Skip to content

Prompt

An answer with sources: the prompt, and its price

A prompt that searches the web and answers with a source for each point. 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 up to 5 Claude Haiku 4.5 messages from the month. 15 of the 15 models can run it; each one's price is below.

The prompt

The prompt

Search the web for [question]. Answer in five bullet points, each with its source, and say where the sources disagree.

Open in llmwise with this prompt

Replace the parts in [brackets] with your own. It's in the prompt library with the others.

What it needs from a model

  • Up to 5 web searches (5 is the most one message makes). On a paid plan each search counts as one more message of the model in use; on Free, search works inside the 5 trial messages, up to 3 a day.

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.

What one run counts as, model by model
ModelsOne run on a paid planRuns on ProOn Free
GPT-6 Luna, GLM 5.3 Flash, and DeepSeek V4.1 FlashEveryday model: from the daily count · In the free trial1 everyday message, plus up to 5 Claude Haiku 4.5 messages from the month50 a month1 of the 5 trial messages, with up to 3 searches a day
DeepSeek V4 Pro, Gemini 3.8 Flash, Claude Haiku 4.5, GLM 5.3, and Grok 4.7In the free trialup to 6 messages of the model41 a month1 of the 5 trial messages, with up to 3 searches a day
Claude Sonnet 5, GPT-6 Sol, Gemini 3.1 Pro (preview), and Kimi K3In the free trialup to 6 messages of the model20 a month1 of the 5 trial messages, with up to 3 searches a day
Claude Opus 5.5up to 6 messages of the model10 a monthNot in the trial
Claude Fable 5.1 and GPT-6 Astraup to 6 messages of the model5 a monthNot in the trial
Runs on Pro ($20 a month): the most you get if the whole monthly allowance, or the 60 everyday messages a day, go to this prompt.

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.

How the number of searches changes the price

The model decides how many searches a question needs, up to 5; fewer searches, more runs. Runs on Pro by searches, on GPT-6 Luna (everyday), Claude Haiku 4.5, Claude Sonnet 5, Claude Opus 5.5, and Claude Fable 5.1.

Runs on Pro by searches per run
SearchesRuns on GPT-6 LunaRuns on Claude Haiku 4.5Runs on Claude Sonnet 5Runs on Claude Opus 5.5Runs on Claude Fable 5.1
1250 a month125 a month62 a month31 a month15 a month
2125 a month83 a month41 a month20 a month10 a month
383 a month62 a month31 a month15 a month7 a month
462 a month50 a month25 a month12 a month6 a month
550 a month41 a month20 a month10 a month5 a month

Questions

Can I run this prompt for free?

Yes, on the models in the free trial: one run on GPT-6 Luna is 1 of the 5 trial messages.

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.