tokenstat
tokenstat

Command R

cohere/command-r · rates as of · Benchmarks · Plans · Calculator

Cohere retrieval model for long-context chat and enterprise RAG workflows

Cheapest input
$0.15
$/MTok · LiteLLM
Cheapest output
$0.6
$/MTok
Context
128K
tokens
Offers
4
2 sources

Offers

Same model, different listings. First-party, router, and aggregator rows stay separate so you can see the spread instead of a single blended number.

SourceProviderInputOutputCache readContext
LiteLLMcheapestcohere/command-r$0.15$0.6$0.015
LiteLLMcheapestcommand-r$0.15$0.6$0.015
LiteLLMcheapestvercel_ai_gateway/cohere/command-r$0.15$0.6$0.015
models.devcohere/command-rNanoGPT$0.476$1.43$0128K

Capabilities

  • In: text
  • Out: text
Released: 2024-03-11Family: command-r

See what you actually spent

tokenstat prices your local sessions at list rates like these, with the cache split kept honest. Free, open source, runs on your machine.

$ curl -fsSL https://tokenstat.ai/install.sh | bash