FLUX.2 Klein 4B BF16
256–1024px resolution (16px steps). Default: 1024×1024, 4 steps. Guidance: 1.0 (fixed). Unified model for generation and multi-reference editing. Sub-second inference.
Test AI image generation for free, then deploy via API.
Estimated cost: calculating… $0.03630/image
2 free images left
{
"model": "gpt-image-2.5",
"prompt": "A nineteenth-century botanical plate of a single hart's-tongue fern, hand-coloured copperplate engraving on aged cream paper. The full plant fills the centre: glossy strap-shaped fronds with wavy margins, a curled fiddlehead unrolling at the base, and the underside of one frond turned toward the viewer to show the rows of rust-brown sori in fine stipple. Two small inset details on the right show a single sorus magnified and a cross-section of the rhizome, each numbered \"1\" and \"2\". The title \"ASPLENIUM SCOLOPENDRIUM\" runs along the bottom in engraved serif capitals, with \"Hart's-tongue Fern - Pl. XLII\" in italic beneath it and a small scale bar marked \"5 cm\". Faint foxing at the corners, muted greens and sepia.",
"width": 1024,
"height": 768,
"seed": 2932183003,
"quality": "high"
}
curl -X POST \
'https://api.deapi.ai/api/v2/images/generations' \
-H 'Accept: application/json' \
-H 'Authorization: Bearer {{ YOUR_API_TOKEN }}' \
-H 'Content-Type: application/json' \
-d '{
"model": "gpt-image-2.5",
"prompt": "A nineteenth-century botanical plate of a single hart'"'"'s-tongue fern, hand-coloured copperplate engraving on aged cream paper. The full plant fills the centre: glossy strap-shaped fronds with wavy margins, a curled fiddlehead unrolling at the base, and the underside of one frond turned toward the viewer to show the rows of rust-brown sori in fine stipple. Two small inset details on the right show a single sorus magnified and a cross-section of the rhizome, each numbered \"1\" and \"2\". The title \"ASPLENIUM SCOLOPENDRIUM\" runs along the bottom in engraved serif capitals, with \"Hart'"'"'s-tongue Fern - Pl. XLII\" in italic beneath it and a small scale bar marked \"5 cm\". Faint foxing at the corners, muted greens and sepia.",
"width": 1024,
"height": 768,
"seed": 2932183003,
"quality": "high"
}'
Built for developers who need power without complexity.
256–1024px resolution (16px steps). Default: 1024×1024, 4 steps. Guidance: 1.0 (fixed). Unified model for generation and multi-reference editing. Sub-second inference.
Text-to-image model built on Google's Gemini 3.1 Flash Image. Renders legible typography, follows long multi-part prompts, and delivers anything from photoreal portraits to labelled diagrams — up to 4096 x 4096 in a single pass.
· Experimental · Partner model · Premium · Generate from a description, with a reasoning pass ahead of generation. The gain is clearest on prompts with several interacting constraints — a layout with specified positions, a scene with a set number of objects, or a design that has to carry a specific line of text. Output runs from 512px up to 2048px.
Experimental · Partner model · Premium Generate from a plain-language description. GPT Image 1.5 follows long, compound instructions closely and renders legible text inside the image — useful for mockups, ad creative and anything carrying a label, sign or headline in frame.
INT8 quantized. Resolution 128–2048 px (16 px steps). 4–16 inference steps. Default: 768x768, 8 steps. Tuned with Z-Image Base for anime-style images. Recognizes several iconic characters from well-known anime.
INT8 quantized. 128–2048px resolution (16px steps). 1–50 inference steps. Default: 768×768, 8 steps. Fastest option for production.
256–2048px resolution (128px steps). 1–10 inference steps. Default: 768×768, 4 steps. No guidance needed. Optimized for speed.
Join developers & vibe coders building AI apps with deAPI. No credit card, zero setup headaches — just pure, instant AI magic.
Need enterprise pricing or SLA? Talk to Sales
You've reached your free daily limit
Your counter resets at 00:00 UTC.
Want to keep going? Register now and get $5 in free credits to start.