📏
Memory & Context
Large Context Window
The maximum amount of text (tokens) the AI can hold in its short-term memory at once. A large context (100k+) means it can read entire books in one prompt.
Which AI has Large Context Window?
15 of 108 tools in the CanIUse matrix support Large Context Window. Open a tool-by-feature answer for the exact plan and source.
Which AI tools support this?
| Tool | Status | Notes | Link |
|---|---|---|---|
| 🤖 ChatGPT | Partial | Standard context | Try ChatGPT (opens in a new tab) |
| 🧠 Claude | Yes | 1M+ tokens | Try Claude (opens in a new tab) |
| ✨ Google Gemini | Yes | 1M+ tokens | Try Google Gemini (opens in a new tab) |
| 🐋 DeepSeek | Yes | 64k tokens | Try DeepSeek (opens in a new tab) |
| 🎨 Midjourney | No | Auto populated | Try Midjourney (opens in a new tab) |
| ✏️ Recraft | No | Not a language model, so this does not apply. | Try Recraft (opens in a new tab) |
| 🖌️ Canva Magic Studio | No | Not a language model, so this does not apply. | Try Canva Magic Studio (opens in a new tab) |
| 🔥 Adobe Firefly | No | Not a language model, so this does not apply. | Try Adobe Firefly (opens in a new tab) |
| 🎥 HeyGen | No | Not a language model, so this does not apply. | Try HeyGen (opens in a new tab) |
| 🎬 Runway | No | Not a language model, so this does not apply. | Try Runway (opens in a new tab) |
| ⚡ Pika | No | Not a language model, so this does not apply. | Try Pika (opens in a new tab) |
| 🎙️ ElevenLabs | No | — | Try ElevenLabs (opens in a new tab) |
| 🎧 Descript | No | — | Try Descript (opens in a new tab) |
| 🎵 Suno | No | Not a language model, so this does not apply. | Try Suno (opens in a new tab) |
| 🎼 Udio | No | Not a language model, so this does not apply. | Try Udio (opens in a new tab) |
| 🕸️ Graphify | No | Not a language model, so this does not apply. | Try Graphify (opens in a new tab) |
| 📊 Napkin AI | No | Not a language model, so this does not apply. | Try Napkin AI (opens in a new tab) |
| 📐 Eraser | No | Not a language model, so this does not apply. | Try Eraser (opens in a new tab) |
| 💡 Whimsical | No | Not a language model, so this does not apply. | Try Whimsical (opens in a new tab) |
| 📌 Miro AI | No | Not a language model, so this does not apply. | Try Miro AI (opens in a new tab) |
| 🔮 Gamma | No | — | Try Gamma (opens in a new tab) |
| 📝 Notion AI | Partial | Bound by the underlying model; Notion does not publish a figure. | Try Notion AI (opens in a new tab) |
| 📈 Julius AI | Partial | Bound by the underlying model; not published as a headline figure. | Try Julius AI (opens in a new tab) |
| 💻 Cursor | Yes | Each chat has a fixed model context window with a usage ring. Cloud Agents let you pick context size; several models document up to 1M-token extended context. | Try Cursor (opens in a new tab) |
| ⚡ v0 | Yes | Auto populated | Try v0 (opens in a new tab) |
| 🐙 GitHub Copilot | Yes | Large codebase context | Try GitHub Copilot (opens in a new tab) |
| 🏄 Windsurf | Partial | Indexes the whole repository; the usable window depends on the selected model. | Try Windsurf (opens in a new tab) |
| 🤖 Microsoft Copilot | Partial | Standard context | Try Microsoft Copilot (opens in a new tab) |
| 🧠 Grok | Partial | Standard context | Try Grok (opens in a new tab) |
| 🔍 Perplexity AI | Partial | Standard context | Try Perplexity AI (opens in a new tab) |
| 🌬️ Mistral AI | Partial | Standard context | Try Mistral AI (opens in a new tab) |
| 🦙 Meta AI | Partial | Standard context | Try Meta AI (opens in a new tab) |
| 🦙 Llama | Yes | 128k tokens | Try Llama (opens in a new tab) |
| 🥧 Pi by Inflection | Partial | Holds long conversations, but no context size is published. | Try Pi by Inflection (opens in a new tab) |
| 🎯 Cohere | Yes | 128k tokens | Try Cohere (opens in a new tab) |
| 🤗 HuggingChat | Yes | Depends on selected model | Try HuggingChat (opens in a new tab) |
| ❓ Poe by Quora | Partial | Depends on which model you pick; Poe routes to many providers. | Try Poe by Quora (opens in a new tab) |
