LLM
OpenAI
GPT-4.1, o3, and o3 Pro for text. GPT Image 2 for images. Sora 2 Pro for video. TTS-1 HD for speech. All from one canvas, your own key.
What you can do
Connect OpenAI across text, image, video, and audio. The Text node runs GPT-4.1, GPT-4.1 Mini, GPT-4o Mini, o3, and o3 Pro. The Image node runs GPT Image 2, GPT Image 1.5, and GPT Image 1 Mini. The Video node runs Sora 2 Pro and Sora 2. The Audio node runs TTS-1 and TTS-1 HD for text-to-speech.
- Text: GPT-4.1, GPT-4.1 Mini, GPT-4o Mini, o3, o3 Pro
- Image: GPT Image 2, GPT Image 1.5, GPT Image 1 Mini
- Video: Sora 2 Pro and Sora 2 text-to-video
- Audio: TTS-1 and TTS-1 HD text-to-speech
- System prompt, temperature, and max-tokens control
- Structured JSON output from text models
- BYO OpenAI API key, no PlugNode markup
Used in these workflows
All use casesAI engineers, product teams, prompt designersMulti-Model A/B TestingRun the same prompt through Gemini and OpenAI in parallel. Compare latency, token cost, and output quality on your actual production prompts.Content teams, product marketers, prompt designersMulti-Model ComparisonRun the same prompt through Gemini, OpenAI, and any other provider on the canvas. Compare outputs, latency, and cost on your actual content, not a benchmark leaderboard.
Related integrations
All integrationsLLMGeminiGoogle Gemini text and vision models on your canvas. Structured JSON output, streaming responses, frame-level reasoning. Bring your own key, pay Google directly.LLMAnthropicClaude Opus 4.7, Sonnet 4.6, and Haiku 4.5 for text generation and reasoning. Extended thinking, system prompts, structured output. BYO Anthropic key.LLMxAI (Grok)Grok 4.3 for text, Grok Image for stills, and Grok Video for clips. All three modalities from one provider, your own xAI key.
Generate your first video ad in 3 minutes.
Free to start. No credit card. Upload a product photo, connect your AI models, click Run.