Inference Logoinference shell

GPT Image 2.6 Flare

OpenAI's GPT Image 2.6 for fast iteration. Text-to-image, edits with masks or markup, complexity control, transparent backgrounds, SVG and animated GIF output.

text to imageimage editing
run in browser →run via APIrun with your agent
maker
openai
category
image
input → output
text → image
runs via
api, javascript and python sdk, belt cli, mcp
updated
2026-11-05
price
$30.00/M output, $5.00/M text input, $8.00/M image input, $0.10/M SVG input, $0.50/M SVG output

api reference

about

openai's gpt image 2.6 for fast iteration. text-to-image, edits with masks or markup, complexity control, transparent backgrounds, svg and animated gif output.

get an api key

create one in settings → api keys. the examples read it from INFERENCE_API_KEY.

bash
1export INFERENCE_API_KEY="inf_your_key"

1. calling the api

install the client

nothing to install. any http client works; the examples use curl, and jq to read responses. every response wraps its result in a data field.

run and get result

send "wait": true to hold the connection until the task finishes. without it the call returns right away with the task still running.

bash
12# "wait": true holds the connection until the task finishes.3# the response is {"data": {"id", "status", "status_text", "output", ...}}4curl -X POST https://api.inference.sh/apps/run \5  -H "Authorization: Bearer $INFERENCE_API_KEY" \6  -H "Content-Type: application/json" \7  -d '{8    "app": "openai/gpt-image-2-6-flare",9    "input": {10      "prompt": "A cat wearing a tiny top hat, oil painting style"11    },12    "wait": true13  }'

stream live updates

get real-time progress updates as the task runs. ideal for showing progress bars, partial results, or long-running tasks. send "stream": true and the response is a server-sent event stream that ends when the task does.

bash
12# "stream": true answers with server-sent events until the task finishes3curl -N -X POST https://api.inference.sh/apps/run \4  -H "Authorization: Bearer $INFERENCE_API_KEY" \5  -H "Content-Type: application/json" \6  -d '{7    "app": "openai/gpt-image-2-6-flare",8    "input": {9      "prompt": "A cat wearing a tiny top hat, oil painting style"10    },11    "stream": true12  }'

run in the background

start the task and get its id back right away, then check on it later. for long tasks, or when you'd rather be called back, see webhooks.

bash
1# without "wait" the call returns the task right away (status 1, "received")2TASK_ID=$(curl -s -X POST https://api.inference.sh/apps/run \3  -H "Authorization: Bearer $INFERENCE_API_KEY" \4  -H "Content-Type: application/json" \5  -d '{6    "app": "openai/gpt-image-2-6-flare",7    "input": {8      "prompt": "A cat wearing a tiny top hat, oil painting style"9    }10  }' | jq -r '.data.id')1112# later: read its state. done when status is 10 (completed), 11 (failed) or 12 (cancelled)13curl -s https://api.inference.sh/tasks/$TASK_ID \14  -H "Authorization: Bearer $INFERENCE_API_KEY" | jq '.data | {status, status_text, output}'

2. authentication

the api uses api keys for authentication. see the authentication docs for detailed setup instructions.

3. files

file inputs are automatically handled by the sdk. you can pass local paths, urls, or base64 data.

automatic upload

pass urls directly or use data uris for inline content.

bash
1# pass URLs or data URIs as input values2curl -X POST https://api.inference.sh/apps/run \3  -H "Authorization: Bearer $INFERENCE_API_KEY" \4  -H "Content-Type: application/json" \5  -d '{6    "app": "openai/gpt-image-2-6-flare",7    "input": {8      "image": "https://example.com/image.png",9      "audio": "data:audio/mp3;base64,..."10    },11    "wait": true12  }'

manual upload

you can also upload files manually and use the returned url.

bash
1# 1. create the file: the response has an upload_url and the file's uri2FILE=$(curl -s -X POST https://api.inference.sh/files \3  -H "Authorization: Bearer $INFERENCE_API_KEY" \4  -H "Content-Type: application/json" \5  -d '{"files": [{"filename": "image.png", "content_type": "image/png"}]}')67# 2. PUT the bytes to upload_url8curl -X PUT "$(echo "$FILE" | jq -r '.data[0].upload_url')" \9  -H "Content-Type: image/png" \10  --data-binary @image.png1112# 3. pass the uri as an input value13echo "$FILE" | jq -r '.data[0].uri'

4. webhooks

get notified when a task completes by providing a webhook url. when the task reaches a terminal state (completed, failed, or cancelled), a POST request is sent to your url with the task result.

bash
1curl -X POST https://api.inference.sh/apps/run \2  -H "Authorization: Bearer $INFERENCE_API_KEY" \3  -H "Content-Type: application/json" \4  -d '{5    "app": "openai/gpt-image-2-6-flare",6    "input": {7        "prompt": "A cat wearing a tiny top hat, oil painting style"8    },9    "webhook": "https://your-server.com/webhook"10  }'

webhook payload

your endpoint receives a JSON POST with the task result:

json
1{2  "event": "task.completed",3  "timestamp": "2024-01-15T10:30:05Z",4  "data": {5    "id": "task_abc123",6    "short_id": "abc123",7    "status": 10,8    "status_text": "completed",9    "output": { ... },10    "created_at": "2024-01-15T10:30:00Z",11    "updated_at": "2024-01-15T10:30:05Z"12  }13}
eventstringtask.completed, task.failed or task.cancelled
timestampstringiso timestamp of the delivery
data.idstringtask id
data.short_idstringshort task id
data.statusnumberterminal status (10=completed, 11=failed, 12=cancelled, 13=rejected)
data.status_textstringthe status as a word: completed, failed or cancelled
data.outputobjecttask output (when completed)
data.errorstringerror message (when failed, omitted otherwise)
data.session_idstringsession id (when the task ran in a session, omitted otherwise)
data.created_atstringiso timestamp
data.updated_atstringiso timestamp

