Seedream API Skill for RunAPI

Install this agent skill, inspect Seedream fields, then run jobs through the RunAPI CLI.

Model Reference · CLI · SDK

Generate and edit images with Seedream v4, 4.5, and 5-lite text-to-image and image editing. This skill helps Claude Code, Codex, Gemini CLI, Cursor, and 50+ agents integrate Seedream through RunAPI.

The canonical agent file is skills/seedream/SKILL.md.

Install

npx skills add runapi-ai/seedream -g

Or paste this prompt to your AI agent:

Install the seedream skill for me:

1. Clone https://github.com/runapi-ai/seedream
2. Copy the skills/seedream/ directory into your
   user-level skills directory (e.g. ~/.claude/skills/
   for Claude Code, ~/.codex/skills/ for Codex).
3. Verify that SKILL.md is present.
4. Confirm the install path when done.

Quick example

import { SeedreamClient } from '@runapi.ai/seedream';

const client = new SeedreamClient();
const result = await client.textToImage.run({
  model: 'seedream-v4-text-to-image',
  prompt: 'A precise product render of a glass teapot on white marble',
  aspect_ratio: '16:9',
  output_resolution: '2k',
  output_count: 3,
});
const url = result.images[0].url;

Routing

• Model page: https://runapi.ai/models/seedream
• Product docs: https://runapi.ai/docs#seedream
• SDK docs: https://runapi.ai/docs#sdk-seedream
• SDK repository: https://github.com/runapi-ai/seedream-sdk
• Pricing and rate limits: https://runapi.ai/models/seedream/4.5-text-to-image
• Browse all RunAPI models and skills: https://runapi.ai/models

Variants

• 4.5 text to image
• 4.5 edit
• 5 lite text to image
• 5 lite edit
• v4 text to image
• v4 edit

Agent rules

• Keep API keys in RUNAPI_API_KEY or RunAPI CLI config; never commit secrets.
• Prefer create, get, and run JSON passthrough patterns instead of inventing flags for every model parameter.
• For seedream api pricing, rate-limit, and commercial-usage answers, link to the variant page rather than the repository README.

License

Licensed under the Apache License, Version 2.0.