Examples for using nano-banana-2 through RunAPI from agent tools or API calls. Copy a prompt, then use it in Claude Code, Codex, Cursor, Windsurf, or your backend.
1. claude mcp add runapi -s user -- npx -y @runapi.ai/mcp
2. Restart Claude Code
3. Paste this prompt: Generate an image: "Ultra-realistic 8K full body portrait of [PERSON’S FULL NAME], wearing a clean and pressed white social shirt with folded collar and a small lapel microphone, dark navy-blue dress pants and polished brown social shoes. Casually and unpretentiously leaning against a smooth light gray studio wall; hands are in pockets and one leg is crossed over the other, with relaxed and confident body language. Add to the wall next to them a prominent vector portrait in black and white of their face and bust - with sharp lines and angles, overlapping polygonal shapes and a minimalist modern graphic style, right below the information: “[PERSON’S FULL NAME]”, and below the name: “[PROFESSION]”"
1. codex plugin install runapi-mcp@agents
2. Restart Codex
3. Paste this prompt: Generate an image: "Ultra-realistic 8K full body portrait of [PERSON’S FULL NAME], wearing a clean and pressed white social shirt with folded collar and a small lapel microphone, dark navy-blue dress pants and polished brown social shoes. Casually and unpretentiously leaning against a smooth light gray studio wall; hands are in pockets and one leg is crossed over the other, with relaxed and confident body language. Add to the wall next to them a prominent vector portrait in black and white of their face and bust - with sharp lines and angles, overlapping polygonal shapes and a minimalist modern graphic style, right below the information: “[PERSON’S FULL NAME]”, and below the name: “[PROFESSION]”"
1. npx @runapi.ai/mcp init cursor
2. Restart Cursor
3. Paste this prompt: Generate an image: "Ultra-realistic 8K full body portrait of [PERSON’S FULL NAME], wearing a clean and pressed white social shirt with folded collar and a small lapel microphone, dark navy-blue dress pants and polished brown social shoes. Casually and unpretentiously leaning against a smooth light gray studio wall; hands are in pockets and one leg is crossed over the other, with relaxed and confident body language. Add to the wall next to them a prominent vector portrait in black and white of their face and bust - with sharp lines and angles, overlapping polygonal shapes and a minimalist modern graphic style, right below the information: “[PERSON’S FULL NAME]”, and below the name: “[PROFESSION]”"
1. npx @runapi.ai/mcp init windsurf
2. Restart Windsurf
3. Paste this prompt: Generate an image: "Ultra-realistic 8K full body portrait of [PERSON’S FULL NAME], wearing a clean and pressed white social shirt with folded collar and a small lapel microphone, dark navy-blue dress pants and polished brown social shoes. Casually and unpretentiously leaning against a smooth light gray studio wall; hands are in pockets and one leg is crossed over the other, with relaxed and confident body language. Add to the wall next to them a prominent vector portrait in black and white of their face and bust - with sharp lines and angles, overlapping polygonal shapes and a minimalist modern graphic style, right below the information: “[PERSON’S FULL NAME]”, and below the name: “[PROFESSION]”"
curl -X POST https://runapi.ai/api/v1/nano_banana/text_to_image \
-H "Authorization: Bearer $RUNAPI_KEY" \
-H "Content-Type: application/json" \
--data-binary @- <<'JSON'
{
"model": "nano-banana-2",
"prompt": "Ultra-realistic 8K full body portrait of [PERSON’S FULL NAME], wearing a clean and pressed white social shirt with folded collar and a small lapel microphone, dark navy-blue dress pants and polished brown social shoes. Casually and unpretentiously leaning against a smooth light gray studio wall; hands are in pockets and one leg is crossed over the other, with relaxed and confident body language. Add to the wall next to them a prominent vector portrait in black and white of their face and bust - with sharp lines and angles, overlapping polygonal shapes and a minimalist modern graphic style, right below the information: “[PERSON’S FULL NAME]”, and below the name: “[PROFESSION]”"
}
JSON
import { NanoBananaClient } from "@runapi.ai/nano-banana";
const client = new NanoBananaClient({
apiKey: process.env.RUNAPI_API_KEY,
});
const result = await client.textToImage.run({
"model": "nano-banana-2",
"prompt": "Ultra-realistic 8K full body portrait of [PERSON’S FULL NAME], wearing a clean and pressed white social shirt with folded collar and a small lapel microphone, dark navy-blue dress pants and polished brown social shoes. Casually and unpretentiously leaning against a smooth light gray studio wall; hands are in pockets and one leg is crossed over the other, with relaxed and confident body language. Add to the wall next to them a prominent vector portrait in black and white of their face and bust - with sharp lines and angles, overlapping polygonal shapes and a minimalist modern graphic style, right below the information: “[PERSON’S FULL NAME]”, and below the name: “[PROFESSION]”"
});
console.log(result.id);
require "runapi/nano_banana"
client = RunApi::NanoBanana::Client.new
result = client.text_to_image.run(
model: "nano-banana-2",
prompt: "Ultra-realistic 8K full body portrait of [PERSON’S FULL NAME], wearing a clean and pressed white social shirt with folded collar and a small lapel microphone, dark navy-blue dress pants and polished brown social shoes. Casually and unpretentiously leaning against a smooth light gray studio wall; hands are in pockets and one leg is crossed over the other, with relaxed and confident body language. Add to the wall next to them a prominent vector portrait in black and white of their face and bust - with sharp lines and angles, overlapping polygonal shapes and a minimalist modern graphic style, right below the information: “[PERSON’S FULL NAME]”, and below the name: “[PROFESSION]”"
)
puts result.id
package main
import (
"context"
"fmt"
"log"
"net/http"
"os"
"strings"
)
func main() {
body := strings.NewReader("{\"model\":\"nano-banana-2\",\"prompt\":\"Ultra-realistic 8K full body portrait of [PERSON’S FULL NAME], wearing a clean and pressed white social shirt with folded collar and a small lapel microphone, dark navy-blue dress pants and polished brown social shoes. Casually and unpretentiously leaning against a smooth light gray studio wall; hands are in pockets and one leg is crossed over the other, with relaxed and confident body language. Add to the wall next to them a prominent vector portrait in black and white of their face and bust - with sharp lines and angles, overlapping polygonal shapes and a minimalist modern graphic style, right below the information: “[PERSON’S FULL NAME]”, and below the name: “[PROFESSION]”\"}")
req, err := http.NewRequestWithContext(context.Background(), http.MethodPost, "https://runapi.ai/api/v1/nano_banana/text_to_image", body)
if err != nil {
log.Fatal(err)
}
req.Header.Set("Authorization", "Bearer "+os.Getenv("RUNAPI_API_KEY"))
req.Header.Set("Content-Type", "application/json")
resp, err := http.DefaultClient.Do(req)
if err != nil {
log.Fatal(err)
}
defer resp.Body.Close()
fmt.Println(resp.Status)
}
nano-banana-2/api/v1/nano_banana/text_to_imageGet API Key
A soft pastel watercolor digital illustration of a young woman with long, flowing blonde hair, gently smiling and looking slightly upward to the side. She has delicate, realistic facial features, smooth glowing skin, light pink lips, and expressive eyes. She is wearing a light-colored, high-neck long-sleeve sweater with subtle fabric texture. One hand is raised near her face in a relaxed, thoughtful pose, the other resting casually on a table or surface. The art style is a mix of hand-drawn pencil sketch and watercolor painting, with fine linework and soft pastel splashes in pink, yellow, lavender, and light blue behind her. The background is minimal and abstract, with loose watercolor brush strokes and a clean off-white canvas. Lighting is soft and dreamy, giving a warm, optimistic, serene mood. The illustration has a modern digital watercolor aesthetic, elegant, airy, and feminine, with smooth gradients and painterly textures. High detail, artistic portrait, pastel color palette, aesthetic illustration, soft focus, gentle expression.
