AI model comparison

Command A vs GPT-4

Side by side comparison of Command A and GPT-4 on pricing, benchmark scores, context window, and more.

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.

Input / 1M
$2.50
Output / 1M
$10
Context
256K

OpenAI's flagship model, GPT-4 is a large-scale multimodal language model capable of solving difficult problems with greater accuracy than previous models due to its broader general knowledge and advanced reasoning

Input / 1M
$30
Output / 1M
$60
Context
8K

Comparing image generators? Compare image models

At a glance

Quick verdict

How the two models stack up on the things people ask about most.

Lower price

cohere logo

Command A

9x cheaper for a typical chat

Higher intelligence score

cohere logo

Command A

7 vs 6.7 on Artificial Analysis

Larger context window

cohere logo

Command A

256K vs 8K tokens

Newer release

cohere logo

Command A

Released March 13, 2025

Benchmarks

Benchmark scores

Independent scores from Artificial Analysis. Higher is better.

Intelligence index

cohere logoCommand A7
openai logoGPT-46.7

Coding index

cohere logoCommand A27.8
openai logoGPT-413.1

Agentic index

cohere logoCommand A1
openai logoGPT-4Not available

Pricing

Command A vs GPT-4 API pricing

Per-token API rates. Cheaper option highlighted.

Metriccohere logoCommand Aopenai logoGPT-4
Input tokensPer 1M tokens$2.50$30
Output tokensPer 1M tokens$10$60
Cached input (read)Per 1M tokensNot availableNot available
Cache writePer 1M tokensNot availableNot available

What it costs in practice

Estimated cost per 1,000 requests at standard rates. Coding and long-document figures also show the cost when the input is already cached.

Chat message

2K in, 500 out

cohere logoCommand A$10
openai logoGPT-4$90

Coding task

30K in, 4K out

cohere logoCommand A$115
openai logoGPT-4$1140

Long document summary

150K in, 2K out

cohere logoCommand A$395
openai logoGPT-4$4620

Specs

Context window and capabilities

How much each model can read, how much it can write, and what it accepts as input.

Metriccohere logoCommand Aopenai logoGPT-4
Context window256K tokens8K tokens
Max output8K tokens4K tokens
Input typesTextText
Output typesTextText
Reasoning effort levelsNot availableNot available
Default reasoning effortNot availableNot available
Release dateMarch 13, 2025May 28, 2023

Features

Supported features

API features available for each model.

Metriccohere logoCommand Aopenai logoGPT-4
Tool callingSupportedSupported
Structured outputsSupportedNot supported
JSON modeSupportedSupported
ReasoningNot supportedNot supported
TemperatureSupportedSupported
Stop sequencesSupportedSupported
Deterministic seedSupportedSupported
Verbosity controlNot supportedNot supported

Our take

Command A is 9x cheaper for a typical chat. Command A scores higher on the Artificial Analysis Intelligence Index (7 vs 6.7). Command A has the larger context window (256K vs 8K tokens). The right pick depends on your workload, so the quickest way to settle it is to send the same prompt to both and compare.

FAQ

Frequently asked questions

Is Command A or GPT-4 cheaper?

Command A is cheaper for a typical chat (2K input tokens and 500 output tokens). Command A costs $2.50 per 1M input tokens and $10 per 1M output tokens, while GPT-4 costs $30 per 1M input tokens and $60 per 1M output tokens.

Which has a bigger context window, Command A or GPT-4?

Command A supports up to 256K tokens of context, compared with 8K for GPT-4.

Is Command A smarter than GPT-4?

On the Artificial Analysis Intelligence Index, Command A scores 7 and GPT-4 scores 6.7, putting Command A ahead. Benchmarks don't capture everything, so the best test is running your own prompts through both.

Can I use Command A and GPT-4 at the same time?

Yes. Shortcut Chat sends one prompt to multiple models at once, so you can see Command A and GPT-4 answer side by side and keep the better response.

cohere logoopenai logo

Why choose? Ask both.

Send one prompt to Command A and GPT-4 at the same time. Compare the answers side by side and keep the best one.