GPT Image 2.6 Sunburst API
gpt-image-2.6-sunburstgpt-image-2.6-sunburst is the precision tier of OpenAI's GPT Image 2.6, built for premium visual work: it spends longer on each image for extra fidelity on intricate detail, and its edits stay scoped to the instruction, with subject and composition preserved across many rounds of revision. In our test calls at the default reasoning effort, a 1K image took 11 to 14 seconds and a 2K image 14 to 16 seconds. It shares every 2.6 ability with Flare: animated GIF output (2 to 64 frames), edits guided by a markup image drawn over the first reference, masks where white marks the area to change, up to 16 reference images and up to 10 outputs per call, and reasoning_effort from low to max. Sizes are aspect_ratio with 1K, 2K or 4K, an exact WIDTHxHEIGHT (multiples of 16, up to 3840 on the long edge, ratio up to 3:1), a preset or auto. Quality defaults to medium on apimodels.app; pass high when the detail is the point of the image. Pricing is per token, from the same price list as Flare: image output $33 per 1M tokens, image input $8.80 (cached $2.20), text input $5.50 (cached $1.375) and text output $11, each request rounded up to $0.0001 — so the cost follows what you ask for, not the tier. Measured requests on 5 November 2026 (16:9, one image): 1K low $0.0154, 1K medium $0.028, 2K low $0.031, 2K medium $0.057. An upper bound is held when the request is accepted and the rest is released afterwards. Limits: SVG output is listed in the model's documentation but currently fails upstream, so apimodels.app returns a 400 for it for now; it will be enabled once it works. A markup image and a mask cannot be combined. GIF frames are laid out on one sheet of at most 3840 px on the longest edge: pass aspect_ratio with 1K / 2K / 4K (or no size) and apimodels.app shrinks the frames automatically to fit; with an exact size, keep it small enough yourself — 960x960 works for up to 16 frames. We have not yet measured how strictly 2.6 respects masks — on the previous generation they acted as hints — so for exact local edits, name the region in the prompt as well. Success is not guaranteed on every call; refusals and upstream errors are never charged. Results are kept for 30 days.
Generate Image
Billed per token: Image output $33 / 1M tokens · image input $8.80 (cached $2.20) · text input $5.50 (cached $1.375) · text output $11. Higher quality, larger sizes, GIF and reference images use more tokens. An upper limit is held when you submit and the unused part is released when the image is ready.
How much the model plans before drawing. Higher settings add detail and take longer.
Result
Generated image will appear here
Enter a prompt and click Generate
Same per-token prices as Flare
Image output $33 per 1M tokens, image input $8.80 (cached $2.20), text $5.50 in (cached $1.375) and $11 out, rounded up to $0.0001 per request — you pay for the tokens your quality, size and format use, not for the tier. Measured: 1K low $0.0154, 2K medium $0.057 per request. Failures free.
Detail that survives a zoom
Built for premium visuals: more time per image for fabric weave, fine type and reflective surfaces. In our tests 1K took 11 to 14 seconds and 2K 14 to 16 seconds at the default reasoning effort.
Edits scoped to the instruction
Subject and composition hold across many rounds of revision. Guide an edit with a markup image — circles, arrows and notes on a transparent PNG — or a mask, not both. Mask strictness on 2.6 is not yet measured by us, so name the region in the prompt as well.
GIF and batches
Animated GIF (2–64 frames), up to 16 reference images in and up to 10 images out per API call.
