API DI MODELLI AI · 32 modelli · workflow skill-first

Sfoglia API di modelli AI per sviluppatori.

Confronta ID modello, prezzi, capacità e skill installabili per app video, immagini, musica, audio e LLM con una sola chiave RunAPI.

All systems normal
# Install the model skill for app development workflows
npx skills add runapi-ai/<model> -g
Installs docs, schemas, pricing context, and setup notes into your developer workspace.
Or use this setup request in your coding tool:
Install the <model> skill for this app:

1. Add runapi-ai/<model> with the skills installer.
2. Load SKILL.md in this workspace.
3. Use its docs, schemas, pricing notes, and setup steps when adding model features.
4. Confirm the install path when done.
OVERVIEW

RunAPI aggrega 32 API di modelli multimodali da 18 provider. Gli sviluppatori possono esplorare capacità, verificare prezzi e installare model skill che portano documentazione, schema e note di setup nel workspace di sviluppo.

  • Un'unica API key per tutti i provider
  • Model skill per lo sviluppo di app
  • Billing misurato per chiamata, senza impegno
  • Le pagine modello includono ID, capacità, prezzi e setup dello skill
CATEGORIES

Sfoglia tutti i modelli

Filtra per modalità o vai direttamente a un provider.

Claude
Anthropic
Text

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

da $0.030 / 1K tokens Visualizza →
DeepSeek
DeepSeek
Text

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

da $0.010 / 1K tokens Visualizza →
ElevenLabs
ElevenLabs
Audio & Music

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

da $0.040 / 1K chars Visualizza →
Embedding
OpenAI
Text

OpenAI text embeddings for semantic search, retrieval, clustering, and ranking workflows.

da $0.010 / 1K tokens Visualizza →
Flux 2
Black Forest Labs
Image

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

da $0.050 / call Visualizza →
Flux Kontext
Black Forest Labs
Image

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

da $0.050 / call Visualizza →
Gemini
Google
Text

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

da $0.020 / 1K tokens Visualizza →
Gemini Omni
Google
Video

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

da $0.0000 / call Visualizza →
GPT
OpenAI
Text

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

da $0.010 / 1K tokens Visualizza →
GPT Image
OpenAI
Image

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

da $0.040 / call Visualizza →
GPT Image 2
OpenAI
Image

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

da $0.060 / call Visualizza →
GPT-4o Image
OpenAI
Image

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

da $0.060 / call Visualizza →
Grok Imagine
xAI
Video

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

da $0.020 / call Visualizza →
Hailuo
MiniMax
Video

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

da $0.300 / call Visualizza →
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.

da $0.480 / second Visualizza →
Ideogram V3
Ideogram
Image

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

da $0.070 / call Visualizza →
Imagen 4
Google
Image

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

da $0.040 / call Visualizza →
InfiniteTalk
MeiGen-AI
Video

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

da $0.120 / second Visualizza →
Kling
Kuaishou
Video

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

da $0.050 / second Visualizza →
Luma
Luma
Video

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

da $0.500 / call Visualizza →
Nano Banana
Google
Image

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

da $0.040 / call Visualizza →
Qwen 2
Alibaba
Image

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

da $0.040 / call Visualizza →
Recraft
Recraft
Utility

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

da $0.010 / call Visualizza →
Runway
Runway
Video

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

da $0.120 / call Visualizza →
Runway Aleph
Runway
Video

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

da $1.10 / call Visualizza →
Seedance
Bytedance
Video

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

da $0.020 / second Visualizza →
Seedream
Bytedance
Image

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

da $0.060 / call Visualizza →
Suno
Suno
Audio & Music

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

da $0.0000 / call Visualizza →
Topaz
Topaz
Utility

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

da $0.140 / second Visualizza →
Veo 3.1
Google
Video

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

da $0.600 / call Visualizza →
Wan
Alibaba
Video

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

da $0.050 / call Visualizza →
Z Image
Alibaba
Image

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

da $0.010 / call Visualizza →
FEATURES

Tutto ciò che serve agli sviluppatori per scegliere API di modelli AI e costruire con skill.

Una chiave per ogni modello

Usa la stessa chiave RunAPI per API video, immagini, musica, audio e LLM senza gestire credenziali specifiche per provider.

Skill per chi crea app

Installa un model skill così il tuo editor ha documentazione, schema, contesto prezzi e passaggi di setup mentre sviluppi.

Costi e latenza prevedibili

Prezzi a consumo per call o per unità: vedi esattamente quanto costa ogni chiamata prima di eseguirla.

QUICKSTART

Installa un model skill per la tua app.

Usa lo skill per caricare documentazione del modello, schema, note sui prezzi e passaggi di setup prima di aggiungere una feature con quel modello.

# Install the model skill for app development workflows
npx skills add runapi-ai/claude -g
Installs docs, schemas, pricing context, and setup notes into your developer workspace.
Or use this setup request in your coding tool:
Install the Claude skill for this app:

1. Add runapi-ai/claude with the skills installer.
2. Load SKILL.md in this workspace.
3. Use its docs, schemas, pricing notes, and setup steps when adding model features.
4. Confirm the install path when done.
PRICING

Paghi solo ciò che chiami.

Tabella prezzi completa →
VIDEO
$0.300 / call

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

IMAGE
$0.060 / call

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

AUDIO & MUSIC
$0.040 / 1K chars

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

LLM
$0.030 / 1K tokens

Large language models for chat, code, and reasoning.

FAQ

Risposte rapide per sviluppatori.

Cosa contiene il catalogo dei modelli?

Il catalogo elenca API di modelli AI supportate con provider, modalità, ID modello, capacità, prezzi e model skill installabili.

Posso chiamare provider diversi con una sola chiave?

Sì. Una singola chiave RunAPI funziona con i modelli video, immagini, musica, audio e LLM supportati.

Mi serve un account separato per ogni provider?

No — una sola chiave RunAPI sblocca l'intero catalogo. La fatturazione è unificata.

Come viene fatturato il prezzo?

A consumo per chiamata o per unità, fatturato mensilmente in USD. Le generazioni non riuscite non vengono addebitate.

Posso self-hostare l'SDK?

I pacchetti SDK su npm, pip e RubyGems hanno licenza MIT.

Dove posso segnalare problemi API?

Apri una issue nel repository pubblico su GitHub o contatta il supporto.

INIZIA ORA

Inizia a costruire con una sola chiave API per modelli AI.

Crea un account gratuito, installa un model skill e passa dal catalogo a una feature modello funzionante.