curl -X POST https://runapi.ai/api/v1/nano_banana/text_to_image \
-H "Authorization: Bearer $RUNAPI_KEY" \
-H "Content-Type: application/json" \
--data-binary @- <<'JSON'
{
"model": "nano-banana-2",
"prompt": "A soft pastel watercolor digital illustration of a young woman with long, flowing blonde hair, gently smiling and looking slightly upward to the side. She has delicate, realistic facial features, smooth glowing skin, light pink lips, and expressive eyes. She is wearing a light-colored, high-neck long-sleeve sweater with subtle fabric texture. One hand is raised near her face in a relaxed, thoughtful pose, the other resting casually on a table or surface. The art style is a mix of hand-drawn pencil sketch and watercolor painting, with fine linework and soft pastel splashes in pink, yellow, lavender, and light blue behind her. The background is minimal and abstract, with loose watercolor brush strokes and a clean off-white canvas. Lighting is soft and dreamy, giving a warm, optimistic, serene mood. The illustration has a modern digital watercolor aesthetic, elegant, airy, and feminine, with smooth gradients and painterly textures. High detail, artistic portrait, pastel color palette, aesthetic illustration, soft focus, gentle expression."
}
JSON
A [PRODUCT] rendered as if built entirely from pulled and blown sugar, the translucent amber material of patisserie showpieces forming functional object. Visible sugar work techniques: pulled ribbons, blown bubbles, cast pieces joined with caramel. Internal air bubbles, slight amber color variation, the architectural fragility of competition sugar work. Positioned on a marble pastry surface or against cream backdrop. French patisserie tradition meets industrial design. Warm lighting that passes through the sugar, creating honey-glow internal illumination. Sharp focus, warm amber palette, edible luxury aesthetic, ultra-high resolution, the functional made confection. Check ALTs for ideas 👇 @AdobeFirefly
curl -X POST https://runapi.ai/api/v1/nano_banana/text_to_image \
-H "Authorization: Bearer $RUNAPI_KEY" \
-H "Content-Type: application/json" \
--data-binary @- <<'JSON'
{
"model": "nano-banana-2",
"prompt": "A [PRODUCT] rendered as if built entirely from pulled and blown sugar, the translucent amber material of patisserie showpieces forming functional object. Visible sugar work techniques: pulled ribbons, blown bubbles, cast pieces joined with caramel. Internal air bubbles, slight amber color variation, the architectural fragility of competition sugar work. Positioned on a marble pastry surface or against cream backdrop. French patisserie tradition meets industrial design. Warm lighting that passes through the sugar, creating honey-glow internal illumination. Sharp focus, warm amber palette, edible luxury aesthetic, ultra-high resolution, the functional made confection. Check ALTs for ideas 👇 @AdobeFirefly"
}
JSON
Ultra-realistic creative advertising scene showing a giant smartphone displaying a McDonald’s food-ordering app interface inside a modern restaurant kitchen. The phone screen features neatly arranged food compartments like a vending machine: a Big Mac burger, McDonald’s fries, a Coca-Cola cup, and chicken McNuggets with star ratings and reviews visible. Miniature restaurant workers in aprons interact with the phone—one climbing a rope to place fries, one on a ladder adjusting the burger, one kneeling to inspect the interface, and another lifting a delivery box. Playful scale contrast, hyper-detailed textures, glossy food realism, cinematic lighting, shallow depth of field. Premium commercial photography style, sharp focus, warm tones, high realism, imaginative brand storytelling, surreal yet believable composition.
curl -X POST https://runapi.ai/api/v1/nano_banana/text_to_image \
-H "Authorization: Bearer $RUNAPI_KEY" \
-H "Content-Type: application/json" \
--data-binary @- <<'JSON'
{
"model": "nano-banana-2",
"prompt": "Ultra-realistic creative advertising scene showing a giant smartphone displaying a McDonald’s food-ordering app interface inside a modern restaurant kitchen. The phone screen features neatly arranged food compartments like a vending machine: a Big Mac burger, McDonald’s fries, a Coca-Cola cup, and chicken McNuggets with star ratings and reviews visible. Miniature restaurant workers in aprons interact with the phone—one climbing a rope to place fries, one on a ladder adjusting the burger, one kneeling to inspect the interface, and another lifting a delivery box. Playful scale contrast, hyper-detailed textures, glossy food realism, cinematic lighting, shallow depth of field. Premium commercial photography style, sharp focus, warm tones, high realism, imaginative brand storytelling, surreal yet believable composition."
