SKILLS · 31 모델 · 50+ 에이전트

통합 AI API 모델 skills를 어떤 에이전트에도 설치하세요.

하나의 skill에 이미지, 비디오, AI 음악, LLM 호출을 위한 설치, 문서, 도구 호출이 포함됩니다. Claude Code, Codex CLI, Gemini CLI 또는 npm/pip에서 바로 사용할 수 있습니다.

모델 보기 → 문서 읽기
All systems normal 
# Works with Claude Code, Codex, Gemini CLI, Cursor, and 50+ agents
npx skills add runapi-ai/<model> -g
The -g flag installs globally so every project picks it up.
Or paste this prompt to your AI agent:
Install the <model> skill for me:

1. Clone https://github.com/runapi-ai/<model>
2. Copy the skills/<model>/ 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.
One skill gives your agent everything it needs to call the API — setup, docs, and recipes.
개요

RunAPI는 18개 제공사의 31개 멀티모달 모델을 모아 CLI로 설치 가능한 skill로 제공합니다. 하나의 키로 전체 통합 AI API 카탈로그를 열고, 하나의 schema가 모든 runtime에서 동작합니다.

  • 모든 제공사에 하나의 API key
  • 전송 전 검증되는 schema-first 도구 호출
  • 호출 단위 과금, 약정 없음
  • Claude Code, Codex, Cursor, Gemini CLI 등 50+ 에이전트 지원
MOST INSTALLED
GPT Image 2 Seedance Nano Banana Suno Claude Veo 3.1
모두 보기 →
카테고리

모든 skills 보기

모달리티로 필터링하거나 제공사로 바로 이동하세요.

Claude
Anthropic
Text

Anthropic's LLM for complex reasoning, code, analysis, and extended-context tasks.

최저 $0.050 / 1K tokens 보기 →
DeepSeek
DeepSeek
Text

Reasoning-first LLMs via RunAPI — flash for fast, low-cost work; pro for complex agentic tasks.

최저 $0.060 / 1K tokens 보기 →
ElevenLabs
ElevenLabs
Audio & Music

Voice synthesis, text-to-speech, sound effects, speech-to-text, and audio isolation.

최저 $0.040 / minute 보기 →
Flux 2
Black Forest Labs
Image

Text-to-image and remix-image with strong prompt adherence from Black Forest Labs.

최저 $0.050 / call 보기 →
Flux Kontext
Black Forest Labs
Image

In-context image editing — local edits, style transfer, and character-consistent generation.

최저 $0.100 / call 보기 →
Gemini
Google
Text

Google's multimodal LLM for chat, code generation, reasoning, and long-context tasks.

최저 $0.030 / 1K tokens 보기 →
Gemini Omni
Google
Image

Voice, character, and multimodal video generation resources for narration, dialogue, and agent media workflows.

최저 $0.0000 / call 보기 →
GPT
OpenAI
Text

OpenAI's flagship LLM for chat, code generation, and multi-step reasoning tasks.

최저 $0.030 / 1K tokens 보기 →
GPT Image
OpenAI
Image

Text-to-image and image editing powered by OpenAI's image generation models.

최저 $0.040 / call 보기 →
GPT Image 2
OpenAI
Image

Latest OpenAI image generation with near-perfect multilingual text rendering inside images.

최저 $0.060 / call 보기 →
GPT-4o Image
OpenAI
Image

Native image generation inside GPT-4o — generate and edit images within the conversation.

최저 $0.060 / call 보기 →
Grok Imagine
xAI
Image

Image and video generation from text — text-to-image, image-to-video, and editing with audio.

최저 $0.020 / call 보기 →
Hailuo
MiniMax
Video

Text and image-to-video at native 1080p with accurate physics simulation and motion.

최저 $0.300 / call 보기 →
HappyHorse
Alibaba
Video

Text, image, and edit-video generation with 720p and 1080p output, duration control, first-frame image support, ordered reference images for character-guided clips, and source-video editing.

최저 $0.480 / second 보기 →
Ideogram V3
Ideogram
Text

Text-to-image with industry-leading in-image text accuracy — posters, logos, and typography.

최저 $0.070 / call 보기 →
Imagen 4
Google
Image

Photorealistic text-to-image with precise typography, broad style range, and up to 2K resolution.

최저 $0.040 / call 보기 →
InfiniteTalk
MeiGen-AI
Video

Audio-driven talking-head animation — lip-sync and animate a portrait from any audio input.

최저 $0.120 / second 보기 →
Kling
Kuaishou
Text

Text and image-to-video at up to 4K 60fps with multimodal audio and AI avatar generation.

최저 $0.050 / second 보기 →
Luma
Luma
Video

Video modification and transformation powered by Luma's Dream Machine model.

최저 $0.500 / call 보기 →
Nano Banana
Google
Image

Fast text-to-image with accurate in-image text rendering and multi-character consistency.

