What is listed in the model catalog?

The catalog lists every supported AI model API with its provider, modality (video, image, audio, LLM, or utility), model IDs, parameter constraints, per-call pricing, and an installable model skill. Each model page shows code samples for curl, Python, Node.js, Ruby, and Go, plus skill install commands for Claude Code, Codex, and Gemini CLI.

Can I call different providers with one key?

Yes. A single RunAPI API key works across all supported video, image, music, audio, and LLM models from every provider in the catalog. You do not need separate accounts, separate credentials, or separate billing relationships with any provider. Add a new model from a different provider to your app by changing one model ID parameter — the API key, request shape, and billing all stay the same.

Do I need a separate account per provider?

No. One RunAPI key unlocks the entire catalog. You do not need accounts with Anthropic, OpenAI, Google, Kuaishou, Suno, Black Forest Labs, or any other provider. RunAPI handles provider authentication, rate limiting, and billing consolidation into a single monthly invoice.

How is pricing billed?

Per-call or per-unit metered, billed monthly in USD. There is no subscription, no minimum spend, and no hidden fees. Failed generations are never charged and credits do not expire. The pricing page shows exact per-model costs, and the check_pricing API endpoint returns real-time rates programmatically so you can build cost-aware workflows that check prices before calling a model.

What modalities does the catalog cover?

The catalog spans five modalities. Video generation includes text-to-video, image-to-video, video editing, and video extension from providers like Kling, Veo, Seedance, Hailuo, Wan, Runway, and Luma. Image generation covers text-to-image, image editing, remix, and in-context editing from Flux, Imagen, GPT Image, Seedream, Ideogram, Nano Banana, and more. Music and audio includes full song generation from Suno, text-to-speech and dialogue from ElevenLabs, and sound effects. LLM covers chat, code generation, reasoning, and embeddings from Claude, GPT, Gemini, DeepSeek, GLM, Kimi, MiniMax, and Qwen. Utility includes image and video upscaling from Topaz and Recraft, background removal, and avatar generation.

What are model skills?

Model skills are installable packages that load a model's docs, typed schemas, pricing notes, and setup steps directly into your coding workspace. They work with Claude Code, Codex, Gemini CLI, Cursor, and VS Code. Install a skill with a single command like npx skills add runapi-ai/kling -g and your coding agent immediately has the right context — parameter constraints, endpoint paths, billing units, and code samples — before you write integration code.

Can I self-host the SDK?

Yes. The SDK packages on npm, Packagist, pip, and RubyGems are MIT-licensed. You can self-host, vendor, or fork them. The SDKs are thin clients that handle authentication, async task polling, and typed responses. They connect to the RunAPI endpoint at https://runapi.ai and work with any standard HTTP client.

How do I add a model to my application?

Browse the catalog, pick a model, and install its skill with a single command. The skill loads docs, typed schemas, pricing notes, and setup steps into your coding workspace so your agent has the right context. Then use the provided code samples to integrate the model — set your RunAPI API key, call the endpoint with the model ID and parameters, and handle the response. The entire flow from catalog browsing to a working API call takes under 10 minutes. SDKs are available for Python, Node.js, PHP, Java, Ruby, and Go.

How quickly are new models added to the catalog?

New models are added within days of a provider release. When a provider ships a new model or variant, RunAPI adds API support, per-call pricing, documentation, a model skill, and code samples so you can call the model as soon as it is production-ready. The catalog is updated continuously — you do not need to wait for a scheduled release cycle.

What happens when a provider changes their API?

RunAPI absorbs provider API changes so your integration code does not break. When a provider updates their request format, response structure, or authentication method, RunAPI adapts the proxy layer to maintain the same stable API surface you integrated against, and the SDKs handle format translation automatically.

Where do I report API issues?

Open an issue on the public GitHub repo or email support at contact@runapi.ai. Include the task ID and model ID so the team can investigate. The status page monitors API uptime in real time.

Model Catalog

Explore 238 AI Models

Browse, compare, and integrate the best AI models for video, image, music, audio, and text generation — all through one unified API.

Get API Key Read the docs

All models available · Real-time pricing

# Available Endpoints
POST /v1/chat/completions # LLM
POST /v1/images/generations # Image
POST /api/v1/kling/text_to_video # Video
POST /v1/audio/speech # TTS
POST /v1/audio/transcriptions # STT
POST /api/v1/suno/text_to_music # Music

const response = await fetch("https://runapi.ai/v1/chat/completions", {
  method: "POST",
  headers: { Authorization: `Bearer ${RUNAPI_API_KEY}`, "Content-Type": "application/json" },
  body: JSON.stringify({ model: "your-model-id", messages: [{ role: "user", content: "Hello" }] })
})
const result = await response.json()

import os
import httpx

response = httpx.post(
    "https://runapi.ai/v1/chat/completions",
    headers={"Authorization": f"Bearer {os.environ['RUNAPI_API_KEY']}"},
    json={"model": "your-model-id", "messages": [{"role": "user", "content": "Hello"}]}
)