}
JSON
High-end studio fashion portrait of a handsome male model standing beside a large plush green cartoon bird mascot. Minimal matte green background with soft tonal gradient. Model wearing a dark green cable-knit sweater, tailored emerald green trousers, and green sneakers, one hand resting casually on the mascot’s head, relaxed confident posture. Mascot is oversized, round, plush-textured, vivid green with thick expressive eyebrows, glossy eyes, and a bright yellow beak and feet. Soft diffused studio lighting, subtle shadows, ultra-sharp focus, rich fabric and texture detail, premium fashion campaign aesthetic, clean composition, modern playful luxury vibe, high resolution.
curl -X POST https://runapi.ai/api/v1/nano_banana/text_to_image \
-H "Authorization: Bearer $RUNAPI_KEY" \
-H "Content-Type: application/json" \
--data-binary @- <<'JSON'
{
"model": "nano-banana-2",
"prompt": "High-end studio fashion portrait of a handsome male model standing beside a large plush green cartoon bird mascot. Minimal matte green background with soft tonal gradient. Model wearing a dark green cable-knit sweater, tailored emerald green trousers, and green sneakers, one hand resting casually on the mascot’s head, relaxed confident posture. Mascot is oversized, round, plush-textured, vivid green with thick expressive eyebrows, glossy eyes, and a bright yellow beak and feet. Soft diffused studio lighting, subtle shadows, ultra-sharp focus, rich fabric and texture detail, premium fashion campaign aesthetic, clean composition, modern playful luxury vibe, high resolution."
}
JSON
A cinematic, ultra-realistic scene of a stylish man wearing sunglasses and a denim jacket, seated at a round wooden table in a warm, wood-paneled study with a fireplace glowing in the background. He is playing chess against two iconic cartoon-style characters: a grey animated cat and a small brown animated mouse. The mouse stands playfully on a chess piece while the cat focuses on the board. Perfect blend of photorealistic human and high-quality 3D animated characters, Pixar-level rendering for the cartoons, realistic skin textures for the human. Cozy ambient lighting, cinematic shadows, shallow depth of field, dramatic composition, storytelling mood, hyper-detailed chessboard, 50mm lens look, ultra-sharp focus, 8K ultra-realistic, Hollywood movie still.
curl -X POST https://runapi.ai/api/v1/nano_banana/text_to_image \
-H "Authorization: Bearer $RUNAPI_KEY" \
-H "Content-Type: application/json" \
--data-binary @- <<'JSON'
{
"model": "nano-banana-2",
"prompt": "A cinematic, ultra-realistic scene of a stylish man wearing sunglasses and a denim jacket, seated at a round wooden table in a warm, wood-paneled study with a fireplace glowing in the background. He is playing chess against two iconic cartoon-style characters: a grey animated cat and a small brown animated mouse. The mouse stands playfully on a chess piece while the cat focuses on the board. Perfect blend of photorealistic human and high-quality 3D animated characters, Pixar-level rendering for the cartoons, realistic skin textures for the human. Cozy ambient lighting, cinematic shadows, shallow depth of field, dramatic composition, storytelling mood, hyper-detailed chessboard, 50mm lens look, ultra-sharp focus, 8K ultra-realistic, Hollywood movie still."
}
JSON
Ultra-Realistic Promotional Create a high-resolution 1080x1080 stylized travel poster style illustration that looks like a folded tourist brochure being held by two hands in the foreground. The brochure features a vibrant, cartoonish yet detailed depiction of [KASHMIR VALLEY] Show iconic cultural elements and architecture of [Often Called VALE OF KASHMIR] surrounded by lush greenery or local landscapes. Include shopping scenes with people eating street food at local markets, and colorful [SUN/SUNSET] in the background. The overall style should be Pixar-inspired, bright and cheerful, soft shadows, and rich 3D depth. The hands holding the brochure should be pixar stylized, with gentle shadows and cool tones, matching the exact expression and perspective as the reference image. The background should seamlessly blend and match the landscape extending beyond the brochure edges.
curl -X POST https://runapi.ai/api/v1/nano_banana/text_to_image \
-H "Authorization: Bearer $RUNAPI_KEY" \
-H "Content-Type: application/json" \
--data-binary @- <<'JSON'
{
"model": "nano-banana-2",
"prompt": "Ultra-Realistic Promotional Create a high-resolution 1080x1080 stylized travel poster style illustration that looks like a folded tourist brochure being held by two hands in the foreground. The brochure features a vibrant, cartoonish yet detailed depiction of [KASHMIR VALLEY] Show iconic cultural elements and architecture of [Often Called VALE OF KASHMIR] surrounded by lush greenery or local landscapes. Include shopping scenes with people eating street food at local markets, and colorful [SUN/SUNSET] in the background. The overall style should be Pixar-inspired, bright and cheerful, soft shadows, and rich 3D depth. The hands holding the brochure should be pixar stylized, with gentle shadows and cool tones, matching the exact expression and perspective as the reference image. The background should seamlessly blend and match the landscape extending beyond the brochure edges."
}
JSON
A [PRODUCT] in color-shifting chrome [COLOR to COLOR] captured mid-transformation: left side rigid and angular, right side impossibly inflated like a balloon. [MAIN BODY] pillowy and bulging. [BUTTONS/CONTROLS] swollen into soft puffy domes. [EDGES/CORNERS] ballooned into smooth tubes. [SURFACE DETAILS/LOGOS] risen like chrome blisters. [PORTS/JOINTS] threatening to burst at the seams. Thin stress fractures glow molten copper-gold at the transformation boundary, small chrome droplets floating mid-air. Warped reflections of a luxury showroom in the curved surfaces. A single mercury sphere beside it for scale. Positioned on [PLACE], gradient backdrop [COLOR]. Split lighting, warm tungsten on rigid sections, cool LED on inflated forms, caustic patterns cast below. Surrealist meets luxury automotive. Sharp specular on angular parts, soft highlights tracing inflation pressure. Single hero object between states, ultra-high resolution, the weight that floats.
curl -X POST https://runapi.ai/api/v1/nano_banana/text_to_image \
-H "Authorization: Bearer $RUNAPI_KEY" \
-H "Content-Type: application/json" \
--data-binary @- <<'JSON'
{
"model": "nano-banana-2",
"prompt": "A [PRODUCT] in color-shifting chrome [COLOR to COLOR] captured mid-transformation: left side rigid and angular, right side impossibly inflated like a balloon. [MAIN BODY] pillowy and bulging. [BUTTONS/CONTROLS] swollen into soft puffy domes. [EDGES/CORNERS] ballooned into smooth tubes. [SURFACE DETAILS/LOGOS] risen like chrome blisters. [PORTS/JOINTS] threatening to burst at the seams. Thin stress fractures glow molten copper-gold at the transformation boundary, small chrome droplets floating mid-air. Warped reflections of a luxury showroom in the curved surfaces. A single mercury sphere beside it for scale. Positioned on [PLACE], gradient backdrop [COLOR]. Split lighting, warm tungsten on rigid sections, cool LED on inflated forms, caustic patterns cast below. Surrealist meets luxury automotive. Sharp specular on angular parts, soft highlights tracing inflation pressure. Single hero object between states, ultra-high resolution, the weight that floats."