최저 $0.040 / call 보기 →
Qwen 2
Alibaba
Image

Text-to-image, image remix, and image editing from Alibaba's Qwen visual model family.

최저 $0.040 / call 보기 →
Recraft
Recraft
Image

AI image upscaling and background removal for design and production workflows.

최저 $0.010 / call 보기 →
Runway
Runway
Video

Video generation and editing — create and transform footage with text prompts.

최저 $0.120 / call 보기 →
Runway Aleph
Runway
Video

Prompt-guided video editing that transforms existing footage with frame-level continuity.

최저 $1.10 / call 보기 →
Seedance
Bytedance
Video

Text and image-to-video with native audio-video joint synthesis, up to 15-second multi-shot clips.

최저 $0.020 / second 보기 →
Seedream
Bytedance
Image

Text-to-image and image editing with strong typography rendering, up to 4K resolution.

최저 $0.060 / call 보기 →
Suno
Suno
Audio & Music

AI music generation — create full songs with vocals, instruments, and lyrics from a text prompt.

최저 $0.0000 / call 보기 →
Topaz
Topaz
Image

AI-powered image and video upscaling — enhance resolution and detail without artifacts.

최저 $0.120 / second 보기 →
Veo 3.1
Google
Video

High-fidelity video generation up to 4K with natively synthesized dialogue, sound effects, and ambience.

최저 $0.300 / call 보기 →
Wan
Alibaba
Video

Comprehensive video and image suite — text-to-video, image-to-video, video editing, and storyboards.

최저 $0.050 / call 보기 →
Z Image
Alibaba
Image

Ultra-fast text-to-image — photorealistic results in ~1 second with 8 inference steps.

최저 $0.010 / call 보기 →
제공사

제공사별로 보기

18개 제공사, 하나의 통합 API.

Alibaba Anthropic Black Forest Labs Bytedance DeepSeek ElevenLabs Google Ideogram Kuaishou Luma MeiGen-AI MiniMax OpenAI Recraft Runway Suno Topaz xAI
SKILLS

Skill은 단순 binding이 아니라 문서, schema, 설치를 하나로 묶은 패키지입니다.

한 번 설치로 모든 에이전트 지원

런타임을 고르고 명령을 붙여넣으면 에이전트가 문서, schema, 어댑터를 가져옵니다.

Schema-first 도구 호출

각 skill은 타입이 있는 JSON schema를 제공합니다. 잘못된 요청은 프로덕션 전에 차단됩니다.

예측 가능한 비용과 지연시간

호출 또는 단위별 요금을 실행 전에 확인할 수 있습니다.

설치 PATTERNS

하나의 명령, 모든 에이전트.

Claude Code, Codex, Gemini CLI, Cursor 및 50+ 에이전트에서 동작합니다.

# Works with Claude Code, Codex, Gemini CLI, Cursor, and 50+ agents
npx skills add runapi-ai/<model> -g
The -g flag installs globally so every project picks it up.
Or paste this prompt to your AI agent:
Install the <model> skill for me:

1. Clone https://github.com/runapi-ai/<model>
2. Copy the skills/<model>/ 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.
요금

호출한 만큼만 지불하세요.

전체 요금표 →
VIDEO
$0.300 / call

Video generation — text-to-video, image-to-video, extend, upscale.

Hailuo Kling Seedance
IMAGE
$0.060 / call

Image generation and editing — text-to-image, remix, upscale.

GPT Image 2 Nano Banana Flux Kontext
AUDIO & MUSIC
$0.040 / minute

Music, speech synthesis, sound effects, and audio processing.

Suno ElevenLabs
LLM
$0.050 / 1K tokens

Large language models for chat, code, and reasoning.

Claude GPT Gemini
FAQ

문서에서 가져온 빠른 답변.

모델 skill이 정확히 무엇인가요?

Skill은 설치, schema, prompt, runtime adapter를 호환 CLI용으로 묶은 패키지입니다.

현재 어떤 CLI를 지원하나요?

Claude Code, Codex, Gemini CLI, Cursor 등 50+ 에이전트에서 동작합니다.

제공사마다 별도 계정이 필요한가요?

아닙니다. 하나의 RunAPI key로 전체 카탈로그를 사용할 수 있고 과금도 통합됩니다.

요금은 어떻게 청구되나요?

호출 또는 단위 기준으로 측정해 월별 USD로 청구됩니다. 실패한 생성은 과금되지 않습니다.

SDK를 직접 호스팅할 수 있나요?

npm, pip, RubyGems의 SDK 패키지는 MIT 라이선스입니다.

문제가 있는 skill은 어디에 신고하나요?

공개 GitHub 저장소에 issue를 열어 주세요.

지금 시작

60초 안에 첫 skill을 설치하세요.

명령 하나, 복잡한 인증 과정 없음, 첫 1,000 calls 무료.

무료 계정 만들기 빠른 시작 읽기 →