splitscreen
Start a room

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

FeatureClaudeAnthropic keyGPTOpenAI keyGeminiGoogle key
Search the webIt looks things up while it answers, and shows what it read.YesThe oldest Claude models search with an earlier, plainer version of it.YesYes, on most modelsNot on 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 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.YesYes, on most modelsNot on Gemini 3.1 Flash Image or Gemini 3 Pro Image. Those two make pictures and take no tools.
Read files you attachDrop in an image or a document and it reads it.YesImages and PDFs alike. Code and text files are read as text. A .zip goes into the code sandbox, where it is unzipped and explored.YesImages are read. A PDF is passed as a note naming the file, not its contents. Code and text files are read as text. A .zip goes into the code sandbox, where it is unzipped and explored.YesImages and PDFs alike. Code and text files are read as text. A .zip cannot be opened here - its sandbox takes no files.
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 3.1 Flash Image, 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 composer calls it Light, Standard and Max.YesYes, on most modelsNot on 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.

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.

Claude

runs on your Anthropic key
Opus 5Bestclaude-opus-5

The default. Strongest all-round reasoning and long code.

SearchCodeFilesVisionThinking
Reads at onceabout 750,000 words
One replyabout 2.3¢ a reply · Standard
Last checkedweb search 3 Sept 2026sandbox 3 Sept 2026
Fable 5.1Bestclaude-fable-5-1

Anthropic's strongest — deepest reasoning, cheapest cache reads.

SearchCodeFilesVisionThinking
Reads at onceabout 750,000 words
One replyabout 4.6¢ a reply · Premium
Last checkedweb search 3 Sept 2026sandbox 3 Sept 2026
Fable 5BestLegacyclaude-fable-5

Fable 5.1 replaces it. Same price, a step behind.

SearchCodeFilesVisionThinking
Reads at onceabout 750,000 words
One replyabout 4.6¢ a reply · Premium
Last checkedweb search 3 Sept 2026sandbox 3 Sept 2026
Opus 4.8BalancedLegacyclaude-opus-4-8

The previous Opus. Same price, a step behind.

SearchCodeFilesVisionThinking
Reads at onceabout 750,000 words
One replyabout 2.3¢ a reply · Standard
Last checkedweb search 3 Sept 2026sandbox 3 Sept 2026
Sonnet 5Balancedclaude-sonnet-5

Quick and capable for everyday work, 40% of Opus.

SearchCodeFilesVisionThinking
Reads at onceabout 750,000 words
One replyabout 0.9¢ a reply · Cheapest
Last checkedweb search 3 Sept 2026sandbox 3 Sept 2026
Haiku 4.5Fastclaude-haiku-4-5

Cheapest and fastest. No sandbox, basic web search.

SearchFilesVision
Reads at onceabout 150,000 words
One replyabout 0.5¢ a reply · Cheapest
Last checkedweb search 3 Sept 2026

GPT

runs on your OpenAI key
GPT-5.6 SolBestgpt-5.6-sol

OpenAI's strongest — search, sandbox and images.

SearchCodeImagesVisionThinking
Reads at onceabout 790,000 words
One replyabout 1.8¢ a reply · Standard
Last checkedweb search 3 Sept 2026sandbox 3 Sept 2026images 3 Sept 2026
GPT-5.6 TerraBalancedgpt-5.6-terra

Everyday GPT at half the price of Sol.

SearchCodeImagesVisionThinking
Reads at onceabout 790,000 words
One replyabout 1¢ a reply · Standard
Last checkedweb search 3 Sept 2026sandbox 3 Sept 2026images 3 Sept 2026
GPT-5.6 LunaFastgpt-5.6-luna

Cheapest GPT — quick lookups and drafts.

SearchCodeImagesVisionThinking
Reads at onceabout 790,000 words
One replyabout 0.1¢ a reply · Cheapest
Last checkedweb search 3 Sept 2026sandbox 3 Sept 2026images 3 Sept 2026

Gemini

runs on your Google key
Gemini 3.8 FlashBestgemini-3.8-flash

The default Gemini. Search, sandbox, huge context.

SearchCodeImagesFilesVisionThinking
Reads at onceabout 790,000 words
One replyabout 0.3¢ a reply · Cheapest
Last checkedweb search 3 Sept 2026sandbox 3 Sept 2026images 3 Sept 2026
Gemini 3.1 ProBestgemini-3.1-pro-preview

Deepest Gemini. Preview, and dearer past 200k tokens.