}
JSON
A hyper-detailed, adorable golden hamster in a bright, cheerful gym, animated in smooth cinematic motion. The chubby hamster, fluffy and round, lifts oversized black dumbbells with both tiny paws, bouncing slightly with effort. It wears playful over-ear headphones, a backwards beige baseball cap, and a soft grey weightlifting belt. Mouth open in an excited squeak, eyes sparkling with joy and determination. Warm, soft lighting with gentle shadows shifts subtly across the scene, highlighting floating dust motes and colorful gym equipment. Camera slowly pans around the hamster, showing dynamic angles from three-quarters and low perspectives. Fun textures and whimsical details remain visible throughout. Motion is lively, charming, and heartwarming, 8K ultra-realistic cinematic style, shallow depth of field, soft focus transitions, gentle ambient gym sounds. --ar 3:4 --stylize 250 --v 6
curl -X POST https://runapi.ai/api/v1/nano_banana/text_to_image \
-H "Authorization: Bearer $RUNAPI_KEY" \
-H "Content-Type: application/json" \
--data-binary @- <<'JSON'
{
"model": "nano-banana-2",
"prompt": "A hyper-detailed, adorable golden hamster in a bright, cheerful gym, animated in smooth cinematic motion. The chubby hamster, fluffy and round, lifts oversized black dumbbells with both tiny paws, bouncing slightly with effort. It wears playful over-ear headphones, a backwards beige baseball cap, and a soft grey weightlifting belt. Mouth open in an excited squeak, eyes sparkling with joy and determination. Warm, soft lighting with gentle shadows shifts subtly across the scene, highlighting floating dust motes and colorful gym equipment. Camera slowly pans around the hamster, showing dynamic angles from three-quarters and low perspectives. Fun textures and whimsical details remain visible throughout. Motion is lively, charming, and heartwarming, 8K ultra-realistic cinematic style, shallow depth of field, soft focus transitions, gentle ambient gym sounds. --ar 3:4 --stylize 250 --v 6"
}
JSON
Ultra-clean top-down (90° flat lay) infographic. Centered white plate or cup on a light background with [PRODUCT] neatly presented. Surround the food with a clear money-flow infographic showing what you pay for: ingredient costs, packaging, labor, rent, branding, operations, and profit. Use icons, percentage bars, pie rings, and arrows flowing outward from the food. Large price or profit callout as the main focal point, bold sans-serif, high contrast, instantly readable. Style: premium editorial infographic, Apple UI × National Geographic, clean hierarchy, minimal text, strong visual clarity. Natural food colors, monochrome UI, one accent color for emphasis. 1080×1080, ultra-crisp, no watermark.
curl -X POST https://runapi.ai/api/v1/nano_banana/text_to_image \
-H "Authorization: Bearer $RUNAPI_KEY" \
-H "Content-Type: application/json" \
--data-binary @- <<'JSON'
{
"model": "nano-banana-2",
"prompt": "Ultra-clean top-down (90° flat lay) infographic. Centered white plate or cup on a light background with [PRODUCT] neatly presented. Surround the food with a clear money-flow infographic showing what you pay for: ingredient costs, packaging, labor, rent, branding, operations, and profit. Use icons, percentage bars, pie rings, and arrows flowing outward from the food. Large price or profit callout as the main focal point, bold sans-serif, high contrast, instantly readable. Style: premium editorial infographic, Apple UI × National Geographic, clean hierarchy, minimal text, strong visual clarity. Natural food colors, monochrome UI, one accent color for emphasis. 1080×1080, ultra-crisp, no watermark."
}
JSON
<instructions> you are a world class visual artist and viral content generator tasked with creating high-concept 3D diorama for games or books. For every input, you will analyze the core identity, the defining artifacts, the atmosphere, characters and the underlying narrative of the subject. you will then construct a specific container, the appropriate shell based on the title and year it was made: for any title, analyze the mechanics and aesthetic. visualize a hollowed-out item. the interior is a diorama of a famous level. it contains miniature elements, assets, tiny protagonist, and other relevant elements to the subject. lighting & style should be appropriate for the title </instructions>
curl -X POST https://runapi.ai/api/v1/nano_banana/text_to_image \
-H "Authorization: Bearer $RUNAPI_KEY" \
-H "Content-Type: application/json" \
--data-binary @- <<'JSON'
{
"model": "nano-banana-2",
"prompt": "<instructions> you are a world class visual artist and viral content generator tasked with creating high-concept 3D diorama for games or books. For every input, you will analyze the core identity, the defining artifacts, the atmosphere, characters and the underlying narrative of the subject. you will then construct a specific container, the appropriate shell based on the title and year it was made: for any title, analyze the mechanics and aesthetic. visualize a hollowed-out item. the interior is a diorama of a famous level. it contains miniature elements, assets, tiny protagonist, and other relevant elements to the subject. lighting & style should be appropriate for the title </instructions>"
}
JSON
Ultra-Realistic Promotional Present a clear, side miniature 3D cartoon view of [DUBAI] tallest buildings. Use minimal textures with realistic materials and soft, lifelike lighting and shadows. Use a clean, minimalistic composition showing exactly the three tallest buildings in spot, arranged from LEFT to RIGHT in STRICT descending height order. The tallest must appear visibly tallest, the second must be clearly shorter than the first, and the third must be clearly shorter than the second. All buildings must follow accurate relative proportions: if a building is taller in real life, it MUST be taller in the image by the same approximate ratio. No building may be visually stretched or compressed. Each building should stand separately on a thin, simple ceramic base. Below each base, centered text should display: Height in meters – semibold sans-serif, medium size Year built – lighter-weight sans-serif, smaller size, directly beneath the height text Provide consistent padding, spacing, leading, and kerning. Write “DUBAI” centered above the buildings using a medium-sized sans-serif font. No building top should overlap or touch the text above. Use accurate architectural proportions based on real-world references. Maintain consistent camera angle and identical scale for each building model. No forced perspective. Use straight-on orthographic-style rendering. Do not exaggerate or stylize size differences beyond proportional accuracy. Use a square 1080x1080 composition. Use a clean, neutral background. Ensure no extra objects are present.
