GPT-Image 2.6 Flare
Model ID
Put this value in the request body's `model` field — not the display name above.
by OpenAI · OpenAI GPT-Image 2.6, speed tier. Text-to-image and reference-image editing, and it can make animated GIFs; billed at OpenAI's official token prices.
Quick start
POST /v1/images/generationshttps://qd.zsopc.com/v1curl https://qd.zsopc.com/v1/images/generations \
-H "Authorization: Bearer sk-gpushare-xxxxxxxx" \
-H "Content-Type: application/json" \
-d '{
"model": "gpt-image-2.6-flare",
"prompt": "一只在竹林里喝茶的熊猫,水彩风格",
"size": "2048x2048",
"n": 1
}'
# 图生图:再加 "image": ["https://.../ref.jpg"](参考图按张另计费)
# 返回的图片 URL 是上游预签名链接,约 24 小时过期 —— 请尽快转存Pricing
Billed per token: input and output are priced separately and settled on the upstream's reported usage.
- Rates
- Image output 12.132Credits/K·
Input image 3.2352Credits/K - Settlement
- Hold on submit → settle on completion → refund the difference
- Input 2,022 Credits · Input image 3,235.2 Credits · Image output 12,132 Credits / 1M
- Failed requests (upstream 4xx / 5xx) are not billed.
- All your API keys share one balance; when it runs out the API returns HTTP 402 `quota_exceeded`.
Sign in and any personal discount on your account will show up here. Sign in
Capabilities & specs
- Category
- Image generation
- Endpoint family
- Image generation (Images)
- Released
- 2026-11-04
- License
- Closed source
Try it
Models like this bill for real per image / per second / per call and are mostly async tasks, so there is no one-click test here. Use the sample code above, or generate in the matching workbench (which has a parameter panel and a cost estimate).
Open the workbenchCommon errors
404 model_not_foundYou passed the display name instead of the model ID.✗ GPT-Image 2.6 Flare→✓ gpt-image-2.6-flare
→ Copy the Model ID at the top of this page
402 quota_exceededInsufficient account balance. All your API keys share one balance.
401 / 403The API key is invalid, or it has a model allowlist that doesn't include this ID.
→ Check the key's status and allowed models
400 invalid_request`size` is below this SKU's minimum, or `n` exceeds the limit of 10.
→ Check your request body against the sample code above