SearchCodeImagesFilesVisionThinking
Reads at onceabout 790,000 words
One replyabout 1¢ a reply · Standard
Last checkedweb search 3 Sept 2026sandbox 3 Sept 2026images 3 Sept 2026
Gemini 3.7 FlashBalancedLegacygemini-3.7-flash

Previous Flash. Same price, a step behind.

SearchCodeImagesFilesVisionThinking
Reads at onceabout 790,000 words
One replyabout 0.3¢ a reply · Cheapest
Last checkedweb search 3 Sept 2026sandbox 3 Sept 2026images 3 Sept 2026
Gemini 3.6 FlashBalancedLegacygemini-3.6-flash

Older Flash, kept for rooms that pinned it.

SearchCodeImagesFilesVisionThinking
Reads at onceabout 790,000 words
One replyabout 0.3¢ a reply · Cheapest
Last checkedweb search 3 Sept 2026sandbox 3 Sept 2026images 3 Sept 2026
Gemini 3.5 FlashBalancedLegacygemini-3.5-flash

Older and dearer than 3.8.

SearchCodeImagesFilesVisionThinking
Reads at onceabout 790,000 words
One replyabout 0.8¢ a reply · Cheapest
Last checkedweb search 3 Sept 2026sandbox 3 Sept 2026images 3 Sept 2026
Gemini 3.5 Flash-LiteFastgemini-3.5-flash-lite

The previous Lite. A little dearer than 3.1.

SearchCodeImagesFilesVisionThinking
Reads at onceabout 790,000 words
One replyabout 0.2¢ a reply · Cheapest
Last checkedweb search 3 Sept 2026sandbox 3 Sept 2026images 3 Sept 2026
Gemini 3.1 Flash-LiteFastgemini-3.1-flash-lite

Cheapest and fastest Gemini for quick lookups.

SearchCodeImagesFilesVisionThinking
Reads at onceabout 790,000 words
One replyabout 0.1¢ a reply · Cheapest
Last checkedweb search 3 Sept 2026sandbox 3 Sept 2026images 3 Sept 2026
Gemini 3.1 Flash ImageFastgemini-3.1-flash-image

Makes images (Nano Banana 2). No search or sandbox.

ImagesFilesVision
Reads at onceabout 100,000 words
One replyabout 4¢ a reply · Premium
Last checkedimages 3 Sept 2026
Gemini 3 Pro ImageBestgemini-3-pro-image

Best images (Nano Banana Pro), up to 4K. No tools.

ImagesFilesVision
Reads at onceabout 50,000 words
One replyabout 8.1¢ a reply · Premium
Last checkedimages 3 Sept 2026

"Last checked" is a real ask we paid for and watched work, most recently on 3 Sept 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 (everything in the room the model has to read, every time) and for what it writes back, at different rates. That is why a long conversation costs 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.

ModelWhat you sendWhat it writesOne reply
Opus 5 · Claude$6.50 / million$32.50 / millionabout 2.3¢ a reply
Fable 5.1 · Claude$13 / million$65 / millionabout 4.6¢ a reply
Fable 5 · Claude$13 / million$65 / millionabout 4.6¢ a reply
Opus 4.8 · Claude$6.50 / million$32.50 / millionabout 2.3¢ a reply
Sonnet 5 · Claude$2.60 / million$13 / millionabout 0.9¢ a reply
Haiku 4.5 · Claude$1.30 / million$6.50 / millionabout 0.5¢ a reply
GPT-5.6 Sol · GPT$5.20 / million$26 / millionabout 1.8¢ a reply
GPT-5.6 Terra · GPT$2.60 / million$15.60 / millionabout 1¢ a reply
GPT-5.6 Luna · GPT$0.26 / million$1.56 / millionabout 0.1¢ a reply
Gemini 3.8 Flash · Gemini$0.97 / million$4.88 / millionabout 0.3¢ a reply
Gemini 3.1 Pro · Gemini$2.60 / million$15.60 / millionabout 1¢ a reply
Gemini 3.7 Flash · Gemini$0.97 / million$4.88 / millionabout 0.3¢ a reply
Gemini 3.6 Flash · Gemini$0.97 / million$4.88 / millionabout 0.3¢ a reply
Gemini 3.5 Flash · Gemini$1.95 / million$11.70 / millionabout 0.8¢ a reply
Gemini 3.5 Flash-Lite · Gemini$0.39 / million$3.25 / millionabout 0.2¢ a reply
Gemini 3.1 Flash-Lite · Gemini$0.33 / million$1.95 / millionabout 0.1¢ a reply
Gemini 3.1 Flash Image · Gemini$0.65 / million$78 / millionabout 4¢ a reply
Gemini 3 Pro Image · Gemini$2.60 / million$156 / millionabout 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.