NOUMENOpen app
NOUMEN

cohere · Balanced

Cohere: Command R+

Added Jan 1, 2024

Compare models

Choose up to 3 models to compare.1 of 3 chosen

Loading models…

Use in the app

104B parameter model that performs conversational language tasks at a higher quality, more reliably, and with a longer context than previous models. It can be used for complex workflows like code generation, retrieval augmented generation (RAG), tool use, and agents

Input
Text
Output
Text
Discovery tier
Balanced

Pricing

USD per 1M tokens
Input
$2.86
Output
$14.25

Reference prices as published by the model provider. API example

Specifications

Context window
128K
Max output
4.1K
Average output (7 days)
146 tokens
Longer than 15% of 468 models

Side by side

Cohere: Command R+ compared

Specifications, prices, speed and benchmark scores next to each other. Benchmarks below show every compared model too.

Compare models

Choose up to 3 models to compare.1 of 3 chosen

Loading models…

Cohere: Command R+cohereThis modelGPT-3.5 TurboOpenAIRemove
ProvidercohereOpenAI
Discovery tierBalancedBalanced
AddedJan 1, 2024Jan 1, 2024
Limits
Context window128KBest16.39K
Max output4.1K4.1K
Average output146 tokens—
Pricing, USD per 1M tokens
Input$2.86$0.50Best
Output$14.25$1.50Best
Benchmark indexes
Intelligence Index5.35.5Best
Coding Index—10.7
Capabilities
Reasoning effort——

Public evaluations

Benchmarks

Independent evaluation results, with how each score ranks among the models in the Noumen catalog.

  • Cohere: Command R+
  • GPT-3.5 Turbo

Intelligence Index

  • Cohere: Command R+5.3
  • GPT-3.5 Turbo5.5

Cohere: Command R+: Better than 1% of 326 scored models

3.8Catalog models by score55.1

Indexes

  • Coding Index

    Composite of the coding evaluations

    • Cohere: Command R+: —
    • GPT-3.5 Turbo: 10.7

Reasoning and knowledge

  • Humanity’s Last Exam

    Expert-level questions across academic fields

    • Cohere: Command R+: 4.6%
    • GPT-3.5 Turbo: —

  • GPQA Diamond

    Graduate-level science questions

    • Cohere: Command R+: 32.3%Top
    • GPT-3.5 Turbo: 29.7%

  • MMLU-Pro

    Multi-subject knowledge and reasoning

    • Cohere: Command R+: 43.2%
    • GPT-3.5 Turbo: 46.2%Top

Coding

  • LiveCodeBench

    Recent competitive programming problems

    • Cohere: Command R+: 12.2%
    • GPT-3.5 Turbo: —

Math

  • AIME

    Competition mathematics

    • Cohere: Command R+: 0.7%
    • GPT-3.5 Turbo: —

  • MATH-500

    Competition math problems

    • Cohere: Command R+: 27.9%
    • GPT-3.5 Turbo: 44.1%Top

Scores from Artificial Analysis, updated Oct 26, 2026.

Developers

Use it through the API

Noumen’s API is OpenAI-compatible: any Chat Completions client works with a base URL and a key.

Read the quickstart
curl https://www.noumen.xyz/api/v1/chat/completions \
  -H "Authorization: Bearer $NOUMEN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "cohere/command-r-plus-08-2024",
    "messages": [{ "role": "user", "content": "Explain this stack trace." }]
  }'
import os
from openai import OpenAI

client = OpenAI(base_url="https://www.noumen.xyz/api/v1", api_key=os.environ["NOUMEN_API_KEY"])
reply = client.chat.completions.create(
    model="cohere/command-r-plus-08-2024",
    messages=[{"role": "user", "content": "Explain this stack trace."}],
)
print(reply.choices[0].message.content)

cohere

Other cohere models, starting with the same family.