Can I run Command A locally?

Yes, the weights are open and hosted on Hugging Face under CohereForAI/c4ai-command-a-03-2025. At 111B parameters you will need substantial VRAM or a multi-GPU setup to run it at full precision; quantized versions reduce that requirement.

What does Command A cost via API?

Cohere charges $2.50 per million input tokens and $10.00 per million output tokens. Agentic tasks that generate long outputs will hit the output rate hard, so factor that into cost estimates before committing.

How is Command A different from other Cohere models?

Command A is Cohere's largest and most capable open-weights release, positioned above their smaller Command R family, with a longer context window and a specific focus on agentic and multilingual business tasks rather than general-purpose chat.

Command A

2469°

#llm #cohere #agents #multilingual #coding #long context

Run this model

Offers / Ads

OpenRouter Terminal / API

Pay per token

Chat with this model in the browser or call it from your code with one API key.

Cohere | 256,000 token context | $2.50/M input, $10.00/M output. Command A is an open-weights 111B parameter model with a 256k context window focused on delivering great performance across agentic, multilingual, and coding use cases. Compared to other leading proprietary and open-weights models Command A delivers maximum performance with minimum hardware costs, excelling on business-critical agentic and multilingual tasks.

Guides for this model

Ollama vs LM Studio (2026): which local AI app to use, and which top models each one runs

How much VRAM do I actually need for local AI?

Open weights vs open source vs API-only: what you are actually allowed to do

What is a GGUF file? Quantized models explained (Q4, Q8, fp8, NF4)

All guides

Captain's notes

Written by Captain, the house editor

Notes from 2026-10-13

Command A is Cohere's 111B open-weights model built around agentic workflows, multilingual tasks, and coding, with a 256,000-token context window. At 111B parameters it is a large model, but Cohere's pitch is that it punches above its weight relative to the hardware it needs. If your work involves multi-step tool use or non-English business tasks, it is worth a serious look.

Known for

Strong agentic performance: built for multi-step, tool-using workflows
256,000-token context window handles very long documents and threads
Multilingual focus, targeting real business use cases across languages
Open weights available on Hugging Face for self-hosted deployment
111B scale with a claimed efficiency advantage over comparable models

Watch out for

111B parameters demands serious hardware to run locally; consumer setups will struggle.
Output pricing at $10.00/M tokens adds up fast in agentic loops that generate heavy responses.
Cohere has not published detailed benchmark numbers on the model page, so independent comparisons are limited.

Best for

Prompts to try

Multi-step research agent

You have access to a web search tool. A user wants to understand the competitive landscape for electric vehicle battery suppliers in Europe as of 2024. Plan the research steps, call the tools you need in sequence, and produce a structured summary with sourced claims. Show your reasoning between each step.

Multilingual contract clause

Here is a termination clause from a French employment contract: 'En cas de faute grave, l'employeur peut procéder à un licenciement sans préavis ni indemnité.' Translate it into English, explain its legal implications for an employee, then rewrite it in plain English suitable for an employee handbook.

Refactor a messy function

Refactor the following Python function so it handles edge cases cleanly, uses type hints, and includes a docstring. Explain each change you make and why. def process(data): result = []; [result.append(x*2) for x in data if x != None]; return result

Compare with

Command R (08-2024)
API-only model
128,000 token context · $0.15/M input, $0.60/M output
Command R+ (08-2024)
API-only model
128,000 token context · $2.50/M input, $10.00/M output
Command A+
API-only model
192,000 token context · $0.30/M input, $1.50/M output
Command R7B (12-2024)
API-only model
128,000 token context · $0.04/M input, $0.15/M output

More text models from cohere

Questions people ask

Can I run Command A locally?: Yes, the weights are open and hosted on Hugging Face under CohereForAI/c4ai-command-a-03-2025. At 111B parameters you will need substantial VRAM or a multi-GPU setup to run it at full precision; quantized versions reduce that requirement.
What does Command A cost via API?: Cohere charges $2.50 per million input tokens and $10.00 per million output tokens. Agentic tasks that generate long outputs will hit the output rate hard, so factor that into cost estimates before committing.
How is Command A different from other Cohere models?: Command A is Cohere's largest and most capable open-weights release, positioned above their smaller Command R family, with a longer context window and a specific focus on agentic and multilingual business tasks rather than general-purpose chat.

