Vibecode integrations
Integrations are APIs an app built with Vibecode can use without API keys of its own: AI models like Claude, GPT, Gemini and Grok, image, video and audio generation, and live data like maps, weather and stock prices. Usage comes out of your plan's credits.
Prices as of
Claude Opus 5.5 is built for coding and long-running agentic work, with a 1M-token context and always-on adaptive thinking.
OpenAI GPT-6 Astra is the flagship of the new GPT-6 family. It is a reasoning-heavy, agentic model built for long-running, complex work like coding, computer use, and browser automation, with a 1M-token context window and multimodal input.
OpenAI GPT-6.1 Sol handles coding and agentic workflows with text and image inputs. Use the Responses API for tool calling.
Claude Fable 5.1 is Anthropic's most capable model, built for the hardest reasoning and long-running agentic work. Thinking is always on, it takes a 1M-token context, and it accepts text, images, and PDFs. Best for complex coding assistants, research, and multi-step agents where quality matters more than cost.
Make any app with Claude Code Integration (Agent SDK). It is like building Cursor for your app. It handles conversation management, tool use, and multi-step reasoning out of the box so you can focus on building great agent experiences. Add intelligent agents that can take actions, answer questions, and complete tasks for your users.
OpenAI GPT-6 Luna is the fastest and cheapest model in the GPT-6 family, built for focused, high-volume work. Great for chat, classification, extraction, and content generation, with text and image input and a 1M-token context window.
OpenAI GPT-5.6 is the newest and most advanced model in the GPT-5 family (also known as GPT-5.6 Sol). It excels at complex reasoning, coding, and agentic tasks with best-in-family accuracy and performance.
Claude Sonnet 5.5 is Anthropic's fast everyday model for coding, agents, and knowledge work, with a 1M-token context and adaptive thinking at half the price of Opus 5.5.
Grok 4.7 is xAI's newest flagship model, great at coding, long-running agents, and visual projects, with text and image input and a 500k-token context window. Grok is generally less scripted and will speak its mind more freely. It's also trained on a lot of Twitter data, so it just has a different personality than the rest of the AI chatbots.
Google Gemini 4 Argon is Google's flagship reasoning model. It thinks before it answers, which makes it the best Gemini for hard problems: complex analysis, math, code, and multi-step planning. It accepts text, images, video, audio, and PDFs as input, supports structured JSON output, and lets you trade speed for depth with a low, medium, or high thinking level.
Google Gemini 3.1 Pro is a very good language model developed by Google. It offers fast and efficient text generation and it works well with any other Google services. The Google Gemini 3.1 Pro model can receive videos as input which means it can literally analyze videos as if it watched the video.
OpenAI GPT Image 2 is their most capable image model. It reasons before generating, renders text reliably (including non-Latin scripts), and outputs up to 2K. Best for product shots, UI mockups, ads, and anything where on-brand text has to come out right the first time.
OpenAI GPT-5.6 Terra is the balanced mid-tier model in the GPT-5.6 family, designed to balance intelligence and cost. It handles chat, content generation, and everyday coding very well at half the cost of the flagship GPT-5.6.
OpenAI GPT-5.6 Luna is the fastest and cheapest member of the GPT-5.6 family, optimized for high-volume workloads. Great for chat, classification, and content generation when you want quick responses at a low cost.
Claude Haiku 5.5 is Anthropic's fastest and cheapest model, built for high-volume work like chat, classification, extraction, and routing, with a 1M-token context and adaptive thinking. Prompts over 100,000 tokens cost 5x more.
Grok 4.6 is xAI's flagship model, great at coding and agentic tasks with real-time web and X search — and it is much more fun to talk to. Grok is generally less scripted and will speak its mind more freely. It's also trained on a lot of Twitter data, so it just has a different personality than the rest of the AI chatbots.
GLM 5.3 is Z.ai's flagship reasoning model, built for coding, agentic tasks, and long-running tool use at a fraction of frontier pricing. Thinking is on by default and can be disabled per request for fast replies.
Muse Wonder is Meta's frontier model for agentic work: it plans multi-step tasks, calls tools in parallel, and recovers from tool errors. Reasoning is always on; set reasoning_effort to "low" for quick replies.
Seedance 2.5 is ByteDance's newest video model. It reasons about the whole shot at once, so motion, lighting, and subject identity stay coherent from the first frame to the last — up to 30 seconds in a single shot. Supports text-to-video and image-to-video with generated audio. Expensive: a 5 second 720p clip costs $2.84.
Google Gemini 3.8 Flash is Google's fast and cost-efficient workhorse model. It handles chat, coding, and agentic tasks with quick responses at a fraction of the cost of Gemini Pro. Like the Pro model, it accepts text, images, video, audio, and PDFs as input, so it can analyze almost any content you throw at it.
