Browse 1632+ curated prompts for image, video, music, and audio generation. Copy a prompt into Claude Code, Codex, Cursor, Windsurf, or use the API code directly.
Whimsical children's book illustration of a small red fox sitting on a moss-covered log in an autumn forest. Golden and amber leaves drift down around the fox, who looks upward with bright curious eyes. The trees are stylized with round, soft canopies in warm oranges, yellows, and deep reds. Soft watercolor textures with visible paper grain. Gentle, warm lighting as if the entire scene glows from within. The style is cozy and inviting, suitable for ages 3-7, with slightly oversized eyes on the fox for expressiveness.
curl -X POST https://runapi.ai/api/v1/seedream/text_to_image \
-H "Authorization: Bearer $RUNAPI_KEY" \
-H "Content-Type: application/json" \
--data-binary @- <<'JSON'
{
"model": "seedream-5-lite-text-to-image",
"prompt": "Whimsical children's book illustration of a small red fox sitting on a moss-covered log in an autumn forest. Golden and amber leaves drift down around the fox, who looks upward with bright curious eyes. The trees are stylized with round, soft canopies in warm oranges, yellows, and deep reds. Soft watercolor textures with visible paper grain. Gentle, warm lighting as if the entire scene glows from within. The style is cozy and inviting, suitable for ages 3-7, with slightly oversized eyes on the fox for expressiveness."
}
JSON
Flat vector illustration of a cozy home office setup viewed from slightly above. A wooden desk holds an open laptop, a potted monstera plant, a ceramic coffee mug with steam rising, scattered sticky notes, and a pair of round glasses. A cat sleeps curled up on an ergonomic chair beside the desk. The wall behind has a pegboard with headphones hanging and a small shelf with three books. Warm, pastel color palette — dusty pink walls, sage green plant, cream desk. Clean lines, no outlines, geometric shapes with subtle grain texture overlay. Suitable for a blog header illustration.
curl -X POST https://runapi.ai/api/v1/flux_2/text_to_image \
-H "Authorization: Bearer $RUNAPI_KEY" \
-H "Content-Type: application/json" \
--data-binary @- <<'JSON'
{
"model": "flux-2-flex-text-to-image",
"prompt": "Flat vector illustration of a cozy home office setup viewed from slightly above. A wooden desk holds an open laptop, a potted monstera plant, a ceramic coffee mug with steam rising, scattered sticky notes, and a pair of round glasses. A cat sleeps curled up on an ergonomic chair beside the desk. The wall behind has a pegboard with headphones hanging and a small shelf with three books. Warm, pastel color palette — dusty pink walls, sage green plant, cream desk. Clean lines, no outlines, geometric shapes with subtle grain texture overlay. Suitable for a blog header illustration."
}
JSON
FAQ
Finding and using RunAPI prompts
What are RunAPI prompts?
RunAPI prompts are curated input examples for image, video, music, and audio models. Each prompt is paired with the model slug and endpoint path so developers can copy the text into an agent or reuse it in backend calls.
Can I filter prompts by model or category?
Yes. Use the modality and category links to narrow the library, then open a model page for examples tied to one specific model slug. Each model page keeps the prompt cards, install steps, and API examples together.
Do I need an API key to browse prompts?
No. Browsing, filtering, and copying prompt text is public. You only need a RunAPI key when you ask an agent or your application to call a model and create a generation task.
How should agents use these prompts?
Install the RunAPI MCP Server in Claude Code, Codex, Cursor, or Windsurf, then paste the prompt instruction shown on the page. The agent can choose the matching RunAPI tool and send the prompt with the listed model.