Command A Reasoning is an open-source chat model from Cohere that takes text inputs and generates text outputs. It is designed for tool use, agentic tasks, and multilingual applications, and can call tools for web search and function calling.
Input
Output
Context
289K
Max Output
4K
Parameters
111.1B
Input Modalities
Output Modalities
Some values come from web research and may be incorrect. Report incorrect data
Download 222 GB · Runs on vLLM v0.32.0 · 4 GGUF builds
| Precision | Weights | One request at 33K tokens | Smallest GPU that fits |
|---|---|---|---|
| FP16 / BF16 | 207 GB | 227 GB | 1x NVIDIA B300 SXM (288 GB) |
| INT8 | 103 GB | 118 GB | 1x NVIDIA H200 NVL (141 GB) |
| INT4 | 51.7 GB | 63.6 GB | 1x NVIDIA A100 PCIe 80GB (80 GB) |
Computed by Inferbase from the 111,057,580,032 parameters in the creator's Hugging Face repository; one request adds its KV cache, activations and framework overhead, with the layer layout estimated from the parameter count.
Public resources
Specification sources
As of Nov 11, 2026.
Answered from the facts on this page, with their sources.
Command A Reasoning has a context window of 288,768 tokens and a maximum output of 4,000 tokens (source: Creator or provider API). A provider may serve less; Inferbase routes on what each provider serves.
Yes. Command A Reasoning is an open-weight model under the Cc by nc 4.0 license. You can download and self-host it within the license terms.
Command A Reasoning has 111,057,580,032 parameters (111.1B), as stated in the creator's Hugging Face repository.
Strengths: 288K token context window; Supports 23 languages. Limitations: License does not allow commercial use (cc-by-nc-4.0). Each is computed from the model's stated facts and benchmark results.
Command A Reasoning accepts Text and produces Text. The Capabilities card lists the API features it supports, such as function calling and structured output.
No benchmark source has published a result for Command A Reasoning yet, so it is shown as unmeasured, not estimated.
Not on Inferbase Managed today. Add your own provider key or endpoint that serves Command A Reasoning, and Inferbase runs it on your account with the same routing and logs.
The weights take 206.9 GB at FP16 / BF16, 103.4 GB at INT8, 51.7 GB at INT4, computed from the 111,057,580,032 parameters its creator publishes. Each request adds its KV cache and the framework's overhead. The hardware section shows one request and the smallest GPU that fits; the GPU planner sizes it for your context length and traffic.
The model card of Command A Reasoning lists 23 languages: English, French, German, Spanish, Italian, Portuguese, Japanese, Korean, Chinese, Arabic, Greek, Persian, Polish, Indonesian, Czech, Hebrew, Hindi, Dutch, Romanian, Russian, Turkish, Ukrainian and Vietnamese. That is what Cohere states; the catalog does not test language quality.
Start on the free plan with 5,000 requests a month, no card required.