Nano Banana 2.1 is Google's newest image generation and editing model, an update to Nano Banana 2 with better visual quality, more accurate text, and steadier characters across multi-turn edits. It renders 1K, 2K, or 4K, accepts up to 14 reference images, and costs about half as much per image as Nano Banana 2.
Channel3 is the API for products — search almost any product online by text, image, or URL across thousands of brands and retailers. Results come back with clean images, current prices, availability, and buy links, with filters for price, brand, and category. Perfect for building shopping apps, gift finders, price comparison tools, and AI shopping assistants. Many brands even pay commissions when users buy through your links.
OpenAI GPT-5.4 Mini is OpenAI's strongest mini model for coding and high-volume workloads. It's very good at chatting, content generation, and coding while optimizing for speed and cost.
OpenAI GPT-5.4 Nano is the most cost-effective model OpenAI offers. Lightning-fast responses for simple tasks, basic conversations, and quick queries.
Grok 4.3 is xAI's affordable model. Quick and inexpensive, great for chat and everyday tasks while maintaining Grok's fun, unfiltered personality. Still trained on Twitter data, so it has a different personality than the rest of the AI chatbots.
GLM 5.3 Flash is the fast, multimodal sibling of GLM 5.3. Near-flagship quality for chat, summarisation, and lightweight agent steps at roughly a tenth of the cost.
Sora 2 is optimized for speed and iteration. Generate draft-quality videos quickly for concepting, social content, and rapid experimentation. Supports text-to-video with optional first-frame reference images.
Sora 2 Pro produces higher fidelity, more stable results suitable for production-quality video. Expect longer render times and higher cost. Ideal for cinematic shots, ads, and polished assets.
Seedance 2.0 is the cheaper, faster ByteDance video model. Clips run up to 15 seconds and it can render all the way to 4K. Supports text-to-video and image-to-video with generated audio. A 5 second 720p clip costs $1.86.
OpenAI GPT-5.6 using the Responses API with native streaming support. Perfect for real-time chat interfaces with live text updates as the AI responds. Supports text generation, multi-turn conversations, and image analysis with efficient SSE-based streaming.
OpenAI GPT-4o Audio Transcription provides highly accurate speech-to-text conversion powered by advanced AI models. It supports multiple languages, handles various accents and audio qualities. Ideal for converting voice recordings, podcasts, meetings, and other audio content into text.
ElevenLabs Flash 2.5 Text-to-Speech is the fastest text-to-speech model available. This is a great model for when you want speech in your apps and allows you to make chatbots respond with voice.
ElevenLabs Sound Effects allows you to generate sound effects from a text prompt. This is great for videos and this is great for when you want to create a sound effect when you press a button in your app.
ElevenLabs Music is a great text-to-music model. It can generate songs with or without lyrics, whether it's for instrumentals, background music, a music video, or a funny meme. You can generate music for any purpose you need.
ElevenLabs Speech to Speech converts any recorded voice into a selected target voice while preserving the original emotion, timing, and delivery. Record your voice and instantly re-voice it in high quality. Perfect for voice changers, dubbing, creator voiceovers, and privacy use cases.
OpenAI GPT Image 1 is the best at generating clean icons and images without backgrounds. It's also excellent at creating cartoon-style characters and illustrations. Perfect for memes, app icons, and any graphics that need a fun, cartoon aesthetic with clear text integration.
OpenAI GPT Image 1.5 is the best at generating clean icons and images without backgrounds. It's also excellent at creating cartoon-style characters and illustrations. Perfect for memes, app icons, and any graphics that need a fun, cartoon aesthetic with clear text integration.
Nano Banana is the world's best AI image editing model. You can upload any image and edit it using simple, natural language instructions. No need to worry about layers or complex editing tools - just tell it what you want to change and it will smartly edit only the parts you specify.
Ideogram 3.0 is a great image generation model with a unique superpower: character references. With just a single image, you can generate new images featuring that same character in different scenes and situations. Perfect for creating consistent characters across your app.
Apple Maps provides comprehensive mapping, location services, and geocoding capabilities. It offers access to map data, directions, place search, and location-based features with seamless integration for iOS and macOS applications.
The Movie Database (TMDB) is a comprehensive entertainment database providing detailed information about movies, TV shows, actors, and crew. It offers rich metadata including ratings, reviews, cast information, images, and streaming availability for building media and entertainment applications.
OpenWeather API provides comprehensive weather data including current conditions, forecasts, historical weather, and climate information. It offers real-time weather updates, hourly and daily forecasts, weather maps, and alerts for any location worldwide.
Stock Market Data powered by Alpha Vantage provides real-time and historical stock market information. Access equity prices, technical indicators, company fundamentals, and market analytics for building financial applications, trading tools, and investment trackers.
Crypto Market Data powered by Alpha Vantage provides real-time and historical cryptocurrency market information. Access digital currency prices, exchange rates, market cap data, and technical indicators for Bitcoin, Ethereum, and other cryptocurrencies to build crypto tracking and trading applications.