GPT-Image-2.6 Sunburst: Pricing, Complexity Control, SVG and GIF Output
Key facts · verified Nov 13, 2026
GPT-Image-2.6 Sunburst is an OpenAI image generation model released on 4 Nov 2026. Its API price is $5 per million input tokens and $30 per million output tokens (text input / image output; image input $8 per 1M). It ranks #2 on LMArena's text-to-image leaderboard (Elo 1406, read 14 Nov 2026). Source: developers.openai.com.
GPT-Image-2.6 Sunburst (gpt-image-2.6-sunburst) is an OpenAI image generation and editing model for detailed compositions and image editing workflows, released on 4 November 2026 as part of Images 2.6 in ChatGPT, Codex and the API. OpenAI's guide covers a complexity setting, markup-guided edits, SVG output and animated GIF output for the model. API pricing is $5 per 1M text input tokens, $8 per 1M image input tokens and $30 per 1M image output tokens.
Token cost calculator
| Model | Input | Output | Cost for this many tokens |
|---|---|---|---|
| GPT-Image-2.6 Sunburst | $0.50 | $0.60 | $1.10 |
List prices per 1M tokens from each model's record (GPT-Image-2.6 Sunburst: $5 in / $30 out). Cached-input and batch discounts are not included. Click a figure to type it. Compare up to 8 models in the token cost calculator.
What GPT-Image-2.6 Sunburst is
GPT-Image-2.6 Sunburst is an image generation and editing model from OpenAI, released on 4 November 2026 with the model id gpt-image-2.6-sunburst. OpenAI describes it as built for detailed visual work and recommends it for detailed compositions and image editing workflows. It takes text and images as input and returns images; it does not accept or produce audio or video. It is one of two GPT Image 2.6 models: its sibling GPT-Image-2.6 Flare uses the same prices and features but is described for fast iteration. On LMArena's image leaderboard GPT-Image-2.6 Sunburst has 1406 Elo (rank 2, medium effort).
Complexity, markup edits, SVG and GIF
OpenAI documents four features for the 2.6 models, shared by Sunburst and Flare. A complexity field sets how much the model plans before rendering: low, medium or high, with high used when the field is left out. OpenAI notes that lower complexity can suit focused edits such as changing a background or a sign, that higher complexity can help with dense text, complex layouts and relationships between objects, and that higher complexity can add latency and unwanted changes; it carries no extra fee. Markup-guided edits take an annotation layer marking where a change should happen, sent to the image edit endpoint, at the same token rates as other edits. SVG output is requested with output_format set to svg on the generations endpoint, one image at a time, and returns static vector content with no scripts or embedded raster images; the API renders a reference image first and bills both that image and the authoring tokens. Animated GIF output works on both the generations and edits endpoints, with frame size, frame count and number of animations limited by the model's pixel budget.
Pricing
OpenAI bills GPT-Image-2.6 Sunburst by tokens rather than per image. Text input costs $5 per million tokens, with cached text input at $1.25. Image input costs $8 per million tokens, with cached image input at $2. Image output costs $30 per million tokens. The number of tokens an image uses depends on its size and quality setting, so the price of a single picture varies with those choices; OpenAI's image generation guide lists the token counts.
Rate limits and safety identifiers
OpenAI does not publish fixed rate limits for GPT-Image-2.6 Sunburst on its model page. Limits follow the account usage tier, which rises automatically as an organisation sends more requests and spends more on the API, and each account can see its own limits in its settings. For apps that serve individual end users, OpenAI's image generation guide recommends sending a stable, privacy-preserving safety_identifier with each generation or edit request: a hash of a username or email address rather than the address itself, up to 128 characters. The older user parameter on the Images API is deprecated but still accepted, and a non-empty safety_identifier takes precedence over it.
Sunburst or Flare, 2.6 or 2.5
OpenAI positions the two 2.6 models by speed and detail rather than by price, which is identical. The 2.5 generation, released on 8 September 2026, also has a Sunburst and a Flare at the same token prices, with low, medium, high, xhigh, max and auto quality settings; the complexity field, markup-guided edits, SVG output and GIF output are documented for the 2.6 models. GPT-Image-2.5 Sunburst has 1429 Elo (rank 1) on the same leaderboard. These are LMArena's figures; the site does not recommend one.
Key Takeaways
- Released 4 November 2026; model id gpt-image-2.6-sunburst.
- Text and image in, image out; described for detailed visual work.
- $5 text input, $8 image input, $30 image output per million tokens.
- Complexity control, markup-guided edits, SVG and animated GIF output.
- LMArena image leaderboard: 1406 Elo (rank 2, medium effort).
Official Resources
Full Specifications
$5 / $30 per million tokens | |
|---|---|
| Identity | |
| Developer | OpenAI |
| Released | Nov 2026 |
| Status | GA - released 4 November 2026 (Images 2.6) |
| Licence | Proprietary |
| Self-hostable | No |
| Cost | |
| Free tier | Not offered via the API - the Free tier is listed as "Not supported" |
| Capability | |
| Image-to-image | Yes - text and image inputs, generation and editing |
| Access | |
| API | Yes - Image API (v1/images/generations, v1/images/edits) and the Responses API image generation tool |
| Chat app | Yes - Images 2.6 in ChatGPT and Codex on all subscription tiers |
| Fine-tuning | Not supported |
| Measured quality | |
| LMArena Elo | 1406 (checked Nov 2026) |
| LMArena rank | Rank 2 |