Inferse
For vendors
AdvertiseTop spots, featured rows, home sponsor Get listedAdd a product we don't cover yet Claim a listingFree: verify the domain, then correct your page Vendor dashboardNumbers, orders and placements
List your platform
Vendor dashboard

Command R7B (12-2024)

Cohere · released 14 Dec 2024

Input$0.038per 1M tokens
Output$0.15per 1M tokens
Context128Ktokens
WeightsClosed
context on a 1K–2M scale

About

Command R7B (12-2024) is a Cohere text model described as a small, fast update of Command R+, delivered in December 2024. Its stated strengths include retrieval-augmented generation (RAG), tool use, agents and tasks that involve complex reasoning. It accepts text and returns text, with a context window of 128,000 tokens and a maximum output of 4,000 tokens. The model ID is `cohere/command-r7b-12-2024`; it was released on 2024-12-14. Pricing is USD 0.0375 per 1M input tokens and USD 0.15 per 1M output tokens. The comparatively short maximum output is worth accounting for when designing tasks that need long responses. Its text-only input and output define the modalities available for integrations. For teams building retrieval, tool-using or agent workflows, those task areas and limits offer the main points to assess before choosing it.

Who it is for

It suits teams building text-based RAG, tool-use or agent workflows, especially where tasks involve complex reasoning. Account for the 4,000-token maximum output when planning response length.

What is good

  • Designed for RAG and tool use
  • Agent tasks are a stated strength
  • 128,000-token context window
  • USD 0.0375 per 1M input tokens

What to know first

  • Maximum output is 4,000 tokens
  • Accepts text inputs only

Verdict

Command R7B is positioned around RAG, tool use and agent tasks, with a 128,000-token context. Its text-only modality and 4,000-token output cap are important constraints.

Details

Lab
Cohereopenrouter.ai · 3 Oct 2026
Context
128Kopenrouter.ai · 3 Oct 2026
Input price
$0.038 / 1Mopenrouter.ai · 3 Oct 2026
Output price
$0.15 / 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
Auto Router 2,000K Context Auto Router (Beta) 2,000K Context Grok 4.20 2,000K Context Grok 4.20 Multi-Agent 2,000K Context Pareto Code Router 2,000K Context Llama 4 Scout 1,311K Context Open source

Listed on Inferse

Sources