Rendering quality

Limited

Auto, Low, Medium, High, XHigh, Max

Planning complexity

Limited

Low, Medium, High (provider default High)

Animation

Limited

2–16 GIF frames; 20–2,000 ms per frame

Transparency

Limited

PNG, WebP and GIF; not JPEG

Editing

Limited

Ordered references, mask or markup; not mask and markup together

Sources and verification

Provider specifications describe the upstream model, not a guarantee of every feature through TokenRex. Prices come from the enabled catalog; benchmark results belong to the exact tested model.

Research notes (5)
  • SVG is described by OpenAI but unavailable through the current image service.
  • Official Standard rates per 1M tokens: $5 text input, $8 image input, $30 image output. Official cached rates: $1.25 text and $2 image; TokenRex does not currently offer verified cache discounts for this model, so normal input rates apply. No cached output rate.
  • No exact-version independently sourced benchmark score was verified. Earlier functional tests are not benchmark rankings or guarantees of identity preservation.
  • Raster sizes: multiples of 16, aspect ratio 1:3–3:1, at most 3840 per edge and 655,360–8,294,400 pixels. GIF has a separate total animation pixel budget; prefer auto.
  • GIF requests use completed JSON; the Playground uses owner-scoped saved jobs. Polling and reopening never regenerate.