Cohere: Command R+ (08-2024)

cohere/command-r-plus-08-2024 · CohereDeclared and measured agree

Tokenizer group (measured): Cohere
Declared tokenizer tag: Cohere
Entered catalogue: 30 August 2024
Last tested: 5 October 2026
Evidence confidence: Moderate

Why moderate: near-exact agreement (49 of 49 strings) with cohere/command-r7b-12-2024, short of a full exact signature.

Evidence

✓ near-exact agreement (49/49) with cohere/command-r7b-12-2024

Compare with Cohere: Command R7B (12-2024)

Report a correction

Identity statement

Cohere: Command R+ (08-2024) is Cohere's model, and its measured tokenizer sits in Cohere's own signature group alongside its sibling models. No other maker's measured model shares it so far.

What we checked

Four different kinds of evidence, and what each one showed

We checked	What we found	Where it came from
How it counts tokens	Counted, using the 49 strings that came back reliably	we measured it
How its API is set up	Set up identically to 1 other listing, field for field	api_bb5648eb
How much it can read and write	Reads up to 128,000 tokens at once, writes up to 4,000	its own listing
Who served our requests	Cohere	we measured it, 5 October 2026

Closest measured models

Agreement across the mutually clean test strings

Cohere: Command R7B (12-2024)cohere/command-r7b-12-202449/49 · 100%Cohere: Command Acohere/command-a49/49 · 100%Cohere: Command R (08-2024)cohere/command-r-08-202448/48 · 100%Upstage: Solar Pro 4upstage/solar-pro422/49 · 45%Upstage: Solar Pro 3upstage/solar-pro-322/49 · 45%Upstage: Solar Mini 4upstage/solar-mini422/49 · 45%

Click a row to open the full comparison.

The measured fingerprint

What each test string cost this model, in tokens

We sent Cohere: Command R+ (08-2024) fifty short pieces of text and recorded what each one cost it in tokens. The bars below are those costs. Two models built on the same tokenizer produce the same bars; a model built on a different one produces a different set, which is what makes this a fingerprint.

All 50 rows, 1 excluded as corrupt

English and whitespace

en-prose14

en-long15

spaces-203

spaces-603

tabs-206

newlines-205

mixed-ws6

Digits

digits-99

digits-1212

digits-3030

digits-sep12

float-long22

CJK

zh-common12

zh-long14

zh-rare18

ja-kana7

ja-kanji9

ko9

Other scripts

ru11

ar10

hex

hi20

th25

el12

Emoji

emoji-basic10

emoji-skin20

emoji-zwj-family11

emoji-zwj-x333

emoji-flags7

emoji-prof20

Rare Unicode

math32

boxdraw29

combining5

cjk-ext-b16

surrogates40

zalgo36

rtl-mix6

Code

py-code27

py-indent15

json28

html17

regex48

camel5

snake11

Repetition and encodings

rare-word-x525

repeat-tok40

base6434

hex16

url23

uuid36

An x marks a row excluded as corrupt (caching or provider interference detected during measurement). Overhead subtracted: 0 prompt tokens.

Declared record

What the catalogue claims about this model

command-r-plus-08-2024 is an update of the [Command R+](/models/cohere/command-r-plus) with roughly 50% higher throughput and 25% lower latencies as compared to the previous Command R+ version, while keeping the hardware footprint...

Modalities: text->text
Declared tokenizer: Cohere
Prompt price: $2.50 / M tokens
Completion price: $10.0 / M tokens

Supported parameters

frequency_penaltymax_tokenspresence_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_p

defaults: {}

Catalogue entry

History

Every observation, kept as taken

30 August 2024Enters the OpenRouter catalogue declared as Cohere.
5 October 2026Fingerprinted in the YFarmX catalogue sweep · 49 of 50 strings measured clean.
5 October 2026YFarmX assessment: consistent with the Cohere family, moderate confidence.