LLM·Dex
Newsletter

Command R+ (08-2024) vs GPT-4o

A complete head-to-head: pricing, context window, benchmarks, modality coverage, and openness, with a programmatic verdict synthesized from the underlying data.

Updated

Command R+ (08-2024) specs · GPT-4o specs
Verdict by category
  • PriceTie

    Both land near $10.00 / 1M output tokens, call it a wash on cost.

  • Context windowTie

    Both ship a 128K-token context window.

  • BenchmarksGPT-4o

    GPT-4o leads in 1 of 1 shared benchmarks; the biggest gap is on MMLU (broad academic knowledge), where it scores 88.7 vs 75.7.

  • ModalitiesGPT-4o

    GPT-4o supports 3 modalities (text, vision, audio) vs 1 for Command R+ (08-2024).

  • OpennessCommand R+ (08-2024)

    Command R+ (08-2024) ships open weights (CC-BY-NC 4.0); GPT-4o is API-only.

On balance GPT-4o edges ahead, winning 2 of 5 categories against Command R+ (08-2024)'s 1. Both land near $10.00 / 1M output tokens, call it a wash on cost. Both ship a 128K-token context window.

GPT-4o leads in 1 of 1 shared benchmarks; the biggest gap is on MMLU (broad academic knowledge), where it scores 88.7 vs 75.7. They differ in modality coverage, Command R+ (08-2024) handles text while GPT-4o handles text, vision, audio, which can be the deciding factor before you even look at benchmarks. Command R+ (08-2024) ships open weights (CC-BY-NC 4.0); GPT-4o is API-only.

Command R+ (08-2024) is the newer of the two, released 4 months after GPT-4o, which usually means a more recent knowledge cutoff and updated safety post-training. Command R+ (08-2024) is usually picked for rag and data extraction workloads, while GPT-4o sees more deployments in chatbots and vision. If pricing matters more than every last benchmark point, run the numbers in the calculator below before committing.

Side-by-side specs

SpecCommand R+ (08-2024)GPT-4o
ProviderCohereOpenAI
ReleasedAug 2024May 2024
Modalitiestexttext, vision, audio
Context window128K tokens128K tokens
Max output,,
Input · 1M$2.50 / 1M tokens$2.50 / 1M tokens
Output · 1M$10.00 / 1M tokens$10.00 / 1M tokens
Knowledge cutoff,2023-10
Open weightsYes (CC-BY-NC 4.0)No
API availableYesYes

Pricing at scale

What you'd actually pay at typical workloads. Numbers come from each model's published per-million-token rates.

  • Light usage, 100k in / 50k out per day$22.50 vs $22.50
  • Heavy usage, 1M in / 500k out per day$225 vs $225
  • RAG workload, 5M in / 200k out per day$435 vs $435

Light usage, 100k in / 50k out per day: both models cost about $22.50 a month, call it a tie. Heavy usage, 1M in / 500k out per day: both models cost about $225 a month, call it a tie. RAG workload, 5M in / 200k out per day: both models cost about $435 a month, call it a tie.

Price calculator

Estimated spend for the listed models at your usage. Numbers are derived from each model's published per-million-token rates.

  • Command R+ (08-2024)$0.750
  • GPT-4o$0.750

Benchmarks compared

Only sourced numbers. Where a benchmark is missing for one model we show the available value rather than fabricating the other.

Command R+ (08-2024)GPT-4o
  • MMLU75.788.7
  • HumanEval,90.2
Pick Command R+ (08-2024) if

Command R+ (08-2024) fits when…

  • RAG-tuned
  • Citation generation
  • Enterprise tooling
  • Self-hosting and on-prem requirements, open weights (CC-BY-NC 4.0).
Pick GPT-4o if

GPT-4o fits when…

  • Native multimodal
  • Mature SDK and tooling
  • Multimodal needs covering vision, audio.
Don't want either?

Consider Command R

Cohere's mid-tier RAG-optimized model, affordable and reliable on retrieval workloads.

See Command R specsCommand R+ (08-2024) vs Command RGPT-4o vs Command R

Frequently asked

  • Is Command R+ (08-2024) or GPT-4o cheaper?
    Both Command R+ (08-2024) and GPT-4o are priced equivalently at $10.00 / 1M tokens per million output tokens.
  • Which has the larger context window?
    Both Command R+ (08-2024) and GPT-4o ship a 128K-token context window.
  • Is Command R+ (08-2024) or GPT-4o better for coding?
    Both Command R+ (08-2024) and GPT-4o are competitive on coding benchmarks. See each model's individual spec page for HumanEval and SWE-bench scores where published. For an opinionated pick, consult our Best LLM for Coding ranking.
  • Are either of these models open source?
    Command R+ (08-2024) ships open weights (CC-BY-NC 4.0). GPT-4o is API-only.
  • When were Command R+ (08-2024) and GPT-4o released?
    Command R+ (08-2024) was released by Cohere on 2024-08-30. GPT-4o was released by OpenAI on 2024-05-13.
Friday digest

The week's AI launches, in your inbox.

One short email every Friday, new models, leaks, and quietly-shipped APIs you missed.