Skip to content
ModelCap

Head-to-head comparison

Command A vs Command R (08-2024)

Command A (Cohere) and Command R (08-2024) (Cohere) compared on the ModelCap Index, API price, context window, provider availability, weight access and every public benchmark board they share. Figures are the same ones shown on the live rankings; nothing here is a hidden score.

Snapshot as of 22 September 2026

As of 22 September 2026, Command A holds the stronger ModelCap Index position (#137 vs #220); Command R (08-2024) is 16.7× cheaper per output token ($0.60/1M vs $10.00/1M); and Command A offers the longer context window (256K vs 128K tokens).

Which should you choose?

Choose Command A if…

  • you want the stronger overall ModelCap Index position — #137 against #220 (40.5 vs 14.2 points).
  • you need the longer context window — 256K tokens against 128K.
  • Arena coding is your yardstick — 1389 against 1282.
  • you want the more recently listed model — Command A was listed 13 March 2025, Command R (08-2024) 30 August 2024.

Choose Command R (08-2024) if…

  • API cost matters — $0.60/1M output tokens against $10.00/1M, about 16.7× cheaper.
  • your workload is prompt-heavy — input tokens cost $0.15/1M against $2.50/1M.

Command A vs Command R (08-2024): specs, pricing and context

Specification comparison of Command A and Command R (08-2024)
FieldCommand ACohereCommand R (08-2024)Cohere
ModelCap Index position#137#220
Index score40.514.2
EvidenceMeasuredMeasured
Input price / 1M tokens$2.50$0.15
Output price / 1M tokens$10.00$0.60
Context window256K tokens128K tokens
Max output tokens8K4K
API providers listed11
Weight accessGated accessAPI only
Input modalitiesTextText
First listed13 March 202530 August 2024
PublisherCohereCohere

Evidence: 2 public benchmark observations across 2 boards · 2 public benchmark observations across 2 boards. Prices are the lowest listed API offer per million tokens observed on the OpenRouter catalogue.

Benchmark scores: Command A vs Command R (08-2024)

Public benchmark boards where Command A or Command R (08-2024) has a published result
BoardCommand ACommand R (08-2024)Leads
Arena codingArena (LMArena)13891383–139512821268–1295Command A
BFCL V4UC Berkeley (Gorilla)46.5Function callingOnly one result
AA τ²-Bench TelecomArtificial Analysis15.2%tau2:telecom:dual-control:pass-at-1:3-repeats:source-model="Command A":reasoning=falseOnly one result
AA Humanity's Last ExamArtificial Analysis4.0%hle:may-2025:text-only-2158:no-tools:pass-at-1:source-model="Command A":reasoning=falseOnly one result

Scores are the sources' own published figures for each model's best evaluated configuration; ModelCap never re-runs a benchmark.

Want a different pairing? Open the interactive comparison tool to swap either model for any current ranked language model.

Command A vs Command R (08-2024): common questions

Is Command A better than Command R (08-2024)?

Command A ranks higher on the ModelCap Index as of 22 September 2026: #137 against #220. That is a capability ranking built from public benchmark evidence with published uncertainty; whether it is "better" for you also depends on price, context and where you can run it. Their published uncertainty intervals do not overlap, but the aggregate Index does not predict performance on every task; compare the relevant benchmark configurations before choosing.

Is Command A cheaper than Command R (08-2024)?

Command R (08-2024) is cheaper on output tokens: $0.60/1M against $10.00/1M. Input tokens are $2.50/1M for Command A and $0.15/1M for Command R (08-2024). Prices are the lowest listed API offer ModelCap observed, in USD per million tokens. For 1,000 requests with 2,000 input and 500 output tokens each (2M input + 0.5M output), the listed-rate estimate is $10.00 for Command A versus $0.60 for Command R (08-2024). Command R (08-2024) costs 94.0% less in this scenario. This excludes caching, batch discounts, prompt-length tiers, tool charges and retries; verify the selected endpoint before budgeting.

Which has the bigger context window, Command A or Command R (08-2024)?

Command A has the larger context window: 256K tokens against 128K.

Which is better for coding, Command A or Command R (08-2024)?

Arena coding: Command A 1389, Command R (08-2024) 1282 — Command A leads.

Are Command A and Command R (08-2024) open-weight models?

Command A: Gated access. Command R (08-2024): API only. Open weights mean the checkpoint can be downloaded and self-hosted under its licence; API-only models are available solely through hosted endpoints.

Where can I run Command A and Command R (08-2024)?

ModelCap currently lists 1 API provider for Command A and 1 for Command R (08-2024), from the OpenRouter catalogue snapshot the site serves; each model page lists the providers and their prices.

How current is this Command A vs Command R (08-2024) comparison?

Every figure comes from the sealed ModelCap dataset published 22 September 2026; the page re-renders within a minute of each data refresh, and the ModelCap Index positions are the same ones shown on the live rankings.

Explore further