Cohere: Command A

Public pricingIntelligence 79/100Large memoryOutils

Cohere: Command A est un modèle texte conçu pour codage, génie logiciel et workflows agentiques. Il associe de bonnes performances en codage et une utilisation fiable des outils et des agents, un contexte de 256K tokens et un profil premium pour un travail fiable sur codage, génie logiciel et workflows agentiques.

Input

$2.50/1M

Output

$10.00/1M

Cached

$0.63/1M

Batch

$1.25/1M

Calculate your Command A bill.

Set your workload — see cost at your exact volume.

What would Command A cost you?

Adjust the workload to see your monthly bill.

1,00010,00050,000250,0001M10M

Technical specifications

Command A at a glance.

Memory

256,000

tokens

Max reply

8,192

tokens

Memory tier

Large

an entire book or large codebase

Tokenizer

—

Released

Mar 2025

Training cutoff

Jul 2024

Availability

Public pricing

Status

active

Benchmarks

Quality benchmarks

Independent evaluations from public leaderboards. Higher is better.

  • aa_intelligence_index

    13

What it can do

Capabilities & limits.

  • Understands images
  • Deep step-by-step thinking
  • Uses tools / calls functions
  • Strict JSON output
  • Streams replies
  • Fine-tunable on your data

When to pick Command A

  • Agentic workflows that call tools or APIs.
  • Long documents, full codebases, or extensive chat histories.

When to look elsewhere

  • Your workload involves images — pick a vision-capable model instead.

Alternatives

Similar models to compare.

FAQ

Command A — the questions we see most.

Pricing, capabilities, alternatives — generated from the same data that powers the calculator above.

Get instant answers from our AI agent

At a typical workload of 50,000 conversations a month with 1,500-token prompts and 800-token replies, Command A costs roughly $588 per month. Input is $2.50 /1M tokens and output is $10.00 /1M tokens.
Command A has a 256,000-token context window (large memory — an entire book or large codebase). That means you can fit about 48,000 words of input and history in a single call.
Beyond text generation, Command A supports calling functions / tools, strict JSON output, fine-tuning on your own data. It streams replies by default.
Command A was released in March 2025, with training data cut off around July 2024.
Models in a similar class include Nova Premier 1.0, GPT-5 Image Mini, GPT-5.4. The "Similar models" section below this FAQ links into each.

Still unsure?

Compare Command A against 100+ other models.

Open the full wizard — pick a use case, set your usage, and see side-by-side monthly costs in under a minute.

Open the comparison wizard