> ## Documentation Index > Fetch the complete documentation index at: https://docs.tess.im/llms.txt > Use this file to discover all available pages before exploring further. # GPT Image 2.6 (Tool) > OpenAI image model in Tess. It replaces GPT Image 2.5 in Chat and in the Agent Studio image step, with the same credit prices. GPT Image 2.6 is OpenAI's **image generation and editing** model in Tess. It replaces [GPT Image 2.5](https://docs.tess.im/en/gpt-image-2-5.md) in **Chat**, through the Images tool, and in the **image step in Agent Studio**. Agents you already saved with GPT Image 2.5 keep running on 2.5. Behind this experience, the implementation uses **Flare** for speed and **Sunburst** for quality and visual precision. | **Tool in Tess** GPT Image 2.6 | **Provider** OpenAI | **Input** Text + image | **Output** Image | | :- | :- | :- | :- | | **Type** Image model | **Access in Tess** Chat · Agent Studio image step | **Internal implementation** Flare · Sunburst | **Release** Nov 9, 2026 | > [!NOTE] > > GPT Image 2.6 is an image model, not a conversational LLM. Credit prices match GPT Image 2.5. See [Models and Costs](https://docs.tess.im/en/models-and-cost.md). ## What powers the tool The experience in Tess is unified, but the implementation brings together two model variants. Both generate images from text and edit existing images. | | GPT Image 2.6 Flare | GPT Image 2.6 Sunburst | | - | - | - | | Profile | Faster variant for everyday generation | Variant aimed at quality and visual precision | | When to ask for it | Drafts and quick iteration | Detailed, demanding visual work | > [!NOTE] > > In Tess, **GPT Image 2.6 appears as a single tool**, without a visual selector for Flare or Sunburst. To use a specific variant, ask for **Flare** or **Sunburst** in Chat. The tool runs the option you named. ## Complexity GPT Image 2.6 adds a `complexity` setting that controls how much detail and structure the model builds into the image. GPT Image 2.5 does not have this setting. | Value | What you get | | - | - | | `low` | Less structure. Faster. | | `medium` | A middle setting between speed and detail. | | `high` | More detail and structure. This is the model default when you omit the setting. | Complexity does not add a separate fee. Billing still follows [generation tokens](https://docs.tess.im/en/generation-token-billing.md), the same rates as GPT Image 2.5. In Chat, name the level in your request, for example: **“Generate this with low complexity.”** ## Formats, size, and quality The tool supports the same output controls as GPT Image 2.5. | Setting | Options | | - | - | | Output format | PNG, JPEG, and WebP | | Size | `auto`, or a width and height such as `1024x1024`, `1024x1536`, or `1536x1024`. Other sizes map to the nearest recommended size. | | Quality | `auto`, `low`, `medium`, or `high`. `auto` lets the model choose. Use `low` for drafts and `high` for finals. | | Background | `auto`, `opaque`, or `transparent`. Transparent backgrounds need PNG or WebP. | | Count | 1 to 10 images. The default is 1. | > [!TIP] > > In Tess Chat, include the format and size in your request—for example: **“Generate a PNG in 1024x1536.”** ## How to use it in Tess Chat **1. Enable GPT Image 2.6** In Chat, open the Tools menu, find the **Images** category, and select **GPT Image 2.6**. It appears as a single option. **2. Define the goal** Say whether you want a new image or an edit of a reference. Attach the reference in Chat when you are editing. **3. Describe the result** Include subject, style, lighting, visible text, format, quality, and complexity. State what must stay unchanged. **4. Refine it in the same conversation** Ask for one change at a time. The thread keeps the visual direction. ## How to use it in Agent Studio On the image step of an agent, select **GPT Image 2.6**. The step follows the style, format, and rules you set on the agent. Agents saved with GPT Image 2.5 keep that model. You do not need to resave them for image generation to keep working. ## Cost Billing uses [generation tokens](https://docs.tess.im/en/generation-token-billing.md), the same conversion as GPT Image 2.5. The lowest cost in the models table is **4 credits** (Low quality, 1024 × 1024). Medium, the commercial default for that square size, is **30 credits**. High is **119 credits**. Edits that include a reference image, other sizes, and higher detail use more tokens. ## Where GPT Image 2.6 creates the most value Use the tool for work such as: * social and ad variations you want to iterate quickly; * product shots that start from a reference; * layouts and images that include exact wording; * drafts at low complexity, then a high-complexity final. > [!NOTE] > > AI-generated images can still misspell text or change a product, a hand, or a logo. Review every asset before you publish it. See also: [GPT Image 2.5 (Tool)](https://docs.tess.im/en/gpt-image-2-5.md) · [Image Generator](https://docs.tess.im/en/image-gen.md) · [Image Generation in Chat](https://docs.tess.im/en/images.md) · [Models and Costs](https://docs.tess.im/en/models-and-cost.md) · [Generation token billing](https://docs.tess.im/en/generation-token-billing.md) · [Image prompting (OpenAI)](https://developers.openai.com/api/docs/guides/image-prompting). This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.