Video Generation in ChatGPT After Sora: Veo, Seedance & More (2026)
Sora is being discontinued - which leaves a gap if you’ve been generating video inside ChatGPT. The good news: you can keep generating video in ChatGPT with CreativeClaw. Connect one app and ChatGPT gains access to Gemini Omni Flash, Grok Imagine, FLUX 3, MiniMax H3, Seedance, LTX, Veo, Kling, and more. Describe the shot, and ChatGPT delivers a finished video inline.
This guide covers the video models worth connecting in ChatGPT now that Sora is winding down, how to pick one, and how async generation works.
Why use CreativeClaw for video generation in ChatGPT?
ChatGPT already generates images with GPT Image and video with Sora - but you're locked to OpenAI's own models. CreativeClaw adds the models OpenAI doesn't ship: Google's Nano Banana and Veo, ByteDance's Seedance, ElevenLabs voices, Flux, Recraft, and more - all without leaving ChatGPT. Here's why it's the simplest way to use video generation in ChatGPT:
- Models OpenAI doesn't have - video generation isn't part of ChatGPT natively. CreativeClaw connects it and dozens of other curated models through one app, so you can use the best model for the job instead of whatever's built in.
- No API keys, no extra accounts - You don't need a Google, ByteDance, or ElevenLabs account. Connect one app and every model is available instantly.
- No subscriptions - Pay only for what you generate. $10 = 1,000 credits. No monthly fees, credits never expire.
- Results inline in ChatGPT - Generated media previews right inside the conversation. No tab-switching, no downloads to manage.
- Let ChatGPT iterate - ChatGPT generates, looks at the result, refines the prompt, and regenerates - all in one conversation. Your assistant becomes your creative director.
- Works in ChatGPT and Codex - CreativeClaw is a remote MCP server. Use it from ChatGPT or the Codex CLI - same account, same models, wherever you work.
Sora is going away - what should you use instead?
Sora was ChatGPT’s built-in video model. With it being discontinued, the strongest replacements are models OpenAI never offered in-chat:
- Google Omni - the recommended default for quality, speed, and value.
- Seedance 2.0 (ByteDance) - director-level camera control and native audio for premium shots.
- Veo 3.1 (Google) - up to 4K resolution with synchronized audio. The premium option for hero content.
- Kling and MiniMax Hailuo - strong on facial expression and budget batch work respectively.
All of them run through CreativeClaw inside ChatGPT - no Sora, no separate accounts.
Compare the video models
| Model | Best for | Resolution | Duration | Credits (5s) | Guide |
|---|---|---|---|---|---|
| Gemini Omni Flash | Recommended default | 720p | Model-dependent | ~130 | Full guide |
| Grok Imagine 1.5 | Flexible generation and references | 480p-1080p | Model-dependent | ~140 at 720p | - |
| FLUX 3 | Draft through premium video | 720p-1080p | Model-dependent | ~55-265 | - |
| MiniMax H3 | Multimodal references, native audio | 768p-2K | Model-dependent | ~160-260 | - |
| LTX 2.3 Fast | Low-cost generation and transforms | Model-dependent | Up to 20s | ~60 | - |
| Seedance 2.0 | Director control, #1 benchmark | 1080p | Up to 15s | ~305 | Full guide |
| Veo 3.1 | Premium quality, 4K | Up to 4K | 4-8s | ~400 | Full guide |
| Kling v3 Pro | Facial expressions | 720p-1080p | 5-10s | 50-280 | - |
| MiniMax Hailuo | Budget-friendly | 768p-1080p | 6-10s | 50-98 | - |
How to choose the right model
- Want the recommended default? - Gemini Omni Flash balances quality, speed, and value. Start here.
- Need 4K or the highest fidelity? - Veo 3.1 from Google, with built-in audio.
- Need realistic facial expressions? - Kling v3 Pro excels at human faces and emotion.
- Generating high volume on a budget? - MiniMax Hailuo delivers solid clips at the lowest cost.
For most marketing and social use cases, start with Gemini Omni Flash, then switch to Seedance, Veo, Kling, or another specialist when the brief calls for it.
How video generation works in ChatGPT
Video generation is asynchronous - it takes longer than images, so ChatGPT handles it in the background:
- You describe the video. “Create a 5-second product reveal of a sneaker rotating on a dark background using Gemini Omni Flash.”
- ChatGPT submits the job. CreativeClaw sends it to the selected model and returns a job ID.
- ChatGPT polls automatically. It checks the status until the clip is ready - you can keep chatting meanwhile.
- Video is delivered. Usually 30 seconds to 2 minutes later, the finished video appears in the conversation.
How to get started
- Connect CreativeClaw in ChatGPT. Open the apps menu, search Creative Claw, enable it, and sign in. See the setup guide.
- Ask ChatGPT to generate a video. Start simple - “Generate a 5-second clip of ocean waves at sunset with Gemini Omni Flash.”
- Iterate. Change the camera, lighting, or duration in the same conversation.
Setup in ChatGPT (and Codex)
ChatGPT (web, desktop, mobile) - Open the apps menu in the message composer, search for Creative Claw, enable it, and sign in. From then on, ask ChatGPT to generate and it uses the connected models. See the full setup guide.
Codex CLI - Add CreativeClaw as a remote MCP server in your Codex configuration using the CreativeClaw MCP URL. Same account and models as ChatGPT, available from your terminal.
No API keys, no per-provider accounts. One connection gives you every supported model - and it's the same account whether you work in ChatGPT or Codex.
Pricing overview
$10 = 1,000 credits, credits never expire. Video uses more credits than images:
| Model | 5s clip | 10s clip |
|---|---|---|
| Veo 3.1 Lite | ~50 | ~100 |
| LTX 2.3 Fast | ~60 | ~120 |
| Gemini Omni Flash | ~130 | ~260 |
| Grok Imagine 1.5 (720p) | ~140 | ~280 |
| FLUX 3 (720p standard) | ~155 | ~310 |
| Seedance 2.0 | ~305 | ~610 |
| Seedance 2.0 Fast | ~245 | ~490 |
| Veo 3.1 | ~400 | ~400 |
Mix budget models for iteration and premium models for finals.
Frequently asked questions
Is Sora really being discontinued? Sora is winding down as a generation option. Rather than wait, you can connect CreativeClaw and generate with Veo 3.1 and Seedance 2.0 in ChatGPT today - models that match or beat Sora on quality.
Can I generate video from an existing image? Yes. Seedance, Veo, and Kling all support image-to-video. Upload a product photo or design and ask ChatGPT to animate it.
Can I add audio? Veo 3.1 and Seedance 2.0 generate synchronized audio automatically. For voiceover on any clip, generate speech with ElevenLabs through the same connection.
Does this work in Codex? Yes. CreativeClaw is a remote MCP server, so the same video models are available from the Codex CLI on the same account.
Ready to try it?
Connect CreativeClaw to Claude in under a minute.
Get Started