About GPT Image 2.6 Sunburst
GPT Image 2.6 Sunburst is an Image Generation API provided by OpenAI. gpt-image-2.6-sunburst is the precision tier of OpenAI's GPT Image 2.6, built for premium visual work: it spends longer on each image for extra fidelity on intricate detail, and its edits stay scoped to the instruction, with subject and composition preserved across many rounds of revision. In our test calls at the default reasoning effort, a 1K image took 11 to 14 seconds and a 2K image 14 to 16 seconds. It shares every 2.6 ability with Flare: animated GIF output (2 to 64 frames), edits guided by a markup image drawn over the first reference, masks where white marks the area to change, up to 16 reference images and up to 10 outputs per call, and reasoning_effort from low to max. Sizes are aspect_ratio with 1K, 2K or 4K, an exact WIDTHxHEIGHT (multiples of 16, up to 3840 on the long edge, ratio up to 3:1), a preset or auto. Quality defaults to medium on apimodels.app; pass high when the detail is the point of the image. Pricing is per token, from the same price list as Flare: image output $33 per 1M tokens, image input $8.80 (cached $2.20), text input $5.50 (cached $1.375) and text output $11, each request rounded up to $0.0001 — so the cost follows what you ask for, not the tier. Measured requests on 5 November 2026 (16:9, one image): 1K low $0.0154, 1K medium $0.028, 2K low $0.031, 2K medium $0.057. An upper bound is held when the request is accepted and the rest is released afterwards. Limits: SVG output is listed in the model's documentation but currently fails upstream, so apimodels.app returns a 400 for it for now; it will be enabled once it works. A markup image and a mask cannot be combined. GIF frames are laid out on one sheet of at most 3840 px on the longest edge: pass aspect_ratio with 1K / 2K / 4K (or no size) and apimodels.app shrinks the frames automatically to fit; with an exact size, keep it small enough yourself — 960x960 works for up to 16 frames. We have not yet measured how strictly 2.6 respects masks — on the previous generation they acted as hints — so for exact local edits, name the region in the prompt as well. Success is not guaranteed on every call; refusals and upstream errors are never charged. Results are kept for 30 days. Through APIMODELS platform, you can access this model via a unified API with transparent pay-as-you-go pricing. Current pricing: Image output: $$33.00 / 1M tokens, Image input: $$8.80 / 1M tokens, Image input (cached): $$2.20 / 1M tokens, Text input: $$5.50 / 1M tokens, Text input (cached): $$1.375 / 1M tokens, Text output: $$11.00 / 1M tokens.
Key Features
- Same per-token prices as Flare -- Image output $33 per 1M tokens, image input $8.80 (cached $2.20), text $5.50 in (cached $1.375) and $11 out, rounded up to $0.0001 per request — you pay for the tokens your quality, size and format use, not for the tier. Measured: 1K low $0.0154, 2K medium $0.057 per request. Failures free.
- Detail that survives a zoom -- Built for premium visuals: more time per image for fabric weave, fine type and reflective surfaces. In our tests 1K took 11 to 14 seconds and 2K 14 to 16 seconds at the default reasoning effort.
- Edits scoped to the instruction -- Subject and composition hold across many rounds of revision. Guide an edit with a markup image — circles, arrows and notes on a transparent PNG — or a mask, not both. Mask strictness on 2.6 is not yet measured by us, so name the region in the prompt as well.
- GIF and batches -- Animated GIF (2–64 frames), up to 16 reference images in and up to 10 images out per API call.
Examples by scenario
Use Cases
E-commerce Product Images
Generate high-quality product visuals for online stores, ads, and marketing materials.
Social Media Content
Create eye-catching visual content for social platforms to boost engagement and brand visibility.
Game Asset Generation
Produce concept art for characters, scenes, and props to accelerate game development.
Marketing Materials
Design posters, banners, and promotional graphics at a fraction of traditional design costs.
Why APIMODELS
- Unified API -- One API key to access all models, no need to register on multiple platforms
- Transparent Pricing -- Pay-as-you-go with per-call pricing published on every model page, ideal for indie developers and startups
- Instant Access -- Start using immediately after signup, supports Stripe and Alipay payments
- Full Documentation -- Detailed API docs with code examples in cURL, Python, and Node.js
Frequently Asked Questions
How much does GPT Image 2.6 Sunburst cost?
