Command R (08-2024)
Cohere · released Aug 30, 2024
- Type
- Proprietary
- Input
- $0.15
- Output
- $0.60
- Cached
- Not published
List price · per 1M tokens · Cohere at 128K context · source ↗
Our take
Written Aug 3, 2026Command R is Cohere's text-only model that can handle up to 128,000 tokens in a single request. It offers broad benchmark coverage across six Arena categories, with coding as its strongest measured area, and is available through two hosted providers.
Pick this for long-context text tasks that need 128,000 tokens in one prompt, or when you want consistent pricing across the two providers we track. Use it if coding assistance is your main need, since that is where its measured scores peak. Skip it if you need image, audio or video input, if maths or creative writing are central to your work, or if you want to verify parameter-level efficiency claims.
The case for it
- Broad benchmark coverage across six Arena categories, from coding to creative writing.
- Coding is the strongest measured category, 31 points above its own text-overall score.
- Arena scores are stable: its text-overall rating moved less than a tenth of a point across consecutive evaluation dates.
The case against it
- Maths and creative writing lag well behind its coding score, with a 74-point gap from strongest to weakest category.
- Parameter count is not published, so efficiency claims cannot be verified.
- Throughput is only confirmed on one of the two tracked providers.
How good is it?
IntelligencePuzzles, maths, exam questions
Arena Text (overall)136th of 143 · 1249.9
CodingWriting and fixing code on its own
Arena Coding137th of 143 · 1280.9
Arena Coding is the only board that has scored it for this.
AgenticPlanning, calling tools, staying on task
Nobody we watch has scored Command R (08-2024) for this. We would take the rating from Arena Agent (IPS).
WritingWe do not rate this
Two boards come close and neither tests writing: Arena Creative Writing asks people which of two replies they prefer, and LiveBench Language tests whether a model understood a passage. So we show where Command R (08-2024) placed and give it no mark out of five.
These tests check whether a model follows instructions — a precondition for all the work above, but not a measure of how well that work is done, which is why they get no rating.
Every published score for this model6 scoresEvery figure we hold, from 6 boards, with who ran it and a link to the source — including the boards no rating above is built on.
Or rent it from someone else
Why this differs from the header. The strip above quotes Cohere's own list price. This is the cheapest live offer at the widest standard context we hold, whoever is serving it — a reseller undercutting a lab is ordinary commerce, not an error.
- per 1M tokens
- $0.15 in / $0.60 out
- Context served
- 128K
- Throughput
- Not measured
| Provider | In / out per 1M tokens | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| OpenRouter | $0.15 / $0.60 | 128K | not measured | Unknown | Unknown | Unknown |
| Cohere | $0.15 / $0.60 | 128K | 26 tok/s | No | Yes30 days | Unknown |
Across the 2 listings we hold: 1 say they do not train on prompts, 0 say they do and 1 do not say. 0 appear in the zero-retention registry we check; the rest are unknown to us rather than confirmed either way.
What each host's API supports
From the parameter list each endpoint publishes. Streaming is omitted: nothing we hold reports it, for any model.
- ✓
- Supported
- ✗
- Not supported
- Not published
- host gave no parameter list
| Provider | Tool calling | JSON output | Strict schema |
|---|---|---|---|
| OpenRouter | ✓ | ✓ | ✓ |
| Cohere | ✓ | ✓ | ✓ |
Tool calling: 2 of 2 listings say yes. JSON output: 2 of 2 listings say yes. Strict schema: 2 of 2 listings say yes.
When we formed this view
Dates behind this page
Prices last checked 6d ago
What we do not know about this model yet
- Nothing we hold says whether an endpoint streams, so we do not show it either way.
- 1 of 2 listings do not say whether they train on prompts.
- We hold no cached-input rate for any of its listings.
Licence and identifiers
What the licence allowsWe hold no licence record for this model. Inside are the identifiers you need to pull it — its Hugging Face repo where we have one, our slug and a machine-readable card.
Licence
Commercial API terms. We hold no licence record for this model, so there is nothing to summarise here.
Identifiers
- Modality record
- text->text
- Catalogue slug
- cohere-command-r-08-2024