5. schema

input

promptstring*

text prompt describing the desired image. for gif output, describe the subject, motion and loop.

example: "A cat wearing a tiny top hat, oil painting style"maxLength:32000
imagesarray

optional image(s) to edit. a mask or markup applies to the first image; the others serve as references.

maskstring(file)

optional mask for the first image. its transparent areas mark where to edit. cannot be combined with markup.

markupstring(file)

optional transparent png with circles, sketches or other annotations showing where to edit. must match the first image's dimensions. cannot be combined with mask.

widthinteger

output width in pixels. must be a multiple of 16. for gif this is the frame width; leave width and height unset to let the model pick a size that fits the frame count.

default: 1024min:256max:3840
heightinteger

output height in pixels. must be a multiple of 16. for gif this is the frame height; leave width and height unset to let the model pick a size that fits the frame count.

default: 1024min:256max:3840
qualitystring

rendering quality. 'low' for drafts, 'high' for final assets, 'xhigh' and 'max' for maximum detail at higher cost. for svg, sets the reference image's quality.

default: "auto"
options:"auto""low""medium""high""xhigh""max"
complexitystring

how much the model plans before rendering, independent of quality and at no extra cost. lower suits focused edits; higher helps dense text and complex layouts but adds latency.

default: "high"
options:"low""medium""high"
ninteger

number of images to generate (1-10). svg output requires 1.

default: 1min:1max:10
output_formatstring

output file format. gif (animated) and svg (vector) are for generation only, not edits.

default: "png"
options:"png""jpeg""webp""gif""svg"
output_compressioninteger

compression level for jpeg/webp (0-100). ignored for other formats.

min:0max:100
frame_countinteger

number of animation frames. used only for gif output.

default: 9min:2max:16
frame_duration_msinteger

delay per animation frame in milliseconds, rounded to 10 ms. used only for gif output.

default: 200min:20max:2000
moderationstring

content moderation strictness. 'auto' applies standard filtering; 'low' is less restrictive.

default: "auto"
options:"auto""low"
backgroundstring

background transparency. 'transparent' requires png or webp output; prompt for an isolated subject. 'opaque' forces a solid background.

default: "auto"
options:"auto""transparent""opaque"

output

imagesarray*

the generated image files.

other image apps

GPT Image 2.6 Sunburst

openai/gpt-image-2-6-sunburst

$30.00/M out, $5.00/M text in, $8.00/M img in; SVG $0.10/$0.50/M in/out

Gemini Nano Banana 2.1

google/gemini-nano-banana-2-1

$1.50/M input, $0.0336–$0.1134/image (1K–4K), +$0.014/query Google Search

Grok Imagine Image 2.0

xai/grok-imagine-image-2-0

$0.04/img low 1k, $0.06/img low 2k, $0.06/img med 1k, $0.08/img med 2k; $0.01/source img (edits)

GPT Image 2.5 Sunburst

openai/gpt-image-2-5-sunburst

$0.006-$0.21 per 1024x1024 image: low $0.006, medium $0.013, high $0.053, xhigh $0.094, max $0.21. Larger sizes cost more; edits add ~$0.008 per reference image.

GPT Image 2.5 Flare

openai/gpt-image-2-5-flare

$0.006-$0.21/image at 1024x1024: low $0.0059, medium $0.0132, high $0.0527, xhigh $0.0937, max $0.2107. Larger sizes cost more; edits add ~$0.0083 per reference image.

more from openai

GPT Image 2.6 Sunburst

openai/gpt-image-2-6-sunburst

$30.00/M out, $5.00/M text in, $8.00/M img in; SVG $0.10/$0.50/M in/out

GPT-6 Sol

openai/gpt-6-sol

$2.00/M input, $0.20/M cached input, $10.00/M output

GPT-6 Luna

openai/gpt-6-luna

$0.10/M input, $0.01/M cached, $0.50/M output

GPT-6.1 Sol

openai/gpt-6-1-sol

$2.00/M input, $0.10/M cached, $10.00/M output

new models

  1. GPT Image 2.6 Sunburst

    openai/gpt-image-2-6-sunburst

    image$30.00/M out, $5.00/M text in, $8.00/M img in; SVG $0.10/$0.50/M in/out

  2. Tripo Auto Rig

    tripo/tripo-rig

    3d$0.01/credit (rig check free, auto rig 25 credits, retarget 10 credits/animation)

  3. Hunyuan 3D Auto Rigging

    tencent/hunyuan-3d-auto-rigging

    3d$0.02/credit, 10 credits/call ($0.20/call)

  4. TokenRig

    infsh/tokenrig

    3dGPU time, billed per millisecond

  5. Hunyuan 3D 3.1

    tencent/hunyuan-3d-3-1

    3d$0.02/credit; Geometry 15cr, Normal 25cr, +10cr views/PBR/face-count

ready to run GPT Image 2.6 Flare?

try in browserbrowse all apps

we use cookies

we use cookies to ensure you get the best experience on our website. for more information on how we use cookies, please see our cookie policy.

by clicking "accept", you agree to our use of cookies.
learn more.