Skip to main content
💻
Modalities

Code Execution

The AI can write and securely execute real code (like Python) in a sandbox to perform math, analyze data, or generate charts.

Which AI has Code Execution?

25 of 108 tools in the CanIUse matrix support Code Execution. Open a tool-by-feature answer for the exact plan and source.

Which AI tools support this?

ToolStatusNotesLink
🤖 ChatGPTYes, requires plus planAdvanced Data AnalysisTry ChatGPT (opens in a new tab)
🧠 ClaudeNo—Try Claude (opens in a new tab)
✨ Google GeminiYes—Try Google Gemini (opens in a new tab)
🐋 DeepSeekYes—Try DeepSeek (opens in a new tab)
🎨 MidjourneyNoAuto populatedTry Midjourney (opens in a new tab)
✏️ RecraftNoNot a code tool.Try Recraft (opens in a new tab)
🖌️ Canva Magic StudioNoNot a code tool.Try Canva Magic Studio (opens in a new tab)
🔥 Adobe FireflyNoNot a code tool.Try Adobe Firefly (opens in a new tab)
🎥 HeyGenNoNot a code tool.Try HeyGen (opens in a new tab)
🎬 RunwayNoNot a code tool.Try Runway (opens in a new tab)
⚡ PikaNoNot a code tool.Try Pika (opens in a new tab)
🎙️ ElevenLabsNo—Try ElevenLabs (opens in a new tab)
🎧 DescriptNo—Try Descript (opens in a new tab)
🎵 SunoNoNot a code tool.Try Suno (opens in a new tab)
🎼 UdioNoNot a code tool.Try Udio (opens in a new tab)
🕸️ GraphifyNoParses code with static analysis rather than executing it.Try Graphify (opens in a new tab)
📊 Napkin AINoNot a code tool.Try Napkin AI (opens in a new tab)
📐 EraserNoReads code to draw diagrams but does not execute it.Try Eraser (opens in a new tab)
💡 WhimsicalNoNot a code tool.Try Whimsical (opens in a new tab)
📌 Miro AINoNot a code tool.Try Miro AI (opens in a new tab)
🔮 GammaNo—Try Gamma (opens in a new tab)
📝 Notion AINo—Try Notion AI (opens in a new tab)
📈 Julius AIYesWrites and runs Python to analyse data and plot charts.Try Julius AI (opens in a new tab)
💻 CursorYesAgent runs shell commands in the terminal, watches output, and can execute tests, linters, and builds as part of a task.Try Cursor (opens in a new tab)
⚡ v0YesAuto populatedTry v0 (opens in a new tab)
🐙 GitHub CopilotYesSpark/Codespaces integrationTry GitHub Copilot (opens in a new tab)
🏄 WindsurfYesCascade runs terminal commands and tests as part of an agentic loop.Try Windsurf (opens in a new tab)
🤖 Microsoft CopilotNo—Try Microsoft Copilot (opens in a new tab)
🧠 GrokNo—Try Grok (opens in a new tab)
🔍 Perplexity AINo—Try Perplexity AI (opens in a new tab)
🌬️ Mistral AINo—Try Mistral AI (opens in a new tab)
🦙 Meta AINo—Try Meta AI (opens in a new tab)
🦙 LlamaNo—Try Llama (opens in a new tab)
🥧 Pi by InflectionNo—Try Pi by Inflection (opens in a new tab)
🎯 CohereNo—Try Cohere (opens in a new tab)
🤗 HuggingChatNo—Try HuggingChat (opens in a new tab)
❓ Poe by QuoraNo—Try Poe by Quora (opens in a new tab)
👤 Character.AINo—Try Character.AI (opens in a new tab)
✍️ JasperNo—Try Jasper (opens in a new tab)
🖊️ WritesonicNo—Try Writesonic (opens in a new tab)
📝 Copy.aiPartialAuto populatedTry Copy.ai (opens in a new tab)
📄 RytrNo—Try Rytr (opens in a new tab)
🌍 DeepLNoAuto populatedTry DeepL (opens in a new tab)
🎨 KreaNoNot a code tool.Try Krea (opens in a new tab)
🖼️ Leonardo.AiNoNot a code tool.Try Leonardo.Ai (opens in a new tab)
