GPT Image 2.5 Flare Text-to-Image by OPENAI
openai/gpt-image-2.5-flare/text-to-imageGPT Image 2.5 Flare generates images from natural-language prompts with arbitrary resolutions up to 3840x2160, five quality tiers including xhigh and max, and first-class transparent backgrounds. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
Set up the model and run your first generation.
Ctrl ⏎Examples
Runs published with this model. Load one into the playground and change whatever you like.
A sleek futuristic aircraft hovering silently above an endless desert, enormous dunes flowing like waves beneath it, several tiny figures walking across the sand below, distant storm clouds approaching across the horizon, sunlight breaking through the clouds, long shadows stretching across the dunes, minimal futuristic design, mysterious and elegant, cinematic science fiction, immense scale, atmospheric perspective, subtle film grain, realistic materials, dramatic composition, photorealistic, 8K
Providers
Where this model can run, priced for your account. Auto routing picks the top row and moves down it if a provider fails.
| Provider | Price | Speed | Completed |
|---|---|---|---|
| Atlas CloudLowest price | $0.0030 /gen | — | — |
| fal.ai | 1 unit | — | — |
| OpenRouter | — | — | — |
Speed and reliability appear once this platform has enough recent runs on a provider.
Questions
- $0.003 per generation on ElliSekiz — the provider's own price, billed 1:1 from a prepaid USD balance with no markup and no subscription. Failed generations are free.
- Atlas Cloud, fal.ai, OpenRouter. Requests route to the cheapest available provider automatically, or you can pin one per request or per model.
- POST to https://ellisekiz.ai/api/v1/generations with "model": "openai/gpt-image-2.5-flare/text-to-image" and your prompt, authenticated with an ElliSekiz API token. The API tab on this page has the full request for this model, including its own parameters.
- quality, size, background, output_format, moderation, n — each one is in the playground form on this page and in the API example.