GPT Image 2.6 Sunburst is available through APIMODELS at: Image output: $$33.00 / 1M tokens, Image input: $$8.80 / 1M tokens, Image input (cached): $$2.20 / 1M tokens, Text input: $$5.50 / 1M tokens, Text input (cached): $$1.375 / 1M tokens, Text output: $$11.00 / 1M tokens. Billing is pay-as-you-go — you only pay for what you generate.
How to use GPT Image 2.6 Sunburst API?
Sign up at APIMODELS, get your API key, and call our unified API endpoint. We provide detailed API documentation with code examples in cURL, Python, and Node.js.
What is the difference between APIMODELS and the official OpenAI API?
APIMODELS offers the same GPT Image 2.6 Sunburst model through our aggregation platform. We provide a unified API interface so you do not need separate accounts for each provider - one API key to access all models.
How much does gpt-image-2.6-sunburst cost?
Per token, from the same price list as Flare: image output $33 per 1M tokens, image input $8.80 (cached $2.20), text input $5.50 (cached $1.375) and text output $11, each request rounded up to $0.0001. High quality, 4K, GIF and reference images use more tokens. Measured requests on 5 November 2026 (16:9): 1K low $0.0154, 1K medium $0.028, 2K low $0.031, 2K medium $0.057. An upper bound is held when you submit and the difference is released; failed requests are not charged.
When is Sunburst worth the extra time over Flare?
When the image will be looked at closely — packaging, print, product detail, dense type — or when an edit has to touch only what you asked for over several rounds. Sunburst took 11 to 16 seconds per image in our default-reasoning tests, versus about 6 seconds for Flare at 1K with low reasoning. For drafts, social posts and volume work Flare is the better fit; the per-token prices are the same.
How do I edit only one part of an image?
Pass the image as a reference and add either a markup image — a transparent PNG the same size as the first reference, with circles, arrows or notes showing what to change — or a mask, where white marks the area to edit and black the area to keep. You cannot send both. We have not measured how strictly 2.6 respects masks yet, so also name the region in the prompt, for example "change only the label on the bottle, keep everything else unchanged".
What are the limits of gpt-image-2.6-sunburst?
Up to 16 reference images and 10 outputs per call; prompts up to 32,000 characters; sizes up to 3840 on the long edge with a ratio of at most 3:1. SVG output is listed in the model's documentation but currently fails upstream, so apimodels.app returns a 400 for it for now; it will be enabled once it works. GIF frames are laid out on one sheet of at most 3840 px on the longest edge: with aspect_ratio plus 1K / 2K / 4K (or no size) apimodels.app shrinks the frames to fit, and with an exact size you keep it small enough yourself — 960x960 works for up to 16 frames. Quality is low, medium, high or auto (no higher tiers). Not every call succeeds — moderation refusals and upstream errors happen and are never charged. Results are kept for 30 days.
How does GPT Image 2.6 Sunburst compare to other Image Generation models?
On APIMODELS, GPT Image 2.6 Sunburst runs alongside 60+ models on one API key and one balance, so choosing is about fit, not lock-in. It supports Highest-fidelity 2.6 tier, Tightly scoped multi-round edits, Animated GIF output, Up to 16 references, 10 outputs, Per-token pricing, and you can weigh it on price and capability against other Image Generation models, then switch by changing a single model-name string — no new account or integration. Browse every Image Generation option with live pricing at apimodels.app/models.
What can GPT Image 2.6 Sunburst do?
GPT Image 2.6 Sunburst supports: Highest-fidelity 2.6 tier, Tightly scoped multi-round edits, Animated GIF output, Up to 16 references, 10 outputs, Per-token pricing. See the APIMODELS docs for full parameters and call examples.
Can I access the GPT Image 2.6 Sunburst API from anywhere (incl. China)?
Yes. APIMODELS exposes GPT Image 2.6 Sunburst through a single unified API and one key — no separate provider accounts, and no need to handle each provider's regional network access yourself.
What payment methods are supported?
We support Stripe (Visa, Mastercard, and other international cards) and Alipay. Credits are available instantly after payment.