Command R7B (12-2024)

Pricing updated daily · Last refreshed Oct 29, 2026

Cohere model with a 128K-token context window, priced at $0.037 per million input tokens and $0.15 per million output tokens.

At a glance

Provider
Cohere
Context window
128,000 tokens
Max output
4,000 tokens
Input price
$0.037 / 1M tokens
Output price
$0.15 / 1M tokens
Input types
text
Function calling
No
Released
December 14, 2024

What it costs

Illustrative request sizes, not measurements of any real product. For your own volumes, use the cost estimator.

Example costs for Command R7B (12-2024)
WorkloadTokens in / outPer requestPer 1,000 requests
Short chat reply1,000 / 500$0.000112$0.1125
Question over retrieved documents8,000 / 500$0.000375$0.3750
Summarise a long document50,000 / 1,500$0.0021$2.10

How it compares

  • Input price ($0.037 per 1M tokens) is the 2nd lowest of 30 models in the catalogue.
  • Output price ($0.15 per 1M tokens) is the lowest of 30.
  • Context window (128K tokens) is the 26th largest of 30.
  • Maximum output (4K tokens) is the 28th largest of 30.
  • On blended price it is 89% cheaper than the median Cohere model in the catalogue.

These are rankings by listed price and size within this catalogue (blended price weights input 3:1 against output), not a measure of output quality.

More from Cohere

Other Cohere models
ModelProviderContextInput $/1MOutput $/1M
Command A+Cohere192K$0.30$1.50
Command ACohere256K$2.50$10.00
Command R (08-2024)Cohere128K$0.15$0.60
Command R+ (08-2024)Cohere128K$2.50$10.00

Try it with your own text

Source: OpenRouter’s public model catalogue (cohere/command-r7b-12-2024), read once a day. These are the prices OpenRouter charges; a provider’s own list price can differ, so check the provider before committing to a budget.

llmtools is a vendor-neutral toolkit for working with large language models — token counting, cost estimation and model comparison, computed in your browser. OpenAI token counts are exact, using the same encoding the model does (o200k_base for GPT-4o, cl100k_base for GPT-4/3.5); Claude and Gemini counts are labelled approximations, since neither publishes a tokenizer that runs client-side. Model pricing is read from OpenRouter’s public catalogue once a day. Nothing you type is ever transmitted anywhere.