Call GPT Image 2.6 Flare and GPT Image 2.6 Sunburst from Python with one function per endpoint: text-to-image, image editing. Built on the official wavespeed SDK and the WaveSpeedAI hosted API — no GPU, pay per generation.
- GPT Image 2.6 API guide, live pricing and playground: wavespeed.ai/gpt-image-2-6-api
- No code: generate in the browser with the AI Image Generator on WaveSpeedAI
pip install git+https://github.com/WaveSpeedAI/gpt-image-2.6-api.git
export WAVESPEED_API_KEY="your-api-key" # https://wavespeed.ai/accesskeyimport gpt_image_api
urls = gpt_image_api.flare_text_to_image(
prompt="A lighthouse on a rocky coast at dawn, soft golden light, long exposure",
)
print(urls[0])Every function waits for the generation to finish and returns a list of output URLs. Optional arguments you leave out are not sent, so the API defaults apply. Inputs such as images, videos and audio are passed as URLs; use gpt_image_api.upload("local-file") to get a URL for a local file.
| Function | Model | Type |
|---|---|---|
flare_text_to_image() |
openai/gpt-image-2.6-flare/text-to-image | text-to-image |
flare_edit() |
openai/gpt-image-2.6-flare/edit | image-to-image |
sunburst_text_to_image() |
openai/gpt-image-2.6-sunburst/text-to-image | text-to-image |
sunburst_edit() |
openai/gpt-image-2.6-sunburst/edit | image-to-image |
Each model page has a playground, live pricing and copy-paste API snippets. Prices are per generation and depend on the settings you choose; check a request before running it with wavespeed price <model> from the CLI.
openai/gpt-image-2.6-flare/text-to-image — OpenAI's GPT Image 2.6 Flare Text-to-Image generates high-quality images from natural-language prompts, with five quality tiers up to 4K and a complexity control. Flare is the fast GPT Image 2.6 tier, returning images in seconds for everyday generation and quick iteration.
| Parameter | Type | Required | Default | Allowed | Description |
|---|---|---|---|---|---|
prompt |
str | yes | The positive prompt for the generation. | ||
aspect_ratio |
str | "1:1" |
1:1, 1:2, 2:1, 1:3, 3:1, 2:3, 3:2, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9, 9:21, 21:9 |
The aspect ratio of the generated image. Defaults to 1:1. | |
resolution |
str | "1k" |
1k, 2k, 4k |
The resolution of the output image. | |
quality |
str | "medium" |
low, medium, high, xhigh, max |
Rendering quality. Higher tiers add detail and cost more: low is the fastest draft tier, medium is the balanced default, high, xhigh and max add fidelity. | |
complexity |
str | "high" |
low, medium, high |
How much planning the model does before drawing. Higher complexity improves layout and scene understanding on detailed prompts and takes a little longer; it does not change the price. | |
output_format |
str | "png" |
png, jpeg, webp, gif, svg |
The format of the output image. gif returns an animation, svg a vector image. | |
frame_count |
int | 9 |
2–16 | GIF only: number of animation frames (2-16). | |
frame_duration_ms |
int | 200 |
20–2000 | GIF only: milliseconds per frame (20-2000). |
openai/gpt-image-2.6-flare/edit — OpenAI's GPT Image 2.6 Flare Edit edits one or more reference images from natural-language instructions, with five quality tiers up to 4K and a complexity control. Flare is the fast GPT Image 2.6 tier, returning images in seconds for everyday generation and quick iteration.
| Parameter | Type | Required | Default | Allowed | Description |
|---|---|---|---|---|---|
prompt |
str | yes | The positive prompt for the generation. | ||
images |
List[str] | yes | up to 16 items | List of URLs of input images for editing. | |
mask_image |
str | Optional mask for the first input image: white marks the area to edit, black the area to keep (a PNG where transparent marks the area to edit is also accepted). It is resized to the first image. | |||
markup_image |
str | Optional transparent PNG of annotations (circles, arrows, notes) drawn over the first input image to show where and how to edit it. Use either mask_image or markup_image. | |||
aspect_ratio |
str | 1:1, 1:2, 2:1, 1:3, 3:1, 2:3, 3:2, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9, 9:21, 21:9 |
The aspect ratio of the generated image. If not specified, it is determined automatically from the input image. | ||
resolution |
str | "1k" |
1k, 2k, 4k |
The resolution of the output image. | |
quality |
str | "medium" |
low, medium, high, xhigh, max |
Rendering quality. Higher tiers add detail and cost more: low is the fastest draft tier, medium is the balanced default, high, xhigh and max add fidelity. | |
complexity |
str | "high" |
low, medium, high |
How much planning the model does before drawing. Higher complexity improves layout and scene understanding on detailed prompts and takes a little longer; it does not change the price. | |
output_format |
str | "png" |
png, jpeg, webp, gif |
The format of the output image. gif returns an animation. | |
frame_count |
int | 9 |
2–16 | GIF only: number of animation frames (2-16). | |
frame_duration_ms |
int | 200 |
20–2000 | GIF only: milliseconds per frame (20-2000). |
openai/gpt-image-2.6-sunburst/text-to-image — OpenAI's GPT Image 2.6 Sunburst Text-to-Image generates high-quality images from natural-language prompts, with five quality tiers up to 4K and a complexity control. Sunburst is the precision-focused GPT Image 2.6 tier: it takes longer per image for higher fidelity and steadier details across repeated edits.