| 👤 Character.AI | Partial | Long chats are summarised as they grow rather than kept in full. | Try Character.AI (opens in a new tab) |
| ✍️ Jasper | Partial | Standard context | Try Jasper (opens in a new tab) |
| 🖊️ Writesonic | Partial | Standard context | Try Writesonic (opens in a new tab) |
| 📝 Copy.ai | Yes | Auto populated | Try Copy.ai (opens in a new tab) |
| 📄 Rytr | No | — | Try Rytr (opens in a new tab) |
| 🌍 DeepL | No | Auto populated | Try DeepL (opens in a new tab) |
| 🎨 Krea | No | Not a language model, so this does not apply. | Try Krea (opens in a new tab) |
| 🖼️ Leonardo.Ai | No | Not a language model, so this does not apply. | Try Leonardo.Ai (opens in a new tab) |
| 📢 AdCreative.ai | No | — | Try AdCreative.ai (opens in a new tab) |
| 🎥 Sora | No | Not a language model, so this does not apply. | Try Sora (opens in a new tab) |
| 👨🎤 Synthesia | No | Auto populated | Try Synthesia (opens in a new tab) |
| 🎙️ Murf AI | No | — | Try Murf AI (opens in a new tab) |
| 📹 Fliki | No | — | Try Fliki (opens in a new tab) |
| ✨ Luma Dream Machine | No | Not a language model, so this does not apply. | Try Luma Dream Machine (opens in a new tab) |
| ⚡ Bolt New | Yes | Auto populated | Try Bolt New (opens in a new tab) |
| 💖 Lovable | Yes | Auto populated | Try Lovable (opens in a new tab) |
| 🔎 You.com | Partial | Depends on which underlying model the query is routed to. | Try You.com (opens in a new tab) |
| ⬆️ HighLevel | Partial | Depends on the model configured for the workflow. | Try HighLevel (opens in a new tab) |
| ⌨️ Claude Code | Yes, requires pro plan | Indexes the repository; Pro lists a 200k context window for Claude. | Try Claude Code (opens in a new tab) |
| ☄️ Comet | Unknown | No token window is published for the Comet assistant. | Try Comet (opens in a new tab) |
| 🎞️ Veo 3 | No | Prompt cap is 1,024 tokens on the Gemini API Veo 3.1 card — not a large LLM context window. | Try Veo 3 (opens in a new tab) |
| 🎥 Kling AI | No | Not an LLM context-window product. Clip length is 3–15 seconds on VIDEO 3.0. | Try Kling AI (opens in a new tab) |
| 📓 NotebookLM | Unknown | Google publishes source-count limits, not a token window for Gemini Notebook chat. | Try NotebookLM (opens in a new tab) |
| 🛸 Google Antigravity | Unknown | Uses Gemini agent models; no token window is published on the Antigravity plans page. | Try Google Antigravity (opens in a new tab) |
| 🧭 Kiro | Unknown | Uses multiple FMs via Bedrock/Auto. No token window is published on the pricing page. | Try Kiro (opens in a new tab) |
| ⬛ FLUX | No | Not an LLM context-window product. | Try FLUX (opens in a new tab) |
| 🌀 Stable Diffusion | No | Not an LLM context-window product. | Try Stable Diffusion (opens in a new tab) |
| 🔤 Ideogram | No | Not an LLM context-window product. | Try Ideogram (opens in a new tab) |
| 🐰 CodeRabbit | Unknown | No token window is published on the pricing page. | Try CodeRabbit (opens in a new tab) |
| 🧃 Replit | Unknown | Intelligent model routing is documented; no token window is published on pricing. | Try Replit (opens in a new tab) |
| 🤝 Aider | Unknown | Depends on the LLM you connect. No window is published as an Aider product spec. | Try Aider (opens in a new tab) |
| 🚀 Warp | Unknown | You pick models (Claude, GPT, Gemini, etc.). No single window is published. | Try Warp (opens in a new tab) |
| 🔷 Tabnine | Unknown | Depends on the connected LLM. No window is published as a Tabnine spec. | Try Tabnine (opens in a new tab) |
| 📝 Grammarly | No | Not an LLM context-window product. Generative prompts are metered (100 free / 2,000 Pro). | Try Grammarly (opens in a new tab) |
| 🔗 n8n | Unknown | Depends on the model you connect. No n8n token window is published. | Try n8n (opens in a new tab) |
| ⚡ Groq | Unknown | Depends on the hosted model. No single Groq window is on the quickstart page. | Try Groq (opens in a new tab) |
