What Command is known for
Cohere builds for business use: Command models are good at working through documents, summarising, and answering from what you give them.
Command models · Cohere
Chat with Command online, next to every other model.
Cohere's Command models in one chat with the rest of the field.
Start freeFree plan · Every model · No card
4 Command models
Every Cohere chat model Portail carries today, listed below.
Up to 256K context
The largest context window in the family, for long files and long chats.
One shared thread
Switch from Command to GPT, Claude, Gemini or anything else mid-conversation.
How Command works on Portail
Pick a Command model from the model picker in any chat. It reads the whole conversation, including anything other models said earlier, and your Portail memory. When you want a second opinion, switch models and keep going, or turn on Council to ask several models at once.
Every plan, Free included, can use every Command model. Plans change the size of your monthly credit allowance, not which models you can pick. Bigger models use credits faster; the cost band in the table shows roughly how fast.
Command models on Portail
Read from Portail's live model catalog. Cost runs from $ (cheapest) to $$$$.
| Model | Context | Images | Reasoning | Cost |
|---|---|---|---|---|
| Command R7B (12-2024) | 128K | No | No | $ |
| Command R+ (08-2024) | 128K | No | No | $$$ |
| Command R (08-2024) | 128K | No | No | $ |
| Command A | 256K | No | No | $$$ |
Questions
How many Command models can I use on Portail?
4 right now, from Cohere. The list follows the live catalog, so new Command models appear as they're added.
Can Command read images?
Not the Command models on Portail today. Switch the thread to a vision model for images.
Can I use Command for free?
Yes. The Free plan includes every model, Command too, with a starter credit allowance and no card. Cheaper Command models stretch it further.
Do I need a Cohere account?
No. Command runs on your Portail account and credits.
Keep reading
Try it on your own prompt.
Every model, one thread, one memory. Free to start.