Captain's verdict
A serious open-weights option if agents and multilingual work are your priority, provided you can stomach the hardware or the output token bill.

Model card on Hugging Face

Captain writes these notes from the model's own description and model card. Prices and context sizes are the provider's at the time of writing and can change.

Ranking badge

Updated Oct 22, 2026

Made this model? Show this badge on your page.

Paste it into your Hugging Face card or Civitai description.

Change colors / personalize / get code

Not this creator?

Get your own badge

How this score adds up

This model has no popularity data from any source yet, so it carries a stand-in number below 7,000° that keeps the lists complete. It never ranks above a model with data. The breakdown appears here as soon as a source reports it.

Glossary: the terms used here

Heat score: One number for how much a model is used and wanted right now, from 0° to 9,999°. Every list on this site that says hottest is sorted by it and nothing else.
Floor: The 7,000° every model with real data starts from. The scale runs from 0° to 9,999°; the part below the floor is reserved for stand-ins (models without data), so that a model with data always ranks above one without. The floor is the same for everyone and decides nothing; the degrees above it are the measurement.
Download-equivalents: Everything the score treats as a download, added up: downloads themselves, each torrent seeder as 1,000, each AI Horde image and each run on a generation site as one.
Log scale: Counting by tens, not by ones: going from 1,000 to 10,000 downloads adds the same degrees as going from 10,000 to 100,000. It keeps giants from crowding out everything else.
Likes: Thumbs up and likes from every source, worth half a download each on the log scale.
Adoption rate: How many downloads a day a model gets right now, from the difference between two readings of a source. A quarter of the weight of the download term.
Measured and estimated: Measured means two readings of a source exist and the difference is real. Estimated means only today's total is known and the past is spread over the model's life; the site says which one it is showing.
Seeder: Someone who keeps a copy of the weights online for others to download over a torrent, or a hosted mirror doing the same. Each one counts as 1,000 downloads.
AI Horde: A volunteer network that generates images for free on donated computers. The number of images it has made with a model is public, and each counts as one download.
Generation sites: Sites that host their own copies of a model and let people generate with it, such as PixAI, SeaArt and Yodayo. Their downloads count like Civitai's and each generation run as one download.
OpenRouter tokens: A text model served through an API, such as Claude or GPT, has no weights to download, so its usage is measured in tokens: the pieces of text it read and wrote through OpenRouter, a gateway many apps use, over the last 30 days. Every 10,000,000 tokens count as one download. Source: OpenRouter (openrouter.ai/rankings), CC BY 4.0.
Full model (checkpoint): The weights themselves, the file that generates on its own. It gets a bonus because add-ons depend on it.
LoRA and embedding: Small add-on files that steer someone else's weights toward a style, a character or a concept. They cannot run alone.
Family and weights: The base a model is built on, such as SD 1.5, SDXL, Flux or Wan. Every model inherits the release date of its family's weights.
Age: Degrees taken off for how long ago the family's weights came out: 150° a year, up to 750°. It keeps old downloads that had years to pile up from freezing the top of the list.
Family boost: A small, bounded nudge for LoRAs of a family this site is pushing forward right now, always listed in the breakdown.
Stand-in score: A stable number below the floor given to a model no source reports on yet, so lists stay complete. It never ranks above a model with data.
New! (grace period): A model less than 7 days old shows New! instead of a score and holds no place in the rankings. Its score is computed from day one, but a model one day old grows faster than anything, so without the wait the week's #1 would always be whatever came out yesterday rather than what held up for a week.
Trend: How a model's growth over a period compares with the typical model's growth over the same period. Faster than typical reads as a rise, slower as a fall.
Typical model: The middle of the catalog: half the models with a figure grew faster over the period, half slower.

Similar Models

AI Models for Image, Video & Text Generation

Command A is a text model for the Text / LLM family listed on ModelTrends.ai, a read-only catalog of open source AI image, video and text models. Compare it with other Text / LLM models and check its heat score to see how it is trending.

More Text / LLM models llm cohere agents multilingual coding long context local

Browse by Model Family