VULCAN VEIL Analyst's AI workbench

Docs · Web · Chat

Choosing a model

You can choose which model answers. Models differ in speed, price, and what they can read, and each one is billed by what you use. This page asks the same question of three models in one chat.

Expand

1. Open the model list

The list is under the message box. Each model is named with the company that runs it for us.

The model list open under the message boxExpand

2. Ask something

Type your question and press Send. Here, GLM 5.3 Flash is asked: "In one sentence, what is a hot spot in crime analysis?" The line beside Send shows what this chat has cost so far.

GLM 5.3 Flash's answer, with the chat's cost beside SendExpand

3. Change the model

Pick another model at any point in a chat. Your next message goes to that model, and it sees the chat so far. Here, DeepSeek V4.1 Flash gets the same question.

DeepSeek V4.1 Flash's answer below the first oneExpand

4. Compare another

Here, Muse Spark Open gets the question too. It costs more per word than the other two, so the chat's cost goes up by more.

Muse Spark Open's answer, with the chat's cost higherExpand

Good to know

  • The models page lists each model's price and what it can read.
  • Your choice lasts until you close the tab. A saved chat keeps the model it was using.
  • Some models read pictures and video, and others do not. See Attaching images and video.
  • Your usage shows each model's requests, tokens, and charges for the month.