<?php
$ch = curl_init("https://runapi.ai/v1/chat/completions");
curl_setopt_array($ch, [CURLOPT_POST => true, CURLOPT_RETURNTRANSFER => true,
  CURLOPT_HTTPHEADER => ["Authorization: Bearer $RUNAPI_API_KEY", "Content-Type: application/json"],
  CURLOPT_POSTFIELDS => json_encode(["model" => "your-model-id", "messages" => [["role" => "user", "content" => "Hello"]])]);
$result = json_decode(curl_exec($ch), true);

HttpClient client = HttpClient.newHttpClient();
HttpRequest request = HttpRequest.newBuilder(URI.create("https://runapi.ai/v1/chat/completions"))
  .header("Authorization", "Bearer " + RUNAPI_API_KEY)
  .header("Content-Type", "application/json")
  .POST(HttpRequest.BodyPublishers.ofString("{\"model\":\"your-model-id\",\"messages\":[]}")).build();
HttpResponse<String> response = client.send(request, HttpResponse.BodyHandlers.ofString());

require "net/http"
uri = URI("https://runapi.ai/v1/chat/completions")
request = Net::HTTP::Post.new(uri)
request["Authorization"] = "Bearer #{ENV.fetch('RUNAPI_API_KEY')}"
request["Content-Type"] = "application/json"
request.body = {model: "your-model-id", messages: []}.to_json

requestBody := strings.NewReader(`{"model":"your-model-id","messages":[]}`)
request, _ := http.NewRequest(http.MethodPost, "https://runapi.ai/v1/chat/completions", requestBody)
request.Header.Set("Authorization", "Bearer "+os.Getenv("RUNAPI_API_KEY"))
request.Header.Set("Content-Type", "application/json")
response, err := http.DefaultClient.Do(request)
defer response.Body.Close()

# Authenticate once
runapi login

# Inspect available models
runapi models list --modality video

# Use the selected model in your workflow
runapi models show <model-id>

Leading AI models, one API

Flux
Midjourney
Whisper
ElevenLabs
HappyHorse
GPT Image 2
Veo
Minimax
Luma
PixVerse
Recraft
Fish Audio
DeepSeek
Qwen
Claude
GPT
Gemini
Seedance
Kling
Suno

Flux
Midjourney
Whisper
ElevenLabs
HappyHorse
GPT Image 2
Veo
Minimax
Luma
PixVerse
Recraft
Fish Audio
DeepSeek
Qwen
Claude
GPT
Gemini
Seedance
Kling
Suno

10 models

Text

Claude

Anthropic

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

Text

DeepSeek

DeepSeek API access via RunAPI — flash for fast, low-cost work; pro for complex agentic tasks.

Text

Embedding

OpenAI

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

Text

Gemini

Google

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

Text

GLM

Z.ai

Z.ai GLM API access via RunAPI — MIT-licensed MoE models with up to 200K context, leading open-weight coding benchmarks.

Text

GPT

OpenAI

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

Text

Grok

xAI

xAI Grok 4.3 and 4.5 API access through RunAPI Responses and Chat Completions for reasoning, tools, and structured output.

Text

Kimi

Moonshot AI

Moonshot AI Kimi API access via RunAPI — kimi-k3 is the current flagship with always-on reasoning; kimi-k2.5 and kimi-k2.6 remain available.

Text

MiMo

Xiaomi

MiMo API via RunAPI — base mimo-v2.5 supports text and remote HTTP(S) images in synchronous OpenAI Chat Completions; mimo-v2.5-pro remains text-only.

Text

MiniMax

MiniMax text API access via RunAPI — sparse MoE models from 200K to 1M context, up to 80.5% SWE-bench Verified.

10 models

Try a Model Now

Pick any model and generate in seconds.

Cache read

Estimated: $0.25 / 1M tokens

Generate

WHY RUNAPI

One API, Every AI Model

Unified Interface

One SDK for 230+ models across all modalities. Switch providers without changing code.

Real-time Pricing

Transparent pay-as-you-go pricing. No subscriptions, no hidden fees, credits never expire.

Enterprise Ready

Team API keys, usage analytics, and priority support.

Get Started in Seconds

Python SDK

pip install runapi-suno

CLI

curl -fsSL https://runapi.ai/cli/install.sh | sh

MCP Server

npx -y @runapi.ai/mcp

What teams build with 200+ models

Video Marketing

Generate ad variants per audience segment with Kling, Veo, and Runway

Product Photography

Create studio-quality product shots with Flux and Midjourney

Podcast Production

Clone voices and generate intros with Fish Audio and ElevenLabs

AI Agents

Give your agent access to any model through MCP or REST

Music for Content

Score videos and podcasts with Suno and Udio

Multilingual TTS

Localize apps into 40+ languages with natural voices

Catalog questions

How do I browse available models?

Visit /models or use the CLI: runapi models list. Filter by modality, provider, or search by name.

Can I use multiple models in one project?

Yes. One API key works across all 230+ models. Switch between video, image, music, audio, and LLM models freely.

How are new models added?

We add new models continuously. Major releases are typically available within days of launch. Follow our changelog for updates.

Can I request a specific model?

Yes. Contact us with the model name and provider. We evaluate all requests and prioritize based on demand.

What happens when a model is retired?

We notify users 30 days before retirement. Your existing code continues working — just update the model parameter to a newer version.

How are models priced?

Text models bill per million input and output tokens; media models bill per second, per image, or per minute. Every rate is listed on the model page and in the pricing table.

Start building with 238 models.

Get API Key View pricing