Models / Cohere/ Command R7B (12-2024)

Command R7B (12-2024)

Cohere · released Dec 14, 2024

Input: text. Output: text.InputOutput
Type
Proprietary
Input
$0.037
Output
$0.15
Cached
Not published

List price · per 1M tokens · Cohere at 128K context · source ↗

Our take

Written Aug 3, 2026

Command R7B is a hosted-only text model from Cohere, released in late 2024 with a 128,000-token request limit. It follows instructions well but scores poorly on knowledge and reasoning tests, making it a narrow-use choice for formatting-heavy document work rather than general intelligence tasks.

Who should pick it

Pick this for long-document processing where instruction formatting matters more than raw knowledge, or where you need predictable pricing across both tracked providers. Use it if 64 tokens per second meets your latency needs. Skip it if you need image or audio input, strong reasoning or broad factual knowledge, or if you want to download and self-host the weights.

The case for it

  • Strong instruction-following compliance relative to its knowledge scores: a 48.5-point gap between IFEval and MMLU-Pro.
  • Identical pricing across both tracked providers, so provider choice does not affect cost.

The case against it

  • Very weak knowledge and reasoning scores, at 28.6% on MMLU-Pro and 7.8% on GPQA Diamond.
  • Throughput on the secondary provider is unverified in our data.
  • Parameter count is undisclosed, which limits hardware planning for anyone considering local deployment.
00

How good is it?

IntelligencePuzzles, maths, exam questions

Scored, not ratedGPQA Diamond · 10th of 16 · 7.8

Command R7B (12-2024) is not on Arena Text (overall), which is where the rating would come from, so there is no rating here. It is on GPQA Diamond, in 10th of 16 with 7.8.

MMLU-Pro 12th of 16

CodingWriting and fixing code on its own

not measured

Nobody we watch has scored Command R7B (12-2024) for this. We would take the rating from Arena Coding.

AgenticPlanning, calling tools, staying on task

not measured

Nobody we watch has scored Command R7B (12-2024) for this. We would take the rating from Arena Agent (IPS).

WritingWe do not rate this

not measured

Nobody we watch has scored this model for writing. 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.

Also scored, on boards we give no mark for
IFEval 6th of 16

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 model3 scoresEvery figure we hold, from 3 boards, with who ran it and a link to the source — including the boards no rating above is built on.
GPQA Diamondreasoning
7.8independentsource ↗
IFEvalchat
77.1independentsource ↗
MMLU-Proreasoning
28.6independentsource ↗
01

Or rent it from someone else

Cheapest published offer

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
$0.037 in / $0.15 out
Context served
128K
Throughput
Not measured
Current provider offers with price, context and prompt-privacy answers
ProviderIn / out per 1M tokensContextThroughputTrains on promptsLogs promptsZero retention
OpenRouter$0.037 / $0.15128Knot measuredUnknownUnknownUnknown
Cohere$0.037 / $0.15128K54 tok/sNoYes30 daysUnknown

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
API features per host
ProviderTool callingJSON outputStrict schema
OpenRouter
Cohere

Tool calling: 0 of 2 listings say yes, 2 say no. JSON output: 2 of 2 listings say yes. Strict schema: 2 of 2 listings say yes.

02

When we formed this view

Dates behind this page

Aug 3, 2026BenchmarkScored 7.8 on GPQA Diamondleaderboard
Aug 3, 2026BenchmarkScored 77.1 on IFEvalleaderboard
Aug 3, 2026BenchmarkScored 28.6 on MMLU-Proleaderboard
Jul 26, 2026ListedListed on LLMapfirst indexed by our pipeline
Dec 14, 2024AnnouncedCommand R7B (12-2024) announced by Cohere

Prices last checked 9d 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.
03

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-r7b-12-2024

Machine-readable model card (omc.json) →

Something wrong on this page? Tell us