| Parameter | Type | Required | Default | Allowed | Description |
|---|---|---|---|---|---|
prompt |
str | yes | The positive prompt for the generation. | ||
aspect_ratio |
str | "1:1" |
1:1, 1:2, 2:1, 1:3, 3:1, 2:3, 3:2, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9, 9:21, 21:9 |
The aspect ratio of the generated image. Defaults to 1:1. | |
resolution |
str | "1k" |
1k, 2k, 4k |
The resolution of the output image. | |
quality |
str | "medium" |
low, medium, high, xhigh, max |
Rendering quality. Higher tiers add detail and cost more: low is the fastest draft tier, medium is the balanced default, high, xhigh and max add fidelity. | |
complexity |
str | "high" |
low, medium, high |
How much planning the model does before drawing. Higher complexity improves layout and scene understanding on detailed prompts and takes a little longer; it does not change the price. | |
output_format |
str | "png" |
png, jpeg, webp, gif, svg |
The format of the output image. gif returns an animation, svg a vector image. | |
frame_count |
int | 9 |
2–16 | GIF only: number of animation frames (2-16). | |
frame_duration_ms |
int | 200 |
20–2000 | GIF only: milliseconds per frame (20-2000). |
openai/gpt-image-2.6-sunburst/edit — OpenAI's GPT Image 2.6 Sunburst Edit edits one or more reference images from natural-language instructions, with five quality tiers up to 4K and a complexity control. Sunburst is the precision-focused GPT Image 2.6 tier: it takes longer per image for higher fidelity and steadier details across repeated edits.
| Parameter | Type | Required | Default | Allowed | Description |
|---|---|---|---|---|---|
prompt |
str | yes | The positive prompt for the generation. | ||
images |
List[str] | yes | up to 16 items | List of URLs of input images for editing. | |
mask_image |
str | Optional mask for the first input image: white marks the area to edit, black the area to keep (a PNG where transparent marks the area to edit is also accepted). It is resized to the first image. | |||
markup_image |
str | Optional transparent PNG of annotations (circles, arrows, notes) drawn over the first input image to show where and how to edit it. Use either mask_image or markup_image. | |||
aspect_ratio |
str | 1:1, 1:2, 2:1, 1:3, 3:1, 2:3, 3:2, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9, 9:21, 21:9 |
The aspect ratio of the generated image. If not specified, it is determined automatically from the input image. | ||
resolution |
str | "1k" |
1k, 2k, 4k |
The resolution of the output image. | |
quality |
str | "medium" |
low, medium, high, xhigh, max |
Rendering quality. Higher tiers add detail and cost more: low is the fastest draft tier, medium is the balanced default, high, xhigh and max add fidelity. | |
complexity |
str | "high" |
low, medium, high |
How much planning the model does before drawing. Higher complexity improves layout and scene understanding on detailed prompts and takes a little longer; it does not change the price. | |
output_format |
str | "png" |
png, jpeg, webp, gif |
The format of the output image. gif returns an animation. | |
frame_count |
int | 9 |
2–16 | GIF only: number of animation frames (2-16). | |
frame_duration_ms |
int | 200 |
20–2000 | GIF only: milliseconds per frame (20-2000). |
The wrapper is a thin layer over the REST API: submit, then poll for the result.
curl -s -X POST "https://api.wavespeed.ai/api/v3/openai/gpt-image-2.6-flare/text-to-image" \
-H "Authorization: Bearer $WAVESPEED_API_KEY" -H "Content-Type: application/json" \
-d '{"prompt": "A lighthouse on a rocky coast at dawn, soft golden light, long exposure"}'
# -> {"data": {"id": "<prediction_id>"}}
curl -s "https://api.wavespeed.ai/api/v3/predictions/<prediction_id>/result" \
-H "Authorization: Bearer $WAVESPEED_API_KEY"
# -> status: completed, outputs: ["<url>"]npm i -g @wavespeed/cli && wavespeed login
wavespeed run openai/gpt-image-2.6-flare/text-to-image -p "your prompt"- awesome-gpt-image-api — prompt library and variant guide
- More model wrappers: Seedance 2.5 · Wan 3.0 · Kling 4.0 · Veo 3.1 · MiniMax H3 · HappyHorse 1.1 · FLUX 3 · Seedream 5.5 · Nano Banana 2.1
- SDKs and tools: Python · JavaScript · CLI · MCP server · ComfyUI nodes
- Full model catalog
- GPT Image 2.6 is a model by OpenAI. This repository is maintained by WaveSpeedAI and wraps the WaveSpeedAI hosted API for it.
- Function signatures and the tables above are generated from the live model schemas (last generated 2026-11-22). The model pages are the source of truth if an endpoint changes.
- Issues and pull requests are welcome. License: MIT.