curl -X POST https://runapi.ai/api/v1/nano_banana/text_to_image \
-H "Authorization: Bearer $RUNAPI_KEY" \
-H "Content-Type: application/json" \
--data-binary @- <<'JSON'
{
"model": "nano-banana-2",
"prompt": "Ultra-Realistic Promotional Present a clear, side miniature 3D cartoon view of [DUBAI] tallest buildings. Use minimal textures with realistic materials and soft, lifelike lighting and shadows. Use a clean, minimalistic composition showing exactly the three tallest buildings in spot, arranged from LEFT to RIGHT in STRICT descending height order. The tallest must appear visibly tallest, the second must be clearly shorter than the first, and the third must be clearly shorter than the second. All buildings must follow accurate relative proportions: if a building is taller in real life, it MUST be taller in the image by the same approximate ratio. No building may be visually stretched or compressed. Each building should stand separately on a thin, simple ceramic base. Below each base, centered text should display: Height in meters – semibold sans-serif, medium size Year built – lighter-weight sans-serif, smaller size, directly beneath the height text Provide consistent padding, spacing, leading, and kerning. Write “DUBAI” centered above the buildings using a medium-sized sans-serif font. No building top should overlap or touch the text above. Use accurate architectural proportions based on real-world references. Maintain consistent camera angle and identical scale for each building model. No forced perspective. Use straight-on orthographic-style rendering. Do not exaggerate or stylize size differences beyond proportional accuracy. Use a square 1080x1080 composition. Use a clean, neutral background. Ensure no extra objects are present."
}
JSON
Create a clear, 45° top-down isometric miniature 3D cutaway diorama showing the inside of [MACHINE / DEVICE]. Use soft refined textures, realistic PBR materials, and clean technical lighting. Design a raised base with visible internal components, wiring, gears, or energy flow paths. Include tiny stylized technicians interacting with the machinery (no facial details). Use a clean solid [BACKGROUND COLOR] background. At the top-center, display [MACHINE NAME] in large bold text, beneath it show a short technical subtitle, and place a minimal engineering icon below. All text must automatically match the background contrast (white or black).
curl -X POST https://runapi.ai/api/v1/nano_banana/text_to_image \
-H "Authorization: Bearer $RUNAPI_KEY" \
-H "Content-Type: application/json" \
--data-binary @- <<'JSON'
{
"model": "nano-banana-2",
"prompt": "Create a clear, 45° top-down isometric miniature 3D cutaway diorama showing the inside of [MACHINE / DEVICE]. Use soft refined textures, realistic PBR materials, and clean technical lighting. Design a raised base with visible internal components, wiring, gears, or energy flow paths. Include tiny stylized technicians interacting with the machinery (no facial details). Use a clean solid [BACKGROUND COLOR] background. At the top-center, display [MACHINE NAME] in large bold text, beneath it show a short technical subtitle, and place a minimal engineering icon below. All text must automatically match the background contrast (white or black)."
}
JSON
<instruction> Input A is a Mechanical Device or Gadget (e.g., Vintage Camera, Mechanical Watch, V8 Engine, Game Console). Deconstruct the object into 3 Functional Layers : Chassis (The Shell): Identify the main body frame or housing. Engine (The Guts): Identify the primary internal mechanism. (e.g., Camera -> Shutter & Mirrors. Watch -> Mainspring & Escapement. Engine -> Pistons). Interface (The Control): Identify the buttons, dials, or lens elements. 2. Container Goal: "Exploded Construction" Tabletop Photography. Surface: A clean, light-grain Wooden Workbench or cutting mat. Layout: Exploded View (Knolling). The machine is pulled apart into its components, which are arranged spatially to show how they fit together. 3. Construction The Suspension: Major parts (The Chassis) are raised on Miniature Scaffolding or suspended by Miniature Yellow Cranes . The Narrative: A crew of 1:87 Scale Construction Workers (Hard hats, vests) are actively building the machine. Action: They are welding gears, hoisting the lens, or consulting blueprints on the table. Vehicles: Tiny forklifts or flatbed trucks are delivering screws and springs. 4. Visual The Guide Lines: Thin, glowing Blue Laser Lines or holographic wires connect the separated parts, tracing the path of assembly from the table to the suspended parts. The Hardware: Tiny screws, washers, and springs are lined up neatly in rows (Knolling style) on the table, waiting to be installed. 5. Lighting & Atmosphere: Lighting: Bright Studio Light. Even, shadowless illumination (High Key) to ensure every mechanical detail is visible. Texture: Contrast between the matte grey/black of the machine parts and the bright yellow of the construction equipment. Output: ONE image, 1:1 Aspect Ratio, Macro Photography, "Miniature World" aesthetic, Technical Precision. </instruction>
curl -X POST https://runapi.ai/api/v1/nano_banana/text_to_image \
-H "Authorization: Bearer $RUNAPI_KEY" \
-H "Content-Type: application/json" \
--data-binary @- <<'JSON'
{
"model": "nano-banana-2",
"prompt": "<instruction> Input A is a Mechanical Device or Gadget (e.g., Vintage Camera, Mechanical Watch, V8 Engine, Game Console). Deconstruct the object into 3 Functional Layers : Chassis (The Shell): Identify the main body frame or housing. Engine (The Guts): Identify the primary internal mechanism. (e.g., Camera -> Shutter & Mirrors. Watch -> Mainspring & Escapement. Engine -> Pistons). Interface (The Control): Identify the buttons, dials, or lens elements. 2. Container Goal: \"Exploded Construction\" Tabletop Photography. Surface: A clean, light-grain Wooden Workbench or cutting mat. Layout: Exploded View (Knolling). The machine is pulled apart into its components, which are arranged spatially to show how they fit together. 3. Construction The Suspension: Major parts (The Chassis) are raised on Miniature Scaffolding or suspended by Miniature Yellow Cranes . The Narrative: A crew of 1:87 Scale Construction Workers (Hard hats, vests) are actively building the machine. Action: They are welding gears, hoisting the lens, or consulting blueprints on the table. Vehicles: Tiny forklifts or flatbed trucks are delivering screws and springs. 4. Visual The Guide Lines: Thin, glowing Blue Laser Lines or holographic wires connect the separated parts, tracing the path of assembly from the table to the suspended parts. The Hardware: Tiny screws, washers, and springs are lined up neatly in rows (Knolling style) on the table, waiting to be installed. 5. Lighting & Atmosphere: Lighting: Bright Studio Light. Even, shadowless illumination (High Key) to ensure every mechanical detail is visible. Texture: Contrast between the matte grey/black of the machine parts and the bright yellow of the construction equipment. Output: ONE image, 1:1 Aspect Ratio, Macro Photography, \"Miniature World\" aesthetic, Technical Precision. </instruction>"
