What each AI can do
splitscreen rooms can ask Claude, GPT or Gemini. They are not the same, and the differences are the kind you only find out about halfway through a job. Here they are in one place, written out rather than ticked off.
Side by side
Swipe sideways to see GPT and Gemini.
| Feature | ClaudeAnthropic key | ChatGPTOpenAI key | GeminiGoogle key |
|---|---|---|---|
| Search the webIt looks things up while it answers, and shows what it read. | YesHaiku 4.5 searches with an earlier, plainer version of it. | Yes | Yes, on most modelsNot on Gemini Nano Banana 2.1, Gemini 3.1 Flash Image or Gemini 3 Pro Image. Those two make pictures and take no tools. |
| Read links you pastePaste a link and it opens that page instead of guessing at it. | Yes, on most modelsNot on Haiku 4.5. It rides the same switch as web search - there is no second chip. | YesGPT reads a pasted link through the same web search tool. | Yes, on most modelsNot on Gemini Nano Banana 2.1, Gemini 3.1 Flash Image or Gemini 3 Pro Image. Those two make pictures and take no tools. |
| Run code in a sandboxIt runs commands and edits files on the provider's own machines - never on yours. | Yes, on most modelsNot on Haiku 4.5. With the sandbox on, files you attach go into it too. | Yes | Yes, on most modelsNot on Gemini Nano Banana 2.1, Gemini 3.1 Flash Image or Gemini 3 Pro Image. Those two make pictures and take no tools. |
| Read files you attachDrop in a file. The note says which kinds each one reads. | YesImages and PDFs alike. Code and text files are read as text. With Code on, a .zip goes to the sandbox and the AI unzips it there. With Code off it is not opened. | YesImages are read. A PDF is not. An ask carrying one is refused before it costs anything - ask Claude or Gemini instead. Code and text files are read as text. With Code on, a .zip goes to the sandbox and the AI unzips it there. With Code off it is not opened. | YesImages and PDFs alike. Code and text files are read as text. A .zip cannot be opened here - its sandbox takes no files. Audio files are listened to. |
| Make imagesIt draws a picture and the room can open it. | NoClaude has no image generation. | YesIt is a tool on the ask, and it carries a per-image fee. | YesImage on a Gemini ask runs on Gemini Nano Banana 2.1, and turns search and the sandbox off for that ask. |
| Choose how hard it thinksA switch in the composer: think lightly, normally, or as hard as it can. | Yes, on most modelsNot on Haiku 4.5. The model menu calls it Low, Standard and High. | Yes | Yes, on most modelsNot on Gemini Nano Banana 2.1, Gemini 3.1 Flash Image or Gemini 3 Pro Image. Those two make pictures and take no tools. |
| How much it can read at onceHow much conversation, or how long a document, it can hold in one go. | YesSizes differ by model - each one is in the table below. | YesSizes differ by model - each one is in the table below. | YesSizes differ by model - each one is in the table below. |
Every answer above is read from the same table the app itself uses to build a request, so this page cannot claim something the room will not do.
Up to 5 GitHub repositories per room. Nothing reaches them until somebody presses Push, unless the owner pushes automatically.
Turn submodules on and the AI reads them at their pinned commit, only where the app is installed.
Every model you can pick
The same list the picker shows, in the same order, with the same tags. Older models stay on the list and are marked, because a room already pinned to one should still be able to see what it is. A tag says what a model is for, not whether your plan includes it: Fast marks the quick, cheap models (Haiku among them), and which models the free daily replies cover is on the pricing page.
Claude
on your Anthropic key, or on creditsThe default. Quick and capable for everyday work and code.
Anthropic's strongest. Deepest reasoning, at the top price.
Deep reasoning and long code. Always thinks, cheaper than Opus 5.
The previous Opus. Opus 5.5 replaces it, for less.
Fable 5.1 replaces it. Same price, a step behind.
An older Opus. Dearer than Opus 5.5 and a step behind.
The previous Sonnet. Same price as Sonnet 5.5.
The previous Haiku. Haiku 5.5 is newer and a tenth of the price.
Cheapest and fastest Claude. Search and sandbox, dearer past 100k tokens.
ChatGPT
on your OpenAI key, or on creditsThe default. Search, sandbox and images, half the price of 5.6 Sol.
Deepest GPT. Five times 6.1 Sol, dearer past 272k tokens.
The previous Sol. Twice the price of GPT-6.1 Sol.
Older everyday GPT. GPT-6.1 Sol is cheaper and newer.
The previous Luna. Over twice the price of GPT-6 Luna.