| 🔀 OpenRouter | Yes, requires plus plan | Window is whatever the selected model publishes. Catalog is at openrouter.ai/models. | Try OpenRouter (opens in a new tab) |
| 🤗 Hugging Face | Unknown | Depends on the model you load. No Hub-wide window. | Try Hugging Face (opens in a new tab) |
| 🎙️ Whisper | No | Not an LLM context-window product. | Try Whisper (opens in a new tab) |
| 🦞 OpenClaw | Unknown | Window size is the model you bring (ChatGPT sign-in, Claude Max, etc.). OpenClaw does not publish its own token limit. | Try OpenClaw (opens in a new tab) |
| 🦦 Otter.ai | No | Not an LLM context-window product. Limits are minutes, not tokens. | Try Otter.ai (opens in a new tab) |
| ⚡ Zapier | No | Task allowances, not a published LLM context window. | Try Zapier (opens in a new tab) |
| ✨ Genspark | Unknown | No token window is published on the homepage. | Try Genspark (opens in a new tab) |
| 🔥 Fireflies.ai | No | Limits are storage/minutes, not an LLM token window. | Try Fireflies.ai (opens in a new tab) |
| 🌊 Fathom | No | Not an LLM token-window product. | Try Fathom (opens in a new tab) |
| 🖼️ Photoroom | No | Not an LLM context-window product. | Try Photoroom (opens in a new tab) |
| 🦜 LangChain | Unknown | Depends on the model you choose. No LangChain token window. | Try LangChain (opens in a new tab) |
| ♻️ Replicate | Unknown | Depends on the model you run. No single Replicate window. | Try Replicate (opens in a new tab) |
| 🤝 Together AI | Unknown | Depends on the open model you host. No single Together window on the homepage. | Try Together AI (opens in a new tab) |
| 📐 Linear | No | Issue limits (250 on Free), not an LLM token window. | Try Linear (opens in a new tab) |
| ✅ ClickUp | Unknown | No token window is published. Brain² “picks the best model”. | Try ClickUp (opens in a new tab) |
| 🌸 Asana | No | Not an LLM token-window product. | Try Asana (opens in a new tab) |
| 🔗 Make | No | Operations quota, not an LLM token window. | Try Make (opens in a new tab) |
| 🎨 Figma | No | AI credits, not a published token window. | Try Figma (opens in a new tab) |
| ✨ Adobe Express | No | Not an LLM context-window product. | Try Adobe Express (opens in a new tab) |
| 🪶 QuillBot | Unknown | Word limits were not fetched this round. | Try QuillBot (opens in a new tab) |
| 📝 Wordtune | Unknown | No token window on the homepage. | Try Wordtune (opens in a new tab) |
| 📊 Beautiful.ai | Unknown | No token window on the homepage. | Try Beautiful.ai (opens in a new tab) |
| 📕 Tome | No | No live product at tome.app. | Try Tome (opens in a new tab) |
| 🪨 Amazon Bedrock | Unknown | Depends on the foundation model you invoke. No single Bedrock window. | Try Amazon Bedrock (opens in a new tab) |
| ☁️ Azure OpenAI Service | Yes, requires plus plan | Depends on the deployed model; gpt-chat-latest lists a 400k context window. | Try Azure OpenAI Service (opens in a new tab) |
| 🔺 Vertex AI | Unknown | Depends on the Gemini/model version deployed. | Try Vertex AI (opens in a new tab) |
| 🌲 Pinecone | No | Retrieval layer, not an LLM context window. | Try Pinecone (opens in a new tab) |
| 🗣️ D-ID | Unknown | Agent context limits were not published on the homepage. | Try D-ID (opens in a new tab) |
| 🎙️ Deepgram | Unknown | Agent context limits were not on the homepage snippet. | Try Deepgram (opens in a new tab) |
| 🎧 AssemblyAI | Unknown | Agent context limits were not checked. | Try AssemblyAI (opens in a new tab) |
| 📻 Adobe Podcast | No | Audio processor, not an LLM. | Try Adobe Podcast (opens in a new tab) |
| 🎵 Stable Audio | No | Not an LLM chat product. | Try Stable Audio (opens in a new tab) |
| 🎬 InVideo | Unknown | Agent context limits were not published. | Try InVideo (opens in a new tab) |
| ⌨️ Raycast AI | Unknown | Depends on the selected model (32+ providers). | Try Raycast AI (opens in a new tab) |
| ⚡ Superhuman | Unknown | Depends on underlying models. Not published on homepage. | Try Superhuman (opens in a new tab) |