GPT Image 2.6 Flare
GPT Image 2.6 Flare is OpenAI's fast GPT Image 2.6 variant for everyday generation and editing. It reads markup drawn on an image, so circles, arrows, and notes point each edit at the right place, and it plans dense text and complex layouts before rendering. Five quality levels run from low to max, output runs from 1024px to 4K with transparent backgrounds, and it can animate a subject into a looping GIF of up to 16 frames or draw it as an SVG.
See more
GPT Image 2.6 Flare is OpenAI's fast GPT Image 2.6 variant for everyday generation and editing. It reads markup drawn on an image, so circles, arrows, and notes point each edit at the right place, and it plans dense text and complex layouts before rendering. Five quality levels run from low to max, output runs from 1024px to 4K with transparent backgrounds, and it can animate a subject into a looping GIF of up to 16 frames or draw it as an SVG.
Connect Claude, Cursor, VS Code, or Codex to Layer’s MCP server and GPT Image 2.6 Flare becomes a tool your agent can reach for — it picks the parameters, runs the generation, and shows you the result in the conversation.
https://mcp.app.layer.ai/mcpAsk your agent
“Use GPT Image 2.6 Flare to generate 4 variations of a crystal sword icon on a transparent background.”
execute_forge({
"base_model_id": "gpt-image-2.6-flare",
"prompt": "A crystal sword icon on a transparent background, game UI art",
"batch_size": 4,
"width": 1024,
"height": 1024
})Authenticate with a personal access token, post the model’s own form, and poll the inference until it completes. Every field below is accepted by this endpoint.
# Start the generation — returns an inference id straight away.
curl -X POST https://api.app.layer.ai/api/v2/workspaces/$WORKSPACE_ID/base-models/openai-gpt-image-2-6-flare/inferences \
-H "Authorization: Bearer $LAYER_TOKEN" \
-H "Content-Type: application/json" \
-d '{
"prompt": "A crystal sword icon on a transparent background, game UI art"
}'
# Poll until status is "complete" — the response then carries the asset URLs.
curl https://api.app.layer.ai/api/v2/workspaces/$WORKSPACE_ID/inferences/$INFERENCE_ID \
-H "Authorization: Bearer $LAYER_TOKEN"- prompt stringrequired
- Describe what to generate, or the change to make.
- color_palette any
- Colors the output should use. This model doesn't take a palette natively, so the colors are added to the prompt.
- projection string
- Equirectangular is a 2:1 360 degree skybox whose sides meet and whose poles are settled.
- aspect_ratio enumdefault SQUARE_1K21 options
- The shape and size of the output. Auto follows the shape of the input.
- quality enumdefault HIGH5 options
- Higher levels render more detail, and can take longer and cost more.
- seed integer
- The starting point for the model's randomness. The same seed and settings give the same result.
- transparency booleandefault false
- Output the subject alone, with no backdrop behind it.
- animated booleandefault false
- Make a looping GIF instead of a still. Every frame is billed.
- animation_frame_count integerdefault 92–16
- How many frames the GIF has. More frames make each one smaller.
- animation_frame_duration_ms integerdefault 20020–2000
- How long each frame shows, in milliseconds.
- svg booleandefault false
- Draw the image as an SVG instead of a raster.
- nine_slice booleandefault false
- Deliver the image as a 9-slice UI element, with its insets recorded on the file.
- guidance_file_init_image file[]
- The image to modify
- guidance_file_reference_image file[]
- Guides the edit
- scene_lighting any
- Where the light comes from, how bright it is and its color.
- tile_grid any
- The grid's shape (isometric or hex), the camera, and the tile's footprint and size, shared by every tile of a set.
- parallax any
- How many layers to split the scene into, where along its depth each one is cut, and whether every layer loops left to right.
- output_fit any
- Trim the transparent margin, and place the image on a canvas of a fixed size.
- prompt_language string
- The language the prompt is written in, so it reaches the model as you meant it.
Why use GPT Image 2.6 Flare for image?
High-quality image generation
GPT Image 2.6 Flare delivers production-ready outputs with clean structure, sharp detail, and strong prompt adherence. Ideal for character art, environments, and marketing assets.
Strong prompt control
The model interprets creative instructions with high accuracy, even when switching between different styles, lighting setups, or character directions.
Clean compositions for UA
Maintains stable framing, clear silhouettes, and high focal clarity. Assets read well at mobile sizes, making it strong for UA experiments and ad creatives.
Rapid character and cosmetic ideation with strong structure
Quickly explore character poses, cosmetic ideas, and early art directions. Clean silhouettes and expressive results help teams evaluate concepts before moving to heavier models.
Fast UA creative exploration and thumbnail testing
Generate clear, high-readability frames that work well for quick A/B testing across networks. Test multiple creative angles and iterate quickly based on results.
Lightweight environment and item exploration for LiveOps
Draft environments, themed content, shop items, and event visuals in a rapid loop. Ideal for early-stage direction setting before committing to final polish.
FAQ
How much does GPT Image 2.6 Flare cost? Is it free?+
How does Layer's pricing work?+
There are no seat fees, feature gates, or plans on Layer. Instead, our platform uses a consumption based system with Creative Units (CUs) with a flexible monthly subscription. Every generation on Layer (image, video, 3D, or audio) consumes a Creative Unit, and you only pay for what you create.
Other image models on Layer
GPT Image 2.5 Sunburst
OpenAI
OpenAI's premium GPT Image 2.5 variant: extra precision across edits and 1024px to 4K output, trading longer generation times for tighter control.
GPT Image 2.5 Flare
OpenAI
OpenAI's default GPT Image 2.5 variant: fast, high-quality generation with natural lighting, richer textures, and precise edits up to 4K.
GPT Image 2
OpenAI
OpenAI image model with strong text rendering, UI generation, and photorealism. Native output up to 4K with three quality tiers.
Ideogram Vectorize 1.0
Ideogram
Convert a raster image to a scalable SVG with Ideogram.
GPT Image 2.6 Sunburst
OpenAI
OpenAI's premium GPT Image 2.6 variant: markup-guided edits with extra precision, five quality levels from low to max, and 1024px to 4K output.
Ideogram Vector 1.0
Ideogram
Ideogram's text-to-vector model. Generates scalable SVG artwork from a prompt, with optional reference images.