Command A

Tool callingStructured output

Hugging Face Launch post Website Docs

Cohere command model for multilingual enterprise agents, tools, and chat

Context: 256K
Released: 1y ago
Parameters: 111B
Input / 1M tokens: $2.50
Output / 1M tokens: $10.00

Sources:models.devOpenRouter

Benchmarks

DeepSWE is the primary coding benchmark where an exact model evaluation exists. Other sourced evaluations appear below; missing scores are not zero.

Not evaluated in DeepSWE 1.1 as of 2026-09-22. Results are only shown for exact model versions in the official dataset. Official leaderboard.

No benchmark results have been matched to this model yet.

Specifications

Developer: Cohere
Model family: Command A
Type: Language model
Predecessor: —
Successor: —
Released: March 13, 2025
Model ID: cohere/command-a
Openness: Open weights
License: —
Parameters: 111B
Input modalities: text
Output modalities: text
Modality: text->text
Native context: 16K
Tokenizer: Other
Max output tokens: 8K
Knowledge cutoff: 2024-06-01
Hugging Face: CohereForAI/c4ai-command-a-03-2025
Source freshness: Metadata synced Oct 8, 2026, 10:17 PM UTC

Open-weight builds

Ollama variants

Every published Ollama tag matched to this model, including parameter editions, instruction/base variants, and quantized builds.

3 builds

Variant	Parameters	Type	Quantization	Size	Context	Input
command-a:111b-03-2025-fp16	111B	—	FP16	222 GB	16K	text
command-a:latest	111B	—	Q4_K_M	67 GB	16K	text
command-a:111b-03-2025-q8_0	111B	—	Q8_0	118 GB	16K	text

Additional source evidence

Source model: cohere/command-a-03-2025
Source family: command-a
Last updated: 2025-03-13
Knowledge cutoff: 2024-06-01
Model context: 256K
Model output limit: 8K
Open weights: Yes
File attachments: No
Reasoning: No
Tool calling: Yes
Temperature control: Yes

Downloadable weights

Hugging Face

Published benchmarks

Benchmark	Score	Evaluation details	Evidence
Aider Polyglot	12 · percent correct	2025-03-14	Source

Complete source record (JSON)

{
  "id": "cohere/command-a-03-2025",
  "name": "Command A",
  "description": "Cohere command model for multilingual enterprise agents, tools, and chat",
  "family": "command-a",
  "last_updated": "2025-03-13",
  "knowledge": "2024-06-01",
  "attachment": false,
  "reasoning": false,
  "tool_call": true,
  "temperature": true,
  "modalities": {
    "input": [
      "text"
    ],
    "output": [
      "text"
    ]
  },
  "limit": {
    "context": 256000,
    "output": 8000
  },
  "benchmarks": [
    {
      "name": "Aider Polyglot",
      "score": 12,
      "source": "https://aider.chat/docs/leaderboards/",
      "metric": "percent correct",
      "date": "2025-03-14"
    }
  ],
  "release_date": "2025-03-13",
  "open_weights": true,
  "weights": [
    {
      "label": "Hugging Face",
      "url": "https://huggingface.co/CohereLabs/c4ai-command-a-03-2025"
    }
  ]
}

Infrastructure

Provider availability

All providers

Provider	Endpoint	Context	Input /M tokens	Output /M tokens	Cached input /M tokens	Cache write /M tokens	Uptime 1d	Data handling
Cohere	cohere	256K	$2.50	$10.00	—	—	100.00%	ZDR: No Training: Unknown Prompt logging: Unknown Retention: Unknown ZDR source Privacy policy Checked 2026-10-15

Provider data:OpenRouter

Deployment graph

Can I run this?

Vertical Tabs only shows compatibility when it has structured evidence tying this exact model to hardware, runtime, quantization, memory use, and observed performance.

Browse hardware