📢 AdCreative.aiNo—Try AdCreative.ai (opens in a new tab)
🎥 SoraNoNot a code tool.Try Sora (opens in a new tab)
👨‍🎤 SynthesiaNoAuto populatedTry Synthesia (opens in a new tab)
🎙️ Murf AINo—Try Murf AI (opens in a new tab)
📹 FlikiNo—Try Fliki (opens in a new tab)
✨ Luma Dream MachineNoNot a code tool.Try Luma Dream Machine (opens in a new tab)
⚡ Bolt NewYesAuto populatedTry Bolt New (opens in a new tab)
💖 LovableYesAuto populatedTry Lovable (opens in a new tab)
🔎 You.comYes—Try You.com (opens in a new tab)
⬆️ HighLevelNo—Try HighLevel (opens in a new tab)
⌨️ Claude CodeYes, requires pro planRuns shell commands, tests, and git operations as part of the agent loop.Try Claude Code (opens in a new tab)
☄️ CometUnknownThe marketing site shows the assistant building a webpage in the browser; that is not a documented code sandbox.Try Comet (opens in a new tab)
🎞️ Veo 3NoNot a code-execution product.Try Veo 3 (opens in a new tab)
🎥 Kling AINoNot a code-execution product.Try Kling AI (opens in a new tab)
📓 NotebookLMYes, requires pro planA secure cloud computer can write and run code in the notebook. Google says Ultra and some Workspace tiers have it now; Pro on the web is rolling out.Try NotebookLM (opens in a new tab)
🛸 Google AntigravityYes, requires free planThe CLI runs shell commands and coding agents. The IDE agent edits and verifies in the project.Try Google Antigravity (opens in a new tab)
🧭 KiroYes, requires free planAgents implement, test, and can run headless in CI. Web sessions run in isolated sandboxes.Try Kiro (opens in a new tab)
⬛ FLUXNoYou run inference code; the model does not execute your Python.Try FLUX (opens in a new tab)
🌀 Stable DiffusionNoYou run inference; the model does not execute your Python.Try Stable Diffusion (opens in a new tab)
🔤 IdeogramNoNot a code-execution sandbox.Try Ideogram (opens in a new tab)
🐰 CodeRabbitPartialCloud Coding Agent can open PRs. Reviews themselves comment; they do not run your app.Try CodeRabbit (opens in a new tab)
🧃 ReplitYes, requires free planThe IDE runs code, hosts apps, and can keep a background task running. Agent writes production-ready code.Try Replit (opens in a new tab)
🤝 AiderYes, requires free planAutomatically lint and test after changes; can fix what those tools report.Try Aider (opens in a new tab)
🚀 WarpYes, requires free planThe terminal runs commands; agents can execute in the shell and open PRs.Try Warp (opens in a new tab)
🔷 TabninePartialAgentic workflows and CLI can change code, test, and open PRs. Completions-only is not a sandbox executor.Try Tabnine (opens in a new tab)
📝 GrammarlyNoDoes not run code.Try Grammarly (opens in a new tab)
🔗 n8nYes, requires free planJavaScript or Python anywhere in a workflow; bash scripts; custom nodes.Try n8n (opens in a new tab)
⚡ GroqYes, requires free planBuilt-in tools on Compound / gpt-oss include safe code execution on Groq infrastructure.Try Groq (opens in a new tab)
🔀 OpenRouterNoYou implement tools via the Agent SDK. OpenRouter does not sandbox your Python.Try OpenRouter (opens in a new tab)
🤗 Hugging FaceYes, requires free planSpaces run apps (including ZeroGPU). Inference Endpoints serve models.Try Hugging Face (opens in a new tab)
🎙️ WhisperNoYou run inference. The model does not execute your code.Try Whisper (opens in a new tab)