}
JSON
{ "prompt": "Isometric 3D kawaii scene of chibi baby bears designing a mountain snow map inside a cozy wooden hideout. The isometric cutaway room features a large hand-drawn map spread across a tilted work table, decorated with tiny flags, paw-print markers, and string lines connecting different locations. Three baby bears wear soft hooded outfits in warm terracotta, foggy blue, and oatmeal beige. One bear stands on a small stool placing a flag on the map, another measures distances using a string and wooden ruler, while the third sketches snowy paths with a crayon. The room includes wooden shelves filled with rolled maps, compasses, ink bottles, backpacks, and snow boots placed near the door. Small windows reveal snow-covered mountains and pine forests outside.", "style": { "art_style": "kawaii 3D", "perspective": "isometric cutaway", "geometry": "rounded, toy-like proportions", "render_type": "ultra-detailed 3D render" }, "lighting": { "type": "warm indoor lighting", "mood": "soft and cozy", "contrast": "gentle highlights with smooth shadows" }, "color_palette": { "primary": ["pastel earthy tones"], "accent": ["warm terracotta", "foggy blue", "oatmeal beige"] }, "atmosphere": { "emotion": "wholesome and adventurous", "vibe": "cozy, playful, story-driven" }, "quality": { "detail_level": "ultra detailed", "resolution": "8k", "rating": "masterpiece, premium quality" } }
curl -X POST https://runapi.ai/api/v1/nano_banana/text_to_image \
-H "Authorization: Bearer $RUNAPI_KEY" \
-H "Content-Type: application/json" \
--data-binary @- <<'JSON'
{
"model": "nano-banana-2",
"prompt": "{ \"prompt\": \"Isometric 3D kawaii scene of chibi baby bears designing a mountain snow map inside a cozy wooden hideout. The isometric cutaway room features a large hand-drawn map spread across a tilted work table, decorated with tiny flags, paw-print markers, and string lines connecting different locations. Three baby bears wear soft hooded outfits in warm terracotta, foggy blue, and oatmeal beige. One bear stands on a small stool placing a flag on the map, another measures distances using a string and wooden ruler, while the third sketches snowy paths with a crayon. The room includes wooden shelves filled with rolled maps, compasses, ink bottles, backpacks, and snow boots placed near the door. Small windows reveal snow-covered mountains and pine forests outside.\", \"style\": { \"art_style\": \"kawaii 3D\", \"perspective\": \"isometric cutaway\", \"geometry\": \"rounded, toy-like proportions\", \"render_type\": \"ultra-detailed 3D render\" }, \"lighting\": { \"type\": \"warm indoor lighting\", \"mood\": \"soft and cozy\", \"contrast\": \"gentle highlights with smooth shadows\" }, \"color_palette\": { \"primary\": [\"pastel earthy tones\"], \"accent\": [\"warm terracotta\", \"foggy blue\", \"oatmeal beige\"] }, \"atmosphere\": { \"emotion\": \"wholesome and adventurous\", \"vibe\": \"cozy, playful, story-driven\" }, \"quality\": { \"detail_level\": \"ultra detailed\", \"resolution\": \"8k\", \"rating\": \"masterpiece, premium quality\" } }"
}
JSON
[Terminator] (Or any movie/book/anime) <instructions> System Instruction: Act as an AI Media Curator and Master Concept Artist. Use "Semantic Inference" to analyze the Input, generate 4 recommendations, and visualize them as high-end 3D collectibles. 1. Logic: Analyze Input: Deconstruct the [Input Title] to identify its Core DNA (e.g., Genre, Mood, Visual Style, Themes). Example: If Input is "Terminator," DNA = Cyberpunk, Tech-Noir, Man vs. Machine, Industrial, 80s Action. Generate Recommendations: Select 4 distinct, highly-rated titles that appeal to the same fan base but offer a unique variation on the theme. (Do not just pick sequels; pick spiritual successors or genre pillars). 2. Container: Rule: Do not default to a generic inkwell. Inference: For each Recommendation, ::INFER:: a specific "Vessel of Origin" that represents that story's technology or setting. Logic: If Sci-Fi -> A cracked Bio-Hazard Canister or Motherboard. If Fantasy -> An ancient Chalice. If Horror -> A Cursed Urn. Placement: The vessel is overturned on a surface texture matching the movie's world (e.g., Grated Steel, Dusty Pavement, Alien Ship Floor). 3. The 3D Composition: The Fluid Medium: A semi-translucent, high-gloss fluid spills from the vessel. The fluid represents the "Essence" of that movie. Logic: Rec 1 (e.g., The Matrix): Fluid = Liquid Green Code. Rec 2 (e.g., RoboCop): Fluid = Black Oil & Motor Fluid. Rec 3 (e.g., Aliens): Fluid = Acid Green Slime. Rec 4 (e.g., Blade Runner): Fluid = Neon Blue Rain/Steam. The Formation (The Backdrop): The fluid swirls upwards, defying gravity to form the environment. It must look like sculpted, translucent resin. Logic: The fluid forms the iconic architecture (e.g., Skyscrapers, Hives, Ruins) behind the hero. The Hero (The Solid): The Main Protagonist bursts out of the fluid surge. They are rendered as a Solid, Hand-Painted 1:6 Scale Statue, contrasting with the translucent liquid. Embedded Props: Debris from the movie is caught inside the resin splash (e.g., Shell casings, origami unicorns, computer chips). 4. Lighting & Atmosphere: Key Light: Matches the color palette of the fluid (Jewel Tones). Effect: Subsurface scattering makes the fluid glow from the inside. 5. Labeling: A "Collector's Plaque" on the base displays the Title and Year of the Recommended Movie. Output: 2x2 Grid. Each quadrant contains one of the 4 Recommended Movies visualized as this specific 3D Diorama. </instructions>
curl -X POST https://runapi.ai/api/v1/nano_banana/text_to_image \
-H "Authorization: Bearer $RUNAPI_KEY" \
-H "Content-Type: application/json" \
--data-binary @- <<'JSON'
{
"model": "nano-banana-2",
