Cohere · LLMs & Coding

Command R7B

Catalog data · checked Nov 16, 2026

Command R7B is a language model from Cohere, released in December 2024. It reads text and writes text, with a context window of 128K tokens and up to 4K output tokens per answer. It costs $0.0375 per million input tokens and $0.15 per million output tokens. That makes it cheaper than 97% of the 185 paid language models we track.

Calculate my costCompare

Input price$0.0375per 1M tokens
Output price$0.15per 1M tokens
Context window128Ktokens per request
Max output4Ktokens per answer
ReleasedDec 2024Dec 2024
Knowledge cutoffJun 2024training data ends
WeightsOpencan be self-hosted

What it can do

  • Tool calling
  • Structured output
  • Reasoning mode
  • Image input
  • File input
  • Audio input
  • Video input
  • Image output
  • Audio output
  • Prompt caching

What it costs in practice

1,000 support replies1,000 chats with 800 input and 250 output tokens each$0.068
Summarize a 300-page reportabout 150,000 input tokens in one request, 2,000 tokens outtoo long
10,000 product descriptions300 input and 200 output tokens per text$0.413
One day of agentic codingabout 3M input and 150K output tokens across many calls$0.135

Calculated from the list prices above. Your bill depends on your real token counts. Use your own numbers →

Compare Command R7B with

Questions & answers

How much does Command R7B cost?

Command R7B costs $0.0375 per 1 million input tokens and $0.15 per 1 million output tokens (USD, list price checked Nov 16, 2026).

How large is the context window of Command R7B?

Command R7B can process up to 128,000 tokens per request and return up to 4,000 tokens. As a rule of thumb, 1,000 tokens are about 750 English words.

Does Command R7B support tool calling?

Yes. The API accepts tool (function) definitions and also supports structured JSON output.

Can Command R7B read images?

No, this model accepts text only.