🦞 OpenClawYes, requires free planMicrosoft Execution Containers / sandbox quotes describe running agent code. Skills can execute on your machine.Try OpenClaw (opens in a new tab)
🦦 Otter.aiNoNot a code sandbox.Try Otter.ai (opens in a new tab)
⚡ ZapierPartialCode by Zapier / webhooks on Professional. Not a general Python notebook.Try Zapier (opens in a new tab)
✨ GensparkUnknownGenTerminal is listed by name. Sandbox execution was not documented.Try Genspark (opens in a new tab)
🔥 Fireflies.aiNoNot a code sandbox.Try Fireflies.ai (opens in a new tab)
🌊 FathomNoNot a code sandbox.Try Fathom (opens in a new tab)
🖼️ PhotoroomNoNot a code sandbox.Try Photoroom (opens in a new tab)
🦜 LangChainYes, requires plus planDeploy path: run agent-generated code in isolated sandboxes.Try LangChain (opens in a new tab)
♻️ ReplicateNoYou call models. Cog packages your code; that is deploy, not a user Python sandbox in chat.Try Replicate (opens in a new tab)
🤝 Together AIYes, requires plus planCode sandboxes are listed on the product page.Try Together AI (opens in a new tab)
📐 LinearYes, requires free planCoding sessions: Linear Agent can set up, run, and test code before returning work (changelog on homepage).Try Linear (opens in a new tab)
✅ ClickUpPartialCodegen Agent is advertised. That is agent code, not a user Python sandbox in chat.Try ClickUp (opens in a new tab)
🌸 AsanaNoNot a code sandbox. StackAI workflows are automation, not a notebook.Try Asana (opens in a new tab)
🔗 MakeUnknownA custom-code module was not confirmed this round.Try Make (opens in a new tab)
🎨 FigmaPartialFigma Make and MCP can produce code/PRs. That is codegen, not a Python sandbox in chat.Try Figma (opens in a new tab)
✨ Adobe ExpressNoNot a code sandbox.Try Adobe Express (opens in a new tab)
🪶 QuillBotNoNot a code sandbox.Try QuillBot (opens in a new tab)
📝 WordtuneNoNot a code sandbox.Try Wordtune (opens in a new tab)
📊 Beautiful.aiNoNot a code sandbox.Try Beautiful.ai (opens in a new tab)
📕 TomeNoNever a code sandbox; URL is 404.Try Tome (opens in a new tab)
🪨 Amazon BedrockPartialAgents can call tools and Lambdas. No first-party Python sandbox in chat.Try Amazon Bedrock (opens in a new tab)
☁️ Azure OpenAI ServiceUnknownCode interpreter on Azure OpenAI was not verified on the catalog page.Try Azure OpenAI Service (opens in a new tab)
🔺 Vertex AIPartialColab Enterprise and notebooks for code. Not a chat Python sandbox.Try Vertex AI (opens in a new tab)
🌲 PineconeNoDatabase and inference APIs, not a code sandbox.Try Pinecone (opens in a new tab)
🗣️ D-IDNoVideo/avatar platform, not a code sandbox.Try D-ID (opens in a new tab)
🎙️ DeepgramNoSTT/TTS APIs, not a code sandbox.Try Deepgram (opens in a new tab)
🎧 AssemblyAINoSTT APIs, not a code sandbox.Try AssemblyAI (opens in a new tab)
📻 Adobe PodcastNoNot a code product.Try Adobe Podcast (opens in a new tab)
🎵 Stable AudioNoNot a code sandbox.Try Stable Audio (opens in a new tab)
🎬 InVideoNoVideo editor, not a code sandbox.Try InVideo (opens in a new tab)
⌨️ Raycast AIUnknownWhether AI runs code locally was not confirmed.Try Raycast AI (opens in a new tab)
⚡ SuperhumanNoNot a code sandbox.Try Superhuman (opens in a new tab)