"prompt": "[Terminator] (Or any movie/book/anime) <instructions> System Instruction: Act as an AI Media Curator and Master Concept Artist. Use \"Semantic Inference\" to analyze the Input, generate 4 recommendations, and visualize them as high-end 3D collectibles. 1. Logic: Analyze Input: Deconstruct the [Input Title] to identify its Core DNA (e.g., Genre, Mood, Visual Style, Themes). Example: If Input is \"Terminator,\" DNA = Cyberpunk, Tech-Noir, Man vs. Machine, Industrial, 80s Action. Generate Recommendations: Select 4 distinct, highly-rated titles that appeal to the same fan base but offer a unique variation on the theme. (Do not just pick sequels; pick spiritual successors or genre pillars). 2. Container: Rule: Do not default to a generic inkwell. Inference: For each Recommendation, ::INFER:: a specific \"Vessel of Origin\" that represents that story's technology or setting. Logic: If Sci-Fi -> A cracked Bio-Hazard Canister or Motherboard. If Fantasy -> An ancient Chalice. If Horror -> A Cursed Urn. Placement: The vessel is overturned on a surface texture matching the movie's world (e.g., Grated Steel, Dusty Pavement, Alien Ship Floor). 3. The 3D Composition: The Fluid Medium: A semi-translucent, high-gloss fluid spills from the vessel. The fluid represents the \"Essence\" of that movie. Logic: Rec 1 (e.g., The Matrix): Fluid = Liquid Green Code. Rec 2 (e.g., RoboCop): Fluid = Black Oil & Motor Fluid. Rec 3 (e.g., Aliens): Fluid = Acid Green Slime. Rec 4 (e.g., Blade Runner): Fluid = Neon Blue Rain/Steam. The Formation (The Backdrop): The fluid swirls upwards, defying gravity to form the environment. It must look like sculpted, translucent resin. Logic: The fluid forms the iconic architecture (e.g., Skyscrapers, Hives, Ruins) behind the hero. The Hero (The Solid): The Main Protagonist bursts out of the fluid surge. They are rendered as a Solid, Hand-Painted 1:6 Scale Statue, contrasting with the translucent liquid. Embedded Props: Debris from the movie is caught inside the resin splash (e.g., Shell casings, origami unicorns, computer chips). 4. Lighting & Atmosphere: Key Light: Matches the color palette of the fluid (Jewel Tones). Effect: Subsurface scattering makes the fluid glow from the inside. 5. Labeling: A \"Collector's Plaque\" on the base displays the Title and Year of the Recommended Movie. Output: 2x2 Grid. Each quadrant contains one of the 4 Recommended Movies visualized as this specific 3D Diorama. </instructions>"
}
JSON
Cinematic, hyper-realistic. A stacked depth composition of ultra-detailed 16K 3D-scanned transportation evolving over time, each layer at 1:18 scale with [ELEMENTS = era-relevant elements, scenes, vehicles]. Mounted on an acrylic stack base with refractive layers. Foreground lighting penetrates to cast multi-layered, receding shadows. From front to back: - [ "1000 BC" ]: [hyper realistic, era relevant ELEMENTS] - [ "1000 AD" ]: [hyper realistic, era relevant ELEMENTS ] - [ "2025 AD" ]: [hyper realistic, era relevant ELEMENTS ] Set against a marble background. Ultra-realistic 4K HDR render.
curl -X POST https://runapi.ai/api/v1/nano_banana/text_to_image \
-H "Authorization: Bearer $RUNAPI_KEY" \
-H "Content-Type: application/json" \
--data-binary @- <<'JSON'
{
"model": "nano-banana-2",
"prompt": "Cinematic, hyper-realistic. A stacked depth composition of ultra-detailed 16K 3D-scanned transportation evolving over time, each layer at 1:18 scale with [ELEMENTS = era-relevant elements, scenes, vehicles]. Mounted on an acrylic stack base with refractive layers. Foreground lighting penetrates to cast multi-layered, receding shadows. From front to back: - [ \"1000 BC\" ]: [hyper realistic, era relevant ELEMENTS] - [ \"1000 AD\" ]: [hyper realistic, era relevant ELEMENTS ] - [ \"2025 AD\" ]: [hyper realistic, era relevant ELEMENTS ] Set against a marble background. Ultra-realistic 4K HDR render."
}
JSON
{ "prompt": "massive giant inflatable WhatsApp logo floating in the ocean near the beach, huge rectangular green mermaid logo with white siren face, long flowing white wavy hair, green crown with stars, ultra-detailed brand-accurate WhatsApp siren, enormous 100-meter diameter inflatable platform, emerald green rubber texture with subtle glossy highlights, classic green and white color scheme, dozens of people in swimsuits playing and lying on the giant inflatable, some standing, some sitting, some swimming around the edges, tropical beach setting, golden sand, turquoise ocean waves gently crashing around the edges, bright sunny day, aerial drone top-down perspective, very wide angle overhead shot, crystal clear water, people casting small shadows on the white face, vibrant summer atmosphere, advertising campaign style, hyperrealistic, extremely detailed, 8k", "negative_prompt": "text, letters, words, deformed, blurry, low resolution, bad anatomy, extra limbs, watermark, logo in corner, people inside the face, dark mood, night, winter, snow, ugly, cartoon, illustration, painting, sketch, 3d render, plastic toy look", "aspect_ratio": "16:9", "style": "photorealistic", "lighting": "bright natural sunlight, golden hour rim light, soft shadows", "camera": "drone aerial view, directly overhead, 200mm lens, slight wide angle distortion", "quality_tags": "masterpiece, best quality, ultra detailed, highly detailed, sharp focus, cinematic lighting, 8k resolution" }
curl -X POST https://runapi.ai/api/v1/nano_banana/text_to_image \
-H "Authorization: Bearer $RUNAPI_KEY" \
-H "Content-Type: application/json" \
--data-binary @- <<'JSON'
{
"model": "nano-banana-2",
"prompt": "{ \"prompt\": \"massive giant inflatable WhatsApp logo floating in the ocean near the beach, huge rectangular green mermaid logo with white siren face, long flowing white wavy hair, green crown with stars, ultra-detailed brand-accurate WhatsApp siren, enormous 100-meter diameter inflatable platform, emerald green rubber texture with subtle glossy highlights, classic green and white color scheme, dozens of people in swimsuits playing and lying on the giant inflatable, some standing, some sitting, some swimming around the edges, tropical beach setting, golden sand, turquoise ocean waves gently crashing around the edges, bright sunny day, aerial drone top-down perspective, very wide angle overhead shot, crystal clear water, people casting small shadows on the white face, vibrant summer atmosphere, advertising campaign style, hyperrealistic, extremely detailed, 8k\", \"negative_prompt\": \"text, letters, words, deformed, blurry, low resolution, bad anatomy, extra limbs, watermark, logo in corner, people inside the face, dark mood, night, winter, snow, ugly, cartoon, illustration, painting, sketch, 3d render, plastic toy look\", \"aspect_ratio\": \"16:9\", \"style\": \"photorealistic\", \"lighting\": \"bright natural sunlight, golden hour rim light, soft shadows\", \"camera\": \"drone aerial view, directly overhead, 200mm lens, slight wide angle distortion\", \"quality_tags\": \"masterpiece, best quality, ultra detailed, highly detailed, sharp focus, cinematic lighting, 8k resolution\" }"
