Command R (08-2024)

Cohere · released 30 Aug 2024

Input$0.15per 1M tokens
Output$0.6per 1M tokens
Context128Ktokens
WeightsClosed
context on a 1K–2M scale

About

Command R (08-2024) is Cohere’s August 2024 update to Command R. It is described as improving multilingual retrieval-augmented generation (RAG) and tool use, with further gains in math, code, and reasoning. The listed summary ends before specifying its final point, so no additional capability is assumed here. The model accepts text input and produces text output, supports tools, and has a 128,000-token context window. Its maximum output is 4,000 tokens. Input costs USD 0.15 per 1M tokens and output costs USD 0.6 per 1M tokens. The model identifier is cohere/command-r-08-2024. Its focus on multilingual RAG and tools makes it relevant to teams building text-based retrieval workflows or tool-using systems. The available facts describe text input only, with no image or video input listed. It was released on 2024-08-30.

Who it is for

Teams working on multilingual text retrieval or tool-using applications may suit this model. Its listed strengths also cover math, code, and reasoning.

What is good

  • Improved multilingual RAG performance
  • Improved tool use
  • 128,000-token context window
  • Input costs USD 0.15 per 1M tokens

What to know first

  • Text input only
  • Maximum output is 4,000 tokens

Verdict

Command R (08-2024) is oriented toward multilingual RAG and tool use, with text output and a 128,000-token context. Its 4,000-token output cap is worth considering for longer responses.

Details

Lab
Cohereopenrouter.ai · 3 Oct 2026
Context
128Kopenrouter.ai · 3 Oct 2026
Input price
$0.15 / 1Mopenrouter.ai · 3 Oct 2026
Output price
$0.6 / 1Mopenrouter.ai · 3 Oct 2026
Max output
4,000 tokensopenrouter.ai · 3 Oct 2026
Inputs
textopenrouter.ai · 3 Oct 2026
Open weights
Noopenrouter.ai · 3 Oct 2026

More longest-context models

See the list