Prompt
Analyze a CSV with code: the prompt, and its price
A prompt that loads a CSV you attach, runs code on it and reports the numbers. Copy it or open it in llmwise, and see which models can run it and what one run counts as on each.
Models and prices checked . Updated .
Short answer
GPT-6 Luna is the least expensive model that can run it: one run counts as 1 everyday message, plus 1 Claude Haiku 4.5 message from the month. 15 of the 15 models can run it; each one's price is below.
The prompt
Load the attached CSV with code and answer [your question]. Show the numbers you computed and the code you ran, and list any rows you had to skip and why.
Replace the parts in [brackets] with your own. It's in the prompt library with the others.
What it needs from a model
A code run in an isolated sandbox, after you approve it (paid plans): 1 Claude Haiku 4.5 message a run, on top of the message.
Which models, and what one run counts as
Start with the least expensive model that can run it, and move up only when the answer isn't good enough: the next model sees the whole chat.
| Models | One run on a paid plan | Runs on Pro |
|---|---|---|
| GPT-6 Luna, GLM 5.3 Flash, and DeepSeek V4.1 FlashEveryday model: from the daily count | 1 everyday message, plus 1 Claude Haiku 4.5 message from the month | 250 a month |
| DeepSeek V4 Pro, Gemini 3.8 Flash, Claude Haiku 4.5, GLM 5.3, and Grok 4.7 | 1 message of the model, plus 1 Claude Haiku 4.5 message | 125 a month |
| Claude Sonnet 5, GPT-6 Sol, Gemini 3.1 Pro (preview), and Kimi K3 | 1 message of the model, plus 1 Claude Haiku 4.5 message | 83 a month |
| Claude Opus 5.5 | 1 message of the model, plus 1 Claude Haiku 4.5 message | 50 a month |
| Claude Fable 5.1 and GPT-6 Astra | 1 message of the model, plus 1 Claude Haiku 4.5 message | 27 a month |
Every limit is published. Paid plans also have a monthly fair-use limit on AI cost: Pro $7.50, Max $20, Ultra $42, Studio $85. Using every message on your plan at typical sizes stays under it; very large messages and heavy research use it faster. Every limit, explained.
Everyday models: for formula help, quick lookups and explaining a chart.
Models with 125 to 250 messages a month on Pro: for cleaning data, pivots, standard statistics and writing the analysis code.
Models with 31 to 62 messages a month on Pro: for messy data, ambiguous questions and analysis you'll present or decide on.
How code runs change the price
Each run is Python or Node.js in an isolated sandbox; it stops after 60 seconds and waits for your approval first. A model that fixes its code and runs it again makes a second run. Runs on Pro by code runs, on GPT-6 Luna (everyday), Claude Haiku 4.5, Claude Sonnet 5, Claude Opus 5.5, and Claude Fable 5.1.
| Code runs | Runs on GPT-6 Luna | Runs on Claude Haiku 4.5 | Runs on Claude Sonnet 5 | Runs on Claude Opus 5.5 | Runs on Claude Fable 5.1 |
|---|---|---|---|---|---|
| 1 | 250 a month | 125 a month | 83 a month | 50 a month | 27 a month |
| 2 | 125 a month | 83 a month | 62 a month | 41 a month | 25 a month |
| 3 | 83 a month | 62 a month | 50 a month | 35 a month | 22 a month |
Questions
Can I run this prompt for free?
No: it uses a tool that's on the paid plans. On Pro ($20 a month) the least a run counts as is 1 everyday message, plus 1 Claude Haiku 4.5 message from the month, on GPT-6 Luna.
Which models can run it?
15 of the 15 models in llmwise can. Start on the least expensive and move up if the answer isn't good enough; the next model sees the whole chat.
Claude, GPT, Gemini, DeepSeek, Grok, Kimi, and GLM, in one chat.
See what a message costs before you send it. Free is 5 messages to try; sign in with an email link, no password or card.