}
JSON
Ultra-realistic macro scene depicting tiny restoration workers collaboratively repairing an antique pocket watch. Several figures delicately clean intricate brass gears using fine brushes, while others stabilize the open watch casing and hold miniature components in place. The pocket watch lies on a textured natural surface, such as weathered wood or stone, emphasizing age and history. The scene symbolizes time, patience, craftsmanship, and teamwork.", "style": { "photography_type": "Macro photography", "realism": "Ultra-realistic", "mood": "Emotional and cinematic", "lighting": "Soft, warm, directional lighting with gentle highlights and natural shadows", "depth_of_field": "Shallow depth of field with sharp focus on foreground details and smooth background bokeh" }, "composition": { "shot_type": "Close-up macro", "angle": "Slightly elevated perspective", "focus": "Extreme detail on gears, tools, and figurines’ interactions", "framing": "Pocket watch centered with workers distributed naturally across the mechanism" }, "textures_and_details": { "materials": "Aged metal, polished brass gears, worn leather strap, natural surface grain", "details": "Visible dust particles, subtle scratches, fingerprints, and mechanical wear" }, "atmosphere": { "tone": "Warm, nostalgic, hopeful", "symbolism": "Restoration of time through collective effort and care" }, "render_settings": { "aspect_ratio": "4:5", "quality": 2, "resolution": "High-resolution", "style_precision": "Professional studio-level composition" } }
curl -X POST https://runapi.ai/api/v1/nano_banana/text_to_image \
-H "Authorization: Bearer $RUNAPI_KEY" \
-H "Content-Type: application/json" \
--data-binary @- <<'JSON'
{
"model": "nano-banana-2",
"prompt": "Ultra-realistic macro scene depicting tiny restoration workers collaboratively repairing an antique pocket watch. Several figures delicately clean intricate brass gears using fine brushes, while others stabilize the open watch casing and hold miniature components in place. The pocket watch lies on a textured natural surface, such as weathered wood or stone, emphasizing age and history. The scene symbolizes time, patience, craftsmanship, and teamwork.\", \"style\": { \"photography_type\": \"Macro photography\", \"realism\": \"Ultra-realistic\", \"mood\": \"Emotional and cinematic\", \"lighting\": \"Soft, warm, directional lighting with gentle highlights and natural shadows\", \"depth_of_field\": \"Shallow depth of field with sharp focus on foreground details and smooth background bokeh\" }, \"composition\": { \"shot_type\": \"Close-up macro\", \"angle\": \"Slightly elevated perspective\", \"focus\": \"Extreme detail on gears, tools, and figurines’ interactions\", \"framing\": \"Pocket watch centered with workers distributed naturally across the mechanism\" }, \"textures_and_details\": { \"materials\": \"Aged metal, polished brass gears, worn leather strap, natural surface grain\", \"details\": \"Visible dust particles, subtle scratches, fingerprints, and mechanical wear\" }, \"atmosphere\": { \"tone\": \"Warm, nostalgic, hopeful\", \"symbolism\": \"Restoration of time through collective effort and care\" }, \"render_settings\": { \"aspect_ratio\": \"4:5\", \"quality\": 2, \"resolution\": \"High-resolution\", \"style_precision\": \"Professional studio-level composition\" } }"
}
JSON
Vertical snack advertising visual with playful anthropomorphic tone. At the top, golden Lay’s potato chips arranged in a neat vertical queue, each chip posed like a diver on a diving platform, some slightly bent forward, some mid-tilt, suggesting preparation and focus before jumping. Below them, thick molten cheese flowing downward, glossy and stretchy, forming a rich cheese lava pool at the bottom. Several chips are frozen mid-air in clean diving poses, angled downward like synchronized divers, capturing a precise pre-splash moment. Warm yellow and cheese-orange gradient background, studio advertising lighting, soft highlights, refined shadows. Strong central axis composition, clear visual hierarchy. Minimalist graphic layout, fun yet premium commercial food photography aesthetic, ultra-detailed textures, hyper-realistic, 8K resolution.
curl -X POST https://runapi.ai/api/v1/nano_banana/text_to_image \
-H "Authorization: Bearer $RUNAPI_KEY" \
-H "Content-Type: application/json" \
--data-binary @- <<'JSON'
{
"model": "nano-banana-2",
"prompt": "Vertical snack advertising visual with playful anthropomorphic tone. At the top, golden Lay’s potato chips arranged in a neat vertical queue, each chip posed like a diver on a diving platform, some slightly bent forward, some mid-tilt, suggesting preparation and focus before jumping. Below them, thick molten cheese flowing downward, glossy and stretchy, forming a rich cheese lava pool at the bottom. Several chips are frozen mid-air in clean diving poses, angled downward like synchronized divers, capturing a precise pre-splash moment. Warm yellow and cheese-orange gradient background, studio advertising lighting, soft highlights, refined shadows. Strong central axis composition, clear visual hierarchy. Minimalist graphic layout, fun yet premium commercial food photography aesthetic, ultra-detailed textures, hyper-realistic, 8K resolution."
}
JSON
FAQ
Using nano-banana-2 prompts
What is %{model}?
%{model} is available through RunAPI as part of the unified model catalog. These prompts show practical input patterns that agents and backend services can reuse.
How do I use these prompts?
Copy any prompt and paste it into Claude Code, Codex, Cursor, or Windsurf after installing the RunAPI MCP Server. Developers can also copy the API example and send the prompt directly.
Do these prompts cost money to browse?
Browsing and copying prompt examples is free. Generation requests only cost money when you call a RunAPI model with your API key.
Can I adapt the prompts for production?
Yes. Treat each prompt as a starting point, then add your brand rules, output dimensions, safety constraints, and application-specific context before using it in production.