Cohere's flagship for enterprise RAG. Optimized for retrieval-augmented generation and tool use.
Context Window
128K
tokens
Max Output
4K
tokens
Input Price
$2.5
per 1M tokens
Output Price
$10
per 1M tokens
Speed
72
tokens/sec
Released
Aug 2024
2024-08-15
Blended Cost
$6.25
per 1M tokens
Value Score
10.9
quality per $
Capabilities
ChatCode GenerationFunction CallingSearch
Benchmarks
Quality Index
68
MMLU Pro
78.5
HumanEval (Coding)
74.8
MATH
58.2
Arena ELO
1170
Price vs Quality
Cheaper is left, more capable is up. 41 of 62 priced models are both cheaper and score at least as high. Self-host models are left off the price axis — their cost depends on the hardware you run them on, not on tokens.
Context Window in Context
Grok 3131K
▸ Command R+128K
GPT-4o128K
GPT-4o Mini128K
Mistral Large 2128K
DeepSeek V3128K
DeepSeek R1128K
Gemma 4 27B128K
Bar length is logarithmic — each full step is 10× the tokens. Shown against the models with the nearest context windows, not the directory extremes.
Capped at 1024 output tokens and 20 queries an hour. The playground gives you full control.
About Command R+
Command R+ is a balanced AI model by Cohere, released on August 15, 2024. It supports a context window of 128K tokens and can generate up to 4K output tokens.
At $2.5 per million input tokens and $10 per million output tokens, its blended cost of $6.25/1M tokens places it in the premium pricing tier. Its value score of 10.9 reflects the balance of quality and cost.
Using Command R+ with Swfte
Access Command R+ through Swfte Connect, our unified LLM gateway. Connect gives you a single API for 50+ models, with automatic routing, cost optimization, and fallback handling. You can also try Command R+ in our AI Playground before integrating.
Deploy a model with Swfte Connect
One gateway, every provider, per-token cost visibility. Swap models without touching your code.