Cheapest GPT. Quick lookups and drafts.
Gemini
on your Google key, or on creditsThe default Gemini. Search, sandbox, huge context.
Deepest Gemini. Preview, and dearer past 200k tokens.
Previous Flash. Same price, a step behind.
Older Flash, kept for rooms that pinned it.
Older and dearer than 3.8.
Fast Gemini for quick lookups. A little dearer than 3.1 Flash-Lite.
Cheapest Gemini. Google shuts it down on 7 May 2027.
Makes images, with sharper text in pictures. No search or sandbox.
Makes images (Nano Banana 2). Nano Banana 2.1 replaces it.
Sharpest Gemini pictures (Nano Banana Pro), up to 4K. No tools.
"Last checked" is a real ask we paid for and watched work, most recently on 3 Oct 2026.
What a token is, since the rates are in them
Providers do not charge by the question, they charge by the piece of text. A token is about three quarters of an English word - so roughly 750 words is 1,000 tokens. You pay for what you send and for what it writes back, at different rates. What you send is the room's instructions, a short summary of the older part of the chat, and the last few exchanges word for word. Turn on "Use full chat" and the whole history goes instead. That is why a long conversation can cost more per reply than a short one, and it is why splitscreen shows you the price of one typical reply instead of the rates: nobody can do this arithmetic in their head, and nobody should have to.
Swipe sideways to see what one reply costs.
| Model | What you send | What it writes | One reply |
|---|---|---|---|
| Sonnet 5.5 · Claude | $2.60 / million | $13 / million | about 0.9¢ a reply |
| Fable 5.1 · Claude | $13 / million | $65 / million | about 4.6¢ a reply |
| Opus 5.5 · Claude | $5.20 / million | $26 / million | about 1.8¢ a reply |
| Opus 5 · Claude | $6.50 / million | $32.50 / million | about 2.3¢ a reply |
| Fable 5 · Claude | $13 / million | $65 / million | about 4.6¢ a reply |
| Opus 4.8 · Claude | $6.50 / million | $32.50 / million | about 2.3¢ a reply |
| Sonnet 5 · Claude | $2.60 / million | $13 / million | about 0.9¢ a reply |
| Haiku 4.5 · Claude | $1.30 / million | $6.50 / million | about 0.5¢ a reply |
| Haiku 5.5 · Claude | $0.13 / million | $0.65 / million | under 0.1¢ a reply |
| GPT-6.1 Sol · ChatGPT | $2.60 / million | $13 / million | about 0.9¢ a reply |
| GPT-6 Astra · ChatGPT | $13 / million | $65 / million | about 4.6¢ a reply |
| GPT-5.6 Sol · ChatGPT | $5.20 / million | $26 / million | about 1.8¢ a reply |
| GPT-5.6 Terra · ChatGPT | $2.60 / million | $15.60 / million | about 1¢ a reply |
| GPT-5.6 Luna · ChatGPT | $0.26 / million | $1.56 / million | about 0.1¢ a reply |
| GPT-6 Luna · ChatGPT | $0.13 / million | $0.65 / million | under 0.1¢ a reply |
| Gemini 3.8 Flash · Gemini | $0.97 / million | $4.88 / million | about 0.3¢ a reply |
| Gemini 3.1 Pro · Gemini | $2.60 / million | $15.60 / million | about 1¢ a reply |
| Gemini 3.7 Flash · Gemini | $0.97 / million | $4.88 / million | about 0.3¢ a reply |
| Gemini 3.6 Flash · Gemini | $0.97 / million | $4.88 / million | about 0.3¢ a reply |
| Gemini 3.5 Flash · Gemini | $1.95 / million | $11.70 / million | about 0.8¢ a reply |
| Gemini 3.5 Flash-Lite · Gemini | $0.39 / million | $3.25 / million | about 0.2¢ a reply |
| Gemini 3.1 Flash-Lite · Gemini | $0.33 / million | $1.95 / million | about 0.1¢ a reply |
| Gemini Nano Banana 2.1 · Gemini | $1.95 / million | $39 / million | about 2.1¢ a reply |
| Gemini 3.1 Flash Image · Gemini | $0.65 / million | $78 / million | about 4¢ a reply |
| Gemini 3 Pro Image · Gemini | $2.60 / million | $156 / million | about 8.1¢ a reply |
Prices shown are our credit prices. On your own API key you pay your provider’s rate, with no markup from us.
“One reply” is one fixed comparison - about 750 words in and 375 words back - priced on every model so the models can be compared. It is not a promise about your replies, which will be longer or shorter than that.