Cohere

Command A Plus

Generally availableOpen weights128K contextReasoning

Summary

Command A Plus is an open-weight language model from Cohere, released on 20 May 2026. It accepts text and images and generates text, with a 128K-token context window and up to 64K output tokens per response. As of 18 Nov 2026, the lowest listed API price is $0.30 per million input tokens and $1.50 per million output tokens (OpenRouter), across 2 providers we track.

Cohere's stronger command model for multilingual agents and enterprise workflows

Last verified 18 Nov 2026. Every figure on this page links to its source.

Specifications

DeveloperCohere
Release date20 May 2026 [models.dev]
StatusGenerally available [models.dev]
WeightsOpen weights [Hugging Face]
Licenseapache-2.0 [Hugging Face]
Parameters219B [Hugging Face]
Context window128K (128,000 tokens) [models.dev]
Max output64K tokens [models.dev]
Knowledge cutoff1 Apr 2025 [models.dev]
InputText and images [models.dev]
OutputText [models.dev]
Reasoning modeYes [models.dev]
Tool callingYes [models.dev]
Structured outputYes [models.dev]
Hugging FaceCohereLabs/command-a-plus-05-2026-bf16 [Hugging Face]

Command A Plus API pricing by provider

USD per million tokens. Sorted by input price.

ProviderInputOutputCached inputContextSource
OpenRouter
cohere/command-a-plus
$0.30$1.50$0.15192KOpenRouter, 18 Nov 2026
Cohere API
command-a-plus-05-2026
$2.50$10–128Kmodels.dev, 18 Nov 2026

Running Command A Plus locally

Estimated memory, from the parameter count and the architecture in config.json on Hugging Face. Includes about 0.8 GB of runtime overhead.

QuantizationWeightsTotal, 8K contextTotal, 32K context
Q4_K_M (4-bit)133 GB134 GB135 GB
Q8_0 (8-bit)232 GB234 GB235 GB
FP16 / BF16 (16-bit)438 GB439 GB440 GB

At 4-bit with an 8K conversation, Command A Plus needs about 134 GB, more than any single consumer graphics card; it needs a unified-memory machine, a multi-GPU setup or a split between graphics card and system RAM. Check your own hardware, or see Best computer for local AI on our sister site AIPCs.

Frequently asked questions

What is the context window of Command A Plus?

Command A Plus has a context window of 128,000 tokens (128K) and can generate up to 64,000 tokens in a single response, according to models.dev.

How much does the Command A Plus API cost?

Through Cohere API, Command A Plus costs $2.50 per million input tokens and $10 per million output tokens. The lowest listed price is $0.30 input / $1.50 output through OpenRouter. Prices last verified 18 Nov 2026.

Is Command A Plus open source?

Command A Plus is an open-weight model: its weights are published on Hugging Face as CohereLabs/command-a-plus-05-2026-bf16 under the apache-2.0 license. Check the license terms before commercial use.

When was Command A Plus released?

Cohere released Command A Plus on 20 May 2026, according to models.dev.

Which providers offer Command A Plus?

We track Command A Plus on 2 providers: OpenRouter, Cohere API.

How much VRAM does Command A Plus need?

About 134 GB at 4-bit (Q4_K_M) with an 8K-token conversation, and about 234 GB at 8-bit. That is more than any single consumer graphics card holds. These are estimates from the model's published parameter count and architecture.

Similar models from other labs

Comparable on output type, weights, release date, price and context window. Prices are the lowest listed, USD per million tokens.

ModelLabReleasedContextInput $/1MOutput $/1MWeights
Muse Glimmer 30BMeta10 Aug 2026131K$0.35$1.50Open
Step 3.7 FlashStepFun29 May 2026256K$0.20$1.15Open
Macaron V1 TallMindlab21 Jul 2026262K$0.25$1.43Open
GLM-4.6VZhipu AI (Z.ai)8 Dec 2025128K$0.30$0.90Open
GLM-4.6V-FlashZhipu AI (Z.ai)8 Dec 2025128K$0.30$0.90Open
Qwen3.8 27BAlibaba (Qwen)14 Aug 2026262K$0.06$1.49Open

Change history

  • License changed from none to apache-2.0
  • Parameter count changed from none to 219B

Sources