Command R (08-2024)
Cohere · released Aug 30, 2024
- Type
- Closed
- Input
- $0.15
- Output
- $0.60
- Cached
- None held
List price · per 1M tokens · Cohere at 128K context · source ↗
Our take
Written Sep 2, 2026Command R is a text-only model from Cohere released in August 2024, built for long-context work with a 128,000-token request limit. Its Arena scores sit in the low-to-mid 1200s, making it a mid-tier generalist rather than a standout performer.
Pick this for budget-conscious long-context tasks where a 128,000-token limit matters more than peak quality, or for Cohere-native integrations where modest throughput is acceptable. Skip it if you need image, audio or video input, want to self-host, or need strong creative writing or maths performance.
The case for it
- Coding is its strongest measured area, scoring 31 points above its own overall average.
- Identical pricing across both tracked providers, so there is no premium for choosing one host over the other.
The case against it
- Creative writing and maths are its weakest measured areas, each roughly 43 points below its own overall average.
- Direct Cohere hosting runs at 4 tokens per second, which is slow for interactive use.
- Proprietary weights with no self-host option and no licence listed.
How good is it?
A general text model for chat and question answering, though it trails the field on everyday questions, writing and code.
- getting answers to everyday questionsArena Text (overall) · 160th of 168
- drafts, rewrites and editingArena Creative Writing · 160th of 168
- writing and completing codeArena Coding · 161st of 168
EverydayGeneral questions and everyday reasoning
Arena Text (overall)160th of 168 · 1250
CodingWriting and fixing code on its own
Arena Coding161st of 168 · 1282
Arena Coding is the only board that has scored it for this.
AgenticPlanning, calling tools, staying on task
Not yet scored on Arena Agent.
WritingDrafting and rewriting prose
Arena Creative Writing160th of 168 · 1209
Arena Creative Writing is the only board that has scored it for this.
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.
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.
Where to rent it
Prices checked 4 hours ago — each listing carries its own date.
Cohere, through OpenRouter
The lab is also the cheapest we hold. The strip above and this offer are the same one, so nothing on this page undercuts Cohere on 128K of context.
- per 1M tokens
- $0.15 in / $0.60 out
- Context served
- 128K
- Throughput
- ~20 tok/s
| Provider | In / out per 1M tokens | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| OpenRouterOpenRouter's own listing | $0.15 / $0.60checked 4 hours ago | 128K | not measured | Unknown | Unknown | Unknown |
| CohereThrough OpenRouter | $0.15 / $0.60checked 4 hours ago | 128K4K max reply | 20 tok/s | No | Yes30 days | Unknown |
OpenRouterAcross the 2 listings we hold: 1 says it does not train on prompts, 0 say they do and 1 does not say. 0 appear in the zero-retention registry we check; the rest are unknown to us.
What each host's API supports
From the parameter list each endpoint publishes. Streaming is omitted: nothing we hold reports it, for any model.
| Provider | Tool calling | JSON output | Strict schema |
|---|---|---|---|
| OpenRouterOpenRouter's own listing | ✓ | ✓ | ✓ |
| CohereThrough OpenRouter | ✓ | ✓ | ✓ |
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
Recent changes
What moved
first indexed by our pipelineEach date is the day we first saw the change, or the day the maker announced it.
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 does not say whether it trains on prompts.
- We hold no cached-input rate for any of its listings.
- We hold no batch or off-peak 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
We hold no licence record for this model, and no record of published weights either — so we can neither summarise its terms nor point you at the weights.
Identifiers
- Takes in, gives back
- Text in, text out
- Catalogue slug
- cohere-command-r-08-2024